Cluster collection communication system applied to AI data stream processing

Abstract

The invention discloses a cluster collection communication system applied to AI data stream processing, which relates to the technical field of distributed systems and network engineering and comprises a topology network deployment module, a data stream spatio-temporal data acquisition module, an optimization verification module, a state monitoring and early warning module and a visual traceability module. The topology network deployment module synchronously processes AI data streams, the data stream spatio-temporal data acquisition module extracts an entropy value and a covariance matrix, the optimization verification module outputs optimization parameters and a credible verification result, the state monitoring early warning module sets an adaptive threshold value to realize graded early warning, and the visual traceability module generates a three-dimensional thermodynamic diagram and a traceability graph. According to the method, the data stream processing efficiency is improved through the star-ring hybrid topology and the low-delay protocol, the decision credibility is enhanced in combination with quantum optimization and block chain verification, accurate early warning and three-dimensional visual traceability acceleration fault positioning are realized by using dynamic weighted monitoring and an adaptive threshold, and an efficient and intelligent full-stack solution is provided for AI trunking communication.

Description

Technical Field

[0001] The present invention relates to the field of distributed systems and network engineering technology, and in particular to a cluster aggregation communication system applied to AI data stream processing. Background Art

[0002] The cluster convergence communication system is a mobile communication system designed for group dispatching and commanding. Its core lies in sharing channel resources. The system dynamically allocates all available channels to all users, supports group calling and emergency calling functions, operates in simplex and half-duplex modes, and improves efficiency through dynamic channel allocation. Its advantages include high spectrum utilization, low network construction cost, high reliability and flexibility. It is widely used in public safety, transportation and industrial fields. Through gateways, multi-standard cluster interconnection can be achieved, supporting voice, data and image transmission to meet complex dispatching needs.

[0003] To address the challenges of traditional cluster-convergence communication systems in processing high-dimensional dynamic data streams, existing technologies employ a single topology structure combined with static threshold monitoring. However, these issues can lead to topological rigidity, making it difficult to balance communication efficiency and fault tolerance, insufficient extraction of spatiotemporal features of data streams leading to optimization decision bias, and centralized verification mechanisms with single-point trust risks. These issues can lead to poor system scalability, delayed response to exceptions, and cross-module collaboration failures. To address these issues, a cluster-convergence communication system for AI data stream processing is proposed. Summary of the Invention

[0004] The present invention aims to provide a cluster aggregation communication system for AI data stream processing to solve the problems raised in the above background technology.

[0005] To solve the above technical problems, the technical solution adopted by the present invention is: a cluster convergence communication system applied to AI data stream processing, including a topology network deployment module, a data stream spatiotemporal data acquisition module, an optimization and verification module, a status monitoring and early warning module, and a visual tracing module;

[0006] The topology network deployment module deploys a star-ring hybrid topology network in the cluster aggregation communication system, combines it with a low-latency protocol, and synchronously processes AI data flows between modules;

[0007] The data stream spatiotemporal data acquisition module, based on a star-ring hybrid topology network, collects and preprocesses operation log data and spatial coordinate data, and extracts sliding window entropy and covariance matrix of each dimension from them;

[0008] The optimization verification module constructs a quantum optimization model and a blockchain verification model based on the sliding window entropy and covariance matrix, and outputs optimized weight parameters and trusted verification results;

[0009] The state monitoring and early warning module dynamically optimizes weight parameters and trustworthy verification results, outputs a comprehensive judgment value, sets an adaptive threshold for the comprehensive judgment value, judges the state of the AI data flow, and issues a graded early warning;

[0010] The visual tracing module generates a three-dimensional spatial heat map and an abnormal event tracing map.

[0011] A further improvement of the technical solution of the present invention is that: in the topology network deployment module, the process of synchronizing the AI data flow between modules includes:

[0012] In the cluster-converged communication system, a star-shaped backbone network is constructed using high-performance routers, serving as core nodes to connect AI data stream processing terminals and execution terminals. A low-latency protocol-driven ring topology subnet is deployed between the quantum optimization model and the blockchain verification model to form a closed-loop redundant link. Heterogeneous data caching gateways are deployed at the star-ring intersection nodes to dynamically divert the peak and average traffic of AI data streams. A dynamic load balancing algorithm is used to optimize the load threshold of the intersection nodes.

[0013] The star-shaped backbone adopts a priority scheduling mechanism and distributes AI data streams to the target terminal through dynamic load balancing. The transmission delay is constrained by the size of a single data packet and the number of routing hops. Each node in the ring subnet uses an alternating verification mechanism to process data. After the quantum optimization node processes the data, the blockchain verification node reversely verifies the integrity of the result along the ring path. The verification period is dynamically adjusted by the real-time load feedback factor. When the star backbone load exceeds the limit, the cache gateway triggers the ring diversion path and directly connects the data to the target node via the ring link. The optimal path is selected based on the inverse square of the load rate and the weighted load rate of the ring link. When a node in the ring subnet fails, the low-latency protocol initiates reverse link retransmission.

[0014] A further improvement of the technical solution of the present invention is that: in the data stream spatiotemporal data acquisition module, the acquisition and preprocessing process of the operation log data and the spatial coordinate data includes:

[0015] Distributed fiber optic sensors are deployed at the edge nodes of the star-shaped backbone network. These sensors capture system events at millisecond frequencies, collect time-stamped operation log data from heterogeneous data streams in real time, and transmit the data to the cache gateway via the star-shaped backbone network.

[0016] Intelligent edge nodes are deployed on the execution terminal side of the ring topology subnet. Based on spatial sensors, the intelligent edge nodes collect spatial coordinate data of device locations and environmental monitoring points in the clustered communication system, synchronously generate environmental status tags, and push them to the cache gateway through the low-latency protocol of the ring subnet.

[0017] The denoising threshold is dynamically set according to the signal energy, and the wavelet threshold denoising algorithm is used to filter out the high-frequency noise in the operation log data. The operation log data and spatial coordinate data are matched by timestamps to construct the spatiotemporal correlation matrix.

[0018] A further improvement of the technical solution of the present invention is that: in the data stream spatiotemporal data acquisition module, the process of extracting sliding window entropy from the pre-processed operation log data includes:

[0019] A dual-channel data interface is configured in the heterogeneous data cache gateway. Channel 1 receives the pre-processed star-shaped trunk operation log data and uses the sliding time window segmentation technology to split the continuous log stream into discrete batches. The data stream peak rate V peak Dynamically adjust the time window length W t , count the event type distribution in a single window, and calculate the occurrence frequency p of the i-th type event i Based on the event frequency, the sliding window entropy S is obtained through a parallel computing framework. The calculation process is as follows:

[0020]

[0021] Among them, D d is the size of a single data packet, N is the number of parallel processing windows, n i is the number of events of type i, and m is the total number of event types in the window.

[0022] A further improvement of the technical solution of the present invention is that: in the data stream spatiotemporal data acquisition module, the process of extracting the covariance matrix of each dimension from the pre-processed spatial coordinate data includes:

[0023] Channel 2 receives the pre-processed spatial coordinate data of the ring subnet and inputs it into the covariance matrix algorithm to calculate the mean and covariance of dimension X and dimension Y, and construct the covariance matrix of each dimension;

[0024] If the coordinate value of a spatial coordinate data point deviates from the mean by more than 3 times the dimensional standard deviation, it is determined to be an outlier and removed.

[0025] A further improvement of the technical solution of the present invention is that: in the optimization verification module, the process of constructing a quantum optimization model and outputting optimized weight parameters includes:

[0026] Using the quantum annealing algorithm, the sliding window entropy is mapped to the quantum Hamiltonian H, and the coupling coefficient J is constructed. ij With the bias term h i , the calculation process is as follows:

[0027] H=∑ i<j J ij σ i σ j+∑ i h i σ i ;

[0028] Among them, σ i ∈{-1,+1} is the quantum bit spin state;

[0029] Initialize the quantum bit spin state and set the initial temperature T c and final temperature T z Based on the real-time load feedback factor α, the annealing rate T(t) is dynamically adjusted according to the exponential function to generate a quantum optimization model. The energy barrier is traversed through the quantum tunneling effect to make the cluster communication system approach the ground state, measure the final quantum bit state, and convert the final quantum bit state σ i The mean is converted to the optimized weight parameter y q , the calculation process is as follows:

[0030] T(t)=T c ·e -αt ;

[0031]

[0032] Where t is the annealing time and N is the total number of quantum bits.

[0033] A further improvement of the technical solution of the present invention is that: in the optimization verification module, the process of constructing a blockchain verification model and outputting a credible verification result includes:

[0034] Based on smart contract technology, the covariance matrix M is broadcast to each blockchain verification node through a ring topology subnet. Each blockchain verification node uses a double SHA-256 chain structure to calculate the covariance matrix hash value H(M) = SHA256(SHA256(M)). If more than 2 / 3 of the blockchain verification nodes return the same H(M), the data is considered complete.

[0035] Adopting a distributed consensus mechanism, executing smart contracts in the proposal, verification, and submission stages, and building a blockchain verification model;

[0036] In the proposal phase, the main blockchain verification node encapsulates the covariance matrix and hash value as a block proposal and broadcasts it along the ring path;

[0037] During the verification phase, each node verifies the distribution consistency of the covariance matrix based on the 3σ anomaly rejection rule and generates a verification result. If the absolute value of the coordinate value of the k-th data point in dimension i minus the mean of dimension i does not exceed three times the standard deviation of dimension i, the verification result is 1; if the absolute value of the coordinate value of the k-th data point in dimension i minus the mean of dimension i exceeds three times the standard deviation of dimension i, the verification result is 0.

[0038] In the submission phase, if more than 2 / 3 of the blockchain verification nodes return a verification result of 1, the smart contract generates a digital signature N = ECDSA (H (M), private key) and writes the signed result (M, N) to the blockchain;

[0039] According to the real-time load rate L of the ring subnet and the load feedback factor β, the consensus round R is dynamically adjusted. If the consensus is passed, the blockchain verification model outputs a credible verification result y v =1, if consensus fails, the blockchain verification model outputs a credible verification result y v =0.

[0040] A further improvement of the technical solution of the present invention is that: in the state monitoring and early warning module, the process of dynamically weighting and optimizing the weight parameters and the credible verification results and outputting the comprehensive judgment value includes:

[0041] Based on the dynamic weight factor γ, the optimization weight parameter y output by the quantum optimization model is q And the trusted verification result y output by the blockchain verification model v Perform dynamic weighting and optimize γ based on historical error backpropagation to output the comprehensive judgment value y. The calculation process is as follows:

[0042] y=γy q +(1-γ)y v ;

[0043]

[0044] Among them, η is the learning rate, L is the cross entropy loss function, Accelerate convergence through mixed-precision computing techniques.

[0045] A further improvement of the technical solution of the present invention is that in the state monitoring and early warning module, the process of setting an adaptive threshold for the comprehensive judgment value, judging the AI data flow state, and performing a graded early warning includes:

[0046] Based on the sliding window entropy fluctuation range and covariance matrix stability, the threshold interval [T min ,T max ], and its calculation process is as follows:

[0047] T min =μ y -k·σ y ;

[0048] T max =μ y +k·σ y ;

[0049]

[0050] Among them, μ y is the mean value of the recent comprehensive judgment value, σ y is the standard deviation, and k is the warning sensitivity;

[0051] If T min <y < T max , it is determined as normal data flow and output to the execution end. If y < T min 、y > T max , and the deviation amplitude Δ = |y - T 边界 | ≤ 0.2σ y , a first-level warning is triggered and it is determined as a mildly abnormal data flow. If Δ > 0.2σ y , a second-level warning and an emergency response instruction are triggered, and it is determined as a severely risky data flow;

[0052] After each batch of data flow processing is completed, the ratio of the number of false alarms to the total number of warnings is used as the error rate E. Based on the error rate, the threshold interval is corrected. The correction process includes: if E > 5%, the threshold interval is expanded to [T min -0.1σ y , T max +0.1σ y . If E < 1%, the threshold interval is reduced to [T min +0.05σ y , T max -0.05σ y . If 1% < E < 5%, the threshold interval remains unchanged.

[0053] A further improvement of the technical solution of the present invention lies in: in the visual traceability module, the process of generating a three-dimensional space heat map and an abnormal event traceability map includes:

[0054] Dynamically weight the covariance matrix elements and the sliding window entropy to generate three-dimensional space heat density values. Based on the collected spatial coordinate data, map the three-dimensional space heat density values to a three-dimensional grid, and fill the heat distribution between discrete points through an interpolation algorithm to generate a three-dimensional space heat map;

[0055] Taking the spatio-temporal correlation matrix, the hierarchical warning signals output by the status monitoring and warning module, and the corresponding time window identifiers as inputs, according to the warning time window identifiers, trace back to the original operation log batches in the cache gateway, extract the abnormal event type distribution and time stamp sequence, screen the coordinate points in the spatio-temporal correlation matrix with elements greater than 0.7, and mark them as the locations where abnormal events occur;

[0056] Construct an abnormal event traceability map and define abnormal event nodes including timestamps, sliding window entropy, warning levels, and associated spatial coordinates. If two abnormal event nodes share the same coordinate point in the spatiotemporal association matrix, the edge weight of the abnormal event traceability map is determined by the difference in sliding window entropy between the two abnormal events. Nodes and edges are rendered in layers according to weights, with high-weight edges highlighted in red and low-weight edges faded in gray.

[0057] Due to the adoption of the above technical solution, the present invention has the following technical advancements compared to the prior art:

[0058] 1. The present invention provides a cluster aggregation communication system for AI data stream processing. By deploying a star-ring hybrid topology network and combining it with a low-latency protocol, it effectively resolves the contradiction between scalability and fault tolerance in the traditional single topology structure, realizes efficient synchronization and load balancing of AI data streams between modules, reduces communication latency to microseconds, and significantly improves cluster throughput.

[0059] 2. The present invention provides a cluster aggregation communication system for AI data stream processing. It extracts sliding window entropy and covariance matrix based on spatiotemporal correlation data, constructs a quantum optimization model and a blockchain verification model, breaks through the local optimal limitations of classical algorithms, ensures decision credibility through distributed ledgers, and makes the optimization weight parameters and system verification results tamper-resistant, thereby improving the accuracy and security of high-dimensional dynamic data stream processing.

[0060] 3. The present invention provides a cluster convergence communication system for AI data stream processing, which innovatively integrates dynamic weighted comprehensive judgment and adaptive threshold learning algorithm to achieve real-time graded early warning of AI data stream status. It also shortens fault location time by more than 80% through three-dimensional spatial heat maps and abnormal event tracing maps, providing intelligent transformation support for operation and maintenance from passive response to active prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0062] Figure 1 A block diagram of the present invention. DETAILED DESCRIPTION

[0063] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0064] Examples, such as Figure 1 As shown, the present invention provides a cluster convergence communication system for AI data stream processing, including a topology network deployment module, a data stream spatiotemporal data acquisition module, an optimization and verification module, a status monitoring and early warning module, and a visual tracing module;

[0065] Topology network deployment module, deploys a star-ring hybrid topology network in the cluster convergence communication system, combines low-latency protocols, and synchronously processes AI data streams between modules. In the cluster convergence communication system, a star backbone network is built through high-performance routers, which serve as core nodes to connect AI data stream processing terminals and execution terminals. A low-latency protocol-driven ring topology subnet is deployed between the quantum optimization model and the blockchain verification model to form a closed-loop redundant link. Heterogeneous data cache gateways are deployed at the star-ring intersection nodes to dynamically divert the peak traffic and average traffic of AI data streams, and optimize the intersection node load threshold through a dynamic load balancing algorithm. Star backbone A priority scheduling mechanism is adopted to distribute AI data streams to the target terminal through dynamic load balancing. The transmission delay is constrained by the size of a single data packet and the number of routing hops. Each node in the ring subnet uses an alternating verification mechanism to process data. After the quantum optimization node processes the data, the blockchain verification node reversely verifies the integrity of the result along the ring path. The verification period is dynamically adjusted by the real-time load feedback factor. When the star backbone load exceeds the limit, the cache gateway triggers the ring diversion path, directly connecting the data to the target node via the ring link, and selects the optimal path based on the inverse square of the load rate and the weighted load rate of the ring link. When a node in the ring subnet fails, the low-latency protocol initiates reverse link retransmission.

[0066] The data stream spatiotemporal data acquisition module, based on a star-ring hybrid topology network, collects and preprocesses operation log data and spatial coordinate data, and extracts sliding window entropy and covariance matrices of each dimension from them. Distributed fiber optic sensors are deployed at the edge nodes of the star backbone network. The distributed fiber optic sensors capture system events at a millisecond frequency, collect time-stamped operation log data in heterogeneous data streams in real time, and transmit them to the cache gateway through the star backbone network. Intelligent edge nodes are deployed on the execution terminal side of the ring topology subnet. The intelligent edge nodes collect spatial coordinate data of device locations and environmental monitoring points in the clustered communication system based on spatial sensors, synchronously generate environmental status tags, and push them to the cache gateway through the low-latency protocol of the ring subnet. The denoising threshold is dynamically set by the signal energy, and the wavelet threshold denoising algorithm is used to filter out high-frequency noise in the operation log data. The operation log data and spatial coordinate data are matched by timestamps to construct a spatiotemporal correlation matrix. A dual-channel data interface is configured on the heterogeneous data cache gateway. Channel 1 receives the preprocessed star backbone operation log data and uses the sliding time window segmentation technology to divide the continuous log stream into discrete batches. The data stream peak rate V is used as the data stream peak rate. peak Dynamically adjust the time window length W t , count the event type distribution in a single window, and calculate the occurrence frequency p of the i-th type event i Based on the event frequency, the sliding window entropy S is obtained through a parallel computing framework. The calculation process is as follows:

[0067]

[0068] Among them, D d is the size of a single data packet, N is the number of parallel processing windows, n i is the number of events of type i, m is the total number of event types in the window, channel 2 receives the pre-processed spatial coordinate data of the ring subnet, inputs it into the covariance matrix algorithm, counts the mean and covariance of dimension X and dimension Y, and constructs the covariance matrix of each dimension. If the coordinate value of a spatial coordinate data point deviates from the mean by more than 3 times the standard deviation of the dimension, it is determined to be an outlier and removed;

[0069] The optimization verification module builds a quantum optimization model and a blockchain verification model based on the sliding window entropy and covariance matrix, outputs the optimized weight parameters and trusted verification results, and uses the quantum annealing algorithm to map the sliding window entropy to the quantum Hamiltonian H and construct the coupling coefficient J. ij With the bias term h i , the calculation process is as follows:

[0070] H=Σ i<j J ij σ i σ j +∑ i hi σ i ;

[0071] Among them, σ i ∈{-1,+1} is the quantum bit spin state, initialize the quantum bit spin state, and set the initial temperature T c and final temperature T z Based on the real-time load feedback factor α, the annealing rate T(t) is dynamically adjusted according to the exponential function to generate a quantum optimization model. The energy barrier is traversed through the quantum tunneling effect to make the cluster communication system approach the ground state, measure the final quantum bit state, and convert the final quantum bit state σ i The mean is converted to the optimized weight parameter y q , the calculation process is as follows:

[0072] T(t)=T c ·e -αt ;

[0073]

[0074] Among them, t is the annealing time, N is the total number of quantum bits, based on smart contract technology, the covariance matrix M is broadcast to each blockchain verification node through the ring topology subnet, and each blockchain verification node uses a double SHA-256 chain structure to calculate the covariance matrix hash value H(M) = SHA256(SHA256(M)). If more than 2 / 3 of the blockchain verification nodes return the same H(M), the data is considered complete. A distributed consensus mechanism is used to execute smart contracts in the proposal stage, verification stage, and submission stage to build a blockchain verification model. In the proposal stage, the main blockchain verification node encapsulates the covariance matrix and hash value as a block proposal and broadcasts it along the ring path. In the verification stage, each node The distribution consistency of the covariance matrix is verified based on the 3σ anomaly rejection rule to generate a verification result. If the absolute value of the coordinate value of the k-th data point in dimension i minus the mean of dimension i does not exceed 3 times the standard deviation of dimension i, the verification result is 1. If the absolute value of the coordinate value of the k-th data point in dimension i minus the mean of dimension i exceeds 3 times the standard deviation of dimension i, the verification result is 0. In the submission phase, if more than 2 / 3 of the blockchain verification nodes return a verification result of 1, the smart contract generates a digital signature N = ECDSA (H (M), private key) and writes the signed result (M, N) to the blockchain. The consensus round is dynamically adjusted according to the real-time load rate L of the ring subnet and the load feedback factor β. If the consensus is passed, the blockchain verification model outputs a credible verification result y v =1, if consensus fails, the blockchain verification model outputs a credible verification result y v =0;

[0075] The state monitoring and early warning module dynamically optimizes the weight parameters and the trusted verification results, outputs a comprehensive judgment value, sets an adaptive threshold for the comprehensive judgment value, judges the state of the AI data flow, and performs graded early warnings. Based on the dynamic weight factor γ, the optimized weight parameter y output by the quantum optimization model is q And the trusted verification result y output by the blockchain verification model v Perform dynamic weighting and optimize γ based on historical error backpropagation to output the comprehensive judgment value y. The calculation process is as follows:

[0076] y=γy q +(1-γ)y v ;

[0077]

[0078] Among them, η is the learning rate, L is the cross entropy loss function, The convergence is accelerated by mixed precision computing technology, and the threshold interval is dynamically set based on the sliding window entropy fluctuation range and covariance matrix stability. min ,T max ], and its calculation process is as follows:

[0079] T min =μ y -k·σ y ;

[0080] T max =μ y +k·σ y ;

[0081]

[0082] Among them, μ y is the mean of the recent comprehensive judgment value, σ y is the standard deviation, k is the warning sensitivity, if T min <y<T max , it is determined to be a normal data flow and output to the execution end. If y <T min 、y>T max , and the deviation amplitude Δ=|yT 边界 |≤0.2σ y , then trigger the first level warning, judged as a slightly abnormal data flow, if Δ>0.2σ y , then trigger the second-level warning and emergency response instructions, and determine it as a serious risk data flow. After each batch of data flow processing is completed, the ratio of the number of false alarms to the total number of warnings is the error rate E. Based on the error rate, the threshold interval is corrected. The correction process includes: if E>5%, then expand the threshold interval to [T min -0.1σ y ,T max+0.1σy ] , if E < 1%, then narrow the threshold interval to [T min +0.05σ y , T max -0.05σ y , if 1% < E < 5%, then keep the threshold interval unchanged;

[0083] The visualization and traceability module generates a 3D spatial heat map and an abnormal event traceability map, dynamically weights the covariance matrix elements and the sliding window entropy, generates the 3D spatial heat density value, based on the collected spatial coordinate data, maps the 3D spatial heat density value to a 3D grid, fills the heat distribution between discrete points through an interpolation algorithm, generates a 3D spatial heat map, takes the spatio-temporal correlation matrix, the hierarchical warning signals output by the status monitoring and warning module and the corresponding time window identifiers as inputs, according to the warning time window identifier, traces back to the original operation log batches in the cache gateway, extracts the abnormal event type distribution and the time stamp sequence, filters the coordinate points with the spatio-temporal correlation matrix elements greater than 0.7, marks them as the occurrence locations of abnormal events, constructs an abnormal event traceability map, defines abnormal event nodes including time stamps, sliding window entropy, warning levels and associated spatial coordinates, if two abnormal event nodes share the same coordinate points in the spatio-temporal correlation matrix, then the edge weights of the abnormal event traceability map are determined by the difference in the sliding window entropy of the two abnormal events, and the nodes and edges are rendered in layers according to the weights, with high-weight edges highlighted in red and low-weight edges faded in gray.

[0084] First, build a star-ring hybrid network architecture through the topology network deployment module, use a low-latency protocol to establish a communication channel between modules, ensure the basic support for the synchronous transmission of AI data streams, then, the data stream spatio-temporal data acquisition module collects operation logs and node spatial coordinates in real time on the hybrid topology, extracts the sliding window entropy and the multi-dimensional covariance matrix after preprocessing, forms a feature set reflecting the dynamic characteristics and spatial distribution of data flow, immediately afterwards, the optimization and verification module drives the quantum optimization algorithm to solve the optimal weight parameters based on the extracted spatio-temporal features, and at the same time uses the blockchain distributed ledger to perform trusted verification on the decision-making process, outputs an optimized result with both efficiency and security, further, the status monitoring and warning module dynamically integrates the optimized weights and verification results, calculates the comprehensive determination value through an adaptive threshold learning algorithm, realizes the real-time hierarchical warning of the AI data stream status, finally, the visualization and traceability module maps the monitoring data and the topology structure to a 3D space, generates a heat map to visually display the abnormal distribution, and constructs a traceability map in combination with a graph neural network, supporting the operation and maintenance personnel to quickly locate the root cause of the fault from a global perspective. Each module forms a complete solution from network deployment, feature extraction, intelligent optimization to status perception and abnormal traceability through closed-loop data flow and collaborative decision-making.

[0085] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A cluster aggregation communication system for AI data stream processing, characterized by: It includes topology network deployment module, data flow spatiotemporal data acquisition module, optimization and verification module, status monitoring and early warning module and visual traceability module; The topology network deployment module deploys a star-ring hybrid topology network in the cluster aggregation communication system, combines it with a low-latency protocol, and synchronously processes AI data flows between modules; The data stream spatiotemporal data acquisition module, based on a star-ring hybrid topology network, collects and preprocesses operation log data and spatial coordinate data, and extracts sliding window entropy and covariance matrix of each dimension from them; The optimization verification module constructs a quantum optimization model and a blockchain verification model based on the sliding window entropy and covariance matrix, and outputs optimized weight parameters and trusted verification results; The state monitoring and early warning module dynamically optimizes weight parameters and trustworthy verification results, outputs a comprehensive judgment value, sets an adaptive threshold for the comprehensive judgment value, judges the state of the AI data flow, and issues a graded early warning; The visual tracing module generates a three-dimensional spatial heat map and an abnormal event tracing map.

2. The cluster aggregation communication system for AI data stream processing according to claim 1, characterized in that: In the topology network deployment module, the process of synchronously processing AI data flows between modules includes: In the cluster-converged communication system, a star-shaped backbone network is constructed using high-performance routers, serving as core nodes to connect AI data stream processing terminals and execution terminals. A low-latency protocol-driven ring topology subnet is deployed between the quantum optimization model and the blockchain verification model to form a closed-loop redundant link. Heterogeneous data caching gateways are deployed at the star-ring intersection nodes to dynamically divert the peak and average traffic of AI data streams. A dynamic load balancing algorithm is used to optimize the load threshold of the intersection nodes. The star-shaped backbone adopts a priority scheduling mechanism and distributes AI data streams to the target terminal through dynamic load balancing. The transmission delay is constrained by the size of a single data packet and the number of routing hops. Each node in the ring subnet uses an alternating verification mechanism to process data. After the quantum optimization node processes the data, the blockchain verification node reversely verifies the integrity of the result along the ring path. The verification period is dynamically adjusted by the real-time load feedback factor. When the star backbone load exceeds the limit, the cache gateway triggers the ring diversion path and directly connects the data to the target node via the ring link. The optimal path is selected based on the inverse square of the load rate and the weighted load rate of the ring link. When a node in the ring subnet fails, the low-latency protocol initiates reverse link retransmission.

3. The cluster aggregation communication system for AI data stream processing according to claim 2, characterized in that: In the data stream spatiotemporal data acquisition module, the acquisition and preprocessing process of operation log data and spatial coordinate data includes: Distributed fiber optic sensors are deployed at the edge nodes of the star-shaped backbone network. These sensors capture system events at millisecond frequencies, collect time-stamped operation log data from heterogeneous data streams in real time, and transmit the data to the cache gateway via the star-shaped backbone network. Intelligent edge nodes are deployed on the execution terminal side of the ring topology subnet. Based on spatial sensors, the intelligent edge nodes collect spatial coordinate data of device locations and environmental monitoring points in the clustered communication system, synchronously generate environmental status tags, and push them to the cache gateway through the low-latency protocol of the ring subnet. The denoising threshold is dynamically set according to the signal energy, and the wavelet threshold denoising algorithm is used to filter out the high-frequency noise in the operation log data. The operation log data and spatial coordinate data are matched by timestamps to construct the spatiotemporal correlation matrix.

4. The cluster aggregation communication system for AI data stream processing according to claim 3, characterized in that: In the data stream spatiotemporal data acquisition module, the process of extracting sliding window entropy from the preprocessed operation log data includes: A dual-channel data interface is configured in the heterogeneous data cache gateway. Channel 1 receives the pre-processed star-shaped trunk operation log data and uses the sliding time window segmentation technology to split the continuous log stream into discrete batches. The data stream peak rate V peak Dynamically adjust the time window length W t , count the event type distribution in a single window, and calculate the occurrence frequency p of the i-th type event i ,Based on the event frequency, the sliding window entropy S is obtained through a parallel computing framework.

5. The cluster aggregation communication system for AI data stream processing according to claim 4, characterized in that: In the data stream spatiotemporal data acquisition module, the process of extracting the covariance matrix of each dimension from the pre-processed spatial coordinate data includes: Channel 2 receives the pre-processed spatial coordinate data of the ring subnet and inputs it into the covariance matrix algorithm to calculate the mean and covariance of dimension X and dimension Y, and construct the covariance matrix of each dimension; If the coordinate value of a spatial coordinate data point deviates from the mean by more than 3 times the dimensional standard deviation, it is determined to be an outlier and removed.

6. The cluster aggregation communication system for AI data stream processing according to claim 5, characterized in that: In the optimization verification module, the process of constructing a quantum optimization model and outputting optimized weight parameters includes: Using the quantum annealing algorithm, the sliding window entropy is mapped to the quantum Hamiltonian H, and the coupling coefficient J is constructed. ij With the bias term h i ; Initialize the quantum bit spin state and set the initial temperature T c and final temperature T z Based on the real-time load feedback factor α, the annealing rate T(t) is dynamically adjusted according to the exponential function to generate a quantum optimization model. The energy barrier is traversed through the quantum tunneling effect to make the cluster communication system approach the ground state, measure the final quantum bit state, and convert the final quantum bit state σ i The mean is converted to the optimized weight parameter y q .

7. The cluster aggregation communication system for AI data stream processing according to claim 6, characterized in that: In the optimization verification module, the process of building a blockchain verification model and outputting a trusted verification result includes: Based on smart contract technology, the covariance matrix M is broadcast to each blockchain verification node through a ring topology subnet. Each blockchain verification node uses a double SHA-256 chain structure to calculate the covariance matrix hash value H(M) = SHA256(SHA256(M)). If more than 2 / 3 of the blockchain verification nodes return the same H(M), the data is considered complete. Adopting a distributed consensus mechanism, executing smart contracts in the proposal, verification, and submission stages, and building a blockchain verification model; In the proposal phase, the main blockchain verification node encapsulates the covariance matrix and hash value as a block proposal and broadcasts it along the ring path; During the verification phase, each node verifies the distribution consistency of the covariance matrix based on the 3σ anomaly rejection rule and generates a verification result. If the absolute value of the coordinate value of the k-th data point in dimension i minus the mean of dimension i does not exceed three times the standard deviation of dimension i, the verification result is 1; if the absolute value of the coordinate value of the k-th data point in dimension i minus the mean of dimension i exceeds three times the standard deviation of dimension i, the verification result is 0. In the submission phase, if more than 2 / 3 of the blockchain verification nodes return a verification result of 1, the smart contract generates a digital signature N = ECDSA (H (M), private key) and writes the signed result (M, N) to the blockchain; Dynamically adjust the consensus rounds based on the real-time load rate L of the ring subnet and the load feedback factor β If the consensus is passed, the blockchain verification model outputs a credible verification result y v =1, if consensus fails, the blockchain verification model outputs a credible verification result y v =0.

8. The cluster aggregation communication system for AI data stream processing according to claim 7, characterized in that: In the state monitoring and early warning module, the process of dynamically weighting and optimizing weight parameters and trustworthy verification results to output a comprehensive judgment value includes: Based on the dynamic weight factor γ, the optimization weight parameter y output by the quantum optimization model is q And the trusted verification result y output by the blockchain verification model v Perform dynamic weighting, optimize γ based on historical error backpropagation, and output the comprehensive judgment value y.

9. The cluster aggregation communication system for AI data stream processing according to claim 8, characterized in that: In the state monitoring and warning module, the process of setting an adaptive threshold for the comprehensive judgment value, judging the AI data flow state, and issuing a graded warning includes: Based on the sliding window entropy fluctuation range and covariance matrix stability, the threshold interval [T min ,T max ]; If T min <y<T max , it is determined to be a normal data flow and output to the execution end. If y <T min 、y>T max , and the deviation amplitude Δ=|yT 边界 |≤0.2σ y , then trigger the first level warning, judged as a slightly abnormal data flow, if Δ>0.2σ y , then trigger the second-level warning and emergency response instructions, and determine it as a serious risk data flow; After the data stream processing of each batch is completed, the error rate E is the ratio of the number of false alarms to the total number of early warnings. Based on the error rate, the threshold interval is corrected. The correction process includes: if E > 5%, the threshold interval is expanded to [T min -0.1σ y ,T max +0.1σ y ; if E < 1%, the threshold interval is reduced to [T min +0.05σ y ,T max -0.05σ y ; if 1% < E < 5%, the threshold interval remains unchanged.

10. The cluster aggregation communication system for AI data stream processing according to claim 9, characterized in that: In the visual traceability module, the process of generating a three-dimensional heat map and an abnormal event traceability map includes: Dynamically weight the covariance matrix elements and the sliding window entropy to generate a three-dimensional spatial thermal density value. Based on the collected spatial coordinate data, the three-dimensional spatial thermal density value is mapped to a three-dimensional grid. The thermal distribution between discrete points is filled in through an interpolation algorithm to generate a three-dimensional spatial thermal map. Taking the spatiotemporal correlation matrix, the graded warning signals output by the status monitoring and warning module, and the corresponding time window identifier as input, the algorithm traces back to the original operation log batches in the cache gateway according to the warning time window identifier, extracts the abnormal event type distribution and timestamp sequence, and selects the coordinate points with spatiotemporal correlation matrix elements greater than 0.7, marking them as the locations where abnormal events occurred. Construct an abnormal event traceability map and define abnormal event nodes including timestamps, sliding window entropy, warning levels, and associated spatial coordinates. If two abnormal event nodes share the same coordinate point in the spatiotemporal association matrix, the edge weight of the abnormal event traceability map is determined by the difference in sliding window entropy between the two abnormal events. Nodes and edges are rendered in layers according to weights, with high-weight edges highlighted in red and low-weight edges faded in gray.

Images