An AI-based intelligent building operation analysis method and system

Abstract

The present invention discloses an AI-based intelligent building operation analysis method and system. The method includes: collecting environmental system data, energy consumption system data, and personnel flow system data of a building through sensors, and performing time alignment on the three types of system data through time axis mapping to obtain an alignment matrix; performing adaptive wavelet packet decomposition on the alignment matrix to obtain extended features, and constructing a feature tensor based on the extended features; using the features in the feature tensor as observation variables to construct a latent variable model, where the latent variable model calculates the influence weight of the latent variable on the observation variable through a measurement equation, and performs dynamic coupling degree calculation based on the influence weight; using the features in the feature tensor as nodes, and using the product of transfer entropy and dynamic coupling degree as edge weights to construct a causal network, and performing root cause analysis on the causal network through the PrefixSpan algorithm. The present invention solves the problem that existing building operation analysis technologies cannot comprehensively consider the dynamic interaction between multi-system data.

Description

Technical Field

[0001] The present invention belongs to the technical field of artificial intelligence, and particularly relates to a method and system for analyzing the operation of a smart building based on AI. Background Art

[0002] In the field of smart buildings, the existing building operation analysis technologies mainly focus on data monitoring and analysis of a single system, such as environmental monitoring, energy consumption assessment, or people flow analysis. Most of these methods are based on traditional data collection means and lack the ability to comprehensively analyze multiple systems, resulting in difficulty in capturing the overall dynamic correlation of building operation. Therefore, the phenomenon of information islands often occurs. In addition, most of the existing technologies rely on static models, lacking real-time and accuracy in analyzing the building operation state, and it is difficult to comprehensively reflect the operation efficiency of the building under different conditions. With the development of artificial intelligence technology, there is an urgent need for a method that integrates data from multiple systems and realizes dynamic analysis to more effectively support the intelligent management and optimization decision-making of buildings.

[0003] Chinese Patent Publication No. CN118643955B discloses a building energy consumption optimization management system and method based on big data analysis. The system includes: a data collection module configured to collect real-time data; a data processing module configured to identify abnormal data and repair the abnormal data; a data analysis module configured to predict the equipment energy consumption at a future moment to obtain the equipment energy consumption trend, and form an initial energy consumption allocation plan according to the equipment energy consumption trend and the mapping relationship network; an energy consumption optimization module configured to obtain the optimal energy consumption allocation plan by using an optimization algorithm; a control management module configured to form a control instruction based on the optimal energy consumption allocation plan and send the control instruction to each device; a visualization interface module configured to visualize various types of data and logs. This invention only relies on simple timestamp matching, which is prone to misjudging the correlation between the environment and energy consumption. At the same time, the time series modeling network of this invention only relies on historical energy consumption data and does not integrate building physical characteristics (such as thermal inertia, equipment efficiency) and multi-scale features, which may lead to long-term energy consumption prediction deviating from reality. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for analyzing the operation of a smart building based on AI to solve the problem that the existing building operation analysis technologies cannot comprehensively consider the dynamic interaction between multi-system data and meet the refined operation and maintenance requirements of smart buildings.

[0005] The technical solution of the present invention is as follows:

[0006] On the one hand, the present invention provides a method for analyzing the operation of a smart building based on AI, including the following steps:

[0007] Collect the environmental system data, energy consumption system data, and pedestrian flow system data of the building through sensors. Based on the three types of system data, construct three types of system pairs: environment - energy consumption, energy consumption - pedestrian flow, and pedestrian flow - environment. And perform time alignment on the three types of system data through time axis mapping to obtain an alignment matrix.

[0008] Perform adaptive wavelet packet decomposition on the alignment matrix to obtain extended features, and construct a feature tensor based on the extended features.

[0009] Use the features in the feature tensor as observed variables to construct a latent variable model. The latent variable model calculates the influence weight of the latent variable on the observed variable through a measurement equation, and performs dynamic coupling degree calculation based on the influence weight to quantify the real-time interaction strength between different system pairs.

[0010] Use the features in the feature tensor as nodes, calculate the transfer entropy based on the feature tensor, and use the product of the transfer entropy and the dynamic coupling degree as the edge weight to construct a causal network. Perform root cause analysis on the causal network through the PrefixSpan algorithm to obtain the causal chain result.

[0011] Preferably, performing time alignment on the three types of system data through time axis mapping to obtain an alignment matrix is specifically as follows:

[0012] Calculate the average time difference of the three types of system data:

[0013]

[0014] In the formula, is the average time difference of the th type of system data, ; is the number of sensors for collecting the th type of sensor, ; is the collection time of the th sensor in the th type of system data; is the standard time.

[0015] Construct a time axis mapping function based on the average time difference as the optimization objective function. The time axis mapping function is expressed as:

[0016]

[0017] In the formula, is the time axis mapping function; is the time; is the ownership weight of the th sensor in the th type of system data; is the Class system data The standard deviation of each sensor; For the Class system data The data collected by each sensor; For the Class system data Cubic spline interpolation function on the time axis of the sensor target.

[0018] The LM algorithm is used to perform nonlinear optimization on the time axis mapping function to find the optimal alignment time, and the three types of system data are time-aligned to output an alignment matrix.

[0019] Preferably, adaptive wavelet packet decomposition is performed on the alignment matrix to obtain extended features, and the feature tensor is constructed based on the extended features as follows:

[0020] The alignment matrix is Fourier transformed to obtain the power spectral density.

[0021] The spectrum of the candidate wavelet basis function is calculated, and the wavelet basis function with the largest integral value is selected based on the spectrum and power spectrum density to construct the wavelet packet decomposition tree. The selected wavelet basis function is expressed as:

[0022]

[0023] In the formula, is the selected wavelet basis function; is a candidate wavelet basis function; is the Nyquist frequency; is the candidate wavelet basis function In frequency The spectrum energy at is the power spectral density, which indicates the alignment matrix at frequency The energy intensity at .

[0024] A first-level wavelet packet decomposition is performed on each characteristic column of the alignment matrix using the selected wavelet basis function to generate high-frequency sub-bands and low-frequency sub-bands.

[0025] For each sub-band node, the Shannon entropy is calculated. If the entropy value of the parent node and the entropy value of the child node satisfy:

[0026]

[0027] In the formula, is the entropy value of the parent node; is the entropy value of the child node; is the entropy reduction rate threshold;

[0028] Then continue to decompose the node until the preset maximum decomposition level is reached or the entropy value of the parent node and the entropy value of the child node do not satisfy the above rules, and the construction of the wavelet packet decomposition tree is completed.

[0029] Calculate the energy entropy for each leaf node of the wavelet packet decomposition tree to obtain the energy entropy class features.

[0030] Calculate the skewness feature, kurtosis feature, and Hurst exponent feature based on the time-domain signal of the features in the alignment matrix.

[0031] Expand the dimension of the alignment matrix based on the energy entropy class features, skewness feature, kurtosis feature, and Hurst exponent feature to obtain the feature tensor.

[0032] Preferably, use the features in the feature tensor as the observed variables to construct a latent variable model. The influence weight of the latent variable on the observed variable is calculated by the measurement equation specifically as follows:

[0033] Use the features in the feature tensor as the observed variables, and each observed variable corresponds to a certain feature dimension in the feature tensor.

[0034] The latent variable model defines that the latent variables include the thermal inertia factor, the human flow dynamic coefficient, and the equipment efficiency index. Based on the observed variables and the latent variables, establish the measurement equation:

[0035]

[0036] In the formula, is the observed variable; is the factor loading matrix, which is used to describe the influence weight of the latent variable on the observed variable; is the latent variable; is the observation error.

[0037] Calculate the estimated value of the latent variable and the estimated value of the factor loading matrix .

[0038] Based on and perform a goodness-of-fit test. If the goodness-of-fit is greater than the set threshold, then calculate the dynamic coupling degree.

[0039] Preferably, calculate the dynamic coupling degree based on the influence weight to quantify the real-time interaction strength between different system pairs specifically as follows:

[0040] Calculate the dynamic Jacobian matrix based on the estimated value of the factor loading matrix:

[0041]

[0042] In the formula, is the dynamic Jacobian matrix; ; is the change rate of the latent variable over time, which is obtained by sliding window difference calculation.

[0043] Calculate the dynamic coupling degree according to the dynamic Jacobian matrix:

[0044]

[0045] In the formula, is the real-time coupling index between two types of systems; is at time , the data pair of the type of system, the Jacobian matrix element of the data of the 、 are respectively 、 the diagonal elements of the data of the

[0046] Preferably, take the features in the feature tensor as nodes, calculate the transfer entropy based on the feature tensor, and take the product of the transfer entropy and the dynamic coupling degree as the edge weight to construct a causal network specifically as follows:

[0047] Take the features in the feature tensor as nodes, discretize the features into three states of -1, 0, and 1, and calculate the transfer entropy between node pairs as the original edge weight. The specific transfer entropy formula is:

[0048]

[0049] In the formula, is the original edge weight from node to node , is the probability function; is the state of node at time ; is the discretized historical sequence of node in the time window , used to control the influence length of the history of node itself; is the discretized historical sequence of node in the time window , used to control the influence length of the history of node itself; is the joint probability, 、 It is a conditional probability estimated by statistical frequency through a sliding window.

[0050] The product of the transfer entropy between node pairs and the dynamic coupling degree of the corresponding system pairs of the node pairs is used as the edge weight for dynamic update to construct a causal network.

[0051] Preferably, root cause analysis is performed on the causal network through the PrefixSpan algorithm, and the causal chain result is specifically:

[0052] Set an activation threshold, and within a preset time window, encode the activation status of the edges in the causal network whose edge weights exceed the activation threshold into a symbol sequence.

[0053] Scan the symbol sequence, count the frequency of each symbol, and retain the symbols whose symbol support exceeds the set threshold as frequent items.

[0054] Recursively construct a projection database to expand the frequent items to generate longer frequent patterns.

[0055] Select the frequent patterns whose support and confidence both exceed the threshold as the causal chain for output, and locate the earliest activated node in the causal chain as the root cause to complete the causal analysis.

[0056] On the other hand, the present invention provides an AI-based intelligent building operation analysis system, including a data acquisition and time alignment module, a tensor construction module, a dynamic coupling degree calculation module, and a root cause analysis module.

[0057] The data acquisition and time alignment module is used to collect environmental system data, energy consumption system data, and pedestrian flow system data of the building through sensors, construct three types of system pairs of environment - energy consumption, energy consumption - pedestrian flow, and pedestrian flow - environment based on the three types of system data, and perform time alignment on the three types of system data through time axis mapping to obtain an alignment matrix.

[0058] The tensor construction module is used to perform adaptive wavelet packet decomposition on the alignment matrix to obtain extended features, and construct a feature tensor based on the extended features.

[0059] The dynamic coupling degree calculation module is used to construct a latent variable model with the features in the feature tensor as observed variables. The latent variable model calculates the influence weight of the latent variable on the observed variable through a measurement equation, and performs dynamic coupling degree calculation based on the influence weight to quantify the real-time interaction intensity between different system pairs.

[0060] The root cause analysis module is used to use the features in the feature tensor as nodes, calculate the transfer entropy based on the feature tensor, and use the product of the transfer entropy and the dynamic coupling degree as the edge weight to construct a causal network, and perform root cause analysis on the causal network through the PrefixSpan algorithm to obtain the causal chain result.

[0061] On the other hand, the present invention also provides an electronic device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the AI-based intelligent building operation analysis method according to any embodiment of the present invention.

[0062] On the other hand, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the AI-based intelligent building operation analysis method according to any embodiment of the present invention.

[0063] Compared with the prior art, the present invention has the following technical effects:

[0064] 1. By introducing a weight factor adaptive to sensor characteristics and a non-linear optimization objective function, the present invention realizes the time alignment of multi-source data, effectively eliminates the pseudo-correlation caused by device clock drift, and ensures the temporal consistency of subsequent analysis.

[0065] 2. By constructing a latent variable model and calculating the dynamic coupling degree using the influence weight of observed variables, the present invention realizes the quantification of the real-time interaction between systems. This innovative method ensures that during the operation of a building, the mutual influence between the environment, energy consumption, and human flow can be monitored and analyzed in real time, thereby providing data-driven decision-making support for managers and significantly improving the flexibility and response speed of building operation analysis.

[0066] 3. By constructing a causal network and using the product of transfer entropy and dynamic coupling degree as the edge weight for root cause analysis, the present invention realizes the in-depth excavation of causal relationships within a complex system. It can clearly reveal the causal chain between different variables, provide a more targeted basis for optimizing building management, and thus improve resource allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 is the overall flowchart of the AI-based intelligent building operation analysis method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0068] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments of the present application and with reference to the accompanying drawings.

[0069] Embodiment 1

[0070] This embodiment provides an AI-based intelligent building operation analysis method. Referring to Figure 1 as shown, it includes the following steps:

[0071] Collect the environmental system data, energy consumption system data, and pedestrian flow system data of the building through sensors. Based on the three types of system data, construct three types of system pairs: environment - energy consumption, energy consumption - pedestrian flow, and pedestrian flow - environment. And perform time alignment on the three types of system data through time axis mapping to obtain an alignment matrix. In addition, conventional data preprocessing steps such as anomaly cleaning need to be performed on the collected data.

[0072] Specifically, collect environmental system data such as temperature, humidity, CO2, and illumination through environmental sensors, collect energy consumption system data such as HVAC power, lighting power, and equipment current through energy consumption meters, and collect pedestrian flow system data such as density, speed, and residence time through pedestrian flow cameras.

[0073] As a preferred implementation method of this embodiment, performing time alignment on the three types of system data through time axis mapping to obtain an alignment matrix is specifically:

[0074] Calculate the average time difference of the three types of system data:

[0075]

[0076] In the formula, is the average time difference of the th type of system data, ; is the number of sensors for collecting the th type of sensor, ; is the th type of system data, and is the collection time of the th sensor;

[0077] Based on the average time difference, construct a time axis mapping function as the optimization objective function, and the time axis mapping function is expressed as:

[0078]

[0079] In the formula, is the time axis mapping function; is the time; is the th type of system data, and is the weight of the th sensor, , is the th type of system data, and is the standard deviation of the is the acquisition data of the th sensor in the system data of type ; is the cubic spline interpolation function on the target time axis of the th sensor in the system data of type ;

[0080] The LM algorithm is used to perform nonlinear optimization on the time axis mapping function to find the optimal alignment time, and the three types of system data are time-aligned to output an alignment matrix.

[0081] Specifically, the algorithm steps of the LM algorithm are as follows: randomly initialize a time alignment scheme; calculate the current error through the objective function; adjust the time alignment scheme according to the error to gradually reduce the error; stop the algorithm when the error change is less than the preset percentage threshold after two consecutive adjustments.

[0082] Perform adaptive wavelet packet decomposition on the alignment matrix to obtain extended features, and construct a feature tensor based on the extended features.

[0083] As a preferred implementation manner of this embodiment, performing adaptive wavelet packet decomposition on the alignment matrix to obtain extended features and constructing a feature tensor based on the extended features is specifically as follows:

[0084] Perform Fourier transform on the alignment matrix to obtain the power spectral density. The specific formula of the power spectral density is:

[0085]

[0086] In the formula, is the power spectral density; is the total number of time points, ; is the frequency; is the time series data of the features in the alignment matrix; is the imaginary unit.

[0087] Different data is suitable for different analysis waveforms, and it is necessary to select the wavelet basis function that best matches the data spectrum. Therefore, calculate the spectrum of the candidate wavelet basis functions, and select the wavelet basis function with the largest integral value based on the spectrum and the power spectral density to construct the wavelet packet decomposition tree. The selected wavelet basis function is expressed as:

[0088]

[0089] In the formula, is the selected wavelet basis function; is the candidate wavelet basis function (such as Daubechies wavelet, Symlets wavelet, etc.); is the Nyquist frequency, , is the sampling frequency; is the candidate wavelet basis function at the frequency spectrum energy; is the power spectral density, indicating the energy intensity of the alignment matrix at the frequency location.

[0090] Perform a first-level wavelet packet decomposition on each eigen-column of the alignment matrix using the selected wavelet basis function to generate high-frequency and low-frequency sub-bands.

[0091] Calculate the Shannon entropy for each sub-band node. The greater the entropy, the more complex the signal, and further decomposition is required. The entropy value formula is expressed as:

[0092]

[0093] In the formula, is the Shannon entropy of the node, describing the degree of chaos of the energy in each frequency band within a single node; is the sub-node ratio of the energy of to the total energy of the parent node.

[0094] In this embodiment, the depth of the wavelet packet decomposition tree is controlled by a dynamic threshold to balance the feature dimension and information volume. If the entropy value of the parent node and the entropy value of the sub-node satisfy:

[0095]

[0096] In the formula, is the entropy value of the parent node; is the entropy value of the sub-node; is the preset entropy reduction rate threshold;

[0097] Then continue to decompose this node until the preset maximum decomposition layer is reached or the entropy value of the parent node and the entropy value of the sub-node do not satisfy the above rules, and the construction of the wavelet packet decomposition tree is completed.

[0098] Calculate the energy entropy for the frequency band corresponding to each leaf node of the wavelet packet decomposition tree to obtain the energy entropy class feature. Usually, the operation analysis of intelligent buildings focuses on time scales above the minute level, and the second-level fluctuations are regarded as noise. Therefore, the energy entropy generally only extracts the hourly energy entropy, daily energy entropy, and weekly energy entropy to explain the physical meaning of the subsequent latent variables. In this embodiment, it is preferably to expand the features of the alignment matrix to the hourly energy entropy (capturing the fluctuations within an hour) and the daily energy entropy (analyzing the daily cycle trend). The calculation formula is expressed as:

[0099]

[0100] In the formula, is the energy entropy; is the layer of the The proportion of each leaf node in the total energy.

[0101] Based on the time-domain signals of the features in the alignment matrix, skewness features, kurtosis features, and Hurst exponent features are calculated. Specifically, the skewness feature is calculated through the mean and standard deviation, and is used to indicate whether the data distribution is symmetric; the kurtosis feature is used to indicate whether the data is steep; the Hurst exponent feature is calculated through rescaled range analysis (R / S analysis) and reflects the long-range correlation of the time series.

[0102] In this embodiment, the frequency-domain energy distribution and time-domain statistical characteristics are integrated to form multi-scale features, and the alignment matrix is dimensionally extended based on energy entropy-like features, skewness features, kurtosis features, and Hurst exponent features to obtain a feature tensor. Specifically, the structure of the feature tensor in this embodiment is preferably: time dimension * original features (4 types of environmental system data, 3 types of energy consumption system data, and 3 types of human flow system data) * extended features (hourly energy entropy, daily energy entropy, skewness, kurtosis, and Hurst exponent). For example, the temperature feature is further extended to 5 types of dimensional features.

[0103] The features in the feature tensor are used as observed variables to construct a latent variable model. The latent variable model calculates the influence weights of the latent variables on the observed variables through a measurement equation, and performs dynamic coupling degree calculation based on the influence weights to quantify the real-time interaction strength between different system pairs.

[0104] As a preferred implementation manner of this embodiment, the physical characteristics of the building system (including thermal inertia, human flow dynamics, and equipment efficiency) are abstracted through latent variables, and a mapping relationship between the observed variables and the latent variables is established. The features in the feature tensor are used as observed variables to construct a latent variable model. The specific method for calculating the influence weights of the latent variables on the observed variables through the measurement equation is as follows:

[0105] The features in the feature tensor are used as observed variables, and each observed variable corresponds to a certain feature dimension in the feature tensor.

[0106] The latent variable model defines that the latent variables include a thermal inertia factor, a human flow dynamics coefficient, and an equipment efficiency index. The thermal inertia factor reflects the heat storage capacity of the building envelope structure; the human flow dynamics coefficient quantifies the comprehensive influence of the human flow density and movement pattern; the equipment efficiency index characterizes the operating efficiency of equipment such as HVAC and lighting.

[0107] Based on the observed variables and the latent variables, a measurement equation is established:

[0108]

[0109] In the formula, is the observed variable; is the factor loading matrix, which is used to describe the influence weights of latent variables on observed variables. , where is the dimension of the observed variable; is the latent variable; is the observation error, which follows a Gaussian distribution.

[0110] The estimated value of the latent variable is calculated by two-stage least squares method and the estimated value of the factor loading matrix . The specific solution process of the two-stage least squares method is as follows:

[0111] First stage: Use principal component analysis (PCA) to extract the estimated value of the latent variable . Specifically, perform PCA analysis on the observed vector to extract the first 3 principal components (representing thermal inertia, human flow dynamics, and equipment efficiency respectively) as the estimated value of the latent variable.

[0112] Second stage: Calculate the estimated value of the factor loading matrix through regression analysis. Specifically, take the measurement equation as the regression model, take the estimated value of the latent variable as the independent variable, and the observed variable as the dependent variable, and solve through ordinary least squares method for the estimated value.

[0113] Based on and perform a fitness test. If the fitness is greater than the set threshold, calculate the dynamic coupling degree. By ensuring that the fitness is greater than the set threshold, it can be ensured that the latent variable model fits well, so as to ensure the reliability of subsequent coupling analysis. Specifically, the closer the fitness index is to 1, the more the latent variable model matches the actual data. Its formula is specifically:

[0114]

[0115] In the formula, is the fitness index; is the trace of the matrix; is the covariance matrix predicted by the latent variable model, which is calculated based on and ; is the covariance matrix of the actual observed data, which is calculated from the observed variables in the eigen-tensor; is the identity matrix.

[0116] As a preferred implementation mode of this embodiment, calculate the dynamic coupling degree based on the influence weight to quantify the real-time interaction intensity between different system pairs. Specifically:

[0117] Estimated value based on the factor loading matrix Calculate the dynamic Jacobian matrix:

[0118]

[0119] where is the dynamic Jacobian matrix; ; is the change rate of the latent variable over time, which is calculated by sliding window differencing (such as the change rate of the latent variable in the past 1 hour).

[0120] Calculate the dynamic coupling degree according to the dynamic Jacobian matrix. The higher the dynamic coupling degree, the stronger the real-time influence between the two types of systems:

[0121]

[0122] where is the real-time coupling index between two types of systems, ; is at time , the Jacobian matrix element of the data pair of the type of system with respect to the data of the , are respectively , the diagonal elements of the data of the

[0123] Furthermore, the three types of data are divided into three types of system pairs: environment - energy consumption, people flow - energy consumption, and environment - people flow. By taking time as the X-axis, system pairs as the Y-axis, and real-time coupling index as the Z-axis, calculate the real-time coupling index of all system pairs at each time point to form a spatio-temporal coupling matrix, so as to generate a three-dimensional surface graph of the coupling degree. And through the persistence detection of the three-dimensional surface graph of the coupling degree (such as identifying continuous time periods where the coupling index exceeds the set threshold), and sorting the contribution degrees of all persistence events, a critical path analysis report can be generated to further explain the correlation between events and data.

[0124] Take the features in the feature tensor as nodes, calculate the transfer entropy based on the feature tensor, and use the product of the transfer entropy and the dynamic coupling degree as the edge weight to construct a causal network. Perform root cause analysis on the causal network through the PrefixSpan algorithm to obtain the causal chain result.

[0125] As a preferred implementation manner of this embodiment, taking the features in the feature tensor as nodes, calculating the transfer entropy based on the feature tensor, and using the product of the transfer entropy and the dynamic coupling degree as the edge weight to construct a causal network specifically is:

[0126] The features in the feature tensor are used as nodes, and the features are discretized into three states: -1, 0, and 1. Specifically, the feature data is normalized and multiplied by a preset value to obtain a normalized value, and the normalized value is discretized into -1, 0, and 1 through a threshold, and the continuous features are discretized into finite states to facilitate the calculation of probability distribution. Furthermore, the random forest algorithm can be used to calculate the feature importance of the features, so as to retain the features with higher importance as nodes.

[0127] The transfer entropy between the node pairs is calculated as the original edge weight. The transfer entropy is used to measure the improvement of the prediction ability of the historical information of one type of data on the future value of another type of data. The specific formula is:

[0128]

[0129] In the formula, For Node To Node The original edge weights of is the probability function; For Node In time Status; For Node In the time window The discretized history sequence of For controlling nodes the length of the impact of one’s own history; For Node In the time window The discretized history sequence of For controlling nodes the length of the impact of one’s own history; is the joint probability, , is the conditional probability, estimated by sliding window statistical frequency.

[0130] The product of the transfer entropy between node pairs and the dynamic coupling degree of the system pairs corresponding to the node pairs is used as the edge weight for dynamic update to construct a causal network. Specifically, each node pair belongs to a system pair, and the transfer entropy of the node pair is multiplied by the dynamic coupling degree of the system pair to which it belongs, highlighting the causal relationship in the important system pairs. The dynamic coupling index is updated in real time through a sliding window (such as the data of the past 1 hour) to reflect the current coupling strength of the system pair. The transfer entropy needs to be based on the statistical probability of sufficiently long data (such as the past 24 hours) to ensure stability. Therefore, it is necessary to formulate an alignment strategy for dynamic update of edge weights, which can be: sliding window alignment or real-time dynamic weight update.

[0131] The specific alignment of the sliding window is as follows: Transfer entropy calculation is based on long-term data (such as a 24-hour window), while the dynamic coupling degree can be based on the moving average version of the same time window.

[0132] The specific real-time dynamic weight update is as follows: The currently calculated dynamic coupling index is used as a weight factor to adjust the transfer entropy value:

[0133]

[0134] In the formula, is the updated transfer entropy value; is the initial transfer entropy value; is the system's dynamic coupling index at the current time.

[0135] Furthermore, a permutation test based on a sliding window can be performed on the edges of the causal network to filter out non-significant edges. The specific implementation steps of the permutation test are as follows: Randomly shuffle the time order of the nodes to disrupt their potential causal relationship with ; Calculate the transfer entropy after shuffling; Repeat multiple times (such as 1000 times) to generate the null distribution of the transfer entropy; Calculate the percentile p of the true TE value in the null distribution; If p is less than the set threshold, the causal relationship is considered significant and the edge is retained; Otherwise, it is filtered.

[0136] As a preferred implementation method of this embodiment, root cause analysis is performed on the causal network through the PrefixSpan algorithm, and the specific result of the causal chain is as follows:

[0137] Set an activation threshold, and encode the activation status of the edges with edge weights exceeding the activation threshold in the causal network within a preset time window as a symbol sequence. The activation condition can be expressed as: , then it is marked as activated (1), otherwise it is not activated (0).

[0138] Scan the symbol sequence, count the frequency of each symbol, and retain the symbols with symbol support exceeding the set threshold as frequent items. The frequent items are the symbols that frequently appear in the time window sequence.

[0139] Recursively construct a projection database to expand the frequent items to generate longer frequent patterns.

[0140] Select the frequent patterns with both support and confidence exceeding the threshold as the causal chain for output, and locate the earliest activated node in the causal chain as the root cause to complete the causal analysis.

[0141] To verify the effectiveness and superiority of the method provided in this embodiment, the following provides some simple cases:

[0142] Configure a virtual machine based on the Ubuntu 22.04 LTS operating system to simulate a building environment:

[0143] Collect data from the central office building. Among them, environmental system data is collected through temperature, humidity, CO2, and light sensors. For energy consumption system data, HVAC power is collected through the central air-conditioning system, lighting power and equipment current are collected through energy consumption meters, and people flow system data is collected through binocular cameras. The sampling duration is set to 24 hours, and the frequency is at 10s intervals.

[0144] Obtain an alignment matrix through time alignment ; Output a feature tensor through adaptive wavelet packet decomposition (Select hourly energy entropy, daily energy entropy, skewness, kurtosis, Hurst index); Construct a causal network to output a causal graph, and obtain causal chains such as "↑ people flow density → ↑ CO2 concentration → ↑ HVAC power". In this causal chain, "↑ people flow density" is the root cause. The root cause analysis of the above causal chain is: The surge in people flow density (morning rush hour) is the root cause of the HVAC energy consumption exceeding the limit (peak value of 350kW) at noon. And the daily energy entropy shows that the HVAC power has periodic fluctuations (once every 2 hours).

[0145] Example Two

[0146] Correspondingly, this embodiment provides an AI-based intelligent building operation analysis system, which is used to implement the AI-based intelligent building operation analysis method as described in Embodiment 1 of the present invention, including a data collection and time alignment module, a tensor construction module, a dynamic coupling degree calculation module, and a root cause analysis module.

[0147] The data collection and time alignment module is used to collect environmental system data, energy consumption system data, and people flow system data of the building through sensors, construct three types of system pairs: environment-energy consumption, energy consumption-people flow, and people flow-environment based on the three types of system data, and perform time alignment on the three types of system data through time axis mapping to obtain an alignment matrix.

[0148] The tensor construction module is used to perform adaptive wavelet packet decomposition on the alignment matrix to obtain extended features, and construct a feature tensor based on the extended features.

[0149] The dynamic coupling degree calculation module is used to construct a latent variable model with the features in the feature tensor as observed variables. The latent variable model calculates the influence weight of the latent variable on the observed variable through a measurement equation, and performs dynamic coupling degree calculation based on the influence weight to quantify the real-time interaction strength between different system pairs.

[0150] A root cause analysis module, which is used to take the features in the feature tensor as nodes, calculate the transfer entropy based on the feature tensor, and use the product of the transfer entropy and the dynamic coupling degree as the edge weight to construct a causal network, and perform root cause analysis on the causal network through the PrefixSpan algorithm to obtain the causal chain result.

[0151] Embodiment III

[0152] This embodiment provides an electronic device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the AI-based intelligent building operation analysis method as described in Embodiment I of the present invention.

[0153] Embodiment IV

[0154] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the AI-based intelligent building operation analysis method as described in Embodiment I of the present invention.

[0155] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent the situation where A exists alone, A and B exist simultaneously, and B exists alone. Where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one of the following" and its similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0156] Those of ordinary skill in the art can realize that the units and algorithm steps described in the embodiments disclosed herein can be implemented by a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0157] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0158] In several embodiments provided by the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs.

[0159] The above are only the embodiments of the present invention, and thus do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. An AI-based method for analyzing the operation of intelligent buildings, characterized in that, It includes the following steps: Collect environmental system data, energy consumption system data, and pedestrian flow system data of a building through sensors, construct three types of system pairs: environment - energy consumption, energy consumption - pedestrian flow, and pedestrian flow - environment based on the three types of system data, and perform time alignment on the three types of system data through time axis mapping to obtain an alignment matrix; Performing time alignment on the three types of system data through time axis mapping to obtain an alignment matrix specifically means: Calculate the average time difference of the three types of system data: Wherein, is the average time difference of the type of system data; ; is the number of type of sensors collected; ; is the acquisition time of the th sensor in the type of system data; is the standard time; Construct a time axis mapping function based on the average time difference as the optimization objective function, and the time axis mapping function is expressed as: Wherein, is the time-axis mapping function; is the time; is the th weight of the th sensor in the th type of system data; is the th standard deviation of the th sensor in the th type of system data; is the acquisition data of the th sensor in the th type of system data; is the cubic spline interpolation function of the th sensor on the target time axis of the th type of system data; Use the LM algorithm to perform non - linear optimization on the time axis mapping function, find the optimal alignment time, and perform time alignment on the three types of system data to output an alignment matrix; Perform adaptive wavelet packet decomposition on the alignment matrix to obtain extended features, and construct a feature tensor based on the extended features; Use the features in the feature tensor as observation variables to construct a latent variable model. The latent variable model calculates the influence weight of the latent variable on the observation variable through a measurement equation, and performs dynamic coupling degree calculation based on the influence weight to quantify the real - time interaction strength between different system pairs; Use the features in the feature tensor as nodes, calculate transfer entropy based on the feature tensor, and use the product of the transfer entropy and the dynamic coupling degree as the edge weight to construct a causal network. Perform root cause analysis on the causal network through the PrefixSpan algorithm to obtain the causal chain result.

2. The AI-based intelligent building operation analysis method according to claim 1, characterized in that, Performing adaptive wavelet packet decomposition on the alignment matrix to obtain extended features, and constructing a feature tensor based on the extended features specifically means: Perform Fourier transform on the alignment matrix to obtain the power spectral density; Calculate the spectrum of candidate wavelet basis functions, and select the wavelet basis function with the largest integral value based on the spectrum and the power spectral density for constructing a wavelet packet decomposition tree. The selected wavelet basis function is expressed as: In the formula, is the selected wavelet basis function; is the candidate wavelet basis function; is the Nyquist frequency; is the candidate wavelet basis function at the frequency spectral energy at; is the power spectral density, indicating the energy intensity of the alignment matrix at the frequency at; Perform first - level wavelet packet decomposition on each feature column of the alignment matrix using the selected wavelet basis function to generate high - frequency sub - bands and low - frequency sub - bands; Calculate the Shannon entropy for each sub - band node. If the entropy value of the parent node and the entropy value of the child node satisfy: In the formula, is the entropy value of the parent node; is the entropy value of the child node; is the threshold of the entropy reduction rate; Then continue to decompose this node until the preset maximum decomposition level is reached or the entropy value of the parent node and the entropy value of the child node do not satisfy the above rules, and complete the construction of the wavelet packet decomposition tree; Calculate the energy entropy for each leaf node of the wavelet packet decomposition tree to obtain energy entropy - like features; Calculate the skewness feature, kurtosis feature, and Hurst exponent feature based on the time - domain signal of the features in the alignment matrix; Perform dimension expansion on the alignment matrix based on the energy entropy - like features, skewness features, kurtosis features, and Hurst exponent features to obtain a feature tensor.

3. The AI-based intelligent building operation analysis method according to claim 1, characterized in that, Using the features in the feature tensor as observation variables to construct a latent variable model, and the latent variable model calculates the influence weight of the latent variable on the observation variable through a measurement equation specifically means: Use the features in the feature tensor as observation variables, and each observation variable corresponds to a certain feature dimension in the feature tensor; The latent variable model defines that the latent variables include a thermal inertia factor, a pedestrian flow dynamic coefficient, and a device efficiency index, and establishes a measurement equation based on the observation variables and the latent variables: In the formula, is the observed variable; is the factor loading matrix, which is used to describe the influence weight of the latent variable on the observed variable; is the latent variable; is the observation error; Calculating the estimated value of the latent variable by two-stage least squares of and the estimated value of the factor loading matrix of ; Based on and perform a fitness test. If the fitness is greater than the set threshold, calculate the dynamic coupling degree.

4. The AI-based intelligent building operation analysis method according to claim 3, wherein, Performing dynamic coupling degree calculation based on the influence weight to quantify the real - time interaction strength between different system pairs specifically means: Estimated value based on the factor loading matrix Calculate the dynamic Jacobian matrix: In the formula, is the dynamic Jacobian matrix; ; is the change rate of the latent variable over time, which is obtained by calculating the sliding window difference. Calculate the dynamic coupling degree according to the dynamic Jacobian matrix: In the formula, is the real-time coupling index between two types of system pairs; is at time , the Jacobian matrix element of the data pair of the type system with respect to the data of the type system; and are respectively the diagonal elements of the data of the type systems.

5. The AI-based intelligent building operation analysis method according to claim 1, wherein Take the features in the feature tensor as nodes, calculate the transfer entropy based on the feature tensor, and use the product of the transfer entropy and the dynamic coupling degree as the edge weight to construct a causal network specifically as follows: Take the features in the feature tensor as nodes, discretize the features into three states of -1, 0, and 1, and calculate the transfer entropy between node pairs as the original edge weight. The specific formula for the transfer entropy is: In the formula, is the original edge weight from node to node ; is the probability function; is the state of node at time ; is the discretized historical sequence of node in the time window , which is used to control the influence length of the node 's own history; is the discretized historical sequence of node in the time window , which is used to control the influence length of the node 's own history; is the joint probability, , are conditional probabilities estimated by sliding window statistics;​​ Dynamically update the product of the transfer entropy between node pairs and the dynamic coupling degree of the corresponding system pairs of nodes as the edge weight to construct a causal network.

6. The AI-based intelligent building operation analysis method according to claim 5, characterized in that, Perform root cause analysis on the causal network through the PrefixSpan algorithm to obtain the causal chain result specifically as follows: Set an activation threshold, and within a preset time window, encode the activation status of the edges in the causal network whose edge weights exceed the activation threshold into a symbol sequence; Scan the symbol sequence, count the frequency of each symbol, and retain the symbols whose symbol support exceeds the set threshold as frequent items; Recursively construct a projection database to expand the frequent items to generate longer frequent patterns; Select the frequent patterns whose support and confidence both exceed the threshold as the causal chain for output, and locate the earliest activated node in the causal chain as the root cause to complete the causal analysis.

7. An AI-based intelligent building operation analysis system, characterized in that, The system is used to implement the AI-based intelligent building operation method described in any one of claims 1-6, including a data acquisition and time alignment module, a tensor construction module, a dynamic coupling degree calculation module, and a root cause analysis module; The data acquisition and time alignment module is used to collect the environmental system data, energy consumption system data, and human flow system data of the building through sensors, construct three types of system pairs of environment-energy consumption, energy consumption-human flow, and human flow-environment based on the three types of system data, and perform time alignment on the three types of system data through time axis mapping to obtain an alignment matrix; The tensor construction module is used to perform adaptive wavelet packet decomposition on the alignment matrix to obtain extended features, and construct a feature tensor based on the extended features; The dynamic coupling degree calculation module is used to construct a latent variable model with the features in the feature tensor as observed variables. The latent variable model calculates the influence weight of the latent variable on the observed variable through a measurement equation, and performs dynamic coupling degree calculation based on the influence weight to quantify the real-time interaction intensity between different system pairs; The root cause analysis module is used to take the features in the feature tensor as nodes, calculate the transfer entropy based on the feature tensor, and use the product of the transfer entropy and the dynamic coupling degree as the edge weight to construct a causal network, and perform root cause analysis on the causal network through the PrefixSpan algorithm to obtain the causal chain result.

8. An electronic device, the electronic device comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the AI-based intelligent building operation analysis method described in any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the AI-based intelligent building operation analysis method described in any one of claims 1 to 6.

Images