Quantum computing-based disaster prevention and rescue method, system, equipment and medium

Abstract

The invention belongs to the technical field of structural data processing and disaster prevention and rescue, and particularly relates to a disaster prevention and rescue method, system and device based on quantum computing and a medium. According to the method, multi-mode quantum sensors are arranged at key points to collect data, noise reduction is carried out on the data through a lambda noise reduction filter, feature extraction is carried out on the noise reduction data through a quantum wavelet transform algorithm, dimension reduction is carried out on the data subjected to feature extraction through quantum principal component analysis, and high-dimensional space mapping is carried out on the dimension reduction data through a kernel function. Vector classification is carried out on the mapped data; the disaster occurrence probability of the classified data is calculated by using quantum Monte Carlo; the disaster influence range is predicted by using a quantum diffusion model; early warning information is generated according to the probability and the disaster influence range; after the scheme is evaluated and optimized, an emergency scheme is issued, disaster prevention and rescue evaluation is carried out according to data before and after a disaster, and suggestions are provided.

Description

Technical Field

[0001] This invention belongs to the field of structural data processing and disaster prevention and relief technology, and in particular relates to a disaster prevention and relief method, system, equipment and medium based on quantum computing. Background Technology

[0002] With the acceleration of global climate change and urbanization, structural disasters such as earthquakes, floods, and landslides are occurring frequently, posing a serious threat to human life and property. Traditional disaster early warning and emergency response systems rely on classical computing technologies and sensor networks to provide basic monitoring and early warning functions. However, traditional sensors are insufficient in terms of accuracy, sensitivity, and anti-interference capabilities, and suffer from high data noise in complex environments, making it difficult to meet the needs of high-precision monitoring. Classical signal processing algorithms are computationally complex and slow when processing large-scale, high-dimensional data, making them unable to respond to disaster monitoring in real time, and their feature extraction accuracy is limited, making it difficult to fully extract information from the data.

[0003] Traditional disaster prediction models, based on classical machine learning algorithms, have limited performance when handling complex nonlinear relationships, exhibiting insufficient prediction accuracy and stability. Especially when dealing with massive amounts of data, classical computing techniques lack the parallel processing capabilities to quickly and accurately predict disaster probability, timing, and impact range. Classical communication technologies have deficiencies in data transmission security and real-time performance; classical encryption technologies face security challenges from quantum computing, and transmission latency and bandwidth bottlenecks make it difficult to meet the high-efficiency requirements of emergency response. Classical IoT technologies are insufficient in device response speed and command execution efficiency, failing to achieve intelligent and automated emergency response. Classical big data analytics techniques are inefficient when processing massive amounts of data, struggling to quickly and accurately assess disaster response effectiveness and identify system deficiencies. Furthermore, classical optimization algorithms have limited performance in generating system optimization suggestions, failing to fully mine data information and propose effective optimization recommendations.

[0004] In summary, disaster prediction suffers from several problems: low data accuracy and weak anti-interference capability in data collection; low data processing efficiency and insufficient disaster prediction accuracy in data processing; high communication latency and slow system response in data communication; and the issuance of early warnings without generating emergency plans when disasters are detected, as well as the lack of post-disaster data evaluation to optimize disaster prediction methods or systems. Summary of the Invention

[0005] To address the aforementioned problems, this invention provides a disaster prevention and relief method, system, equipment, and medium based on quantum computing. This invention collects data by deploying multimodal quantum sensors at key structural points, denoises the data using a λ-denoising filter, extracts features from the denoised data using a quantum wavelet transform algorithm, reduces the dimensionality of the extracted data using quantum principal component analysis, maps the dimensionality-reduced data to a high-dimensional space using a kernel function, performs vector classification on the mapped data, calculates the probability of disaster occurrence using quantum Monte Carlo on the classified data, predicts the disaster's impact range using a quantum diffusion model, generates early warning information based on the probability and the disaster's impact range, distributes the early warning information via quantum communication technology, generates emergency plans based on the disaster's impact range, evaluates and optimizes the plans, distributes the emergency plans, and assesses disaster prevention and relief efforts based on data before and after the disaster, providing recommendations.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a disaster prevention and relief method based on quantum computing, comprising the following steps: Step S1: Deploy multimodal quantum sensors at key points of the structure, collect data from the multimodal quantum sensors in real time, and upload the data to the server in real time. Step S2: After receiving the data, the server uses a λ noise reduction filter to denoise the data, extracts features from the denoised data using an algorithm, and performs dimensionality reduction on the extracted data to obtain higher quality data. Step S3: Map the processed dimensionality-reduced data to a high-dimensional space, classify the mapped data, and use the classified data to assess the probability of disaster occurrence and predict the scope of disaster impact. Step S4: When a disaster occurs, based on the probability of the disaster, an emergency plan is generated based on the disaster impact range prediction data, and the plan is evaluated. The optimal plan after evaluation is optimized by an algorithm, and the emergency plan is distributed through Internet of Things technology. Step S5: Based on the data collected before and after the disaster, the data is aggregated and classified to evaluate the emergency response plan and the disaster level, and optimization suggestions are proposed.

[0007] In a second aspect, the present invention provides a disaster prevention and relief system based on quantum computing, comprising a sensor network construction module, a data preprocessing submodule, a disaster prediction and dissemination module, an emergency response plan module, and a post-disaster assessment and recommendation module. The sensor network module includes a sensor deployment submodule and a data acquisition submodule; by collecting multimodal data from key locations, it provides a data foundation for disaster prediction and emergency response. The sensor deployment submodule collects multimodal data at key points of the structure by deploying multimodal quantum sensors at these key points. To improve the measurement accuracy, a quantum measurement sensitivity S is proposed. q This is used inside the sensor to improve the accuracy of the acquired data; the calculation formula is:

[0008] in, For the sensitivity of quantum sensors, The change in quantum state, For the measurement error of a classic sensor, The number of quantum entangled states; when the sensitivity Only data with a value greater than 1 is valid data; The data acquisition submodule acquires data from the multimodal quantum sensor in real time and transmits the acquired multimodal quantum data to the server via long-connection technology; The data preprocessing submodule includes a data denoising submodule, a feature extraction submodule, and a principal component analysis submodule; it provides high-quality data for further disaster prediction through data preprocessing. The data denoising submodule uses a λ-denoising filter to suppress noise through the coherence of quantum states. Its denoising effect is expressed as:

[0009] in, The signal-to-noise ratio after quantum noise reduction; Signal power; Noise power; t Noise reduction time; The quantum coherence time is used to obtain the denoised multimodal data; the denoising ratio is used to determine whether the data meets the requirements. If it does not meet the requirements, denoising is performed again until it does. The feature extraction submodule uses quantum wavelet transform to perform multi-scale feature extraction on the denoised data. It completes feature extraction through a transform kernel function to obtain high-dimensional data. The kernel function expression is as follows:

[0010] in, The result is a quantum wavelet transform. Signals represented by quantum states; a For scale parameters; b These are translation parameters; These are classical wavelet basis functions; The principal component analysis submodule performs dimensionality reduction on the high-dimensional data after feature extraction using quantum principal component analysis, obtaining the dimensionality-reduced data and calculating its compression efficiency. The calculation formula is as follows:

[0011] Among them, Dim ori Dim represents the original data dimension. red CR represents the dimension of the data after dimensionality reduction; N is the number of qubits. If CR = 1, it means that no dimensionality reduction was performed and the computational efficiency was not improved; CR > 1 means that dimensionality reduction was performed and the computational efficiency was improved; CR < 1 means that the dimension of the data after dimensionality reduction is larger than the dimension of the original data and the computational efficiency is reduced. The disaster prediction and dissemination module includes a data classification submodule, a disaster prediction submodule, and a disaster dissemination submodule; it combines quantum support vector machines and quantum neural networks to predict disaster probability, timing, and impact range, enhancing prediction accuracy; and it employs quantum encrypted communication technology to ensure the secure transmission and real-time dissemination of early warning information, buying time for emergency response. The data classification submodule maps the dimensionality-reduced data to a higher-dimensional space using a quantum kernel function. The formula for calculating the kernel function is as follows:

[0012] in, For quantum state mapping function, Let i be the quantum state in the i-th scenario; the data in the high-dimensional space is classified and calculated using a quantum support vector machine, and the classification calculation function formula is:

[0013] in, The classification results; For Lagrange multipliers; Category labels; For bias terms, The quantum kernel function is used to predict its classification based on the classification results. The disaster prediction submodule uses quantum Monte Carlo simulation to calculate the probability of disaster occurrence from the classified data. The calculation formula is as follows:

[0014] in, The probability of a disaster occurring; The quantum state of a disaster event; Let M be the quantum state of the j-th scenario; M is the number of simulations. The quantum diffusion model is used to predict the disaster impact range of the classified data. The diffusion equation is as follows:

[0015] in, This is the density function of the disaster's impact; The quantum diffusion coefficient; For the Laplace operator; The disaster dissemination submodule, upon confirming the occurrence probability of a disaster, generates early warning information based on data analysis and prediction results. This early warning information is then encrypted using quantum key distribution technology and transmitted via quantum communication to the construction management platform and on-site personnel's terminals, enabling real-time dissemination of the early warning information. The security of quantum key distribution is guaranteed by the non-cloning property of quantum states. The emergency response module includes a response generation submodule, a dynamic adjustment submodule, and a response distribution submodule. Based on quantum optimization algorithms, it generates the optimal emergency response plan and dynamically adjusts personnel evacuation, equipment scheduling, and resource allocation strategies. Through quantum Internet of Things technology, it distributes the emergency response plan to equipment and personnel terminals, optimizing the efficiency of instruction transmission and execution. The scheme generation and optimization submodule generates emergency schemes based on the disaster prediction impact range obtained in step S34; it then evaluates the emergency schemes using a quantum genetic algorithm fitness function, the formula of which is:

[0016] in, This is the fitness value; For the sake of efficiency; For the security of the solution; Cost of the solution; , and Let be the weighting coefficient, satisfying The optimal contingency plan is obtained based on the fitness value; the optimal contingency plan after evaluation is optimized using quantum state encoding, and the optimization process can be expressed as follows:

[0017] in, The optimal quantum state is represented by H, where H is the Hamiltonian and represents the optimization objective. This represents the expected value of the quantum state. The dynamic adjustment submodule combines the optimized solution with denoised real-time multimodal quantum data to dynamically adjust the optimal emergency response plan in real time. The adjustment strategy is as follows:

[0018] in, This is the revised plan; This is the current solution; The learning rate; The gradient of the fitness function is given; for the optimal solution to implement the adjustment, resources are optimally allocated using quantum linear programming (QLP), with the objective function being:

[0019] The constraints are:

[0020] Where Z is the objective function value; Let i be the efficiency coefficient of resource i; The amount allocated to resource i; Let be the coefficient of resource i with respect to constraint j; To constrain the upper limit of j; The solution's distribution sub-module will utilize quantum Internet of Things (IoT) technology to distribute emergency plans to construction equipment and personnel terminals, ensuring real-time transmission and execution of instructions. The communication efficiency of the quantum IoT is determined by the quantum bit transmission rate and network topology, as shown in the formula:

[0021] in, To improve the communication efficiency of the quantum Internet of Things; The number of qubits; This refers to the transmission rate of a quantum bit. Let be the complexity of the network topology; quantum computing is used to optimize the device response time, and the formula is:

[0022] in, For optimized device response time; Line response time; The time reduction brought about by quantum optimization; the quantum Internet of Things uses quantum key distribution technology, and its security can be expressed as:

[0023] in, For the security of the quantum Internet of Things; The probability that an eavesdropper will successfully obtain information is calculated using the following formula:

[0024] in, and These are the quantum states of the sender and receiver, respectively. The post-disaster assessment and recommendation module includes an assessment sub-module and a recommendation sub-module; it utilizes quantum big data analysis technology to assess the effectiveness of disaster response, identify system deficiencies, and propose optimization suggestions to improve system performance. The evaluation submodule uses a quantum clustering algorithm to classify disaster data, and its objective function is:

[0025] Where E is the clustering error; k is the number of clusters; Let x be the i-th cluster; x be the data point; a quantum regression model is used to predict the emergency response effect based on the classified data, and its regression equation is:

[0026] Where y is the predicted value; is a quantum state, representing the input characteristics; H is the Hamiltonian, representing the regression parameter; The error term is defined; the merits of the emergency response plan are determined based on the predicted values; quantum big data analysis technology is used to assess the disaster impact of the categorized data, and the assessment indicators are as follows:

[0027] Where I represents the disaster impact score; Let be the weight of the i-th indicator; Let be a function of the i-th indicator; x represents disaster data; the level of this disaster is determined based on the disaster impact score I; The suggestion submodule, based on quantum clustering and regression results, generates system optimization suggestions, using the following formula:

[0028] in, To optimize the scoring; The weight of the j-th optimization suggestion; Let y be the function of the j-th optimization suggestion; y is the predicted value, which provides optimization suggestions for this category based on the optimization suggestion score.

[0029] A third aspect of the present invention provides an electronic device including a memory 102, a processor 101, a display module 103, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps described in any of the preceding quantum computing-based disaster prevention and relief methods.

[0030] A fourth aspect of the present invention provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps described in any of the preceding quantum computing-based disaster prevention and relief methods.

[0031] The beneficial effects of this invention are as follows: By incorporating a quantum sensitivity algorithm into the sensor, the accuracy and sensitivity of the collected data are improved, providing a high-quality data foundation for the accuracy and reliability of disaster prediction; by reducing data noise, the anti-interference ability of the data is increased. High-dimensional data is obtained through feature extraction, and then dimensionality reduction is performed through principal component analysis to obtain higher-quality data; by improving the parallel processing capability of quantum computing through data preprocessing, the data processing efficiency of disaster prediction is improved; by using a quantum hybrid machine learning model, combining quantum support vector machines and quantum neural networks, the probability, timing, and impact range of disasters are predicted, improving the accuracy and stability of prediction; by adopting quantum communication technology, data latency is reduced and data security is enhanced; by establishing, implementing, and adjusting emergency plans and resource allocation, the efficiency of disaster emergency response is improved, providing guidance for disaster emergency response; by evaluating emergency plans and disaster processes after a disaster, effective optimization suggestions are proposed, improving the overall data processing performance and prediction reliability of the system; this invention realizes a closed-loop operation of disaster prevention and relief through data acquisition, data preprocessing, disaster prediction, emergency plans, and post-disaster assessment, fundamentally changing the limitations of passive response and fragmented processing in traditional disaster response, and providing systematic and forward-looking advantages for disaster prevention and relief work. Attached Figure Description

[0032] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 A flowchart illustrating the method of this invention; Figure 2 This is a schematic diagram of the system structure of the present invention; Figure 3 This is a schematic diagram of the device structure of the present invention.

[0034] Among them, 101 is the processor, 102 is the memory, and 103 is the display module. Detailed Implementation

[0035] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0036] Unless otherwise defined, all technical and scientific terms used in this application have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this application and in the specification of this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0037] Example 1, as Figure 1 The disaster prevention and relief method based on quantum computing shown includes the following steps: Step S1: Deploy multimodal quantum sensors at key structural points, collect data from the multimodal quantum sensors in real time, and upload the data to the server in real time; the specific steps are as follows: Step S11 involves deploying multimodal quantum sensors, including quantum accelerometers, quantum gyroscopes, quantum humidity sensors, and quantum strain sensors, at key locations on the structure to monitor structural vibration, deformation, stress distribution, and environmental parameters such as temperature and humidity in real time. To improve the measurement accuracy of the data, a quantum measurement sensitivity S is proposed. q This is used inside the sensor to improve the accuracy of the acquired data; the calculation formula is:

[0038] in, For the sensitivity of quantum sensors, The change in quantum state, For the measurement error of a classic sensor, The number of quantum entangled states; when the sensitivity Only data with a value greater than 1 is valid data; Step S12: Real-time data collection is performed on the multimodal quantum sensors deployed at each location, and the collected data is uploaded to the server in real time via long-connection technology.

[0039] Step S2: After receiving the data, the server uses a λ noise reduction filter to denoise the data, extracts features from the denoised data using an algorithm, and then performs dimensionality reduction on the extracted data to obtain higher-quality data. The specific steps are as follows: Step S21: The server receives the multimodal quantum data from each location, applies a λ-denoising filter to the original multimodal quantum data from each location, suppresses noise through the coherence of quantum states, and calculates the denoising effect on the denoised data using the following formula:

[0040] in, The signal-to-noise ratio after quantum noise reduction; Signal power; Noise power; t Noise reduction time; For quantum coherence time; Step S22: Confirm whether the data has been successfully denoised by checking the noise reduction ratio. 20. Proceed to step S23; otherwise, proceed to step S21. Step S23: The denoised multimodal quantum data is processed using algorithms such as quantum Fourier transform and quantum wavelet transform to extract key features of structural vibration, deformation, and environmental changes. Quantum wavelet transform extracts multi-scale features of the signal, resulting in high-dimensional data. The core function of the transform is:

[0041] in The result is a quantum wavelet transform. Signals represented by quantum states; a For scale parameters; b These are translation parameters; These are classical wavelet basis functions; Step S24: Quantum principal component analysis is used to reduce the dimensionality of the high-dimensional data after feature extraction, thereby reducing the N-order covariance matrix of the high-dimensional data. Data is encoded into quantum states using qubits. Quantum superposition, controlled operations, and inverse quantum Fourier transforms are then performed on the quantum state data to obtain eigenvalue phases. The covariance matrix is ​​then extracted based on these phases. The main eigenvalues ​​are determined, and the top k largest eigenvalues ​​and their corresponding eigenvectors are selected. These eigenvectors constitute the dimensionality-reduced data space, resulting in the dimensionality-reduced data. The compression efficiency (CR) of the dimensionality-reduced data is then calculated using the following formula:

[0042] Among them, Dim ori Dim represents the original data dimension. red The dimension of the data after dimensionality reduction; N is the number of qubits; Step S25: Confirm the quality of the dimensionality-reduced data based on the compression efficiency. If CR = 1, it means that no dimensionality reduction was performed and the computational efficiency was not improved; if CR > 1, it means that dimensionality reduction was performed and the computational efficiency was improved; if CR < 1, it means that the dimension of the dimensionality-reduced data is greater than the dimension of the original data and the computational efficiency is reduced.

[0043] Step S3 involves mapping the processed dimensionality-reduced data to a high-dimensional space, classifying the mapped data, and using the classified data to assess the probability of disaster occurrence and predict the scope of disaster impact. The specific steps are as follows: Step S31 involves submitting the preprocessed dimensionality-reduced data to a quantum hybrid machine learning model to train the model to identify early signals of disasters, such as earthquakes, floods, and landslides. Utilizing the parallel processing capabilities of quantum computing, massive amounts of data can be rapidly analyzed to predict the probability, timing, and impact range of disasters, thus enabling data analysis. Step S32: In low-dimensional space, data may be linearly inseparable, meaning that different categories of data cannot be separated by a single straight line (or hyperplane). By mapping the data to a high-dimensional space, the originally linearly inseparable data may become linearly separable. Furthermore, high-dimensional space can provide more feature dimensions, thereby capturing complex patterns and relationships within the data. Using quantum kernel functions Mapping dimensionality-reduced data to a higher-dimensional space involves using kernel functions such as linear kernels, polynomial kernels, and Gaussian kernels; the quantum kernel function is defined as:

[0044] in, For quantum state mapping function, Let be the quantum state in the i-th scenario; classify the data in the high-dimensional space using a quantum support vector machine, and find a hyperplane that maximizes the margin between the two classes of data. The formula for calculating the classification decision function is:

[0045] in, The classification results; For Lagrange multipliers; Category labels; For bias terms, The quantum kernel function is used to predict its classification based on the classification results. Step S33: Use quantum Monte Carlo simulation to calculate the probability of disaster occurrence on the classified data. The calculation formula is as follows:

[0046] in, The probability of a disaster occurring; The quantum state of a disaster event; Let M be the quantum state of the j-th scenario; M be the number of simulations; low-risk threshold: >15%, applicable to situations with a small impact area or sufficient emergency resources. Medium risk threshold: >10%, applicable to situations with moderate impact or moderate emergency resources. High-risk threshold: >5%, applicable to situations with a large impact area or limited emergency resources.

[0047] Different types of disasters (earthquakes, floods, landslides, etc.) have different probabilities of occurrence and affected areas, therefore their threshold values ​​may differ. For earthquake early warning, due to the suddenness and high destructiveness of earthquakes, a lower threshold is typically used. >5%; For flood warnings, due to the high probability of floods and their wide impact, a medium threshold is usually used. >10%; For landslide early warning, because the impact range of landslides is relatively small but highly destructive, a medium threshold is usually used. >10%. In addition, adjustments should be made based on a comprehensive consideration of the actual situation on site for other disaster scenarios.

[0048] Step S34: Use the quantum diffusion model to predict the disaster impact range of the classified data. The diffusion equation is:

[0049] in, Let be the density function of the disaster impact, representing the intensity of the impact at location x and time t; The quantum diffusion coefficient reflects the speed and extent of disaster propagation; For the Laplace operator, it describes the spatial diffusion characteristics of a disaster; Step S35: When a disaster is confirmed to have occurred based on the probability of occurrence, an early warning message is generated based on the data analysis and prediction results. This message is then encrypted using quantum key distribution technology and transmitted via quantum communication to the construction management platform and on-site personnel's terminals. Leveraging the low latency of quantum communication, the early warning message is disseminated in real time. Regarding the security calculation of quantum key distribution, the security is guaranteed by the no-cloning property of quantum states, and its security can be expressed as:

[0050] in, The probability that an eavesdropper will successfully obtain the key is calculated using the following formula:

[0051] in, and These are the quantum states of the sender and receiver, respectively. To optimize quantum communication latency, leveraging the low-latency characteristics of quantum entangled states, the communication latency can be optimized as follows:

[0052] in, d represents the total delay of quantum communication; This is the speed of quantum state transmission, close to the speed of light; This refers to the processing time at the quantum computing center; For the encryption of early warning information, quantum one-time pad encryption technology is adopted. The encryption process of early warning information is as follows:

[0053] in, It is encrypted; For quantum keys; This is a plaintext warning message; This is a bitwise XOR operation; For calculating the bandwidth of quantum communication, the bandwidth is determined by the transmission rate of the qubits, and the formula is as follows:

[0054] in, For quantum communication bandwidth; The number of qubits; This refers to the quantum bit transmission rate.

[0055] Step S4: Based on the probability of disaster occurrence, when the disaster is confirmed, an emergency plan is generated based on the disaster impact range prediction data, and the plan is evaluated. The optimal plan is then optimized using an algorithm, and the emergency plan is distributed via IoT technology. The specific steps are as follows: Step S41: Based on the probability of disaster occurrence, when the disaster occurs, generate an emergency plan according to the predicted impact range of the disaster obtained in step S34. The relationship between the predicted scope of impact and the emergency response plan includes: 1) Emergency resource allocation. Based on the predicted impact range, it can be determined which areas may be severely threatened by the disaster, thereby prioritizing the allocation of emergency resources such as rescue teams, medical equipment, and supplies.

[0056] 2) Evacuation route planning Predicting the impact range can help develop reasonable evacuation routes and prevent people from entering dangerous areas. For example, in the event of a toxic gas leak, safe evacuation routes can be planned based on the impact range predicted by a diffusion model.

[0057] 3) Disaster Response Priority Based on the predicted impact range, disaster response priorities can be determined, with priority given to severely affected areas. For example, in a fire, predicting the direction and speed of fire spread allows for priority protection of potentially threatened residential areas or critical facilities.

[0058] 4) Risk assessment and early warning Impact range prediction can be used to assess the risk level of a disaster and issue corresponding early warning information. For example, based on the inundation range predicted by a flood diffusion model, a flood warning can be issued in advance to remind residents to take precautions.

[0059] Step S42: The emergency response plan is evaluated using the fitness function of the quantum genetic algorithm, the formula of which is:

[0060] in, This is the fitness value; For the sake of efficiency; For the security of the solution; Cost of the solution; , and Let be the weighting coefficient, satisfying The optimal emergency response plan can be determined based on the fitness value. Step S43: The optimal emergency response plan after evaluation is optimized using quantum state encoding. The optimization process can be expressed as follows:

[0061] in, The optimal quantum state is represented by H, where H is the Hamiltonian and represents the optimization objective. This represents the expected value of the quantum state. Step S44: Based on the optimized solution and the real-time multimodal quantum data after noise reduction in step S21, the optimal emergency solution is dynamically adjusted in real time. The adjustment strategy is as follows:

[0062] in, This is the revised plan; This is the current solution; The learning rate; The gradient of the fitness function; Step S45: Optimal resource allocation is performed on the optimal solution for the adjustment, using quantum linear programming (QLP) to optimize resource allocation. The objective function is:

[0063] The constraints are:

[0064] Where Z is the objective function value; Let i be the efficiency coefficient of resource i; The allocation amount for resource i; Let be the coefficient of resource i with respect to constraint j; To constrain the upper limit of j; Step S46 involves using quantum Internet of Things (IoT) technology to distribute emergency plans to construction equipment (such as cranes and excavators) and personnel terminals, ensuring real-time transmission and execution of instructions. The communication efficiency of the quantum IoT is determined by the quantum bit transmission rate and network topology, as shown in the formula:

[0065] in, To improve the communication efficiency of the quantum Internet of Things; The number of qubits; This refers to the transmission rate of a quantum bit. The complexity of the network topology; The formula for optimizing device response time using quantum computing is:

[0066] in, For optimized device response time; Line response time; The time reduction resulting from quantum optimization; The quantum Internet of Things uses quantum key distribution technology, and its security can be expressed as:

[0067] in, For the security of the quantum Internet of Things; The probability that an eavesdropper will successfully obtain information is calculated using the following formula:

[0068] in, and These are the quantum states of the sender and receiver, respectively.

[0069] Step S5: Based on the data collected before and after the disaster, the data is aggregated and classified to evaluate the emergency response plan and disaster level, and optimization suggestions are proposed. The specific steps are as follows: Step S51: Collect multimodal quantum data and emergency response data before and after the disaster, after noise reduction in step S21, and process the data using quantum clustering algorithm and quantum regression model; Step S52: Classify the disaster data using the quantum clustering algorithm. The objective function is:

[0070] Where E is the clustering error; k is the number of clusters; Let x be the i-th cluster; x is the data point. Step S53: Use a quantum regression model to predict the effectiveness of the emergency response based on the classified data. The regression equation is as follows:

[0071] Where y is the predicted value; is a quantum state, representing the input characteristics; H is the Hamiltonian, representing the regression parameter; This is the error term; the merits of a certain quantitative indicator of this emergency plan are determined based on the predicted value; the indicators include, but are not limited to, response time, resource utilization rate, disaster impact degree, safety score, quantum communication efficiency, and probability of disaster occurrence. The corresponding tables for each indicator level are as follows:

[0072] Step S54: Use quantum big data analysis technology to conduct a disaster impact assessment on the classified data. The assessment indicators are as follows:

[0073] Where I represents the disaster impact score; Let be the weight of the i-th indicator; the weight coefficient can be adjusted according to different projects and expert opinions. Let be a function of the i-th indicator; x is the disaster data; the level of this disaster is determined based on the disaster impact score I.

[0074] Disaster Level Table:

[0075] 1) Extremely low impact: The impact of the disaster is minimal, with almost no loss or damage. It is suitable for minor disasters or disaster scenarios that have been successfully prevented.

[0076] 2) Low impact: The disaster has a low impact, causing minor losses or damage, and is suitable for small-scale disasters or controllable disaster scenarios.

[0077] 3) Moderate impact: The disaster has a moderate impact, causing a certain degree of loss or damage. It is applicable to medium-scale disaster scenarios and requires certain emergency measures.

[0078] 4) Higher impact: The disaster has a higher impact, causing significant losses or damage. It is applicable to large-scale disaster scenarios and requires emergency response measures.

[0079] 5) Extremely high impact: The disaster has an extremely high impact, causing significant losses or damage. It applies to large-scale disasters or catastrophic events and requires comprehensive emergency response and post-disaster reconstruction measures.

[0080] Step S55: Based on the quantum clustering and regression results, generate system optimization suggestions, the formula of which is:

[0081] in, To optimize the scoring; The weight of the j-th optimization suggestion; Let y be the function of the j-th optimization suggestion; y is the predicted value, which provides optimization suggestions for this category based on the optimization suggestion score.

[0082] Example 2, as Figure 2 As shown, a disaster prevention and relief system based on quantum computing includes a sensor network construction module, a data preprocessing submodule, a disaster prediction and dissemination module, an emergency response plan module, and a post-disaster assessment and recommendation module. The sensor network module includes a sensor deployment submodule and a data acquisition submodule; by collecting multimodal data from key locations, it provides a data foundation for disaster prediction and emergency response. The sensor deployment submodule collects multimodal data at key points of the structure by deploying multimodal quantum sensors at these key points. To improve the measurement accuracy, a quantum measurement sensitivity S is proposed. q This is used inside the sensor to improve the accuracy of the acquired data; the calculation formula is:

[0083] in, For the sensitivity of quantum sensors, The change in quantum state, For the measurement error of a classic sensor, The number of quantum entangled states; when the sensitivity Only data with a value greater than 1 is valid data; The data acquisition submodule acquires data from the multimodal quantum sensor in real time and transmits the acquired multimodal quantum data to the server via long-connection technology; The data preprocessing submodule includes a data denoising submodule, a feature extraction submodule, and a principal component analysis submodule; it provides high-quality data for further disaster prediction through data preprocessing. The data denoising submodule uses a lambda denoising filter to suppress noise through the coherence of quantum states; its denoising effect is expressed as:

[0084] in, The signal-to-noise ratio after quantum noise reduction; Signal power; Noise power; t Noise reduction time; The quantum coherence time is used to obtain the denoised multimodal data; the denoising ratio is used to determine whether the data meets the requirements. If it does not meet the requirements, denoising is performed again until it does. The feature extraction submodule uses quantum wavelet transform to perform multi-scale feature extraction on the denoised data. It completes feature extraction through a transform kernel function to obtain high-dimensional data. The kernel function expression is as follows:

[0085] in, The result is a quantum wavelet transform. Signals represented by quantum states; a For scale parameters; b These are translation parameters; These are classical wavelet basis functions; The principal component analysis submodule performs dimensionality reduction on the high-dimensional data after feature extraction using quantum principal component analysis, obtaining the dimensionality-reduced data. The compression efficiency (CR) is calculated to determine whether computational efficiency has been improved; the calculation formula is as follows:

[0086] Among them, Dim ori Dim represents the original data dimension. red CR represents the dimension of the data after dimensionality reduction; N is the number of qubits. If CR = 1, it means that no dimensionality reduction was performed and the computational efficiency was not improved; CR > 1 means that dimensionality reduction was performed and the computational efficiency was improved; CR < 1 means that the dimension of the data after dimensionality reduction is larger than the dimension of the original data and the computational efficiency is reduced. The disaster prediction and dissemination module includes a data classification submodule, a disaster prediction submodule, and a disaster dissemination submodule; it combines quantum support vector machines and quantum neural networks to predict disaster probability, timing, and impact range, enhancing prediction accuracy; and it employs quantum encrypted communication technology to ensure the secure transmission and real-time dissemination of early warning information, buying time for emergency response. The data classification submodule maps the dimensionality-reduced data to a higher-dimensional space using a quantum kernel function, which is defined as:

[0087] in, For quantum state mapping function, Let i be the quantum state in the i-th scenario; the data in the high-dimensional space is classified and calculated using a quantum support vector machine, and the classification calculation function formula is:

[0088] in, The classification results; For Lagrange multipliers; Category labels; For bias terms, The quantum kernel function is used to predict its classification based on the classification results. The disaster prediction submodule uses quantum Monte Carlo simulation to calculate the probability of disaster occurrence from the classified data. The calculation formula is as follows:

[0089] in, The probability of a disaster occurring; The quantum state of a disaster event; Let M be the quantum state of the j-th scenario; M is the number of simulations. The quantum diffusion model is used to predict the disaster impact range of the classified data. The diffusion equation is as follows:

[0090] in, This is the density function of the disaster's impact; The quantum diffusion coefficient; For the Laplace operator; The disaster dissemination submodule, upon confirming the occurrence probability of a disaster, generates early warning information based on data analysis and prediction results. This early warning information is then encrypted using quantum key distribution technology and transmitted via quantum communication to the construction management platform and on-site personnel's terminals, achieving real-time dissemination of the early warning information. The security calculation for quantum key distribution is guaranteed by the no-cloning property of quantum states, and its security can be expressed as:

[0091] in, The probability that an eavesdropper will successfully obtain the key is calculated using the following formula:

[0092] in, and These are the quantum states of the sender and receiver, respectively. To optimize quantum communication delay, leveraging the low-latency characteristics of quantum entanglement, the communication delay can be optimized as follows:

[0093] in, d represents the total delay of quantum communication; This is the speed of quantum state transmission, close to the speed of light; This refers to the processing time at the quantum computing center; For the encryption of early warning information, quantum one-time pad encryption technology is adopted. The encryption process of early warning information is as follows:

[0094] in, It is encrypted; For quantum keys; This is a plaintext warning message; This is a bitwise XOR operation; For calculating the bandwidth of quantum communication, the bandwidth is determined by the transmission rate of the qubits, and the formula is as follows:

[0095] in, For quantum communication bandwidth; The number of qubits; This refers to the quantum bit transmission rate.

[0096] The emergency response module includes a response generation submodule, a dynamic adjustment submodule, and a response distribution submodule. Based on quantum optimization algorithms, it generates the optimal emergency response plan and dynamically adjusts personnel evacuation, equipment scheduling, and resource allocation strategies. Through quantum Internet of Things technology, it distributes the emergency response plan to equipment and personnel terminals, optimizing the efficiency of instruction transmission and execution. The scheme generation and optimization submodule generates emergency schemes based on the disaster prediction impact range obtained in step S34; it then evaluates the emergency schemes using a quantum genetic algorithm fitness function, the formula of which is:

[0097] in, This is the fitness value; For the sake of efficiency; For the security of the solution; Cost of the solution; , and Let be the weighting coefficient, satisfying The optimal contingency plan is obtained based on the fitness value; the optimal contingency plan after evaluation is optimized using quantum state encoding, and the optimization process can be expressed as follows:

[0098] in, The optimal quantum state is represented by H, where H is the Hamiltonian and represents the optimization objective. This represents the expected value of the quantum state. The dynamic adjustment submodule combines the optimized solution with denoised real-time multimodal quantum data to dynamically adjust the optimal emergency response plan in real time. The adjustment strategy is as follows:

[0099] in, This is the revised plan; This is the current solution; The learning rate; The gradient of the fitness function is given; for the optimal solution to implement the adjustment, resources are optimally allocated using quantum linear programming (QLP), with the objective function being:

[0100] The constraints are:

[0101] Where Z is the objective function value; Let i be the efficiency coefficient of resource i; The allocation amount for resource i; Let be the coefficient of resource i with respect to constraint j; To constrain the upper limit of j; The solution's distribution sub-module will utilize quantum Internet of Things (IoT) technology to distribute emergency plans to construction equipment and personnel terminals, ensuring real-time transmission and execution of instructions. The communication efficiency of the quantum IoT is determined by the quantum bit transmission rate and network topology, as shown in the formula:

[0102] in, To improve the communication efficiency of the quantum Internet of Things; The number of qubits; This refers to the transmission rate of a quantum bit. Let be the complexity of the network topology; quantum computing is used to optimize device response time, and the formula is:

[0103] in, For optimized device response time; Line response time; The time reduction brought about by quantum optimization; the quantum Internet of Things uses quantum key distribution technology to ensure data security; The post-disaster assessment and recommendation module includes an assessment sub-module and a recommendation sub-module; it utilizes quantum big data analysis technology to assess the effectiveness of disaster response, identify system deficiencies, and propose optimization suggestions to improve system performance. The evaluation submodule uses a quantum clustering algorithm to classify disaster data, and its objective function is:

[0104] Where E is the clustering error; k is the number of clusters; Let x be the i-th cluster; x be the data point; a quantum regression model is used to predict the emergency response effect based on the classified data, and its regression equation is:

[0105] Where y is the predicted value; is a quantum state, representing the input characteristics; H is the Hamiltonian, representing the regression parameter; The error term is defined; the merits of the emergency response plan are determined based on the predicted values; quantum big data analysis technology is used to assess the disaster impact of the categorized data, and the assessment indicators are as follows:

[0106] Where I represents the disaster impact score; Let be the weight of the i-th indicator; Let be a function of the i-th indicator; x represents disaster data; the level of this disaster is determined based on the disaster impact score I; The suggestion submodule, based on quantum clustering and regression results, generates system optimization suggestions, using the following formula:

[0107] in, To optimize the scoring; The weight of the j-th optimization suggestion; Let y be the function of the j-th optimization suggestion; y is the predicted value, which provides optimization suggestions for this category based on the optimization suggestion score.

[0108] Example 3, as Figure 3 As shown, a computer device includes a processor 101, a memory 102, a display module 103, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the quantum computing-based disaster prevention and relief method described in Embodiment 1.

[0109] Example 4: A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the quantum computing-based disaster prevention and relief method described in Example 1.

[0110] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A disaster prevention and relief method based on quantum computing, characterized in that: Includes the following steps: Step S1, Data Acquisition Step: Deploy multimodal quantum sensors at key points of the structure, acquire data from the multimodal quantum sensors in real time, and upload the data to the server in real time; Step S2, data preprocessing step: After receiving the data, the server uses a λ noise reduction filter to denoise the data, uses quantum Fourier transform and quantum wavelet transform to extract features from the denoised data, and performs dimensionality reduction on the extracted data to obtain higher quality data. Step S3, Disaster Prediction and Early Warning Issuance Steps: Map the processed dimensionality-reduced data to a high-dimensional space, classify the mapped data, use the classified data to assess the probability of disaster occurrence and predict the scope of disaster impact, and issue disaster early warning information based on the prediction results; Step S4, Emergency Plan Optimization and Distribution: Based on the probability of disaster occurrence, when the disaster occurs, an emergency plan is generated based on the disaster impact range prediction data, and the plan is evaluated. The optimal plan after evaluation is optimized using quantum state encoding algorithm, and the emergency plan is distributed through quantum Internet of Things. Step S5, Disaster and Solution Assessment: Based on the data collected before and after the disaster, the emergency response plan and disaster level are assessed by aggregating and classifying the data, and optimization suggestions are proposed.

2. The disaster prevention and relief method based on quantum computing according to claim 1, characterized in that: The specific steps for S1 are as follows: Step S11: Deploy multimodal quantum sensors at key locations on the structure and calculate the quantum measurement sensitivity S. q The calculation formula is: in, For the sensitivity of quantum sensors, The change in quantum state, For the measurement error of a classic sensor, The number of quantum entangled states; sensitivity Data with a value greater than 1 is valid data; Step S12: Real-time data collection is performed on the multimodal quantum sensors deployed at each location, and the collected data is uploaded to the server in real time via long-connection technology.

3. The disaster prevention and relief method based on quantum computing according to claim 2, characterized in that: The specific steps for S2 are as follows: Step S21: The server receives the multimodal quantum data from each location, applies a λ-denoising filter to the original multimodal quantum data from each location, suppresses noise through the coherence of quantum states, and calculates the denoising effect on the denoised data using the following formula: in, The signal-to-noise ratio after quantum noise reduction; Signal power; Noise power; t Noise reduction time; For quantum coherence time; Step S22: Confirm whether the data has been successfully denoised by checking the noise reduction ratio.

20. Proceed to step S23; otherwise, proceed to step S21. Step S23: The denoised multimodal quantum data is processed using quantum Fourier transform and quantum wavelet transform. Quantum wavelet transform extracts multi-scale features of the signal to obtain high-dimensional data. The core function of the transform is: in, The result is a quantum wavelet transform. Signals represented by quantum states; a For scale parameters; b These are translation parameters; These are classical wavelet basis functions; Step S24: Quantum principal component analysis is used to reduce the dimensionality of the high-dimensional data after feature extraction, thereby reducing the N-order covariance matrix of the high-dimensional data. Data is encoded into quantum states using qubits. Quantum superposition, controlled operations, and inverse quantum Fourier transforms are then performed on the quantum state data to obtain eigenvalue phases. The covariance matrix is ​​then extracted based on these phases. The principal eigenvalues ​​are determined, and the top k largest eigenvalues ​​and their corresponding eigenvectors are selected. These eigenvectors constitute the dimensionality-reduced data space, resulting in the dimensionality-reduced data. The compression efficiency (CR) of the dimensionality-reduced data is then calculated using the following formula: Among them, Dim ori Dim represents the original data dimension. red The dimension of the data after dimensionality reduction; N is the number of qubits; Step S25: Confirm the quality of the dimensionality-reduced data based on the compression efficiency. If CR = 1, it means that no dimensionality reduction was performed and the computation efficiency remains unchanged; if CR > 1, it means that dimensionality reduction was performed and the computation efficiency improved; if CR < 1, it means that the dimension of the data after dimensionality reduction is greater than that of the original data and the computation efficiency decreases.

4. The disaster prevention and relief method based on quantum computing according to claim 3, characterized in that: The specific steps for S3 are as follows: Step S31: Submit the preprocessed dimensionality reduction data to the quantum hybrid machine learning model for data analysis; Step S32, using a quantum kernel function The formula for mapping dimensionality-reduced data to a high-dimensional space is as follows: in, For quantum state mapping function, Let i be the quantum state in the i-th scenario; the data in the high-dimensional space is classified and calculated using a quantum support vector machine, and the classification calculation function formula is: in, The classification results; For Lagrange multipliers; Category labels; For bias terms, The quantum kernel function is used to predict its classification based on the classification results. Step S33: Use quantum Monte Carlo simulation to calculate the probability of disaster occurrence on the classified data. The calculation formula is as follows: in, The probability of a disaster occurring; The quantum state of a disaster event; Let M be the quantum state of the j-th scenario; M is the number of simulations. Step S34: Use the quantum diffusion model to predict the disaster impact range of the classified data. The diffusion equation is: in, Let be the density function of the disaster impact, representing the intensity of the impact at location x and time t; The quantum diffusion coefficient reflects the speed and extent of disaster propagation; For the Laplace operator, it describes the spatial diffusion characteristics of a disaster; Step S35: When a disaster is confirmed to have occurred based on the probability of occurrence, an early warning message is generated based on the data analysis and prediction results. This message is then encrypted using quantum key distribution technology and transmitted via quantum communication to the construction management platform and on-site personnel's terminals, enabling real-time dissemination of the early warning information. The security of quantum key distribution is guaranteed by the non-cloning property of quantum states, and its security can be expressed as: in, The probability that an eavesdropper will successfully obtain the key is calculated using the following formula: in, and These are the quantum states of the sender and receiver, respectively. To optimize quantum communication latency, leveraging the low-latency characteristics of quantum entangled states, the communication latency can be optimized as follows: in, d represents the total delay of quantum communication; This refers to the quantum state transmission speed; This refers to the processing time at the quantum computing center; For the encryption of early warning information, quantum one-time pad encryption technology is adopted. The encryption process of early warning information is as follows: in, It is encrypted; For quantum keys; This is a plaintext warning message; This is a bitwise XOR operation; For calculating the bandwidth of quantum communication, the bandwidth is determined by the transmission rate of the qubits, and the formula is as follows: in, For quantum communication bandwidth; The number of qubits; This refers to the quantum bit transmission rate.

5. The disaster prevention and relief method based on quantum computing according to claim 4, characterized in that: The specific steps for S4 are as follows: Step S41: Based on the probability of disaster occurrence, when the disaster occurs, generate an emergency plan according to the predicted impact range of the disaster obtained in step S34. Step S42: The emergency response plan is evaluated using the fitness function of the quantum genetic algorithm, the formula of which is: in, This is the fitness value; For the sake of efficiency; For the security of the solution; Cost of the solution; , and Let be the weighting coefficient, satisfying The optimal emergency response plan can be determined based on the fitness value. Step S43: The optimal emergency response plan after evaluation is optimized using quantum state encoding. The optimization process can be expressed as follows: in, The optimal quantum state is represented by H, where H is the Hamiltonian and represents the optimization objective. This represents the expected value of the quantum state. Step S44: Based on the optimized solution and the real-time multimodal quantum data after noise reduction in step S21, the optimal emergency solution is dynamically adjusted in real time. The adjustment strategy is as follows: in, This is the revised plan; This is the current solution; The learning rate; The gradient of the fitness function; Step S45: Optimal resource allocation is performed on the optimal solution for the adjustment, using quantum linear programming (QLP) to optimize resource allocation. The objective function is: The constraints are: Where Z is the objective function value; Let i be the efficiency coefficient of resource i; The allocation amount for resource i; Let be the coefficient of resource i with respect to constraint j; To constrain the upper limit of j; Step S46: Emergency response plans are issued using quantum Internet of Things (IoT) technology to ensure real-time transmission and execution of instructions. The communication efficiency of the quantum IoT is determined by the quantum bit transmission rate and network topology, as shown in the formula: in, To improve the communication efficiency of the quantum Internet of Things; The number of qubits; This refers to the transmission rate of a quantum bit. The complexity of the network topology; The formula for optimizing device response time using quantum computing is: in, For optimized device response time; Line response time; The time reduction resulting from quantum optimization; The quantum Internet of Things uses quantum key distribution technology, and its security can be expressed as: in, For the security of the quantum Internet of Things; The probability that an eavesdropper will successfully obtain information is calculated using the following formula: in, and These are the quantum states of the sender and receiver, respectively.

6. The disaster prevention and relief method based on quantum computing according to claim 5, characterized in that: The specific steps for S5 are as follows: Step S51: Collect multimodal quantum data and emergency response data before and after the disaster, after noise reduction in step S21, and process the data using quantum clustering algorithm and quantum regression model; Step S52: Classify the disaster data using the quantum clustering algorithm. The objective function is: Where E is the clustering error; k is the number of clusters; Let x be the i-th cluster; x is the data point. Step S53: Use a quantum regression model to predict the effectiveness of the emergency response based on the classified data. The regression equation is as follows: Where y is the predicted value; is a quantum state, representing the input characteristics; H is the Hamiltonian, representing the regression parameter; This represents the error term; the merits of this emergency response plan are determined based on the predicted values. Step S54: Use quantum big data analysis technology to conduct a disaster impact assessment on the classified data. The assessment indicators are as follows: Where I represents the disaster impact score; Let be the weight of the i-th indicator; Let be a function of the i-th indicator; x represents disaster data; the level of this disaster is determined based on the disaster impact score I; Step S55: Based on the quantum clustering and regression results, generate system optimization suggestions, the formula of which is: in, To optimize the scoring; The weight of the j-th optimization suggestion; Let y be the function of the j-th optimization suggestion; y is the predicted value, which provides optimization suggestions for this category based on the optimization suggestion score.

7. A disaster prevention and relief system based on quantum computing, characterized in that: It includes a sensor network construction module, a data preprocessing sub-module, a disaster prediction and dissemination module, an emergency response plan module, and a post-disaster assessment and recommendations module; The sensor network module includes a sensor deployment submodule and a data acquisition submodule; by collecting multimodal data from key locations, it provides a data foundation for disaster prediction and emergency response. The sensor deployment submodule collects multimodal data from key points in the structure by deploying multimodal quantum sensors at these key points, and proposes a quantum measurement sensitivity S. q This is used inside the sensor to improve the accuracy of the acquired data; the calculation formula is: in, For the sensitivity of quantum sensors, The change in quantum state, For the measurement error of a classic sensor, The number of quantum entangled states; when the sensitivity Only data with a value greater than 1 is valid data; The data acquisition submodule acquires data from the multimodal quantum sensor in real time and transmits the acquired multimodal quantum data to the server via long-connection technology; The data preprocessing submodule includes a data denoising submodule, a feature extraction submodule, and a principal component analysis submodule; it provides high-quality data for disaster prediction through data preprocessing. The data denoising submodule uses a lambda denoising filter to suppress noise through the coherence of quantum states; its denoising effect is expressed as: in, The signal-to-noise ratio after quantum noise reduction; Signal power; Noise power; t Noise reduction time; The quantum coherence time is used to obtain the denoised multimodal data; the denoising ratio is used to determine whether the data meets the requirements. If it does not meet the requirements, denoising is performed again until it does. The feature extraction submodule uses quantum wavelet transform to perform multi-scale feature extraction on the denoised data. It completes feature extraction through a transform kernel function to obtain high-dimensional data. The kernel function expression is as follows: in, The result is a quantum wavelet transform. Signals represented by quantum states; a For scale parameters; b These are translation parameters; These are classical wavelet basis functions; The principal component analysis submodule performs dimensionality reduction on the high-dimensional data after feature extraction using quantum principal component analysis, obtaining the dimensionality-reduced data. The compression efficiency (CR) is calculated to determine whether computational efficiency has been improved; the calculation formula is as follows: Among them, Dim ori Dim represents the original data dimension. red CR represents the dimension of the data after dimensionality reduction; N is the number of qubits. If CR = 1, it means that no dimensionality reduction was performed and the computational efficiency was not improved; CR > 1 means that dimensionality reduction was performed and the computational efficiency was improved; CR < 1 means that the dimension of the data after dimensionality reduction is larger than the dimension of the original data and the computational efficiency is reduced. The disaster prediction and dissemination module combines quantum support vector machines and quantum neural networks to predict disaster probability, timing, and impact range, enhancing prediction accuracy; it also employs quantum encrypted communication technology to ensure the secure transmission and real-time dissemination of early warning information. The emergency response module includes a response generation submodule, a dynamic adjustment submodule, and a response distribution submodule. Based on a quantum optimization algorithm, it generates the optimal emergency response plan and dynamically adjusts personnel evacuation, equipment scheduling, and resource allocation strategies. Through quantum Internet of Things technology, the emergency response plan is distributed to equipment and personnel terminals. The scheme generation and optimization submodule generates emergency schemes based on the disaster prediction impact range obtained in step S34; it then evaluates the emergency schemes using a quantum genetic algorithm fitness function, the formula of which is: in, This is the fitness value; For the sake of efficiency; For the security of the solution; Cost of the solution; , and Let be the weighting coefficient, satisfying The optimal contingency plan is obtained based on the fitness value; the optimal contingency plan after evaluation is optimized using quantum state encoding, and the optimization process can be expressed as follows: in, The optimal quantum state is represented by H, where H is the Hamiltonian and represents the optimization objective. This represents the expected value of the quantum state. The dynamic adjustment submodule combines the optimized solution with denoised real-time multimodal quantum data to dynamically adjust the optimal emergency response plan in real time. The adjustment strategy is as follows: in, This is the revised plan; This is the current solution; The learning rate; The gradient of the fitness function is given; for the optimal solution to implement the adjustment, resources are optimally allocated using quantum linear programming (QLP), with the objective function being: The constraints are: Where Z is the objective function value; Let i be the efficiency coefficient of resource i; The allocation amount for resource i; Let be the coefficient of resource i with respect to constraint j; To constrain the upper limit of j; The solution's distribution sub-module will utilize quantum Internet of Things (IoT) technology to distribute emergency plans to construction equipment and personnel terminals, ensuring real-time transmission and execution of instructions. The communication efficiency of the quantum IoT is determined by the quantum bit transmission rate and network topology, as shown in the formula: in, To improve the communication efficiency of the quantum Internet of Things; The number of qubits; This refers to the transmission rate of a quantum bit. Let be the complexity of the network topology; quantum computing is used to optimize device response time, and the formula is: in, For optimized device response time; Line response time; The time reduction resulting from quantum optimization; The post-disaster assessment and recommendations module includes an assessment sub-module and a recommendations sub-module; it utilizes quantum big data analysis technology to assess the effectiveness of disaster response, identify system deficiencies, and propose optimization suggestions. The evaluation submodule uses a quantum clustering algorithm to classify disaster data, and its objective function is: Where E is the clustering error; k is the number of clusters; Let x be the i-th cluster; x be the data point; a quantum regression model is used to predict the emergency response effect based on the classified data, and its regression equation is: Where y is the predicted value; is a quantum state, representing the input characteristics; H is the Hamiltonian, representing the regression parameter; The error term is defined; the merits of the emergency response plan are determined based on the predicted values; quantum big data analysis technology is used to assess the disaster impact of the categorized data, and the assessment indicators are as follows: Where I represents the disaster impact score; Let be the weight of the i-th indicator; Let be a function of the i-th indicator; x represents disaster data; the level of this disaster is determined based on the disaster impact score I; The suggestion submodule, based on quantum clustering and regression results, generates system optimization suggestions, using the following formula: in, To optimize the scoring; The weight of the j-th optimization suggestion; Let y be the function of the j-th optimization suggestion; y is the predicted value, which provides optimization suggestions for this category based on the optimization suggestion score.

8. The disaster prevention and relief system based on quantum computing according to claim 7, characterized in that: The disaster prediction and dissemination module includes a data classification submodule, a disaster prediction submodule, and a disaster dissemination submodule; The data classification submodule maps the dimensionality-reduced data to a higher-dimensional space using a quantum kernel function. The formula for calculating the kernel function is as follows: in, For quantum state mapping function, Let i be the quantum state in the i-th scenario; the data in the high-dimensional space is classified and calculated using a quantum support vector machine, and the classification calculation function formula is: in, The classification results; For Lagrange multipliers; Category labels; For bias terms, The quantum kernel function is used to predict its classification based on the classification results. The disaster prediction submodule uses quantum Monte Carlo simulation to calculate the probability of disaster occurrence from the classified data. The calculation formula is as follows: in, The probability of a disaster occurring; The quantum state of a disaster event; Let M be the quantum state of the j-th scenario; M is the number of simulations. The quantum diffusion model is used to predict the disaster impact range of the classified data. The diffusion equation is as follows: in, This is the density function of the disaster's impact; The quantum diffusion coefficient; For the Laplace operator; The disaster dissemination submodule, upon confirming the occurrence probability of a disaster, generates early warning information based on data analysis and prediction results. This early warning information is then encrypted using quantum key distribution technology and transmitted via quantum communication to the construction management platform and on-site personnel's terminals, achieving real-time dissemination of the early warning information. The security calculation for quantum key distribution is guaranteed by the no-cloning property of quantum states, and its security can be expressed as: in, The probability that an eavesdropper will successfully obtain the key is calculated using the following formula: in, and These are the quantum states of the sender and receiver, respectively. To optimize quantum communication delay, leveraging the low-latency characteristics of quantum entanglement, the communication delay can be optimized as follows: in, d represents the total delay of quantum communication; This refers to the quantum state transmission speed; This refers to the processing time at the quantum computing center; For the encryption of early warning information, quantum one-time pad encryption technology is adopted. The encryption process of early warning information is as follows: in, It is encrypted; For quantum keys; This is a plaintext warning message; This is a bitwise XOR operation; For calculating the bandwidth of quantum communication, the bandwidth is determined by the transmission rate of the qubits, and the formula is as follows: in, For quantum communication bandwidth; The number of qubits; This refers to the quantum bit transmission rate.

9. An electronic device comprising a memory (102), a processor (101), a display module (103), and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the quantum computing-based disaster prevention and relief method as described in any one of claims 1 to 6.

10. A readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the quantum computing-based disaster prevention and relief method as described in any one of claims 1 to 6.

Images