Anti-attack smart park management system, method and device and storage medium

Abstract

The invention discloses an anti-attack smart park management system, method and device, and a storage medium, relates to the technical field of park management, and aims to solve the problem of low regulation and control efficiency of traditional park management on multi-device resources and an access control system. The system comprises an edge trusted processing layer which is used for performing feature compression and integrity verification on multi-source equipment data including energy consumption measurement data, access control biological features and equipment state data through a zero-knowledge proof algorithm, and outputting verification features carrying cryptographic proof; the block chain evidence storage network is used for constructing a distributed account book according to the verification characteristics and generating a charging voucher and an equipment health voucher; the micro-service scheduling center is used for dynamically distributing service resources based on a priority weighted polling algorithm and integrating anti-interference communication to transmit a voucher data packet comprising a charging voucher and an equipment health voucher; and the intelligent decision center is used for generating an access control instruction and an equipment regulation and control strategy based on the digital twin model and the voucher data packet.

Description

Technical Field

[0001] The present application relates to the field of park management technology, and in particular to an attack-resistant smart park management system, method, device and storage medium. Background Art

[0002] With the acceleration of urbanization and the rapid development of science and technology, the park, as an important part of the urban economy, its management level and service quality are directly related to the overall image and economic development of the city.

[0003] Currently, traditional campus management models rely heavily on manual operations. For example, traditional cost accounting relies on manual calculations, a cumbersome process prone to human error, resulting in inaccurate accounting results and, in turn, inefficient resource allocation. Traditional access control relies on physical media such as physical cards, which are prone to loss or duplication, posing security risks and inefficient access control. Consequently, traditional campus management models lack intelligence and are unable to effectively integrate and optimize campus resources, leading to reduced efficiency in controlling multiple device resources and access control systems. Summary of the Invention

[0004] The purpose of this application is to provide an attack-resistant smart campus management system, method, equipment and storage medium, aiming to solve the problem of low efficiency of traditional campus management in regulating multiple device resources and access control systems.

[0005] To achieve the above objectives, this application adopts the following technical solutions: The present application provides an attack-resistant smart campus management system, which includes: an edge trusted processing layer for receiving multi-source device data, and performing feature compression and integrity verification on the multi-source device data through a zero-knowledge proof algorithm, and outputting verification features carrying cryptographic proofs. The multi-source device data includes energy consumption metering data, access control biometrics, and device status data; a blockchain evidence storage network for building a distributed ledger based on the verification features, and generating billing vouchers and device health certificates; a microservice scheduling hub for dynamically allocating service resources based on a priority-weighted polling algorithm, and integrating anti-interference communication transmission credential data packets, the credential data packets including billing vouchers and device health certificates; an intelligent decision-making hub for generating access control instructions and device regulation strategies based on a digital twin model and credential data packets.

[0006] The attack-resistant smart campus management system provided by the embodiment of the present application performs zero-knowledge proof verification on multi-source device data through the edge trusted processing layer, realizes feature compression and integrity verification under the premise of ensuring data privacy, reduces data transmission volume while ensuring the credibility of the data source; the blockchain evidence storage network builds a distributed ledger and generates a dual-credential mechanism to decouple billing from device health status. When the device is abnormal, the billing voucher can be frozen to prevent erroneous data from entering the settlement process; the microservice scheduling center adopts a priority weighted polling algorithm, combined with anti-interference communication, which can still ensure the stable transmission of credential data packets in complex electromagnetic environments; the intelligent decision-making center integrates digital twin models and real-time credential data, which can not only optimize equipment control strategies through personnel flow predictions, but also adjust access control permissions in time based on biometric attack detection, and finally form a closed-loop control system from data collection to execution feedback, thereby improving the dynamic control efficiency of multi-device resource scheduling and access control systems in the park.

[0007] In some embodiments, the above-mentioned edge trusted processing layer includes: a data cleaning module, which is used to filter out abnormal data in multi-source device data to obtain valid data, and abnormal data is data carrying invalid spatiotemporal labels; a feature distillation module, which is used to compress the feature dimensions of valid data and generate feature vectors; a verification module, which is used to verify the integrity of the feature vector based on a zero-knowledge proof algorithm and output verification features.

[0008] Based on this, this application compresses data dimensions through spatiotemporal anomaly cleaning and feature distillation, combined with zero-knowledge proof verification, to improve data validity and lightweight level at the source, laying the foundation for trusted transmission.

[0009] In some embodiments, the above-mentioned blockchain evidence storage network is specifically used to: generate billing vouchers and equipment health certificates based on verification features, freeze the billing vouchers and issue an alarm when the score of the equipment health certificate is lower than the preset score, and output the unfrozen billing vouchers to the distributed ledger, which includes the property ledger, the owner ledger and the energy supplier ledger.

[0010] Based on this, this application realizes the dynamic binding of equipment status and economic behavior through the freezing mechanism triggered by health score and the three-party account sharing rules, thereby enhancing the accuracy of voucher regulation.

[0011] In some embodiments, the above-mentioned microservice scheduling center includes: a resource allocation module for allocating hardware acceleration channels to the intelligent decision-making center; a dynamic frequency modulation module for dynamically adjusting the communication bandwidth of the hardware acceleration channel according to the load of the blockchain evidence storage network; a protocol switching module for enabling anti-interference communication combining frequency hopping spread spectrum and forward error correction coding when there are power fluctuations in the smart park.

[0012] Based on this, this application ensures the robustness of credential data transmission in extreme environments through dynamic frequency modulation of hardware acceleration channels and protocol switching under power fluctuations.

[0013] In some embodiments, the above-mentioned intelligent decision-making center includes: a digital twin construction module, which is used to integrate the digital twin model and the credential data packet to generate a dynamic image including the device health score; a behavior deduction module, which is used to predict the personnel flow trajectory in the dynamic image through the spatiotemporal graph neural network; an anti-counterfeiting module, which is used to use multi-spectral liveness detection to identify biometric attacks in the dynamic image and obtain biometric authentication results. Multi-spectral liveness detection includes vascular imaging and three-dimensional micro-deformation; a control decision module, which is used to generate access control instructions and equipment control strategies based on the personnel flow trajectory, equipment health score and biometric authentication results.

[0014] Based on this, this application improves the collaborative efficiency of access control and equipment control by integrating three-factor decision-making: health score, personnel trajectory prediction, and biological attack detection.

[0015] In some embodiments, the anti-counterfeiting module is specifically used to: use a pre-trained adversarial generative network to identify deep counterfeit features in dynamic images; generate an alarm message when it is detected that the strength of the deep counterfeit feature exceeds a preset strength; the control decision module is specifically used to trigger a disguised response mechanism, send a false pass signal to the security system, and generate an access control instruction to control the access control actuator to lock the abnormal channel.

[0016] Based on this, this application combines deep fake identification with camouflage response mechanism to upgrade passive interception to active trapping, thereby strengthening the security control capabilities of the access control system.

[0017] In some embodiments, the attack-resistant smart campus management system provided by the embodiments of the present application also includes: a federated learning cluster, which is used to: train the equipment fault prediction model at each edge node to obtain gradient parameters; exchange gradient parameters through homomorphic encryption, generate a global model and synchronize it to the edge trusted processing layer and the intelligent decision-making center, and the global model is used to drive the output of verification features and the generation of equipment control strategies.

[0018] Based on this, this application drives the dual iterative optimization of data verification and strategy generation through encrypted gradient exchange of federated learning and synchronization with the global model.

[0019] The present application provides an attack-resistant smart park management method, which includes: receiving multi-source device data, and performing feature compression and integrity verification on the multi-source device data through a zero-knowledge proof algorithm, and outputting verification features carrying cryptographic proofs, wherein the multi-source device data includes energy consumption metering data, access control biometrics, and device status data; constructing a distributed ledger based on the verification features, and generating billing vouchers and device health credentials; dynamically allocating service resources based on a priority-weighted polling algorithm, and integrating anti-interference communication transmission voucher data packets, wherein the voucher data packets include billing vouchers and device health credentials; generating access control instructions and device regulation strategies based on a digital twin model and the voucher data packets.

[0020] In some embodiments, the above-mentioned feature compression and integrity verification of multi-source device data through a zero-knowledge proof algorithm, and output of verification features carrying cryptographic proofs, include: filtering abnormal data in multi-source device data to obtain valid data, where abnormal data is data carrying invalid time and space labels; compressing the feature dimensions of valid data to generate a feature vector; and performing integrity verification on the feature vector based on a zero-knowledge proof algorithm to output a verification feature.

[0021] In some embodiments, the above-mentioned construction of a distributed ledger based on verification features and generation of billing vouchers and device health certificates includes: generating billing vouchers and device health certificates based on verification features, freezing the billing vouchers and issuing an alarm when the score of the device health certificate is lower than a preset score, and outputting the unfrozen billing vouchers to the distributed ledger, which includes a property ledger, an owner ledger, and an energy supplier ledger.

[0022] In some embodiments, the above-mentioned priority-weighted polling algorithm dynamically allocates service resources and integrates anti-interference communication transmission certificate data packets, including: allocating hardware acceleration channels to the intelligent decision-making center; dynamically adjusting the communication bandwidth of the hardware acceleration channel according to the load of the blockchain evidence storage network; and enabling anti-interference communication combining frequency hopping spread spectrum and forward error correction coding in the presence of power fluctuations in the smart park.

[0023] In some embodiments, the above-mentioned generation of access control instructions and equipment control strategies based on the digital twin model and the credential data packet includes: fusing the digital twin model and the credential data packet to generate a dynamic image including a device health score; predicting the personnel flow trajectory in the dynamic image through a spatiotemporal graph neural network; using multispectral liveness detection to identify biometric attacks in the dynamic image to obtain biometric authentication results, and multispectral liveness detection includes vascular imaging and three-dimensional micro-deformation; generating access control instructions and equipment control strategies based on the personnel flow trajectory, device health score and biometric authentication results.

[0024] In some embodiments, the above-mentioned use of multispectral liveness detection to identify biometric attacks in dynamic images and obtain biometric authentication results includes: using a pre-trained adversarial generative network to identify deep fake features in dynamic images, and generating an alarm message when it is detected that the strength of the deep fake feature exceeds a preset strength; the above-mentioned generation of access control instructions and equipment control strategies based on personnel flow trajectories, equipment health scores and biometric authentication results, including triggering a camouflage response mechanism, sending a false pass signal to the security system, and generating access control instructions to control the access control actuator to lock abnormal channels.

[0025] In some embodiments, the attack-resistant smart park management method provided by the embodiments of the present application also includes: training the equipment fault prediction model at each edge node to obtain gradient parameters; exchanging the gradient parameters through homomorphic encryption, generating a global model and synchronizing it to the edge trusted processing layer and the intelligent decision-making center. The global model is used to drive the output of verification features and the generation of equipment control strategies.

[0026] The present application provides an electronic device comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the above-described anti-attack smart campus management system.

[0027] The present application provides a computer-readable storage medium, which stores instructions. When the instructions are executed on a terminal, the terminal executes the above-described anti-attack smart park management system.

[0028] The present application provides a computer program product comprising instructions, which, when executed by a computer, enables the computer to execute the above-described anti-attack smart park management system.

[0029] The present application provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled, and the processor is used to run computer programs or instructions to implement the above-described attack-resistant smart campus management system.

[0030] Specifically, the chip provided in the embodiment of the present application also includes a memory for storing computer programs or instructions. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0032] Figure 1An architecture diagram of an attack-resistant smart park management system provided in an embodiment of the present application; Figure 2 This is an architectural diagram of the edge trusted processing layer in an attack-resistant smart park management system provided in an embodiment of the present application; Figure 3 An architectural diagram of a microservice scheduling hub in an attack-resistant smart park management system provided in an embodiment of the present application; Figure 4 This is an architectural diagram of an intelligent decision-making center in an attack-resistant smart park management system provided in an embodiment of the present application; Figure 5 A flowchart of an attack-resistant smart park management method provided in an embodiment of the present application; Figure 6 A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0034] In the description of this application, it should be understood that the terms "upper," "lower," "left," "right," "front," "back," "inner," "outer," and the like, indicating directions or positional relationships, are based on the directions or relative positional relationships shown in the accompanying drawings and are intended solely to facilitate the description of this application and simplify the description. They do not indicate or imply that the devices or components referred to must have a specific direction, be constructed, or operate in a specific direction. Therefore, they should not be construed as limitations on this application. Unless otherwise specified, the above-mentioned directionality descriptions may be flexibly set in actual application, provided that the relative positional relationships shown in the accompanying drawings are met.

[0035] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0036] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," "connected," and "connected" should be understood broadly. For example, they may refer to fixed connections, detachable connections, or integral connections. They may be directly connected, indirectly connected through an intermediary, or internally connected between two components. Those skilled in the art will understand the specific meanings of these terms in this application based on the specific circumstances.

[0037] In some embodiments, the terms "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, article, or apparatus that includes the element.

[0038] In some embodiments, words such as "exemplary" or "for example" are used to indicate an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0039] In the description of this specification, specific features, structures, materials or characteristics may be combined in an appropriate manner in any one or more embodiments or examples.

[0040] Currently, park management relies heavily on manual operations, which has the following significant shortcomings: The existing property cost accounting system is highly dependent on manual calculations, involving the integration of multi-source data (such as water and electricity meter readings, common area coefficients) and the application of complex apportionment rules, resulting in a long single accounting cycle. In addition, errors may exist in the manual intervention links (data entry, formula application, and bill generation), resulting in a decrease in the efficiency of resource allocation.

[0041] Traditional access control systems use magnetic cards as identity carriers, which have inherent defects of physical media, such as easy copying, risk of loss, and inconvenience for users to carry, resulting in reduced management efficiency of the access control system.

[0042] Traditional subsystems (security monitoring, energy management, and vehicle scheduling) use independent architectures, and the data and control commands between systems are incompatible, resulting in inefficient equipment linkage control and reduced efficiency in regulating global resources.

[0043] In summary, traditional campus management solutions have the problem of low efficiency in regulating multiple device resources and access control systems.

[0044] In this context, to address the low efficiency of traditional campus management in regulating multiple device resources and access control systems in related technologies, this application provides an attack-resistant smart campus management system, method, device, and storage medium. Through a five-level linkage architecture consisting of an edge trusted processing layer, a blockchain evidence storage network, a microservice scheduling hub, an intelligent decision-making hub, and a federated learning cluster, a closed loop of data collection, trusted evidence storage, resource scheduling, and decision optimization is achieved to improve the efficiency of regulating multiple device resources and access control systems.

[0045] Figure 1 The architecture diagram of the attack-resistant smart park management system provided in the embodiment of the present application. The attack-resistant smart park management system 100 includes a data acquisition layer 110, an edge trusted processing layer 120, a blockchain evidence network 130, a microservice scheduling hub 140, an intelligent decision-making hub 150 and a federated learning cluster 160. Among them, the data acquisition layer 110 is connected to the edge trusted processing layer 120, the edge trusted processing layer 120 is connected to the blockchain evidence network 130 and the federated learning cluster 160 respectively, the blockchain evidence network 130 is connected to the microservice scheduling hub 140, the microservice scheduling hub 140 is connected to the intelligent decision-making hub 150, and the intelligent decision-making hub 150 is connected to the federated learning cluster 160.

[0046] In some embodiments, the edge trusted processing layer 120 is used to receive multi-source device data, perform feature compression and integrity verification on the multi-source device data through a zero-knowledge proof algorithm, and output verification features carrying cryptographic proofs.

[0047] Among them, multi-source device data includes energy consumption metering data, access control biometrics, and device status data.

[0048] Optionally, combined Figure 1 ,like Figure 2 As shown, the edge trusted processing layer 120 may include: a data cleaning module 121 , a feature distillation module 122 , and a verification module 123 .

[0049] In some embodiments, data cleaning module 121 is used to filter out abnormal data from multi-source device data to obtain valid data. Feature distillation module 122 is used to compress the feature dimensions of valid data to generate feature vectors. Verification module 123 is used to verify the integrity of the feature vectors based on a zero-knowledge proof algorithm and output verification features.

[0050] Among them, abnormal data is data with invalid spatiotemporal labels.

[0051] For example, energy consumption metering data can come from smart meters within a campus. Data cleaning module 121 can identify and filter out abnormal data caused by sensor failure or network delays by comparing timestamps with geographic location information. For example, if the timestamp deviates from the Network Time Protocol (NTP) server by more than 5 minutes or the location coordinates deviate from the campus fence by more than 100 meters, the data is considered invalid.

[0052] For example, the feature distillation module 122 may use the t-distributed stochastic neighbor embedding (t-SNE) algorithm to reduce the dimensionality of high-dimensional features. For example, using the t-SNE algorithm, a 128-dimensional feature can be compressed to 8 dimensions while retaining 92% of the between-class variance.

[0053] For example, the verification module 123 may implement zero-knowledge succinct non-interactive argument of knowledge (zk-SNARKs) verification using the Groth zero-knowledge proof protocol. The verification function is:

[0054] Among them, σ is a public parameter generated through a trusted setup ceremony; φ is a circuit constraint that defines the dimensionality compression rule of the feature vector; {c_i} is the committed value of the feature vector v.

[0055] For example, for a 10KB facial feature vector v, an open source library (such as the Libsnark library) can be used to generate a proof (taking <50ms), and the proof size is only 288 bytes.

[0056] In this way, this application compresses data dimensions through spatiotemporal anomaly cleaning and feature distillation, combined with zero-knowledge proof verification, to improve data validity and lightweight level at the source, laying the foundation for trusted transmission.

[0057] In some embodiments, the blockchain evidence network 130 is used to build a distributed ledger based on the verification features output by the edge trusted processing layer 120 and generate billing vouchers and device health credentials.

[0058] Among them, the distributed ledger includes property ledger, owner ledger and energy supplier ledger.

[0059] In the embodiment of the present application, the distributed ledger supports multi-chain parallel and cross-chain interaction; the billing voucher may include billing information such as electricity consumption, water consumption, and gas consumption; the equipment health voucher may include health information such as equipment operating status, failure rate, and maintenance records; the alarm mechanism can be implemented through SMS, email, or application push.

[0060] Exemplarily, the blockchain evidence storage network 130 is specifically used to: generate billing vouchers and device health certificates based on verification features; when the score of the device health certificate is lower than the preset score, freeze the billing voucher and issue an alarm; and output the unfrozen billing voucher to the distributed ledger.

[0061] The preset score may be a manually set value that can be flexibly adjusted according to actual scenarios. For example, the preset score may be 70 points.

[0062] In some embodiments, the score of the device health credential can be calculated using the vibration spectrum entropy value: H=-∑p(f)log2p(f).

[0063] Where p(f) is the power spectral density of frequency f, and the health score S = 100 - 20H. When S < 70, the credential freezing mechanism is triggered.

[0064] For example, if the cooling water pump vibration spectrum H = 1.8 and the health score S = 64, the billing voucher is frozen and a work order (equipment identification, fault code, and unfreezing conditions) is triggered. The unfrozen vouchers are then split into 50% for the property management, 30% for the owner, and 20% for the energy supplier.

[0065] In an embodiment of the present application, the generation of billing vouchers can be based on a prepaid or postpaid mode, supporting complex billing strategies such as tiered electricity prices and peak-valley electricity prices (such as 1.2 yuan / kWh in peak period, 0.8 yuan / kWh in flat period, and 0.4 yuan / kWh in valley period); the scoring of equipment health certificates can be calculated using a fuzzy comprehensive evaluation method or a hierarchical analysis method; the alarm mechanism can integrate functions such as sound and light alarms and automatic dialing.

[0066] In this way, this application realizes the dynamic binding of equipment status and economic behavior through the freezing mechanism triggered by health score and the three-party account sharing rules, thereby enhancing the accuracy of voucher regulation.

[0067] In some embodiments, the microservice scheduling hub 140 is used to dynamically allocate service resources based on a priority-weighted round-robin algorithm and integrate anti-interference communication transmission certificate data packets.

[0068] The credential data package includes billing credentials and device health credentials.

[0069] For example, the microservice scheduling hub 140 can allocate hardware acceleration channels to the intelligent decision-making hub to increase data processing speed. Simultaneously, the communication bandwidth of the hardware acceleration channels is dynamically adjusted based on the load of the blockchain evidence storage network 130 to ensure the rational use of network resources. Furthermore, when interference sources such as power fluctuations exist in the smart park, the system uses an anti-interference communication technology that combines frequency-hopping spread spectrum (FHSS) and forward error correction (FEC) to ensure the complete transmission of credential data packets.

[0070] Specifically, the hardware acceleration channel can be implemented using a graphics processing unit (GPU) or a field-programmable gate array (FPGA) chip; the dynamic adjustment of the communication bandwidth can be achieved based on a network load monitoring algorithm.

[0071] Optionally, combined Figure 1 ,like Figure 3 As shown, the microservice scheduling hub 140 may include: a resource allocation module 141 , a dynamic frequency modulation module 142 , and a protocol switching module 143 .

[0072] For example, the resource allocation module 141 is used to allocate hardware acceleration channels to the intelligent decision-making center. The dynamic frequency modulation module 142 is used to dynamically adjust the communication bandwidth of the hardware acceleration channel according to the load of the blockchain evidence storage network.

[0073] Specifically, when the load rate is less than 30%, the bandwidth is 100 MHz; when the load rate is 30-70%, the bandwidth is 50 MHz; when the load rate is greater than 70%, the bandwidth is 20 MHz.

[0074] Exemplarily, the protocol switching module 143 is used to enable anti-interference communication combining frequency hopping spread spectrum and forward error correction coding when there is power fluctuation in the smart park.

[0075] For example, when power fluctuates, the protocol switching module 143 activates 1024-frequency FHSS, and the frequency hopping sequence is controlled by an advanced encryption standard (AES)-128 pseudo-random code generator; forward error correction can correct 16-byte burst errors, and the coding efficiency reaches 87.5%.

[0076] In this way, the present application ensures the robustness of credential data transmission in extreme environments by dynamically modulating the frequency of the hardware acceleration channel and switching protocols under power fluctuations.

[0077] In some embodiments, the intelligent decision-making center 150 is used to generate access control instructions and equipment control strategies based on the digital twin model and the credential data packet.

[0078] For example, the intelligent decision-making center 150 integrates the digital twin model with the credential data package to generate a dynamic image that includes a device health score. A spatiotemporal graph neural network is used to predict the flow of personnel within the dynamic image. Multispectral liveness detection (including vascular imaging and 3D micro-deformation) is used to identify biometric attacks within the dynamic image, resulting in biometric authentication results. Finally, access control instructions and device control strategies are generated based on the personnel flow, device health score, and biometric authentication results.

[0079] Specifically, the spatio-temporal graph neural network can adopt the spatio-temporal graph convolutional network (ST-GCN) algorithm; multispectral liveness detection can adopt near-infrared and visible light fusion imaging technology; and biometric authentication results can be identified using deep learning algorithms.

[0080] Optionally, combined Figure 1 ,like Figure 4 As shown, the intelligent decision-making center 150 may include: a digital twin construction module 151, a behavior deduction module 152, an anti-counterfeiting module 153, and a control decision module 154.

[0081] Exemplarily, the digital twin construction module 151 is used to fuse the digital twin model with the credential data package to generate a dynamic image that includes a device health score. The behavior deduction module 152 is used to predict the movement of personnel in the dynamic image using a spatiotemporal graph neural network. The anti-counterfeiting module 153 uses multispectral liveness detection to identify biometric attacks in the dynamic image and obtain biometric authentication results. The control decision module 154 is used to generate access control instructions and device control strategies based on the movement of personnel, device health scores, and biometric authentication results.

[0082] Among them, multispectral liveness detection includes vascular imaging and three-dimensional micro-deformation.

[0083] Specifically, the digital twin model is first integrated with the credential data package to construct a dynamic image containing data such as device health scores, personnel location information, and environmental parameters. Subsequently, a spatiotemporal graph neural network is used to predict personnel flow trajectories within the dynamic image, enabling proactive adjustments to access control permissions. Furthermore, multispectral liveness detection technology is used to identify biometric attacks within the dynamic image, ensuring the security of the access control system. Finally, based on the prediction and authentication results, corresponding access control instructions and device control strategies are generated.

[0084] In this way, this application improves the collaborative efficiency of access control and equipment control by integrating three-factor decision-making of health score, personnel trajectory prediction and biological attack detection.

[0085] Optionally, the anti-counterfeiting module 153 is specifically configured to: utilize a pre-trained generative adversarial network to identify deep forgery features in dynamic images, and generate an alarm message when it is detected that the strength of the deep forgery features exceeds a preset strength.

[0086] The preset intensity may be a manually set value, which may be flexibly adjusted according to the scenario, for example, the preset intensity may be 0.9%.

[0087] In some embodiments, a pre-trained generative adversarial network (GAN) can be used to perform in-depth analysis of facial images of people in dynamic mirrors to identify deepfake features (such as unnatural facial expressions, inconsistent lighting, etc.). If a deepfake feature strength of 0.92 is detected, the system generates an alarm message and notifies security personnel for manual review.

[0088] For example, the generative adversarial network can adopt advanced models such as style-based GAN or large-scale GAN; the detection of deep fake features can be achieved by feature extraction and classification algorithms; and the warning information can be sent via SMS, email or application push.

[0089] Optionally, the control decision module 154 is specifically configured to trigger a disguised response mechanism, send a false pass signal to the security system, and generate an access control instruction to control the access control actuator to lock an abnormal channel.

[0090] In some embodiments, when an illegal intrusion or counterfeit attack is detected, a camouflaged response mechanism can be triggered, sending a false access signal to the security system, misleading the attacker into believing the attack was successful. Simultaneously, an access control command is generated, controlling the access control actuator to lock the abnormal passage, preventing further intrusion.

[0091] Specifically, the false pass signal may adopt the same format and encoding method as the real pass signal; the access control actuator may adopt electromagnetic lock or motor drive to achieve the locking and opening of the channel.

[0092] For example, when a three-dimensional mask attack (forgery strength 0.92) is detected, the access control screen displays a green "Verification Passed" indicator light (lasts 3 seconds), sends the real coordinates and attack characteristics to the security background, and finally the electromagnetic lock performs physical locking (power-off locking mode, pulling force >800N).

[0093] In the attack-resistant smart campus management system provided in the embodiment of the present application, zero-knowledge proof verification is performed on multi-source device data through the edge trusted processing layer, and feature compression and integrity verification are achieved under the premise of ensuring data privacy, reducing data transmission volume while ensuring the credibility of the data source; the blockchain evidence storage network builds a distributed ledger and generates a dual-credential mechanism to decouple billing from device health status. When the device is abnormal, the billing voucher can be frozen to prevent erroneous data from entering the settlement process; the microservice scheduling center adopts a priority weighted polling algorithm, combined with anti-interference communication, which can still ensure the stable transmission of credential data packets in complex electromagnetic environments; the intelligent decision-making center integrates digital twin models and real-time credential data, which can not only optimize equipment control strategies through personnel flow predictions, but also adjust access control permissions in time based on biometric attack detection, and finally form a closed-loop control system from data collection to execution feedback, thereby improving the dynamic control efficiency of multi-device resource scheduling and access control systems in the park.

[0094] In some embodiments, the federated learning cluster 160 is used to: train the device fault prediction model at each edge node to obtain gradient parameters, exchange the gradient parameters through homomorphic encryption, generate a global model and synchronize it to the edge trusted processing layer 120 and the intelligent decision-making center 150.

[0095] For example, a device fault prediction model can be trained at each edge node to obtain gradient parameters. Subsequently, the gradient parameters are exchanged using homomorphic encryption technology to ensure data privacy during transmission. Finally, a global model is generated and synchronized to the edge trusted processing layer 120 and the intelligent decision-making hub 150, driving the output of verification features and the generation of device control policies.

[0096] Specifically, the equipment failure prediction model can adopt recurrent neural networks such as long short-term memory (LSTM) or gated recurrent unit (GRU); the synchronization of the global model can be achieved using a distributed consensus algorithm.

[0097] Among them, the global model is used to drive the output of verification features and the generation of equipment control strategies.

[0098] In this way, this application drives the dual iterative optimization of data verification and strategy generation through encrypted gradient exchange of federated learning and synchronization with the global model.

[0099] Refer to the following Figure 5 The attack-resistant smart park management method provided in the embodiment of the present application is described.

[0100] Figure 5 This is a flow chart of the method for the anti-attack smart park management method provided in the embodiment of the present application. The subject of executing the method can be Figure 1 The attack-resistant smart campus management system shown can also be various devices / modules in the attack-resistant smart campus management system, such as integrated circuits or chips, and the embodiments of the present application do not make specific limitations on this.

[0101] For example, Figure 5 As shown, the anti-attack smart park management system provided in the embodiment of the present application may include the following S501 to S504: S501. Receive multi-source device data, perform feature compression and integrity verification on the multi-source device data using a zero-knowledge proof algorithm, and output verification features carrying cryptographic proof.

[0102] Optionally, the feature compression and integrity verification may include: filtering abnormal data in multi-source device data to obtain valid data, compressing the feature dimensions of the valid data, and generating a feature vector; performing integrity verification on the feature vector based on a zero-knowledge proof algorithm, and outputting a verification feature.

[0103] S502: Build a distributed ledger based on the verification features and generate billing vouchers and device health vouchers.

[0104] Optionally, the above-mentioned generation of billing vouchers and device health certificates may include: generating billing vouchers and device health certificates based on verification features, freezing the billing vouchers and issuing an alarm when the score of the device health certificate is lower than a preset score, and outputting the unfrozen billing vouchers to the distributed ledger.

[0105] S503 : Dynamically allocate service resources based on a priority-weighted round-robin algorithm, and integrate anti-interference communication transmission certificate data packets.

[0106] Optionally, the above-mentioned dynamic allocation of service resources may include: allocating a hardware acceleration channel to the intelligent decision-making center; and dynamically adjusting the communication bandwidth of the hardware acceleration channel according to the load of the blockchain evidence storage network.

[0107] Optionally, the above-mentioned integrated anti-interference communication may include: in the event of power fluctuations in the smart park, enabling anti-interference communication combining frequency hopping spread spectrum and forward error correction coding.

[0108] S504. Generate access control instructions and equipment control strategies based on the digital twin model and credential data packet.

[0109] Optionally, the above-mentioned generation of access control instructions and device control strategies may include: integrating the digital twin model and the credential data packet to generate a dynamic image including the device health score, predicting the personnel flow trajectory in the dynamic image through the spatiotemporal graph neural network, and using multispectral liveness detection to identify biometric attacks in the dynamic image to obtain biometric authentication results.

[0110] Among them, multispectral liveness detection includes vascular imaging and three-dimensional micro-deformation.

[0111] Further optionally, the above-mentioned biometric authentication result may include: using a pre-trained adversarial generative network to identify deep fake features in dynamic images, and generating an alarm message when it is detected that the strength of the deep fake feature exceeds a preset strength.

[0112] Optionally, after obtaining the personnel flow trajectory, device health score and biometric authentication results, access control instructions and device regulation strategies can be generated based on the personnel flow trajectory, device health score and biometric authentication results.

[0113] For example, a disguised response mechanism may be triggered to send a false pass signal to the security system, thereby generating an access control instruction to control the access control actuator to lock the abnormal passage.

[0114] Optionally, the attack-resistant smart park management method provided by the embodiment of the present application may also include: training the equipment fault prediction model at each edge node to obtain gradient parameters, exchanging the gradient parameters through homomorphic encryption, generating a global model and synchronizing it to the edge trusted processing layer and the intelligent decision-making center.

[0115] Among them, the global model is used to drive the output of verification features and the generation of equipment control strategies.

[0116] It should be noted that the detailed description of the method embodiment part in this application can refer to the relevant description of the system embodiment part above, and in order to avoid repetition, it will not be repeated here.

[0117] The above mainly introduces the solutions provided by the embodiments of the present application from the perspective of systems and methods. In order to achieve the above functions, the electronic device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily appreciate that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software driven hardware manner depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0118] In the embodiment of the present application, the functional modules of the electronic device can be divided according to the above method. For example, the electronic device can include functional modules corresponding to the functional divisions, or two or more functions can be integrated into one processing module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0119] Figure 6 This is a structural diagram of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device 600 includes but is not limited to: a processor 601 and a memory 602 .

[0120] The memory 602 is used to store executable instructions of the processor 601. It is understandable that the processor 601 is configured to execute instructions to implement the anti-attack smart park management system in the above embodiment.

[0121] It should be noted that those skilled in the art can understand that Figure 6 The electronic device structure shown in the figure does not limit the electronic device, and the electronic device may include Figure 6 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0122] The processor 601 is the control center of the electronic device. It connects the various parts of the entire electronic device using various interfaces and lines. By running or executing software programs and / or modules stored in the memory 602 and calling data stored in the memory 602, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 601 may include one or more processing units. Optionally, the processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly handles wireless communications. It is understood that the modem processor may not be integrated into the processor 601.

[0123] The memory 602 can be used to store software programs and various data. The memory 602 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and application programs required by at least one functional module (such as a determination unit, a processing unit, etc.). Furthermore, the memory 602 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0124] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 602 including instructions. The above instructions can be executed by the processor 601 of the electronic device 600 to implement the attack-resistant smart campus management system in the above embodiment.

[0125] In actual implementation, Figure 1 The steps performed by the data collection layer 110, edge trusted processing layer 120, blockchain evidence network 130, microservice scheduling center 140, intelligent decision center 150 and federated learning cluster 160 can all be performed by Figure 6 The processor 601 in the embodiment calls the computer program stored in the memory 602. The specific execution process can be referred to the description of the method part in the above embodiment, which will not be repeated here.

[0126] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0127] In an exemplary embodiment, the embodiment of the present application also provides a computer program product including one or more instructions, which can be executed by the processor 601 of the electronic device to complete the attack-resistant smart campus management system in the above embodiment.

[0128] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the electronic device, the various processes of the above-mentioned method embodiment are implemented and the same technical effect as the above-mentioned method can be achieved. To avoid repetition, they will not be repeated here.

[0129] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete the full classification or partial functions described above.

[0130] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0131] The units described as separate components may or may not be physically separate, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0132] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0133] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.

[0134] The above are only specific embodiments of the present application, but the scope of protection of this 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. An anti-attack smart park management system, characterized in that: include: The edge trusted processing layer is used to receive multi-source device data, perform feature compression and integrity verification on the multi-source device data using a zero-knowledge proof algorithm, and output verification features with cryptographic proofs. The multi-source device data includes energy consumption metering data, access control biometrics, and device status data. A blockchain evidence storage network is used to build a distributed ledger based on the verification features and generate billing vouchers and device health certificates; A microservice scheduling hub for dynamically allocating service resources based on a priority-weighted round-robin algorithm and integrating an anti-interference communication transmission credential data packet, the credential data packet including the billing credential and the device health credential; The intelligent decision-making center is used to generate access control instructions and equipment control strategies based on the digital twin model and the credential data packet.

2. The system according to claim 1, wherein: The edge trusted processing layer includes: a data cleaning module, configured to filter abnormal data from the multi-source device data to obtain valid data, wherein the abnormal data is data carrying invalid spatiotemporal labels; A feature distillation module is used to compress the feature dimensions of the valid data and generate a feature vector; A verification module is used to perform integrity verification on the feature vector based on the zero-knowledge proof algorithm and output the verification feature.

3. The system according to claim 2, characterized in that The blockchain evidence storage network is specifically used for: Based on the verification feature, generating the billing certificate and the device health certificate; If the score of the device health certificate is lower than a preset score, freeze the billing certificate and issue an alarm; The unfrozen billing voucher is output to the distributed ledger, which includes a property ledger, an owner ledger, and an energy supplier ledger.

4. The system according to claim 1, wherein: The microservice scheduling hub includes: A resource allocation module, configured to allocate a hardware acceleration channel to the intelligent decision-making hub; A dynamic frequency modulation module, configured to dynamically adjust the communication bandwidth of the hardware acceleration channel according to the load of the blockchain evidence storage network; The protocol switching module is used to enable anti-interference communication using a combination of frequency hopping spread spectrum and forward error correction coding when there are power fluctuations in the smart park.

5. The system according to claim 1, wherein: The intelligent decision-making center includes: A digital twin construction module, configured to fuse the digital twin model with the credential data packet to generate a dynamic image including a device health score; A behavior deduction module, used to predict the flow trajectory of people in the dynamic mirror through a spatiotemporal graph neural network; an anti-counterfeiting module for identifying biometric attacks in the dynamic image using multispectral liveness detection, wherein the multispectral liveness detection includes vascular imaging and three-dimensional micro-deformation, and obtaining a biometric authentication result; A control decision module is used to generate the access control instructions and the equipment regulation strategy according to the personnel flow trajectory, the equipment health score and the biometric authentication result.

6. The system according to claim 5, characterized in that The anti-counterfeiting module is specifically used to: Using a pre-trained generative adversarial network to identify deep fake features in the dynamic image; If the strength of the deep fake feature is detected to exceed a preset strength, generating an alarm message; The control decision module is specifically used to trigger a disguised response mechanism, send a false pass signal to the security system, and generate the access control instruction to control the access control actuator to lock the abnormal channel.

7. The system according to claim 1, wherein: Also includes: Federated learning clusters for: Train the device failure prediction model at each edge node to obtain the gradient parameters; The gradient parameters are exchanged through homomorphic encryption to generate a global model and synchronize it to the edge trusted processing layer and the intelligent decision-making center. The global model is used to drive the output of the verification feature and the generation of the device control strategy.

8. An anti-attack smart park management method, characterized in that: The method comprises: Receive multi-source device data, perform feature compression and integrity verification on the multi-source device data using a zero-knowledge proof algorithm, and output verification features with cryptographic proofs. The multi-source device data includes energy consumption metering data, access control biometrics, and device status data. Building a distributed ledger based on the verification features and generating billing vouchers and device health vouchers; Dynamically allocating service resources based on a priority-weighted round-robin algorithm and integrating an anti-interference communication transmission credential data packet, the credential data packet including the billing credential and the device health credential; Based on the digital twin model and the credential data packet, access control instructions and equipment control strategies are generated.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method of claim 8.

10. A computer-readable storage medium storing instructions, characterized in that: When a computer executes the instruction, the computer performs the method of claim 8 .

Images