Global Data Sensing Method, Device and Equipment Based on Diffusion Model

Abstract

This application relates to a global data sensing method, device, and equipment based on a diffusion model. The method includes: obtaining local monitoring data corresponding to a building structure and obtaining a target posterior differential model, and then obtaining initial global sensing data corresponding to the building structure, and then iteratively solving the target posterior differential model according to the local monitoring data and the initial global sensing data to obtain target global sensing data corresponding to the building structure. Using this method can improve the monitoring accuracy of global sensing data.

Description

Technical Field

[0001] This application relates to the technical field of civil engineering structures, and particularly to a global data sensing method, device, and equipment based on a diffusion model. Background Art

[0002] In the field of civil engineering, in order to ensure that building structures operate in a safe state, it is necessary to monitor the global sensing data of building structures in real time.

[0003] Traditional global data sensing methods based on diffusion models usually deploy sensors at different positions of building structures to obtain global sensing data of building structures; or use conventional machine learning models to calculate the global sensing data of building structures.

[0004] However, the above-mentioned global data sensing method based on the diffusion model has the problem of low monitoring accuracy. Summary of the Invention

[0005] Based on this, in order to solve the above technical problems, it is necessary to provide a global data sensing method, device, and equipment based on a diffusion model that can improve monitoring accuracy.

[0006] In a first aspect, this application provides a global data sensing method based on a diffusion model, including:

[0007] Obtain local monitoring data corresponding to a building structure, and obtain a target posterior differential model, where the target posterior differential model is trained according to sample global sensing data corresponding to the building structure;

[0008] Obtain initial global sensing data corresponding to the building structure, where the initial global sensing data is obtained by sampling a standard multivariate Gaussian distribution;

[0009] Iteratively solve the target posterior differential model according to the local monitoring data and the initial global sensing data to obtain target global sensing data corresponding to the building structure.

[0010] In one embodiment, iteratively solving the target posterior differential model according to the local monitoring data and the initial global sensing data to obtain target global sensing data corresponding to the building structure includes:

[0011] For each iterative solution process, solve the target posterior differential model according to the local monitoring data and the first intermediate global sensing data to obtain second intermediate global sensing data;

[0012] If the current number of iterative solution times reaches the target number of iterative solution times, determine the second intermediate global sensing data as the target global sensing data;

[0013] Wherein, in the case that the current iterative solution process is the first iterative solution process, the first intermediate global sensing data is the initial global sensing data; in the case that the current iterative solution process is not the first iterative solution process, the first intermediate global sensing data is the second intermediate global sensing data obtained from the previous iterative solution process.

[0014] In one embodiment, solving the target posterior differential model according to the local monitoring data and the first intermediate global sensing data to obtain the second intermediate global sensing data includes:

[0015] Determining the prior score corresponding to the current iterative solution process according to the first intermediate global sensing data and the target prior score estimator included in the target posterior differential model, and determining the noise-free global sensing data according to the prior score;

[0016] Determining the likelihood score corresponding to the current iterative solution process according to the noise-free global sensing data and the local monitoring data;

[0017] Determining the second intermediate global sensing data according to the prior score, the likelihood score and the target posterior differential model.

[0018] In one embodiment, the method further includes:

[0019] Obtaining a plurality of sample global sensing data, and iteratively optimizing the initial prior score estimator according to each sample global sensing data to obtain the target prior score estimator; wherein, the plurality of sample global sensing data includes historical global sensing data and / or simulation global sensing data corresponding to the building structure;

[0020] Determining the target posterior differential model according to the target prior score estimator.

[0021] In one embodiment, iteratively optimizing the initial prior score estimator according to each sample global sensing data to obtain the target prior score estimator includes:

[0022] For each iterative optimization process, adding noise to the sample global sensing data corresponding to the iterative optimization process according to different sampling time steps to obtain the sample global sensing data after noise addition corresponding to each sampling time step;

[0023] Optimizing the intermediate prior score estimator according to each sample global state number after noise addition to obtain the optimized intermediate prior score estimator;

[0024] Detecting whether the preset convergence condition is satisfied, and if the preset convergence condition is satisfied, determining the optimized intermediate prior score estimator as the target prior score estimator;

[0025] Among them, when the iterative optimization process is the first iterative optimization process, the intermediate prior score estimator is the initial prior score estimator; when the iterative optimization process is not the first iterative optimization process, the intermediate prior score estimator is the optimized intermediate prior score estimator obtained from the previous iterative optimization process.

[0026] In one embodiment, the sample global sensing data corresponding to the iterative optimization process is denoised according to different sampling time steps to obtain the denoised sample global sensing data corresponding to each sampling time step, including:

[0027] For each sampling time step, obtain the sampling noise corresponding to the sampling time step;

[0028] Denoise the sample global sensing data according to the sampling noise to obtain the denoised sample global sensing data corresponding to the sampling time step.

[0029] In a second aspect, the present application also provides a data monitoring device, including:

[0030] An acquisition module, configured to acquire local monitoring data corresponding to a building structure and acquire a target posterior differential model, where the target posterior differential model is trained according to the sample global sensing data corresponding to the building structure;

[0031] An initial value acquisition module, configured to acquire initial global sensing data corresponding to the building structure, where the initial global sensing data is obtained by sampling a standard multivariate Gaussian distribution;

[0032] A solving module, configured to perform iterative solution on the target posterior differential model according to the local monitoring data and the initial global sensing data to obtain target global sensing data corresponding to the building structure.

[0033] In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the method in the first aspect as described above are implemented.

[0034] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method in the first aspect as described above are implemented.

[0035] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method in the first aspect as described above are implemented.

[0036] The above-mentioned global data sensing method, device, and equipment based on the diffusion model obtain local monitoring data corresponding to the building structure and obtain the target posterior differential model. Then, the initial global sensing data corresponding to the building structure is obtained. Based on the local monitoring data and the initial global sensing data, the target posterior differential model can be iteratively solved to obtain the target global sensing data corresponding to the building structure. Among them, the initial global sensing data is obtained by sampling a standard multivariate Gaussian distribution, and the target posterior differential model is trained according to the sample global sensing data corresponding to the building structure. In this way, the target posterior differential model trained based on the initial global sensing data for the sample global sensing data is iteratively solved, and the local monitoring data of the building structure is integrated during the iterative solution process. Finally, the target global sensing data corresponding to the target building structure is automatically obtained, avoiding the problems of low monitoring accuracy caused by the possible incomplete deployment of sensors in the related technology when obtaining the global sensing data of the building structure by arranging sensors at different positions of the building structure, and the problems of low monitoring accuracy caused by sensitivity to noise when using conventional machine learning models to calculate the global sensing data of the building structure. The target global sensing data of the building structure obtained through the technical solution provided in this application is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] To more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can be obtained based on these drawings.

[0038] Figure 1 It is an application environment diagram of the global data sensing method based on the diffusion model in an embodiment;

[0039] Figure 2 It is a flowchart of the global data sensing method based on the diffusion model in an embodiment;

[0040] Figure 3 It is a flowchart of the process of determining the target posterior differential model in another embodiment;

[0041] Figure 4 It is a flowchart of step 203 in another embodiment;

[0042] Figure 5 It is a flowchart of an exemplary global data sensing method based on the diffusion model in an embodiment;

[0043] Figure 6Schematic flow chart of a global data sensing method based on a diffusion model where the building structure is a steel plate shear wall in an embodiment;

[0044] Figure 7 Structural block diagram of a data monitoring device in an embodiment;

[0045] Figure 8 Internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0046] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] In the field of civil engineering, in order to ensure that a building structure works in a safe state, it is necessary to monitor the global sensing data of the building structure in real time.

[0048] In the traditional global data sensing method based on a diffusion model, sensors are usually arranged at different positions of a building structure to obtain the global sensing data of the building structure. However, due to factors such as cost and layout position limitations, these sensors can often only cover some positions of the structure and it is difficult to directly monitor the global sensing data of the building structure. For example, on a 1:10 scale containment model, although hundreds of sensors are arranged, for a surface area of 180 m², its coverage is still negligible. Therefore, this method has the problem of low monitoring accuracy.

[0049] Alternatively, in related technologies, a conventional machine learning model is also used to calculate the global sensing data of a building structure. Conventional machine learning models such as multi-layer perceptrons, convolutional neural networks, long short-term memory models, etc. However, conventional machine learning models rely on a large amount of data for training and are extremely sensitive to noise. The noise will be amplified to the output end of the conventional machine learning model, resulting in low monitoring accuracy.

[0050] In view of this, the present application provides a global data sensing method, device and equipment based on a diffusion model. By obtaining local monitoring data corresponding to a building structure and obtaining a target posterior differential model, and then obtaining initial global sensing data corresponding to the building structure, the target posterior differential model can be iteratively solved according to the local monitoring data and the initial global sensing data to obtain target global sensing data corresponding to the building structure. Among them, the target posterior differential model is trained according to sample global sensing data corresponding to the building structure, and the initial global sensing data is obtained by sampling a standard multivariate Gaussian distribution. In this way, the target posterior differential model trained based on the initial global sensing data for the sample global sensing data is iteratively solved, and the local monitoring data of the building structure is fused in the iterative solving process, and finally the target global sensing data corresponding to the target building structure is automatically obtained, avoiding the problem of low monitoring accuracy caused by the possible incomplete deployment of sensors in the related art when obtaining the global sensing data of the building structure by arranging sensors at different positions of the building structure, and the problem of low monitoring accuracy caused by sensitivity to noise when using a conventional machine learning model to calculate the global sensing data of the building structure. The global sensing data of the building structure obtained by the technical solution provided by the present application has higher accuracy.

[0051] The global data sensing method based on a diffusion model provided by an embodiment of the present application can be applied to an application environment such as Figure 1 shown. Among them, the data storage system can store the data that the server 101 needs to process. The data storage system can be integrated on the server 101, or placed in the cloud or other network servers. The server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0052] In an exemplary embodiment, as Figure 2 shown, a global data sensing method based on a diffusion model is provided. Taking the method applied to the Figure 1 server 101 in it as an example, it includes the following steps 201 to step 203. Among them:

[0053] Step 201, obtain local monitoring data corresponding to a building structure and obtain a target posterior differential model.

[0054] The local monitoring data can be the state data of the building structure at a preset position, and the state data can include the current displacement, deformation, etc. of this part of the position; the local monitoring data can also be the relevant environmental data of the environment where the building structure is located.

[0055] Optionally, the server may obtain local monitoring data through sensors deployed at preset locations of the building structure; optionally, the server may obtain archived local monitoring data from a database.

[0056] After obtaining the local monitoring data, the server can obtain a target posterior differential model for processing the local monitoring data. In an embodiment of the present application, the target posterior differential model is constructed based on a diffusion model and is trained based on sample global sensor data corresponding to the building structure. The target posterior differential model can be a model constructed based on a diffusion model, which can reversely restore the global sensor data that is forward diffused into data noise to the global sensor data corresponding to the local monitoring data based on the local monitoring data.

[0057] Optionally, the server may directly obtain a pre-trained target posterior differential model from a database; optionally, the server may obtain sample global sensor data corresponding to the building structure, and train the target posterior differential model based on the sample global sensor data.

[0058] In an embodiment of the present application, the global sensor data refers to all current status data of the building structure, and the sample global sensor data can be used to train the target posterior differential model. Optionally, the server can obtain historical global sensor data collected by the sensor through a database as sample global sensor data; optionally, the server can simulate the building structure to obtain simulated global sensor data related to the building structure. In this way, the server can use the simulated global sensor data as sample global sensor data.

[0059] Step 202: Acquire initial global sensor data corresponding to the building structure.

[0060] In an embodiment of the present application, in order to solve the target posterior differential model, it is necessary to determine an initial global sensor data. The initial global sensor data can be data noise corresponding to the building structure. The data noise is pure noise data. The server can use the target posterior differential model to reversely restore the data noise to the global sensor data corresponding to the local monitoring data based on the local monitoring data.

[0061] In one possible implementation, the initial global sensor data is obtained by sampling a standard multivariate Gaussian distribution. In this embodiment of the present application, the server needs to first determine the target number of iterative solutions of the target posterior differential model. The server can sample the preset data distribution according to the target number of iterative solutions to obtain the initial state data corresponding to the building structure. The preset data distribution can be the distribution that the global sensor data obeys after continuous diffusion and noise addition. In this embodiment of the present application, the preset data distribution can be a standard multivariate Gaussian distribution.

[0062] Step 203: Iteratively solve the target posterior differential model based on the local monitoring data and the initial global sensing data to obtain the target global sensing data corresponding to the building structure.

[0063] After obtaining the local monitoring data and the initial global sensing data, the server can iteratively solve the target posterior differential model based on the local monitoring data and the initial global sensing data.

[0064] Optionally, the server can set a preset number of iterative solutions. When the iterative solution process reaches this preset number of iterative solutions, the server can obtain the target global sensing data. Optionally, the server can detect whether the results of each iterative solution process tend to be stable. The detection process can include: detecting whether the differences between the results of consecutive iterative solution processes are all within a preset numerical range. If so, it is determined that the results tend to be stable, and the server can determine the target global sensing data based on the results of the iterative solution.

[0065] In this way, in the above embodiment, the target posterior differential model trained based on the initial global sensing data for the sample global sensing data is iteratively solved. The local monitoring data of the building structure is integrated during the iterative solution process, and finally, the target global sensing data corresponding to the target building structure is automatically obtained, avoiding the problem of low monitoring accuracy caused by the possible incomplete deployment of sensors in the related art when obtaining the global sensing data of the building structure by arranging sensors at different positions of the building structure, and the problem of low monitoring accuracy caused by sensitivity to noise when using a conventional machine learning model to calculate the global sensing data of the building structure. The global sensing data of the building structure obtained through the technical solution provided in this application is more accurate.

[0066] In one embodiment, based on the above Figure 2 illustrated embodiment, refer to Figure 3 , this embodiment relates to the process of determining the target posterior differential model. As Figure 3 shown, this process can include Step 301 and Step 302.

[0067] Step 301: Obtain multiple sample global sensing data, and iteratively optimize the initial prior score estimator according to each sample global sensing data to obtain the target prior score estimator.

[0068] In the embodiment of the present application, the target posterior differential model is constructed based on the diffusion model. The diffusion model includes a forward diffusion process and a reverse diffusion process. The forward diffusion process is to iteratively add noise to the conventional global sensing data. After multiple (T times) iterative diffusions, the conventional global sensing data is diffused into data noise that follows a Gaussian distribution with a mean of 0 and a variance of the identity matrix. The reverse diffusion process is to gradually reverse-diffuse the pure noise sampled from the Gaussian distribution into the corresponding global sensing data.

[0069] According to the above principle, the target posterior differential model can be constructed.

[0070] In the process of constructing the target posterior differential model, first obtain the target prior score estimator. In the embodiment of the present application, the server can iteratively optimize the initial prior score estimator through multiple sample global sensing data to obtain the target prior score estimator, where the multiple sample global sensing data includes historical global sensing data corresponding to the building structure and / or simulated global sensing data.

[0071] Let the sample global sensing data after t forward iterative diffusions be x t , and the forward diffusion process can be modeled as a Markov chain. The transition kernel function of each iterative diffusion can be referred to the following formula:

[0072] (1)

[0073] Where, represents the distribution that the sample global sensing data follows after the t-th forward iterative diffusion, and β t represents the noise scaling factor in the t-th forward iterative diffusion, which is used to control the noise intensity added in each forward iterative diffusion process. In the embodiment of the present application, β t <1, and I represents the identity matrix.

[0074] The reparameterized iterative formula in each forward iterative diffusion process can be referred to the following formula:

[0075] (2)

[0076] Where, is the noise sampled from the standard Gaussian distribution.

[0077] Let , and , substituting these parameters into formulas (1) and (2), the following formulas can be obtained:

[0078] , (3)

[0079] In summary, it can be seen that when the number of forward iterative diffusion times \(t\) is large enough, the information carried by the sample global sensing data is gradually eliminated and becomes pure data noise obeying the \(N(0, I)\) distribution.

[0080] Therefore, by mathematically transforming Formulas 1 and 2, the corresponding backward stochastic differential equation can be obtained:

[0081] (4)

[0082] The only unknown term in Formula 4 is the prior probability distribution of the prior score. Then, the initial prior score estimator can be set as . In this initial prior score estimator, \(\theta\) represents the parameter to be optimized in the initial prior score estimator, \(x(t)\) is the sample global sensing data after \(t\) times of forward iterative diffusion, and \(t\) is the number of forward iterative diffusion times. Based on the above formula, the relevant objective function of the initial prior score estimator can be set, which can be specifically referred to the following formula:

[0083] (5)

[0084] In this way, based on the above objective function, the server can iteratively optimize the initial prior score estimator according to each sample global sensing data to obtain the target prior score estimator.

[0085] Regarding the specific iterative optimization process, the server can preset a loss function. In this way, the server can iteratively optimize the target prior score estimator according to the above optimization objective function and the preset loss function, so as to obtain the target prior score estimator.

[0086] In a possible implementation manner, for each iterative optimization process, the server can add noise to the sample global sensing data corresponding to the iterative optimization process according to different sampling time steps to obtain the sample global sensing data after noise addition corresponding to each sampling time step, and optimize the intermediate prior score estimator according to each sample global state number after noise addition to obtain the optimized intermediate prior score estimator. At this time, the server can detect whether the preset convergence condition is satisfied. If the preset convergence condition is satisfied, it is determined that the optimized intermediate prior score estimator is the target prior score estimator; where, in the case that the iterative optimization process is the first iterative optimization process, the intermediate prior score estimator is the initial prior score estimator; in the case that the iterative optimization process is not the first iterative optimization process, the intermediate prior score estimator is the optimized intermediate prior score estimator obtained from the previous iterative optimization process.

[0087] In the embodiments of the present application, for each iteration optimization process, multiple sampling time steps can be uniformly sampled first. For example, the number of sampling time steps can be M, and the sampling time steps can be set as t j , where , j represents the serial number corresponding to each sampling time step.

[0088] According to different sampling time steps, the server can perform noise addition processing on the sample global sensing data corresponding to the iteration optimization process, so as to obtain the sample global sensing data after noise addition processing corresponding to each sampling time step. This process can specifically include: for each sampling time step, the server obtains the sampling noise corresponding to the sampling time step, and performs noise addition processing on the sample global sensing data according to the sampling noise, so as to obtain the sample global sensing data after noise addition processing corresponding to the sampling time step.

[0089] In the embodiments of the present application, for each sampling time step, the server can sample the sampling noise from the standard normal distribution according to the sampling time step, and the sampling noise is the data noise corresponding to the above , and the server can substitute the sampling noise and the sample global sensing data into the above formula 3, and the sample global sensing data after noise addition processing corresponding to the sampling time step can be obtained.

[0090] After obtaining the sample global sensing data after noise addition processing corresponding to each sampling time step, the server can optimize the intermediate prior score estimator according to the sample global sensing data after each noise addition processing, so as to obtain the optimized intermediate prior score estimator. Therefore, the server can preset a loss function, and optimize the intermediate prior score estimator based on the loss function, the above objective function, and the sample global sensing data after each noise addition processing.

[0091] It can be understood that the purpose of optimizing the prior score estimator is to accurately evaluate the prior score. Therefore, the server needs to determine the relationship between the data noise and the prior score gradient. From the above formula 3, the data noise and the relationship between the prior score gradient can be determined, which can be specifically referred to the following formula:

[0092] (6)

[0093] Based on this, the loss function corresponding to each iteration optimization process can be specifically referred to the following formula:

[0094] (7)

[0095] That is, for each iteration optimization process, the average value of the error between the prior score evaluated by the prior score estimator corresponding to each sampling time step and the prior score gradient is calculated. This average value is the loss value. By making it as small as possible, a more optimized prior score estimator can be obtained.

[0096] In the embodiments of the present application, after each round of iterative optimization, the server can detect whether the preset convergence condition is met. Optionally, the preset convergence condition may include whether the number of current iterative optimizations has reached the preset number; optionally, the preset convergence condition may also include whether the loss value has reached the preset threshold; optionally, the preset convergence condition may also include whether the loss value tends to be stable. It can be understood that the server can detect whether any one of the above preset convergence conditions is met to determine the target prior score estimator, or the server can also detect whether all the above preset convergence conditions are simultaneously met to determine the target prior score estimator.

[0097] Step 302, determine the target posterior differential model according to the target prior score estimator.

[0098] In the embodiments of the present application, in order to incorporate the local monitoring data y into the sampling process, the prior score in the above formula 4 can be replaced with the posterior score to obtain the posterior differential model, so that subsequently, the pure data noise sampled from the Gaussian distribution can be gradually reversed and diffused into the corresponding global sensing data by using the local monitoring data y. The posterior differential model can be referred to the following formula:

[0099] (8)

[0100] For the convenience of calculation, the server can use a preset method (such as Bayes' formula) to split the posterior score into the posterior score and the likelihood score. The splitting result can be referred to the following formula:

[0101] (9)

[0102] Among them, the prior score can be estimated by using the obtained target prior score estimator, so as to obtain the final target posterior differential equation.

[0103] Regarding the likelihood score, its specific calculation process can be referred to the following content.

[0104] In a possible implementation manner, the following approximation can be made to the likelihood score first:

[0105] (10)

[0106] In this way, the unclear probability distribution Approximated as a relatively well-defined probability distribution , where is an estimated value of the global sensing data.

[0107] Based on the above, it can be understood that the probability distribution characterizes the probability distribution that the global sensing data is when the local monitoring data is y, and regarding it can be estimated by the following formula:

[0108] (11)

[0109] In the current scenario, the approximated likelihood function describes a forward problem with a unique solution and the solution is stable, and it can be processed in a relatively simple way.

[0110] Since the likelihood function describes the probability distribution of observing the local monitoring data y given the estimated value of the global sensing data , that is, this likelihood function is constructed based on the forward diffusion model, therefore, an abstract forward diffusion model can be defined, specifically referring to the following formula:

[0111] (12)

[0112] where A(·) maps the global sensing data to the local monitoring data y, and quantifies the error in the local monitoring data by introducing Gaussian noise n, and its standard deviation σ can be determined according to the actual acquisition scenario of the local monitoring data.

[0113] When the physical quantities of the global sensing data and the local monitoring data of the building structure are the same, the observation matrix can be used as the forward model to directly extract the local monitoring data from the estimated global sensing data, and this method is relatively simple; if there are differences in the physical quantities of the global sensing data and the local monitoring data, a neural network needs to be used to construct a differentiable mapping relationship between the two. The specific process is to first obtain training data through numerical simulation and on-site measurement, and then use deep learning algorithms such as multi-layer perceptrons to learn and approximate the complex mapping relationship between the physical quantities of the global sensing data and the local monitoring data, so as to train and obtain the forward model.

[0114] Regarding the training process of the forward model, the following content can be referred to: input the sample global sensing data into the forward model to obtain the predicted local monitoring data output by the forward model, and continuously adjust the relevant parameters of the forward model according to the predicted local monitoring data, the local monitoring data, and a preset loss function, so as to obtain a trained forward model.

[0115] After obtaining the trained forward model, the server can model the likelihood function and then derive the likelihood score. By combining the expressions of the likelihood score and the prior score, a stochastic differential equation with the posterior score can be modeled.

[0116] The specific formula of the likelihood function can refer to the following formula:

[0117] (13)

[0118] Taking the logarithm and derivative of it, the final likelihood score can be obtained:

[0119] (14)

[0120] Among them, the hyperparameter , this parameter is used to quantify the credibility of local monitoring data, and the specific value is determined according to the actual acquisition scenario of local monitoring data.

[0121] Substituting this likelihood score and the prior score estimated by the above prior score estimator into Formula 8, the target posterior differential model can be obtained.

[0122] In one embodiment, based on the above Figure 2 shown embodiment, see Figure 4 , this embodiment involves the process of iteratively solving the target posterior differential model according to local monitoring data and initial global sensing data to obtain the target global sensing data corresponding to the building structure. As Figure 4 shown, step 203 may include step 401 and step 402.

[0123] Step 401, for each iterative solution process, solve the target posterior differential model according to local monitoring data and the first intermediate global sensing data to obtain the second intermediate global sensing data.

[0124] It can be understood that the target posterior differential model is a continuously backward diffusion process. Therefore, the server can iteratively solve the target posterior differential model based on local monitoring data y and initial global sensing data x T to obtain the final global sensing data x0.

[0125] For each iterative solution process, in a possible implementation manner, based on Figure 3 the shown target posterior differential model, the server can adopt a preset solution method, that is, the Euler-Maruyama method for solution.

[0126] In a possible implementation manner, the target iterative solution number T can be preset first. It can be understood that when T is large enough, the initial global sensing data x TSubject to the standard multivariate Gaussian distribution, it can be sampled from the standard multivariate Gaussian distribution according to the number of iterative solutions.

[0127] Based on the above, the first intermediate global sensing data can be set as x t , where t represents the value obtained by subtracting the current number of iterative solutions from the target number of iterative solutions T.

[0128] For each iterative solution process, in a possible implementation, the server can determine the prior score corresponding to the current iterative solution process according to the first intermediate global sensing data and the target prior score estimator included in the target posterior differential model, and determine the noise-free global sensing data according to the prior score. According to the noise-free global sensing data and the local monitoring data, the server can determine the likelihood score corresponding to the current iterative solution process. According to the prior score, the likelihood score, and the target posterior differential model, the server can determine the second intermediate global sensing data.

[0129] In the embodiment of the present application, the server can estimate the prior score according to the first intermediate global sensing data x t and the target prior score estimator to obtain the prior score .

[0130] According to the prior score and the above formula 11, the server can determine the noise-free global sensing data corresponding to the first intermediate global sensing data x t . .

[0131] According to the noise-free global sensing data and the local monitoring data y, substituting them into the above formula 14, the likelihood score corresponding to the current iterative solution process can be obtained .

[0132] According to the prior score and the likelihood score, substituting them into formula 9, the posterior score corresponding to the current iterative solution process can be obtained .

[0133] According to the posterior score and the target posterior differential model (formula 8), the server can obtain the second intermediate global sensing data x corresponding to the current iterative solution process t-1 .

[0134] Step 402, if the current number of iterative solutions reaches the target number of iterative solutions, then determine the second intermediate global sensing data as the target global sensing data.

[0135] Wherein, in the case that the current iterative solution process is the first iterative solution process, the first intermediate global sensing data is the initial global sensing data; in the case that the current iterative solution process is not the first iterative solution process, the first intermediate global sensing data is the second intermediate global sensing data obtained in the previous iterative solution process.

[0136] It can be understood that after obtaining the second intermediate global sensing data x t-1 the server can monitor whether the number of previous iterative solution times reaches the target iterative solution times T. If so, the server can determine that the iterative solution process ends, and the second intermediate global sensing data x t-1 is the target global sensing data x0.

[0137] In one embodiment, referring to Figure 5 an exemplary global data sensing method based on a diffusion model is provided. This method can be applied to the server in the implementation environment shown in Figure 1 shown.

[0138] Step 501, obtain multiple sample global sensing data, and for each iterative optimization process, for each sampling time step, obtain the sampling noise corresponding to the sampling time step.

[0139] Step 502, perform noise addition processing on the sample global sensing data according to the sampling noise to obtain the sample global sensing data after noise addition processing corresponding to the sampling time step.

[0140] Step 503, optimize the intermediate prior score estimator according to the sample global state numbers after noise addition processing to obtain the optimized intermediate prior score estimator.

[0141] Step 504, detect whether the preset convergence condition is satisfied. If the preset convergence condition is satisfied, determine the optimized intermediate prior score estimator as the target prior score estimator.

[0142] Wherein, in the case that the iterative optimization process is the first iterative optimization process, the intermediate prior score estimator is the initial prior score estimator. In the case that the iterative optimization process is not the first iterative optimization process, the intermediate prior score estimator is the optimized intermediate prior score estimator obtained in the previous iterative optimization process.

[0143] Among them, the multiple sample global sensing data includes historical global sensing data corresponding to the building structure and / or simulation global sensing data.

[0144] Step 505, determine the target posterior differential model according to the target prior score estimator.

[0145] Step 506, obtain the local monitoring data corresponding to the building structure and obtain the target posterior differential model.

[0146] Among them, the target posterior differential model is trained based on the sample global sensing data corresponding to the building structure.

[0147] Step 507: Obtain the initial global sensing data corresponding to the building structure.

[0148] Among them, the initial global sensing data is obtained by sampling from a standard multivariate Gaussian distribution.

[0149] Step 508: For each iteration solving process, determine the prior score corresponding to the current iteration solving process according to the first intermediate global sensing data and the target prior score estimator included in the target posterior differential model, and determine the noiseless global sensing data according to the prior score.

[0150] Step 509: Determine the likelihood score corresponding to the current iteration solving process according to the noiseless global sensing data and the local monitoring data.

[0151] Step 510: Determine the second intermediate global sensing data according to the prior score, the likelihood score and the target posterior differential model.

[0152] Step 511: If the current iteration solving times reach the target iteration solving times, determine the second intermediate global sensing data as the target global sensing data.

[0153] Among them, in the case where the current iteration solving process is the first iteration solving process, the first intermediate global sensing data is the initial global sensing data. In the case where the current iteration solving process is not the first iteration solving process, the first intermediate global sensing data is the second intermediate global sensing data obtained in the previous iteration solving process.

[0154] It should be understood that although each step in the flowcharts involved in the above-mentioned embodiments is displayed sequentially according to the indication of the arrows, these steps do not necessarily need to be executed sequentially according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily need to be executed at the same moment, but can be executed at different moments. The execution order of these steps or stages does not necessarily need to be sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0155] Based on Figure 5 the embodiments shown, refer to Figure 6, taking the steel plate shear wall as an example of the building structure, the process of obtaining the target global sensing data can be seen. This process includes T iterative solution processes. The server first extracts the local monitoring data from the corresponding information collected by the sensors, samples to obtain the initial global sensing data, and based on this, estimates the prior score and the posterior score, and finally obtains the global sensing data.

[0156] Based on the same inventive concept, an embodiment of the present application further provides a data monitoring device for implementing the above-mentioned global data sensing method based on the diffusion model. The implementation solutions provided by this device to solve problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the following data monitoring devices can refer to the limitations on the global data sensing method based on the diffusion model in the above text, and will not be repeated here.

[0157] In an exemplary embodiment, as Figure 7 shown, a data monitoring device is provided, including: an acquisition module 701, an initial value acquisition module 702, and a solution module 703, where:

[0158] The acquisition module 701 is used to acquire the local monitoring data corresponding to the building structure and acquire the target posterior differential model, and the target posterior differential model is trained according to the sample global sensing data corresponding to the building structure;

[0159] The initial value acquisition module 702 is used to acquire the initial global sensing data corresponding to the building structure, and the initial global sensing data is obtained by sampling the standard multivariate Gaussian distribution;

[0160] The solution module 703 is used to iteratively solve the target posterior differential model according to the local monitoring data and the initial global sensing data to obtain the target global sensing data corresponding to the building structure.

[0161] In an embodiment, the solution module 703 includes:

[0162] ! The intermediate solution unit is used to solve the target posterior differential model according to the local monitoring data and the first intermediate global sensing data for each iterative solution process to obtain the second intermediate global sensing data;

[0163] The target determination unit is used to determine the second intermediate global sensing data as the target global sensing data if the current iterative solution times reach the target iterative solution times;

[0164] Wherein, in the case that the current iterative solution process is the first iterative solution process, the first intermediate global sensing data is the initial global sensing data; in the case that the current iterative solution process is not the first iterative solution process, the first intermediate global sensing data is the second intermediate global sensing data obtained in the previous iterative solution process.

[0165] In one embodiment, the intermediate solution unit is specifically configured to perform:

[0166] Determine the prior score corresponding to the current iterative solution process according to the first intermediate global sensing data and the target prior score estimator included in the target posterior differential model, and determine the noise-free global sensing data according to the prior score;

[0167] Determine the likelihood score corresponding to the current iterative solution process according to the noise-free global sensing data and the local monitoring data;

[0168] Determine the second intermediate global sensing data according to the prior score, the likelihood score, and the target posterior differential model.

[0169] In one embodiment, the device further includes:

[0170] An iterative optimization module, configured to obtain a plurality of the sample global sensing data, and iteratively optimize an initial prior score estimator according to each of the sample global sensing data to obtain a target prior score estimator; wherein, the plurality of sample global sensing data includes historical global sensing data and / or simulation global sensing data corresponding to the building structure;

[0171] A model determination module, configured to determine the target posterior differential model according to the target prior score estimator.

[0172] In one embodiment, the iterative optimization module includes:

[0173] A noise addition unit, configured to, for each iterative optimization process, perform noise addition processing on the sample global sensing data corresponding to the iterative optimization process according to different sampling time steps to obtain the sample global sensing data after noise addition processing corresponding to each sampling time step;

[0174] An optimization unit, configured to optimize an intermediate prior score estimator according to each of the sample global state numbers after noise addition processing to obtain an optimized intermediate prior score estimator;

[0175] A detection unit, configured to detect whether a preset convergence condition is satisfied. If the preset convergence condition is satisfied, determine that the optimized intermediate prior score estimator is the target prior score estimator;

[0176] Wherein, when the iterative optimization process is the first iterative optimization process, the intermediate prior score estimator is the initial prior score estimator; when the iterative optimization process is not the first iterative optimization process, the intermediate prior score estimator is the optimized intermediate prior score estimator obtained from the previous iterative optimization process.

[0177] In one embodiment, the noise adding unit is specifically configured to perform:

[0178] For each of the sampling time steps, obtain the sampling noise corresponding to the sampling time step;

[0179] Add noise to the sample global sensing data according to the sampling noise to obtain the sample global sensing data after noise addition corresponding to the sampling time step.

[0180] Each module in the above data monitoring device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0181] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 7 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data monitoring data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a global data sensing method based on a diffusion model.

[0182] Those skilled in the art can understand that Figure 7 the structure shown in

[0183] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0184] Obtain local monitoring data corresponding to a building structure, and obtain a target posterior differential model, where the target posterior differential model is trained according to sample global sensing data corresponding to the building structure;

[0185] Obtain initial global sensing data corresponding to the building structure, where the initial global sensing data is obtained by sampling a standard multivariate Gaussian distribution;

[0186] Iteratively solve the target posterior differential model according to the local monitoring data and the initial global sensing data to obtain target global sensing data corresponding to the building structure.

[0187] In an embodiment, when the processor executes the computer program, the following steps are further implemented:

[0188] For each iterative solution process, solve the target posterior differential model according to the local monitoring data and first intermediate global sensing data to obtain second intermediate global sensing data;

[0189] If the current number of iterative solution times reaches the target number of iterative solution times, determine the second intermediate global sensing data as the target global sensing data;

[0190] Among them, in the case where the current iterative solution process is the first iterative solution process, the first intermediate global sensing data is the initial global sensing data; in the case where the current iterative solution process is not the first iterative solution process, the first intermediate global sensing data is the second intermediate global sensing data obtained in the previous iterative solution process.

[0191] In an embodiment, when the processor executes the computer program, the following steps are further implemented:

[0192] Determine a prior score corresponding to the current iterative solution process according to the first intermediate global sensing data and a target prior score estimator included in the target posterior differential model, and determine noise-free global sensing data according to the prior score;

[0193] Determine a likelihood score corresponding to the current iterative solution process according to the noise-free global sensing data and the local monitoring data;

[0194] Determine the second intermediate global sensing data according to the prior score, the likelihood score, and the target posterior differential model.

[0195] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0196] Obtain a plurality of the sample global sensing data, and iteratively optimize an initial prior score estimator according to each of the sample global sensing data to obtain a target prior score estimator; wherein, the plurality of the sample global sensing data includes historical global sensing data and / or simulated global sensing data corresponding to the building structure;

[0197] Determine the target posterior differential model according to the target prior score estimator.

[0198] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0199] For each iterative optimization process, perform noise addition processing on the sample global sensing data corresponding to the iterative optimization process according to different sampling time steps to obtain the sample global sensing data after noise addition processing corresponding to each of the sampling time steps;

[0200] Optimize an intermediate prior score estimator according to each of the sample global state numbers after noise addition processing to obtain an optimized intermediate prior score estimator;

[0201] Detect whether a preset convergence condition is satisfied. If the preset convergence condition is satisfied, determine the optimized intermediate prior score estimator as the target prior score estimator;

[0202] Wherein, in the case that the iterative optimization process is the first iterative optimization process, the intermediate prior score estimator is the initial prior score estimator; in the case that the iterative optimization process is not the first iterative optimization process, the intermediate prior score estimator is the optimized intermediate prior score estimator obtained from the previous iterative optimization process.

[0203] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0204] For each of the sampling time steps, obtain the sampling noise corresponding to the sampling time step;

[0205] Perform noise addition processing on the sample global sensing data according to the sampling noise to obtain the sample global sensing data after noise addition processing corresponding to the sampling time step.

[0206] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0207] Obtain the local monitoring data corresponding to the building structure, and obtain the target posterior differential model, where the target posterior differential model is trained based on the sample global sensing data corresponding to the building structure;

[0208] Obtain the initial global sensing data corresponding to the building structure, where the initial global sensing data is obtained by sampling from a standard multivariate Gaussian distribution;

[0209] Iteratively solve the target posterior differential model according to the local monitoring data and the initial global sensing data to obtain the target global sensing data corresponding to the building structure.

[0210] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0211] For each iterative solution process, solve the target posterior differential model according to the local monitoring data and the first intermediate global sensing data to obtain the second intermediate global sensing data;

[0212] If the current number of iterative solution times reaches the target number of iterative solution times, determine the second intermediate global sensing data as the target global sensing data;

[0213] Wherein, in the case where the current iterative solution process is the first iterative solution process, the first intermediate global sensing data is the initial global sensing data; in the case where the current iterative solution process is not the first iterative solution process, the first intermediate global sensing data is the second intermediate global sensing data obtained in the previous iterative solution process.

[0214] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0215] Determine the prior score corresponding to the current iterative solution process according to the first intermediate global sensing data and the target prior score estimator included in the target posterior differential model, and determine the noise-free global sensing data according to the prior score;

[0216] Determine the likelihood score corresponding to the current iterative solution process according to the noise-free global sensing data and the local monitoring data;

[0217] Determine the second intermediate global sensing data according to the prior score, the likelihood score and the target posterior differential model.

[0218] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0219] Obtain multiple pieces of the sample global sensing data, and iteratively optimize an initial prior score estimator according to each piece of the sample global sensing data to obtain a target prior score estimator; wherein, the multiple pieces of the sample global sensing data include historical global sensing data and / or simulated global sensing data corresponding to the building structure;

[0220] Determine the target posterior differential model according to the target prior score estimator.

[0221] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0222] For each iterative optimization process, perform noise addition processing on the sample global sensing data corresponding to the iterative optimization process according to different sampling time steps to obtain the sample global sensing data after noise addition processing corresponding to each sampling time step;

[0223] Optimize an intermediate prior score estimator according to each piece of the sample global state data after noise addition processing to obtain an optimized intermediate prior score estimator;

[0224] Detect whether a preset convergence condition is satisfied. If the preset convergence condition is satisfied, determine the optimized intermediate prior score estimator as the target prior score estimator;

[0225] Wherein, in the case where the iterative optimization process is the first iterative optimization process, the intermediate prior score estimator is the initial prior score estimator; in the case where the iterative optimization process is not the first iterative optimization process, the intermediate prior score estimator is the optimized intermediate prior score estimator obtained from the previous iterative optimization process.

[0226] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0227] For each sampling time step, obtain the sampling noise corresponding to the sampling time step;

[0228] Perform noise addition processing on the sample global sensing data according to the sampling noise to obtain the sample global sensing data after noise addition processing corresponding to the sampling time step.

[0229] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0230] Obtain local monitoring data corresponding to a building structure, and obtain a target posterior differential model, where the target posterior differential model is trained according to sample global sensing data corresponding to the building structure;

[0231] Obtain the initial global sensing data corresponding to the building structure, where the initial global sensing data is obtained by sampling a standard multivariate Gaussian distribution;

[0232] Iteratively solve the target posterior differential model according to the local monitoring data and the initial global sensing data to obtain the target global sensing data corresponding to the building structure.

[0233] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0234] For each iterative solution process, solve the target posterior differential model according to the local monitoring data and the first intermediate global sensing data to obtain the second intermediate global sensing data;

[0235] If the current number of iterative solution times reaches the target number of iterative solution times, determine the second intermediate global sensing data as the target global sensing data;

[0236] Wherein, in the case where the current iterative solution process is the first iterative solution process, the first intermediate global sensing data is the initial global sensing data; in the case where the current iterative solution process is not the first iterative solution process, the first intermediate global sensing data is the second intermediate global sensing data obtained in the previous iterative solution process.

[0237] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0238] Determine the prior score corresponding to the current iterative solution process according to the first intermediate global sensing data and the target prior score estimator included in the target posterior differential model, and determine the noise-free global sensing data according to the prior score;

[0239] Determine the likelihood score corresponding to the current iterative solution process according to the noise-free global sensing data and the local monitoring data;

[0240] Determine the second intermediate global sensing data according to the prior score, the likelihood score and the target posterior differential model.

[0241] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0242] Obtain multiple pieces of the sample global sensing data, and iteratively optimize the initial prior score estimator according to each piece of the sample global sensing data to obtain the target prior score estimator; wherein, the multiple pieces of the sample global sensing data include the historical global sensing data and / or the simulation global sensing data corresponding to the building structure;

[0243] Determine the target posterior differential model according to the target prior score estimator.

[0244] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0245] For each iteration optimization process, add noise to the sample global sensing data corresponding to the iteration optimization process according to different sampling time steps, and obtain the sample global sensing data after noise addition corresponding to each sampling time step;

[0246] Optimize the intermediate prior score estimator according to the sample global state numbers after noise addition for each of them, and obtain the optimized intermediate prior score estimator;

[0247] Detect whether a preset convergence condition is satisfied. If the preset convergence condition is satisfied, determine the optimized intermediate prior score estimator as the target prior score estimator;

[0248] Wherein, in the case where the iteration optimization process is the first iteration optimization process, the intermediate prior score estimator is the initial prior score estimator; in the case where the iteration optimization process is not the first iteration optimization process, the intermediate prior score estimator is the optimized intermediate prior score estimator obtained from the previous iteration optimization process.

[0249] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0250] For each sampling time step, obtain the sampling noise corresponding to the sampling time step;

[0251] Add noise to the sample global sensing data according to the sampling noise, and obtain the sample global sensing data after noise addition corresponding to the sampling time step.

[0252] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0253] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0254] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this application.

[0255] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A global data sensing method based on a diffusion model, characterized in that: The method comprises: Acquiring a plurality of sample global sensor data, and iteratively optimizing an initial prior score estimator based on each of the sample global sensor data to obtain a target prior score estimator; wherein the plurality of sample global sensor data include historical global sensor data and / or simulated global sensor data corresponding to the building structure; determining a target posterior differential model based on the target prior score estimator; Obtaining local monitoring data corresponding to the building structure and obtaining the target posterior differential model, wherein the target posterior differential model is trained based on sample global sensor data corresponding to the building structure and is constructed based on a diffusion model; Acquiring initial global sensor data corresponding to the building structure, wherein the initial global sensor data is obtained by sampling a standard multivariate Gaussian distribution; The target posterior differential model is iteratively solved according to the local monitoring data and the initial global sensor data, and the target global sensor data corresponding to the building structure is obtained by reverse restoration.

2. The method according to claim 1, characterized in that The iteratively solving the target posterior differential model according to the local monitoring data and the initial global sensor data to obtain the target global sensor data corresponding to the building structure includes: In each iterative solution process, the target posterior differential model is solved according to the local monitoring data and the first intermediate global sensor data to obtain second intermediate global sensor data; If the current number of iterative solutions reaches the target number of iterative solutions, determining the second intermediate global sensor data as the target global sensor data; Among them, when the current iterative solution process is the first iterative solution process, the first intermediate global sensor data is the initial global sensor data; when the current iterative solution process is not the first iterative solution process, the first intermediate global sensor data is the second intermediate global sensor data obtained in the previous iterative solution process.

3. The method according to claim 2, characterized in that Solving the target posterior differential model according to the local monitoring data and the first intermediate global sensor data to obtain the second intermediate global sensor data includes: Determining a priori score corresponding to the current iterative solution process according to the first intermediate global sensor data and a target priori score estimator included in the target posterior differential model, and determining noise-free global sensor data according to the priori score; Determining a likelihood score corresponding to the current iterative solution process based on the noise-free global sensor data and the local monitoring data; The second intermediate global sensor data is determined according to the prior score, the likelihood score, and the target posterior differential model.

4. The method according to claim 1, wherein The iterative optimization of the initial prior score estimator according to the global sensor data of each sample to obtain the target prior score estimator includes: For each iterative optimization process, performing noise processing on the sample global sensor data corresponding to the iterative optimization process according to different sampling time steps, to obtain the sample global sensor data after noise processing corresponding to each sampling time step; Optimizing the intermediate prior score estimator according to the global state number of each sample after the noise processing to obtain an optimized intermediate prior score estimator; Detecting whether a preset convergence condition is satisfied, and if so, determining the optimized intermediate prior score estimator as the target prior score estimator; Among them, when the iterative optimization process is the first iterative optimization process, the intermediate prior score estimator is the initial prior score estimator; when the iterative optimization process is not the first iterative optimization process, the intermediate prior score estimator is the optimized intermediate prior score estimator obtained in the previous iterative optimization process.

5. The method according to claim 4, characterized in that The step of performing noise processing on the sample global sensor data corresponding to the iterative optimization process according to different sampling time steps to obtain the sample global sensor data after noise processing corresponding to each sampling time step includes: For each of the sampling time steps, obtaining the sampling noise corresponding to the sampling time step; Noise processing is performed on the sample global sensor data according to the sampling noise to obtain the noise-processed sample global sensor data corresponding to the sampling time step.

6. A global data sensing device based on a diffusion model, characterized in that: The device comprises: an iterative optimization module, configured to obtain a plurality of sample global sensor data and iteratively optimize an initial prior score estimator based on each of the sample global sensor data to obtain a target prior score estimator; wherein the plurality of sample global sensor data include historical global sensor data and / or simulated global sensor data corresponding to the building structure; a model determination module, configured to determine a target posterior differential model based on the target prior score estimator; an acquisition module, configured to acquire local monitoring data corresponding to the building structure and acquire the target posterior differential model, wherein the target posterior differential model is trained based on sample global sensor data corresponding to the building structure and is constructed based on a diffusion model; An initial value acquisition module, configured to acquire initial global sensor data corresponding to the building structure, wherein the initial global sensor data is obtained by sampling a standard multivariate Gaussian distribution; A solution module is used to iteratively solve the target posterior differential model according to the local monitoring data and the initial global sensor data, and reversely restore the target global sensor data corresponding to the building structure.

7. The device according to claim 6, characterized in that The solution module includes: an intermediate solving unit, configured to solve the target posterior differential model according to the local monitoring data and the first intermediate global sensor data in each iterative solving process to obtain second intermediate global sensor data; a target determining unit, configured to determine the second intermediate global sensor data as the target global sensor data if the current number of iterative solutions reaches a target number of iterative solutions; Among them, when the current iterative solution process is the first iterative solution process, the first intermediate global sensor data is the initial global sensor data; when the current iterative solution process is not the first iterative solution process, the first intermediate global sensor data is the second intermediate global sensor data obtained in the previous iterative solution process.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images