Building environment state determination method and system and nonvolatile storage medium

Abstract

The invention discloses a building environment state determination method and system and a nonvolatile storage medium. The method comprises the following steps: acquiring current measurement values corresponding to various environmental parameters of a building respectively, and historical measurement values corresponding to the various environmental parameters respectively; filtering is carried out based on the current measurement values corresponding to the various environmental parameters respectively, and first correction values corresponding to the various environmental parameters respectively are determined; determining probabilities respectively corresponding to the plurality of candidate environment states under the condition of first correction values respectively corresponding to the plurality of environment parameters; and taking the environment states of which the probabilities are greater than a preset probability threshold in the plurality of candidate environment states as a second candidate environment state set, and determining a target environment state of the building from the second candidate environment state set based on the historical measurement values corresponding to the plurality of environment parameters. According to the method and the device, the technical problem of low accuracy of a building environment state determination result in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent building management, and in particular to a method and system for determining a building environment state and a non-volatile storage medium. Background Art

[0002] As modern buildings become more intelligent, the importance of indoor environmental quality to building management becomes increasingly significant. Excellent indoor air quality and a comfortable indoor climate directly affect the health and comfort of residents. Therefore, intelligent control of the building's environmental status has become an important part of intelligent buildings, and its core lies in the ability to detect environmental status with high precision. In related technologies, the detection of building environmental status is mostly based on single-parameter sensors, which cannot fully reflect the diversity of indoor environments. There are also detection blind spots in air quality, particulate matter concentration, etc., which cannot meet the needs of modern intelligent buildings for multi-dimensional environmental information. In addition, during long-term use, sensors may have errors, redundancy, and low accuracy in detection data due to noise, sensor aging, and other reasons. This further leads to large errors in the building's environmental status detection results and low accuracy in determining the building's environmental status.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] The embodiments of the present application provide a method, system, and non-volatile storage medium for determining a building environment state, so as to at least solve the technical problem of low accuracy of building environment state determination results existing in the related art.

[0005] According to one aspect of an embodiment of the present application, a method for determining a building environmental state is provided, including: obtaining current measurement values ​​corresponding to a plurality of environmental parameters of the building, and historical measurement values ​​corresponding to the plurality of environmental parameters, wherein a measurement error between the historical measurement value and the current measurement value is less than a preset error threshold, and the measurement error indicates a degree of similarity between an environmental state corresponding to the current measurement value and an environmental state corresponding to the historical measurement value; filtering based on the current measurement values ​​corresponding to the plurality of environmental parameters, and determining first correction values ​​corresponding to the plurality of environmental parameters; determining the probabilities corresponding to a plurality of candidate environmental states under the condition of the first correction values ​​corresponding to the plurality of environmental parameters; taking an environmental state whose probability among the plurality of candidate environmental states is greater than a preset probability threshold as a second candidate environmental state set, and determining a target environmental state of the building from the second candidate environmental state set based on the historical measurement values ​​corresponding to the plurality of environmental parameters.

[0006] According to another aspect of an embodiment of the present application, a building environment state determination system is provided, including: a multi-parameter sensor module and a data processing and fusion module, wherein the multi-parameter sensor module is used to obtain current measurement values ​​corresponding to multiple environmental parameters of the building, and historical measurement values ​​corresponding to multiple environmental parameters, wherein the measurement value error between the historical measurement value and the current measurement value is less than a preset error threshold, and the measurement value error represents the degree of similarity between the environmental state corresponding to the current measurement value and the environmental state corresponding to the historical measurement value; the data processing and fusion module is connected to the multi-parameter sensor module, and is used to filter based on the current measurement values ​​corresponding to the multiple environmental parameters, and determine first correction values ​​corresponding to the multiple environmental parameters; under the condition of the first correction values ​​corresponding to the multiple environmental parameters, using data fusion to determine the probabilities corresponding to multiple candidate environmental states; taking the environmental states with probabilities greater than the preset probability threshold among the multiple candidate environmental states as a second candidate environmental state set, and determining the target environmental state of the building from the second candidate environmental state set based on the historical measurement values ​​corresponding to the multiple environmental parameters.

[0007] According to another aspect of an embodiment of the present application, a non-volatile storage medium is provided. The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executed by any one of the building environment status determination methods.

[0008] In an embodiment of the present application, current measurement values ​​corresponding to multiple environmental parameters of a building and historical measurement values ​​corresponding to the multiple environmental parameters are obtained, wherein the measurement error between the historical measurement value and the current measurement value is less than a preset error threshold, and the measurement error indicates the degree of similarity between the environmental state corresponding to the current measurement value and the environmental state corresponding to the historical measurement value; filtering is performed based on the current measurement values ​​corresponding to the multiple environmental parameters to determine first correction values ​​corresponding to the multiple environmental parameters; under the condition of the first correction values ​​corresponding to the multiple environmental parameters, the probabilities corresponding to multiple candidate environmental states are determined; environmental states with probabilities greater than the preset probability threshold among the multiple candidate environmental states are used as a second candidate environmental state set, and the target environmental state of the building is determined from the second candidate environmental state set based on the historical measurement values ​​corresponding to the multiple environmental parameters. The purpose of determining the building environmental state by filtering and fusing the multiple environmental parameter data obtained by the sensor is achieved, achieving the technical effect of improving the accuracy of the building environmental state determination result, thereby solving the technical problem of low accuracy of the building environmental state determination result existing in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0010] Figure 1 is a flowchart of an optional building environment status determination method provided according to an embodiment of the present application;

[0011] Figure 2 is a structural diagram of an optional building environment status determination system provided according to an embodiment of the present application;

[0012] Figure 3 is a schematic diagram of an optional building environment status determination system provided according to an embodiment of the present application;

[0013] Figure 4 This is a first module diagram of an optional building environment status determination system provided according to an embodiment of the present application;

[0014] Figure 5 is a second module diagram of an optional building environment status determination system provided according to an embodiment of the present application;

[0015] Figure 6 is a third module diagram of an optional building environment status determination system provided according to an embodiment of the present application;

[0016] Figure 7 is a fourth module diagram of an optional building environment status determination system provided according to an embodiment of the present application;

[0017] Figure 8 This is a fifth module diagram of an optional building environment status determination system provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] For ease of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0021] PM2.5 refers to particulate matter in the atmosphere with a diameter of less than or equal to 2.5 microns, also known as fine particulate matter. It mainly comes from industrial emissions, automobile exhaust, construction, biomass burning (such as burning wood and crop residues) and natural dust.

[0022] Kalman filtering is a method for state estimation of dynamic systems subject to noise interference. It has the characteristics of being able to process real-time data, provide continuous and recursive state estimation, and handle uncertainty and noise in dynamic systems.

[0023] Data drift is the phenomenon in which a measurement result or output signal from a sensor, measurement device, or data collection system systematically changes over time relative to its true or expected value. This change is typically not caused by immediate changes in the external environment, but rather by long-term effects of internal system factors such as sensor aging, device wear, temperature changes, power supply fluctuations, and software algorithm degradation.

[0024] According to an embodiment of the present application, a method embodiment of a method for determining a building environment state is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] Figure 1 is a flowchart of an optional building environment status determination method provided according to an embodiment of the present application, such as Figure 1 As shown, the method includes the following steps:

[0026] Step S102: obtaining current measurement values ​​corresponding to various environmental parameters of the building, as well as historical measurement values ​​corresponding to various environmental parameters, wherein a measurement error between the historical measurement value and the current measurement value is less than a preset error threshold, and the measurement error indicates a degree of similarity between the environmental state corresponding to the current measurement value and the environmental state corresponding to the historical measurement value;

[0027] It can be understood that by installing a variety of sensors inside the building, the building environment is detected, and the current measurement values ​​corresponding to the various environmental parameters of the building and the historical measurement values ​​corresponding to the various environmental parameters are collected, wherein the measurement error between the historical measurement value and the current measurement value is less than a preset error threshold, and the measurement error is used to quantify the similarity between the environmental state corresponding to the current measurement value and the environmental state corresponding to the historical measurement value. The above-mentioned measurement values ​​are, for example, temperature, humidity, carbon dioxide concentration, fine particulate matter concentration, volatile organic compound gas, and natural light intensity. By using a variety of sensors, a variety of environmental parameters of the building can be detected and data collected, and then key environmental parameters such as temperature, humidity, carbon dioxide concentration, PM2.5 concentration, volatile organic compound concentration and natural light intensity in the building can be comprehensively detected, providing data support for determining the building environment state.

[0028] Optionally, the multiple sensors mentioned above may include temperature sensors, humidity sensors, carbon dioxide sensors, PM2.5 sensors, volatile organic compound sensors, and light sensors. The temperature sensor is used to measure the building's temperature parameters and thereby control temperature equipment, such as a heating, ventilation, and air conditioning system, to maintain a comfortable indoor temperature level. The humidity sensor is used to measure the humidity parameters in the air and thereby adjust humidity equipment, such as a humidifier or dehumidifier, to maintain the building's humidity level. The carbon dioxide sensor is used to measure the carbon dioxide concentration in the air and thereby adjust the building's ventilation equipment, such as determining whether to turn on or increase ventilation, to maintain the building's air quality. The PM2.5 sensor is used to measure the fine particulate matter concentration parameter in the air. The volatile organic compound sensor is used to measure the presence of predetermined types of volatile organic compound gases in the air. The light sensor unit is used to measure the natural light intensity in the building and thereby adjust the indoor lighting equipment to maintain the building's light intensity based on the natural light intensity.

[0029] Alternatively, noise sensors and magnetic field sensors can be installed in buildings to measure the noise intensity and magnetic field strength of the building. The noise sensor measures the noise intensity of the building and adjusts noise reduction equipment to maintain the building's noise level accordingly. The magnetic field sensor measures the magnetic field strength of the building and adjusts magnetic field adjustment equipment to maintain the building's magnetic field strength accordingly.

[0030] Alternatively, passive infrared sensors can be installed in buildings to detect the movement of people or objects. These sensors can sense the presence and movement of people or objects by detecting passive infrared radiation. This allows them to control smart devices in the building, such as smart locks and curtains, improving building security and system intelligence, while also promoting energy conservation and emission reduction.

[0031] Step S104, filtering based on the current measurement values ​​corresponding to the various environmental parameters, and determining first correction values ​​corresponding to the various environmental parameters;

[0032] It can be understood that filtering the current measured values ​​corresponding to various building environmental parameters removes outliers and noise, resulting in first corrected values ​​corresponding to each of the various environmental parameters to ensure data cleanliness. Filtering the measured values ​​removes random noise, making the data smoother and more stable. This improves the reliability of the test results and ensures that the system can quickly reflect dynamic changes in indoor environmental parameters. Furthermore, more accurate environmental parameter data enables the building control system to respond more quickly to environmental changes, rationally adjust the operating status of equipment such as HVAC, humidifiers, dehumidifiers, and air purification systems, improve energy efficiency, and reduce unnecessary equipment operation.

[0033] In an optional embodiment, filtering is performed based on the current measurement values ​​corresponding to the multiple environmental parameters to determine the first correction values ​​corresponding to the multiple environmental parameters, including: obtaining the historical correction values ​​corresponding to the multiple environmental parameters; filtering based on the current measurement values ​​and historical correction values ​​corresponding to the multiple environmental parameters to determine the second correction values ​​corresponding to the multiple environmental parameters; performing data drift correction based on the second correction values ​​corresponding to the multiple environmental parameters to determine the first correction values ​​corresponding to the multiple environmental parameters.

[0034] It can be understood that historical correction values ​​corresponding to various environmental parameters are obtained, and based on the historical correction values ​​corresponding to the various environmental parameters, the current measurement values ​​corresponding to the various environmental parameters are filtered to obtain second correction values ​​corresponding to the various environmental parameters. The second correction values ​​corresponding to the various environmental parameters are corrected to eliminate data errors caused by data drift, such as sensor aging, and obtain first correction values ​​corresponding to the various environmental parameters. Filtering can effectively filter out random noise, improve data accuracy and stability, and at the same time, by processing sensor measurements in real time, it can quickly respond to dynamic changes in the building environment, ensuring the timeliness and effectiveness of the building control system.

[0035] Optionally, a Kalman filter algorithm can be used to filter the measurement values ​​corresponding to multiple environmental parameters (e.g., current measurement values ​​and historical measurement values). Taking the current measurement value as an example, the Kalman filter process includes two stages: prediction and update. The prediction stage uses the state transition matrix, the control input matrix, and the process noise covariance to estimate the current predicted state. The current predicted state is in the form of a vector, which is composed of the current predicted measurement values ​​corresponding to the multiple environmental parameters obtained based on the historical correction values ​​corresponding to the multiple environmental parameters. The update stage calculates the Kalman gain and corrects the predicted state based on the observation matrix, the measurement value, and the measurement noise covariance, ultimately determining a more accurate second correction value.

[0036] The prediction process of the Kalman filter algorithm can be achieved in the following ways:

[0037]

[0038] P k|k-1 =AP k-1|k-1 A T +Q

[0039] in, is the current forecast status, is a vector of historical correction values, A is the state transfer matrix, B is the control input matrix, u k is the control input, P k|k-1 is the covariance matrix of the current forecast state, P k-1|k-1 is the covariance matrix of the historical correction values, is the transposed matrix of the state transfer matrix, and Q is the process noise covariance.

[0040] The update process of the Kalman filter algorithm can be achieved as follows:

[0041] K k =P k|k-1 H T (HP k|k-1 H T +R) -1

[0042]

[0043] P k|k =(IK k H)P k|k-1

[0044] Among them, K k is the Kalman gain, H is the observation matrix, H T is the transposed matrix of the observation matrix, R is the measurement noise covariance, is a vector consisting of the second correction values ​​corresponding to various environmental parameters, z kis the vector of current measurement values ​​(i.e., the current measurement values ​​corresponding to various environmental parameters), P k|k is the covariance matrix of the second correction value, and I is the identity matrix.

[0045] The state prediction formula estimates the current environmental state (i.e., the current predicted state). Based on the optimal estimate from the previous moment (i.e., the historical correction value), the state transition matrix (used to describe the system's dynamic characteristics), the control input matrix, and the control input (used to describe the system's changes under external control), the current estimated value of the sensor data (i.e., the current predicted measurement value) is predicted. This determines the current predicted state, providing a preliminary reference for subsequent update steps.

[0046] The covariance prediction formula predicts the covariance matrix of the current environmental state, representing the uncertainty of the current environmental state. The covariance matrix quantifies the error in the current predicted state, while the process noise covariance represents the inherent variability of the system itself and is used to assess measurement error.

[0047] The Kalman gain formula calculates the weight coefficient between the current measurement and the predicted value (i.e., the current predicted measurement), balancing the uncertainty between the predicted value and the actual current measurement. When the uncertainty of the predicted value is large, the Kalman gain increases confidence in the current measurement; conversely, when the uncertainty of the predicted value is low, it increases confidence in the predicted value. Dynamic adjustment of the Kalman gain allows the system to dynamically adjust its reliance on the predicted and current measurement values ​​based on real-time noise characteristics, thereby improving the accuracy of determining the building environment status.

[0048] The function of the state update formula is to update the optimal state estimate at the current moment (i.e., the vector composed of the second correction values ​​corresponding to multiple environmental parameters). By taking a weighted average of the current measured value and the predicted value, the influence of noise on the estimation result is reduced. The observation matrix is ​​used to map the predicted value to the measurement space to calculate the difference between the current measured value and the predicted value, thereby improving the accuracy of the estimate.

[0049] The function of the covariance update formula is to update the covariance matrix of the current predicted state to reflect the uncertainty after the optimal state estimation. The unit matrix is ​​used to ensure the correct form of the matrix calculation. The smaller the value of the updated covariance matrix, the lower the uncertainty of the system state.

[0050] Optionally, after using the Kalman filter algorithm to obtain the second correction values ​​corresponding to multiple environmental parameters, a linear regression model can be used to correct the second correction values ​​to eliminate data errors caused by data drift, such as sensor aging, and obtain the first correction values ​​corresponding to multiple environmental parameters.

[0051] The second correction value is corrected based on the linear regression model. The first correction value can be determined as follows:

[0052] y=αx+β

[0053] Where y is the first correction value, x is the second correction value, and α and β are calibration coefficients.

[0054] In an optional embodiment, the method further includes: determining a health index representing a sensor that collects the multiple environmental parameters based on differences between first correction values ​​corresponding to the multiple environmental parameters and second correction values ​​corresponding to the multiple environmental parameters.

[0055] It can be understood that the difference between the first correction value corresponding to the various environmental parameters and the second correction value corresponding to the various environmental parameters that eliminates data drift is calculated by taking the difference. Based on this difference, the sensor's health index is determined. Monitoring the health index facilitates predictive maintenance. When the health index falls below a preset threshold, the system triggers a fault alarm, alerting the user to perform maintenance or replacement, avoiding data distortion or system downtime and ensuring the continuity and reliability of building regulation and control.

[0056] Optionally, based on the difference between the first correction value and the second correction value, a health index HI of the sensor is determined. The health index HI may be determined as follows:

[0057]

[0058] Where N is the total number of sampled data points, y i is the first correction value at the i-th time point, is the second correction value at the i-th time point, is the absolute error between the actual measurement value at time point i and the second corrected value (i.e. the absolute value of the difference).

[0059] In an optional embodiment, the method further includes: encrypting the first correction value using a predetermined encryption algorithm to obtain an encrypted first correction value; transmitting the encrypted first correction value to a data processing server, wherein the data processing server is used to parse the encrypted first correction value of the building.

[0060] It can be understood that before the first correction value is transmitted for data, it is necessary to encrypt the first correction value. The first correction value is encrypted using a predetermined encryption algorithm, such as the AES (Advanced Encryption Standard)-128 encryption algorithm (i.e., an encryption algorithm using a 128-bit key), to obtain an encrypted first correction value. The encrypted first correction value is transmitted to a data processing server, which decrypts and parses the encrypted first correction value. The encryption algorithm can effectively prevent eavesdropping and tampering of data during transmission, ensure the confidentiality and integrity of environmental parameter data, and improve the information security level of the building management system. At the same time, encrypted transmission can ensure that only servers with the correct key can parse the data, prevent illegal access and data leakage, and ensure the safe operation of the building management system.

[0061] Step S106, determining the probabilities corresponding to the plurality of candidate environmental states under the conditions of the first correction values ​​corresponding to the plurality of environmental parameters;

[0062] It can be understood that multiple possible candidate environmental states for the building are first determined, and a priori probabilities for each candidate state are determined based on prior knowledge. This is the probability of the candidate state occurring in the absence of new data. Based on the prior probabilities corresponding to the multiple candidate environmental states, the probabilities corresponding to the multiple candidate environmental states are determined, respectively, under the conditions of first correction values ​​corresponding to the various environmental parameters. These probabilities reflect the probability of the multiple candidate environmental states occurring under the conditions of the first correction values. This process improves the accuracy of building environmental state determinations. Accurate environmental state estimation aids decision-making in building control systems, avoiding over-regulation or under-response, thereby improving energy efficiency and the comfort of the living or working environment.

[0063] Alternatively, a multi-parameter Bayesian approach can be used to determine the probabilities corresponding to multiple candidate environmental states. The Bayesian inference process includes conditional probabilities and multi-parameter Bayesian updates. Conditional probabilities can be determined as follows:

[0064]

[0065] Where P(A|B) represents the probability of event A occurring given that event B has occurred, P(B|A) is the probability of event B given that event A has occurred, and P(A) and P(B) are the prior probabilities of events A and B.

[0066] Assuming that there are multiple sensor data sources, the first correction values ​​D1, D2, ..., D corresponding to the various environmental parameters of the sensors are obtained. n , S is a candidate environment state. Multi-parameter Bayesian update can be achieved as follows:

[0067]

[0068] Among them, P(S|D1, D2, ..., D n ) represents the first correction value D1, D2, ..., D n The probability of the candidate environment state S under the condition of n |S) represents the first correction values ​​D1, D2, ..., D corresponding to the various environmental parameters under the condition of the candidate environmental state S. n The probability of simultaneous occurrence of the response; P(S) represents the prior probability of the candidate environment state S; P(D1, D2, ..., D n ) represents the first correction values ​​D1, D2, ..., D corresponding to the various environmental parameters under the condition of no environmental state. n The joint probability of .

[0069] The function of the conditional probability formula is to calculate the probability of an event when a known event occurs. It plays a key role in multi-parameter fusion. It can infer the probability of environmental states that are not directly measured (i.e., candidate environmental states) by using the first correction values ​​corresponding to various environmental parameters of the known sensor.

[0070] The function of the multi-parameter Bayesian update formula is to fuse the first correction values ​​corresponding to multiple environmental parameters from multiple sensors to update and obtain a more accurate posterior probability of the candidate environmental state, thereby establishing associations between sensor data and dynamically adjusting the weights of each parameter.

[0071] Through multi-parameter Bayesian updating, the sensor system can integrate information from multiple data sources in complex environments, resulting in a more accurate estimate of the final environmental state. Through recursive updating, the algorithm dynamically adjusts the weights of each sensor parameter, thereby optimizing the system's perception of the environmental state.

[0072] Step S108 , taking the environmental states with probabilities greater than a preset probability threshold among the multiple candidate environmental states as a second candidate environmental state set, and determining the target environmental state of the building from the second candidate environmental state set based on the historical measurement values ​​corresponding to the multiple environmental parameters.

[0073] It can be understood that a probability threshold is pre-set, and the probabilities corresponding to multiple candidate environmental states are compared with the probability threshold. A second set of candidate environmental states is obtained, consisting of environmental states with probabilities greater than the probability threshold. Based on historical measurement values ​​corresponding to various environmental parameters, the target environmental state of the building is determined from this second set of candidate environmental states. By setting a probability threshold to select highly probable environmental states to form the second set of candidate environmental states, and combining this with analysis of historical measurement values, the accuracy of the building environmental state determination can be effectively improved.

[0074] In an optional embodiment, based on the historical measurement values ​​corresponding to multiple environmental parameters, the target environmental state of the building is determined from the second candidate environmental state set, including: based on the historical measurement values ​​corresponding to the multiple environmental parameters, using a pre-trained environmental state prediction model to obtain the historical environmental state of the building, wherein the environmental state prediction model pre-learns the correspondence between the measurement values ​​of multiple environmental parameters of the building and the environmental state; comparing the multiple candidate environmental states included in the second candidate environmental state set with the historical environmental states respectively, and determining the errors corresponding to the multiple candidate environmental states included in the second candidate environmental state set; and taking the candidate environmental state with the smallest error among the multiple candidate environmental states included in the second candidate environmental state set as the target environmental state.

[0075] It can be understood that the historical measurement values ​​corresponding to the various environmental parameters are input into the pre-trained environmental state prediction model to obtain the historical environmental states corresponding to the historical measurement values ​​corresponding to the various environmental parameters. The above-mentioned environmental state prediction model pre-learns the correspondence between the measurement values ​​of the various environmental parameters of the building and the environmental state, and the measurement value error between the historical measurement value and the current measurement value is less than the preset error threshold. The multiple candidate environmental states included in the second candidate environmental state set are respectively analyzed with the historical environmental state to obtain the errors corresponding to the multiple candidate environmental states included in the second candidate environmental state set. The candidate environmental state corresponding to the minimum error among the errors corresponding to the multiple candidate environmental states included in the second candidate environmental state set is used as the target environmental state. By utilizing the environmental state prediction model trained based on historical data, combined with the error control of the current measurement value and the historical measurement value, and performing error analysis on the candidate environmental states, the accuracy of the building environmental state determination result can be effectively improved, and the problem of inaccurate prediction caused by data deviation or model simplification can be avoided.

[0076] In an optional embodiment, before selecting the environmental states with probabilities greater than a preset probability threshold among multiple candidate environmental states as the second candidate environmental state set, the method further includes: obtaining weather information of the area where the building is located; and determining the probability threshold based on the weather information and historical measurement values ​​corresponding to multiple environmental parameters.

[0077] It will be appreciated that to determine the second set of candidate environmental states from multiple candidate environmental states, a probability threshold is first determined as needed. Weather information for the building's area is obtained, and the probability threshold is determined based on this weather information and historical measurements corresponding to various environmental parameters. Using weather information and historical measurements to determine the probability threshold effectively avoids the problem of a fixed probability threshold being inflexible to weather changes in the building's area, thereby improving the accuracy of the environmental state determination results.

[0078] Optionally, a score value for the collected weather information can be determined through a weighted calculation, and based on the correspondence between the score value and the probability threshold, a probability threshold corresponding to the current weather information can be determined. First, various weather types are determined based on the collected weather information; second, the weather information corresponding to the aforementioned various weather types is normalized to eliminate dimensional differences between the data; weights corresponding to each weather type are determined, and a weighted sum is taken based on the normalized weather information and the weights corresponding to each weather type to obtain a score value for the weather information.

[0079] Through the above steps S102 to S108, the purpose of determining the building environment status can be achieved by filtering and fusing the various environmental parameter data obtained by the sensor, thereby achieving the technical effect of improving the accuracy of the building environment status determination results, and thus solving the technical problem of low accuracy of the building environment status determination results existing in related technologies.

[0080] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0081] A building environment status determination system is also provided in an embodiment of the present application. The building environment status determination system provided in an embodiment of the present application is introduced below.

[0082] Figure 2 is a structural diagram of a building environment status determination system provided in accordance with an embodiment of the present application, such as Figure 2 As shown, the system includes: a multi-parameter sensor module 202 and a data processing and fusion module 204. The system is described below.

[0083] The multi-parameter sensor module 202 is configured to obtain current measurement values ​​corresponding to various environmental parameters of the building, as well as historical measurement values ​​corresponding to various environmental parameters, wherein a measurement error between the historical measurement values ​​and the current measurement values ​​is less than a preset error threshold, and the measurement error indicates a degree of similarity between the environmental state corresponding to the current measurement value and the environmental state corresponding to the historical measurement values;

[0084] The data processing and fusion module 204 is connected to the multi-parameter sensor module 202, and is used to filter based on the current measurement values ​​corresponding to the multiple environmental parameters, and determine the first correction values ​​corresponding to the multiple environmental parameters; under the conditions of the first correction values ​​corresponding to the multiple environmental parameters, use data fusion to determine the probabilities corresponding to the multiple candidate environmental states; take the environmental states with probabilities greater than a pre-set probability threshold among the multiple candidate environmental states as the second candidate environmental state set, and determine the target environmental state of the building from the second candidate environmental state set based on the historical measurement values ​​corresponding to the multiple environmental parameters.

[0085] It is understood that the multi-parameter sensor module is located on one side of the interior of the sensor body and is connected to the data processing and fusion module. The multi-parameter sensor module is responsible for real-time detection of multiple environmental parameters within the building and transmits the data collected by the sensors to the data processing and fusion module for processing, enabling flexible adjustment of management strategies based on building needs and adapting to different building scenarios. The multi-parameter sensor module enables comprehensive detection of the indoor environment, providing a richer set of measurement values ​​corresponding to multiple building environmental parameters (e.g., current and historical measurements). This allows for flexible adjustment of sensor types and parameter settings to accommodate various building application scenarios, ensuring that the building environmental status determination system obtains accurate environmental status information and improving regulatory control effectiveness. The data processing and fusion module is located on one side of the interior of the sensor body and is connected to the multi-parameter sensor module and the self-calibration and self-diagnosis module. It is responsible for pre-processing and fusing the multiple environmental parameter data collected by the multi-parameter sensor module, eliminating data noise, and transmitting the processed data to the self-calibration and self-diagnosis module for calibration and diagnosis of the sensor health status. The data processing and fusion module can effectively reduce the noise and redundancy in the measurement values ​​obtained by sensors, enhance the stability and accuracy of the data, and at the same time, provide high-quality environmental data support for determining the building environment status by reflecting environmental changes in real time. The data processing and fusion module also supports rapid response, which helps the system to take the average and weighted calculation between the measurement values ​​obtained by different sensors, thereby reducing the error of a single sensor data.

[0086] Optionally, Figure 3This is a schematic diagram of an optional building environment status determination system provided according to an embodiment of the present application. As shown in 3, the indoor environment sensor system (i.e., the building environment status determination system) includes a multi-parameter sensor module 202, a data processing and fusion module 204, a self-calibration and self-diagnosis module 206, a communication module 208, and a power management module 210.

[0087] As an optional embodiment, the multi-parameter sensor module includes: a temperature sensor unit, a humidity sensor unit, a carbon dioxide sensor unit, a fine particulate matter concentration PM2.5 sensor unit, a volatile organic compound sensor unit, and a light sensor unit, wherein the temperature sensor unit is used to measure the temperature parameter of the building, wherein the temperature parameter is used to adjust the temperature equipment that maintains the temperature of the building; the humidity sensor unit is used to measure the humidity parameter in the air, wherein the humidity parameter is used to adjust the humidity equipment that maintains the humidity of the building; the carbon dioxide sensor unit is used to measure the carbon dioxide concentration parameter in the air, wherein the carbon dioxide concentration parameter is used to adjust the ventilation equipment that maintains the air quality of the building; the fine particulate matter concentration PM2.5 sensor unit is used to measure the fine particulate matter concentration parameter in the air; the volatile organic compound sensor unit is used to measure a predetermined type of volatile organic compound gas in the air; and the light sensor unit is used to measure the natural light intensity of the building, wherein the natural light intensity is used to adjust the indoor lighting equipment that maintains the light intensity of the building.

[0088] It is understood that the various sensor modules include a temperature sensor unit, a humidity sensor unit, a carbon dioxide sensor unit, a PM2.5 sensor unit, a volatile organic compound sensor unit, and a light sensor unit. The temperature sensor unit is used to measure the building's temperature parameters and thereby control temperature equipment, such as a heating, ventilation, and air conditioning system, to maintain a comfortable indoor temperature level. The humidity sensor unit is used to measure the humidity parameters in the air and thereby adjust humidity equipment, such as a humidifier or dehumidifier, to maintain the building's humidity level. The carbon dioxide sensor unit is used to measure the carbon dioxide concentration in the air and thereby adjust the building's ventilation equipment, such as determining whether to turn on or increase ventilation, to maintain the building's air quality. The PM2.5 sensor unit is used to measure the concentration parameters of fine particulate matter in the air. The volatile organic compound sensor unit is used to measure the presence of predetermined types of volatile organic compound gases in the air. The light sensor unit is used to measure the natural light intensity in the building and thereby adjust the indoor lighting equipment to maintain the building's light intensity based on the natural light intensity. Through a variety of sensors, various environmental parameters of the building can be detected and data collected, and key environmental parameters such as temperature, humidity, carbon dioxide concentration, PM2.5 concentration, volatile organic compound concentration and natural light intensity in the building can be comprehensively detected to provide data support for determining the environmental status of the building.

[0089] As an optional embodiment, the multi-parameter sensor module also includes: a noise sensor unit and a magnetic field sensor unit, wherein the noise sensor unit is used to measure the noise intensity of the building, wherein the noise intensity is used to adjust the noise reduction equipment to maintain the noise level of the building; the magnetic field sensor unit is used to measure the magnetic field strength of the building, wherein the magnetic field strength is used to adjust the magnetic field adjustment equipment to maintain the magnetic field strength of the building.

[0090] It is understood that the various sensor modules can also include noise sensor units and magnetic field sensor units. The noise sensor unit is used to measure the noise intensity of the building and, based on the noise intensity, adjust the noise reduction equipment to maintain the building's noise level. The magnetic field sensor unit is used to measure the magnetic field strength of the building and, based on the magnetic field strength, adjust the magnetic field adjustment equipment to maintain the building's magnetic field strength. By measuring key environmental parameters such as noise intensity and magnetic field strength, more comprehensive data support can be provided for the building's environmental status, ensuring that the building's noise level and magnetic field strength are maintained at safe levels and improving the building's environmental comfort.

[0091] Optionally, Figure 4 This is a first module diagram of an optional building environment status determination system provided according to an embodiment of the present application, such as Figure 4As shown, the multi-parameter sensor module 202 includes a temperature sensor unit 2021, a humidity sensor unit 2022, a carbon dioxide sensor unit 2023, a fine particulate matter concentration PM2.5 sensor unit 2024, a volatile organic compound sensor unit 2025, a light sensor unit 2026, a noise sensor unit 2027 and a magnetic field sensor unit 2028. The temperature sensor unit can be used to help the building adjust the HVAC in real time to maintain a suitable room temperature, improve the comfort of the living or working environment, and quickly identify abnormal temperature fluctuations, and then take timely measures to prevent room temperature fluctuations from adversely affecting human health and equipment operation; the humidity sensor unit can improve indoor air quality, help prevent the growth of mold and bacteria, reduce allergens in indoor air, protect the health of residents, and prevent corrosion caused by high humidity and cracking caused by low humidity; the carbon dioxide sensor unit can be used to decide whether to start the ventilation system to ensure that the indoor air of the building is fresh, and by increasing ventilation, the harm of carbon dioxide accumulation to the human body can be reduced. At the same time, unnecessary ventilation operations can be reduced to achieve higher energy efficiency; the PM2.5 sensor unit (i.e., fine particulate matter concentration PM2.5 sensor unit) can be used to start the air purification system in time to filter out harmful particulate matter, protect indoor air quality, and reduce damage to the respiratory system. Provide air quality information to residents and managers, so that they can make necessary air purification decisions to ensure that the building's air quality meets environmental standards; the volatile organic compound sensor unit can protect the health and safety of residents, reduce the risk of residents being exposed to harmful substances, and enable air purification equipment to automatically adjust its operating intensity, improve purification efficiency, reduce unnecessary operation, and save energy consumption; the light sensor unit can measure the natural light intensity of the building, and then adjust the indoor lighting equipment that maintains the building's light intensity according to the natural light intensity, to ensure that the light intensity in the building is maintained at an appropriate level; the noise sensor unit can measure the noise intensity of the building, and then adjust the noise reduction equipment that maintains the building's noise level according to the noise intensity, to avoid excessive noise from harming people in the building; the magnetic field sensor unit can measure the magnetic field strength of the building, and then adjust the magnetic field adjustment equipment that maintains the building's magnetic field strength according to the magnetic field strength, to avoid damage caused by the magnetic field to various equipment in the building.

[0092] Alternatively, passive infrared sensor units can be installed in buildings to detect the movement of people or objects within them. These units can sense the presence and movement of people or objects by detecting passive infrared radiation, and can then control smart devices in the building, such as smart locks and smart curtains. This improves building security, enhances the intelligence of the system, and promotes energy conservation and emission reduction.

[0093] Optionally, Figure 5This is a second module diagram of an optional building environment status determination system provided according to an embodiment of the present application, such as Figure 5 As shown, the data processing and fusion module 204 includes a data preprocessing unit 2041, a Kalman filter unit 2042, a Bayesian inference unit 2043, and a data storage unit 2024. The data preprocessing unit performs preliminary filtering and sorting on the data collected by the multi-parameter sensor module to remove outliers and noise; the Kalman filter unit dynamically processes the sensor data based on the Kalman filter algorithm; the Bayesian inference unit analyzes the correlation between the sensor data and performs correlation fusion on the data; and the data storage unit temporarily stores the preprocessed and fused data.

[0094] Optionally, the data preprocessing unit removes outliers and noise from the data, ensuring cleaner and more accurate data input to subsequent processing units. This reduces the impact of inaccurate data on analysis results, improves system stability in complex environments, and enables the sensor to maintain good data processing performance in high-noise environments. This helps reduce the processing burden on subsequent units, speeds up data processing, and enhances the overall system response efficiency. The Kalman filter unit effectively filters random noise from sensor data, making it smoother and more accurate. It gradually optimizes the measured values, resulting in higher accuracy and improved reliability of sensor data. This ensures the system can quickly reflect dynamic changes in indoor environmental parameters and provides timely and effective data support for building control. The Bayesian inference unit facilitates a more comprehensive assessment of environmental conditions, making the data fusion process more scientific and rational, reducing data redundancy, improving the system's environmental perception, and providing a more reliable decision-making basis for subsequent system control. The data storage unit provides reliable data support for the building environmental status determination system, preventing data loss. It serves as the foundation for the system's intelligent prediction and optimization decisions, and supports the continuity and stability of building control.

[0095] As an optional embodiment, the building environment status determination system provided by the embodiment of the present application further includes: a self-calibration and self-diagnosis module, the self-calibration and self-diagnosis module includes: an automatic calibration unit, a self-diagnosis unit, wherein the automatic calibration unit is used to perform data drift correction based on the second correction values ​​corresponding to the multiple environmental parameters, and determine the first correction values ​​corresponding to the multiple environmental parameters, wherein the second correction values ​​corresponding to the multiple environmental parameters are the historical correction values ​​corresponding to the multiple environmental parameters obtained by the data processing and fusion module; the values ​​are obtained by filtering the current measurement values ​​and the historical correction values ​​corresponding to the multiple environmental parameters; the self-diagnosis unit is connected to the automatic calibration unit, and is used to determine the health index representing the health status of the sensor based on the difference between the first correction value and the second correction value.

[0096] It is understood that the self-calibration and self-diagnosis module is located inside the sensor body. It is connected to the data processing and fusion module, the communication module, and the power management module. The self-calibration and self-diagnosis module is responsible for further correcting the second correction value obtained by the data processing and fusion module to eliminate data drift errors and obtain a first correction value. Based on this first correction value, the self-calibration and self-diagnosis module performs sensor fault diagnosis and determines the sensor's health. The communication module is responsible for processing the results obtained from this process and transmitting them to the data processing server. The power management module is responsible for providing power support for this process. The self-calibration and self-diagnosis module maintains the long-term accuracy and reliability of the building environmental status determination system through automatic calibration and health monitoring. The self-calibration and self-diagnosis module includes an automatic calibration unit and a self-diagnosis unit. The automatic calibration unit is responsible for correcting data drift in the second correction values ​​corresponding to the various environmental parameters obtained by the data processing and fusion module to avoid errors caused by factors such as sensor device aging. The second correction values ​​corresponding to the various environmental parameters are obtained by filtering the current measurement values ​​and historical correction values ​​corresponding to the various environmental parameters obtained by the multi-parameter sensor module. The self-diagnostic unit performs health checks on the multi-parameter sensor module, determining the sensor's health index to measure its health. Through self-calibration and self-diagnosis, the system can promptly detect sensor failures and issue fault warnings, thereby avoiding data distortion or interruptions. Furthermore, by monitoring sensor status in real time, the need for manual calibration and testing can be reduced, lowering overall maintenance costs and extending equipment life.

[0097] Optionally, Figure 6 is a third module diagram of an optional building environment status determination system provided according to an embodiment of the present application, such as Figure 6 As shown, the self-calibration and self-diagnosis module includes an automatic calibration unit 2061, a health status detection unit (i.e., a self-diagnosis unit) 2062, a fault detection unit 2063, and a fault alarm unit 2064. The automatic calibration unit is used to automatically calibrate sensor data based on reference values ​​to correct drift. The health status detection unit is used to detect the operating status of the sensor in real time and evaluate sensor performance by determining and analyzing the health index. The fault detection unit uses a fault detection algorithm to identify and isolate faulty sensors when data is abnormal. The fault alarm unit is used to issue a warning signal when a sensor fault is detected, prompting the user to perform maintenance or replacement.

[0098] Optionally, the auto-calibration unit can automatically correct drift caused by environmental changes, sensor aging, and other factors, ensuring data remains highly accurate at all times. This effectively reduces the frequency of manual calibration, lowers maintenance costs and workload, reduces sensor overload caused by data deviations, and increases the lifespan and stability of the equipment. The health status detection unit can perform preventive maintenance before sensor performance drops below critical values, avoiding system downtime caused by sensor failure, improving system reliability, and enhancing the overall operational efficiency and stability of the building environmental status determination system. The fault detection unit prevents faulty sensor devices from affecting other parts of the system, preventing their erroneous data from interfering with the overall system data quality. This ensures accurate and reliable measurement data from other functioning sensors, reduces system downtime, and ensures the continuous and stable operation of the building environmental status determination system. The fault alarm unit prevents the system from being continuously affected by faulty sensor devices, reduces system maintenance risks, ensures the long-term stability of the system, and thereby improves the safety and reliability of building environmental control.

[0099] As an optional embodiment, the building environment status determination system provided in the embodiment of the present application further includes: a communication module, the communication module includes: a communication protocol support unit, a data encryption unit, and a data transmission unit, wherein the communication protocol support unit is used to provide a communication protocol between the communication module and the data processing server; the data encryption unit is connected to the communication protocol support unit, and is used to encrypt the first correction value using a predetermined encryption algorithm to obtain an encrypted first correction value; the data transmission unit is connected to the data encryption unit, and is used to transmit the encrypted first correction value to the data processing server, wherein the data processing server is used to parse the encrypted first correction value of the building.

[0100] As will be understood, the communication module is located inside the sensor body. It connects to the self-calibration and self-diagnosis module and the data processing and fusion module. The communication module processes the first correction value, sensor health index, building environmental status, and other data obtained by the self-calibration and self-diagnosis module and the data processing and fusion module, and transmits them to the data processing server. It can also transmit instructions from the data processing server. The communication module is responsible for transmitting data collected by the multi-parameter sensor module and processed by the data processing and fusion module to the data processing server and supports multiple communication protocols. The communication module supports multiple communication protocols and encrypts data to prevent malicious tampering or theft of sensor data, ensuring the confidentiality and integrity of environmental data. Furthermore, the communication module can receive building management instructions, enabling intelligent control and feedback. Before data transmission, the first correction value must be encrypted. This is encrypted using a predetermined encryption algorithm, such as AES-128, to obtain the encrypted first correction value. The encrypted first correction value is then transmitted to the data processing server, where it is decrypted and analyzed. Through encryption algorithms, data can be effectively prevented from being eavesdropped and tampered with during transmission, ensuring the confidentiality and integrity of environmental parameter data and improving the information security level of the building management system. At the same time, encrypted transmission can ensure that only servers with the correct keys can parse the data, preventing illegal access and data leakage, and ensuring the safe operation of the building management system.

[0101] Optionally, Figure 7 FIG4 is a fourth module diagram of an optional building environment status determination system provided according to an embodiment of the present application, such as Figure 7 As shown, the communication module includes a communication protocol support unit 2081, a data transmission unit 2082, a data encryption unit 2083, and a data receiving and parsing unit 2084. The communication protocol support unit is used to provide support for multiple communication protocols, achieving seamless integration between the various modules of the building environment status determination system. The data transmission unit is responsible for data transmission between the sensor and the building management system. The data encryption unit uses a predetermined encryption algorithm, such as AES-128, to encrypt the first correction value obtained from the data processing and fusion module. The data receiving and parsing unit is used to parse received building control instructions and execute corresponding operations.

[0102] Optionally, a communication protocol support unit can enhance system compatibility, integrating the various modules within the building environmental status determination system. This also provides the system with enhanced scalability, facilitating future system upgrades or adjustments. A data transmission unit ensures real-time updates of environmental monitoring data, enabling the system to rapidly respond to environmental changes, reduce data loss or delays caused by transmission delays or interruptions, ensure the continuity of monitoring data, and meet the requirements of multi-parameter environmental monitoring. A data encryption unit protects the confidentiality and integrity of environmental data, enhancing the system's data security capabilities, effectively preventing potential cyberattacks and protecting transmitted data from threats such as network hijacking, thereby improving the data security of the building environmental status determination system. A data reception and analysis unit supports remote control and feedback of the system, enabling two-way interaction between the multi-parameter sensor module and the communication module. This allows for flexible adjustment of environmental control strategies and adjustment parameters to meet building environmental control requirements, reduce manual intervention, and enhance the automation level of building regulation and control.

[0103] As an optional embodiment, the building environment status determination system provided in the embodiment of the present application further includes: a power management module, the power management module includes: a clean power generation unit and a battery power supply unit, wherein the clean power generation unit is used to power the building; the battery power supply unit is used to switch the clean power generation unit to the battery power supply unit when the power generation of the clean power generation unit is less than the minimum power, wherein the minimum power is the minimum power required to maintain normal operation of the building.

[0104] It can be understood that the power management module is arranged on one side of the interior of the sensor body. The power management module is connected to the self-calibration and self-diagnosis module, and is responsible for providing power support for the entire building environment status determination system. The power management module provides power support for the system and issues an early warning when the battery is low. The power management module includes a clean power generation unit and a battery power supply unit. The clean power generation unit uses clean energy to provide power to the building. When the clean power generation unit can provide sufficient power to maintain the normal operation of the building, the clean power generation unit is used to power the building. When the clean power generation unit cannot provide sufficient power to maintain the normal operation of the building (that is, when the power provided by the clean power generation unit is lower than the minimum power required for the normal operation of the building), the battery power supply unit is switched to provide power to the building. By providing multiple power supply modes for the building, it is possible to quickly switch to another power supply mode when one power supply mode cannot maintain the normal operation of the building, thereby avoiding system operation interruptions caused by insufficient power supply, improving the stability of the system, and enhancing the safety and reliability of building environment control.

[0105] Optionally, Figure 8 is a fifth module diagram of an optional building environment status determination system provided according to an embodiment of the present application, such as Figure 8As shown, the power management module includes a clean power generation unit 2101, a battery power unit 2102, an intelligent power switching unit 2103, and a power detection and alarm unit 2104. The clean power unit uses clean power generation to power the building; the battery power unit provides backup power; the intelligent power switching unit automatically switches between clean power and battery power modes based on the power status; and the power detection and alarm unit monitors the battery status in real time and issues an alert when the battery level falls below a set threshold (i.e., the minimum level), prompting the user to replace or perform maintenance on the battery.

[0106] Optionally, the clean power generation unit can be powered by photovoltaic panels. Utilizing photovoltaic panels when sunlight is sufficient reduces reliance on batteries and, consequently, energy consumption. The battery-powered unit ensures stable power to the building even when sunlight is absent or the photovoltaic power supply is insufficient, improving system reliability and preventing system downtime due to power outages. Photovoltaic power generation units (i.e., clean power generation units powered by photovoltaics) help reduce reliance on traditional electricity, lowering the carbon footprint, reducing battery drain frequency, and extending battery life. This reduces the frequency of battery replacement and maintenance, making the system sustainable and providing energy for the system. The battery-powered unit ensures continuous system operation in various environments, ensuring stable operation and extending overall system uptime, enabling all-day, continuous power supply. The intelligent power switching unit improves the system's energy efficiency, ensures seamless switching between the two power supply units, and ensures continuous system operation without power interruption during the switchover. This improves system reliability and user experience, makes power management more intelligent and convenient, and helps reduce operational workload and complexity. The power detection and alarm unit helps the system to reasonably arrange battery maintenance plans, prevent battery over-discharge, extend battery life, and thus reduce replacement frequency and cost.

[0107] Alternatively, the output power of photovoltaic power generation can be determined as follows:

[0108] P=A·G·η

[0109] Where A is the area of ​​the photovoltaic panel, G is the incident light intensity, and η is the photovoltaic conversion efficiency.

[0110] The photovoltaic power output power formula is used to calculate the output power of photovoltaic panels. The power generation is determined based on the area of ​​the photovoltaic panel, the incident light intensity and the photovoltaic conversion efficiency. It can estimate the solar power supply capacity in the current environment in real time.

[0111] In a building environment state determination system provided by an embodiment of the present application, a multi-parameter sensor module 202 is used to obtain current measurement values ​​corresponding to multiple environmental parameters of a building, as well as historical measurement values ​​corresponding to multiple environmental parameters, wherein a measurement value error between the historical measurement value and the current measurement value is less than a preset error threshold, and the measurement value error indicates the degree of similarity between the environmental state corresponding to the current measurement value and the environmental state corresponding to the historical measurement value; a data processing and fusion module 204 is connected to the multi-parameter sensor module 202, and is used to perform filtering based on the current measurement values ​​corresponding to the multiple environmental parameters, and determine first correction values ​​corresponding to the multiple environmental parameters; under the condition of the first correction values ​​corresponding to the multiple environmental parameters, data fusion is used to determine the probabilities corresponding to multiple candidate environmental states; the environmental states with probabilities greater than the preset probability threshold among the multiple candidate environmental states are taken as a second candidate environmental state set, and the target environmental state of the building is determined from the second candidate environmental state set based on the historical measurement values ​​corresponding to the multiple environmental parameters. The purpose of determining the building environment status is achieved by filtering and fusing the various environmental parameter data obtained by the sensor, thereby achieving the technical effect of improving the accuracy of the building environment status determination results, and thus solving the technical problem of low accuracy of the building environment status determination results existing in the related technology.

[0112] Based on the above embodiments and optional embodiments, the present application proposes an optional implementation mode. According to the embodiment of the present application, a building conditioning and control system (i.e., a building environment status determination system) is provided for determining the environment status of a building.

[0113] With the increasing intelligence of modern buildings, the importance of indoor environmental quality to building management is becoming increasingly significant. Good indoor air quality and a comfortable indoor climate environment directly affect the health and comfort of residents, and are closely related to the energy efficiency and operating costs of buildings. Therefore, intelligent building regulation and control systems have become an important part of intelligent buildings. The core of intelligent building regulation and control systems lies in high-precision environmental detection and control capabilities.

[0114] Traditional building environmental control systems are mostly based on single-parameter sensors for monitoring. This approach cannot fully reflect the diversity of indoor environments and has detection blind spots in areas such as air quality and particulate matter concentration. It cannot meet the needs of modern intelligent buildings for multidimensional environmental information. In addition, traditional sensors are prone to data drift during long-term use, affecting measurement accuracy. At the same time, there is noise in data processing, resulting in errors, redundancy, and low accuracy in the detection data. In related technologies, systems with weak data processing and fusion capabilities cannot reflect environmental changes in real time when used in building environmental control, reducing the timeliness of system response. Furthermore, single sensors require frequent manual calibration and maintenance during actual use, resulting in high maintenance costs and an inability to guarantee the long-term stability and reliability of the system. In terms of communication and data transmission, traditional systems support a single communication protocol with poor compatibility, resulting in poor system integration, especially when integrating across systems. Furthermore, data transmission security is lacking, and transmitted data is at risk of malicious tampering or theft. In addition, sensors in traditional building conditioning and control systems usually rely on a single power supply, such as a battery, which can easily lead to power depletion and shutdown. This problem is particularly prominent in scenarios where maintenance is inconvenient for long periods of time.

[0115] The building conditioning and control system provided in the embodiment of the present application specifically includes a multi-parameter sensor module, a data processing and fusion module, a self-calibration and self-diagnosis module, a communication module and a power management module. The above modules are all arranged on the sensor body. These modules are introduced separately below.

[0116] A multi-parameter sensor module is installed on one side of the sensor body. This module is responsible for real-time detection of various environmental parameters within the building and transmits the data collected by the sensors to the data processing and fusion module for processing, enabling flexible adjustment of management strategies based on building needs. It can also adapt to different building scenarios. The multi-parameter sensor module enables comprehensive detection of the indoor environment, providing a richer set of measurement values ​​corresponding to various building environmental parameters. This allows for flexible adjustment of sensor types and parameter settings to accommodate a variety of building application scenarios, ensuring that the building environmental status determination system can obtain accurate environmental status information and improve the effectiveness of regulatory control.

[0117] The various sensor modules include temperature sensor units, humidity sensor units, carbon dioxide sensor units, fine particulate matter concentration PM2.5 sensor units, volatile organic compound sensor units, light sensor units, and passive infrared sensor units. The temperature sensor unit can be used to help buildings adjust HVAC in real time to maintain a suitable room temperature, improve the comfort of the living or working environment, and quickly identify abnormal temperature fluctuations, and then take timely measures to prevent room temperature fluctuations from adversely affecting human health and equipment operation; the humidity sensor unit can improve indoor air quality, help prevent the growth of mold and bacteria, reduce allergens in indoor air, protect the health of residents, and prevent corrosion caused by high humidity and cracking caused by low humidity; the carbon dioxide sensor unit can be used to decide whether to start the ventilation system to ensure fresh indoor air in the building, and by increasing ventilation, reduce the harm of carbon dioxide accumulation to the human body. At the same time, it can reduce unnecessary ventilation operations and achieve higher energy efficiency; the PM2.5 sensor unit (i.e., fine particulate matter concentration PM2.5 sensor unit) can be used to start the air purification system in time to filter out harmful particles It can protect indoor air quality, reduce damage to the respiratory system, provide air quality information to residents and managers, and make necessary air purification decisions to ensure that the building's air quality meets environmental standards; the volatile organic compound sensor unit can protect the health and safety of residents, reduce the risk of residents being exposed to harmful substances, and enable air purification equipment to automatically adjust its operating intensity, improve purification efficiency, reduce unnecessary operation, and save energy consumption; the light sensor unit can measure the natural light intensity of the building, and then adjust the indoor lighting equipment that maintains the light intensity of the building according to the natural light intensity, ensuring that the light intensity in the building is maintained at an appropriate level; the passive infrared sensor unit can sense the presence and movement of human beings or objects by detecting passive infrared radiation, and then control smart devices in the building, such as smart locks and smart curtains, etc., to improve the safety of the building and the intelligence level of the system, and promote energy conservation and emission reduction.

[0118] A data processing and fusion module is set on the internal side of the sensor body. The data processing and fusion module can effectively reduce the noise and redundancy in the measurement values ​​obtained by the sensor, enhance the stability and accuracy of the data, and at the same time, provide high-quality environmental data support for determining the building environment status by reflecting environmental changes in real time. The data processing and fusion module also supports fast response, which helps the system to take the average and weighted calculation between the measurement values ​​obtained by different sensors, thereby reducing the error of a single sensor data.

[0119] The data preprocessing unit includes a data preprocessing unit, a Kalman filter unit, a Bayesian inference unit, and a data storage unit. The data preprocessing unit is used to perform preliminary filtering and sorting of the data collected by the multi-parameter sensor module to remove outliers and noise; the Kalman filter unit dynamically processes the sensor data based on the Kalman filter algorithm; the Bayesian inference unit analyzes the correlation between the sensor data and performs correlation fusion on the data; and the data storage unit temporarily stores the preprocessed and fused data.

[0120] The data preprocessing unit removes outliers and noise from the data, ensuring cleaner and more accurate data input to subsequent processing units. This reduces the impact of inaccurate data on analysis results, improves system stability in complex environments, and enables the sensor to maintain good data processing performance in high-noise environments. This helps reduce the processing burden on subsequent units, speeds up data processing, and enhances the system's overall response efficiency. The Kalman filter unit effectively filters random noise from sensor data, making it smoother and more accurate. It gradually optimizes measurement values, resulting in higher accuracy and improved reliability of sensor data. This ensures the system can quickly reflect dynamic changes in indoor environmental parameters and provides timely and effective data support for building control. The Bayesian inference unit facilitates a more comprehensive assessment of environmental conditions, making the data fusion process more scientific and rational, reducing data redundancy, improving the system's environmental perception, and providing more reliable decision-making for subsequent system control. The data storage unit provides reliable data support for the building environmental status determination system, preventing data loss. It serves as the foundation for the system's intelligent prediction and optimization decisions, and supports the continuity and stability of building control.

[0121] In the Kalman filter unit, the Kalman filter process includes prediction and update. The implementation of the prediction process and update process of the Kalman filter algorithm is the same as above and will not be repeated here.

[0122] The Bayesian inference unit process includes conditional probability and multi-parameter Bayesian update. The method for determining conditional probability and updating multi-parameter Bayesian is the same as described above and will not be repeated here.

[0123] Through multi-parameter Bayesian updating, the sensor system can integrate information from multiple data sources in complex environments, resulting in a more accurate estimate of the final environmental state. Through recursive updating, the algorithm dynamically adjusts the weights of each sensor parameter, thereby optimizing the system's perception of the environmental state.

[0124] A self-calibration and self-diagnosis module is located inside the sensor body. This module maintains the system's long-term accuracy and reliability through automatic calibration and health monitoring. This module allows the system to promptly detect sensor failures and issue fault warnings, effectively preventing data distortion or interruptions and facilitating system maintenance. Furthermore, real-time monitoring of sensor status reduces the need for manual calibration and testing, lowering overall maintenance costs and extending the device's lifespan.

[0125] The self-calibration and self-diagnosis module includes an automatic calibration unit, a health status monitoring unit, a fault detection unit, and a fault alarm unit. The automatic calibration unit is used to automatically correct sensor data (i.e., the second correction value) based on a reference value to correct drift. The health status monitoring unit is used to detect the operating status of the sensor in real time and evaluate sensor performance by determining and analyzing the health index. The fault detection unit uses a fault detection algorithm to identify and isolate faulty sensors when data is abnormal. The fault alarm unit is used to issue a warning signal when a sensor fault is detected, prompting the user to perform maintenance or replacement.

[0126] The auto-calibration unit automatically corrects drift caused by environmental changes, sensor aging, and other factors, ensuring consistently high data accuracy. This effectively reduces the frequency of manual calibration, lowers maintenance costs and workload, reduces sensor overload caused by data deviations, and increases the lifespan and stability of the equipment. The health status detection unit performs preventive maintenance before sensor performance drops below critical values, avoiding system downtime caused by sensor failure, improving system reliability, and enhancing the overall operational efficiency and stability of the building environmental status determination system. The fault detection unit prevents faulty sensor devices from affecting other parts of the system, preventing their erroneous data from interfering with the overall system data quality. It ensures accurate and reliable measurement data from other functioning sensors, reduces system downtime, and ensures the continuous and stable operation of the building environmental status determination system. The fault alarm unit prevents the system from being continuously affected by faulty sensor devices, reduces system maintenance risks, ensures long-term system stability, and thus improves the safety and reliability of building environmental control.

[0127] The self-calibration and self-diagnosis module performs self-calibration on the data based on the linear regression model. The method for determining the first correction value through self-calibration is the same as described above and will not be repeated here.

[0128] The self-calibration and self-diagnosis module detects the sensor status through the health index. The method for determining the health index HI is the same as described above and will not be repeated here.

[0129] The function of the linear regression calibration model formula is to correct the systematic deviation in the sensor data. Through the linear regression calibration model, the system can adjust the second correction value of the sensor to be closer to the actual measurement value. The function of the health index is to detect the operating status of the sensor and evaluate the current health status of the sensor through the absolute error between the first correction value and the second correction value. By detecting the health index, the system can identify whether the sensor is in normal working condition. If the health index is lower than the preset threshold, a fault alarm will be triggered to remind maintenance or replacement, effectively ensuring the reliability of system data and the long-term stability of the sensor.

[0130] A communication module is located inside the sensor body. This module transmits the data collected and processed by the multi-parameter sensor module to the data processing center and supports multiple communication protocols. This module supports multiple communication protocols and encrypts data to prevent malicious tampering or theft, ensuring the confidentiality and integrity of environmental data. Furthermore, the module can receive building management instructions, enabling intelligent control and feedback.

[0131] The communication module includes a communication protocol support unit, a data transmission unit, a data encryption unit, and a data reception and parsing unit. The communication protocol support unit supports multiple communication protocols, enabling seamless integration between the various modules of the building environmental status determination system. The data transmission unit is responsible for data transmission between sensors and the building management system. The data encryption unit uses the AES-128 encryption algorithm to encrypt the first correction value obtained from the data processing and fusion module. The data reception and parsing unit parses received building control commands and executes the corresponding operations.

[0132] The communication protocol support unit ensures system compatibility and integrates the various modules within the building environmental status determination system. This also provides the system with excellent scalability, facilitating future system upgrades or adjustments. The data transmission unit ensures real-time updates of environmental monitoring data, enabling the system to rapidly respond to environmental changes, reducing data loss or delays caused by transmission delays or interruptions, ensuring data continuity, and meeting the requirements of multi-parameter environmental monitoring. The data encryption unit protects the confidentiality and integrity of environmental data, enhancing the system's data security capabilities, effectively preventing potential cyberattacks and protecting transmitted data from threats such as network hijacking, thereby improving the data security of the building environmental status determination system. The data reception and analysis unit supports remote control and feedback of the system, enabling two-way interaction between the multi-parameter sensor module and the communication module. This allows for flexible adjustment of environmental control strategies and adjustment parameters to meet building environmental control requirements, reduce manual intervention, and enhance the automation level of building regulation and control.

[0133] A power management module is located inside the sensor body. This module provides power to the system and issues warnings when the battery is low. When sunlight is sufficient, the system utilizes photovoltaic panels for power, reducing reliance on batteries and lowering energy consumption. The battery-powered unit ensures stable power to the building even in the absence of sunlight or when the photovoltaic power supply is insufficient, enhancing system reliability and preventing downtime due to power outages.

[0134] The power management module includes a photovoltaic power generation unit, a battery power unit, an intelligent power switching unit, and a power detection and alarm unit. The photovoltaic power generation unit uses photovoltaic panels to power the building when there is sunlight; the battery power unit provides backup power; the intelligent power switching unit automatically switches between clean power and battery power modes based on the power supply status; and the power detection and alarm unit monitors the battery status in real time and issues an alert when the power level falls below a set threshold (i.e., the minimum power level), prompting the user to replace or perform maintenance on the battery.

[0135] Photovoltaic power generation units (i.e., clean power generation units powered by photovoltaics) help reduce dependence on traditional electricity, lower carbon footprints, reduce the frequency of battery consumption, extend battery life, and thus reduce the frequency of battery replacement and maintenance, making the system sustainable and providing energy for the system. Battery-powered units can ensure that the system continues to work in various environments, guarantee the stable operation of the system, extend the overall operation time of the system, and enable the system to have all-weather continuous power supply capabilities. Intelligent power switching units can improve the system's energy utilization efficiency, ensure seamless switching between the two power supply units, ensure the continuity of system operation, so that the system will not be interrupted during switching, improve system reliability and user experience, make the power management process more intelligent and convenient, and help reduce the workload and complexity of operation and maintenance. The power detection and alarm unit helps the system to reasonably arrange battery maintenance plans, prevent battery over-discharge, extend battery life, and thus reduce replacement frequency and cost.

[0136] The power management module determines the output power of photovoltaic power generation based on the area of ​​the photovoltaic panels, the incident light intensity, and the photovoltaic conversion efficiency, thereby providing a real-time estimate of the solar power supply capacity in the current environment. The method for determining the output power of photovoltaic power generation is the same as described above and will not be repeated here.

[0137] The above optional implementation methods can achieve at least the following effects: the multi-parameter sensor module can detect multiple environmental factors at the same time, providing comprehensive indoor air quality and climate data for the building control system, thereby improving the detection accuracy and better meeting the environmental control needs of different scenes in the building; the data processing and fusion module of Kalman filtering and Bayesian inference algorithm can effectively reduce data noise, eliminate redundancy and deviation between sensor data, and the fused data has higher accuracy and can reflect environmental changes in real time. At the same time, high-precision data enables the building control system to respond to environmental changes more quickly, improving the building energy efficiency management effect; the self-calibration and self-diagnosis module can automatically correct sensor data drift, so that the sensor can maintain high accuracy during long-term use, and the health index can be used in real time. Detecting the operating status of sensors, detecting and reporting faults in advance, facilitating timely maintenance and replacement, greatly improving the long-term stability and reliability of the system, and reducing maintenance costs and the need for manual intervention; the communication module supports multiple communication protocols, has good compatibility, and is suitable for a variety of building control scenarios. The communication module uses the AES-128 encryption algorithm to ensure the security of data during transmission and prevent data from being maliciously tampered with or leaked; by equipping a photovoltaic and battery dual power supply system, photovoltaic power generation is used for power supply during the day when there is sufficient sunlight, reducing battery use and energy consumption. The power management module can automatically switch the power supply mode according to actual power consumption and alarm when the battery is low, ensuring the continuous and stable operation of the system in different scenarios, improving the energy efficiency of the system and extending the service life of the sensor.

[0138] An embodiment of the present application provides a non-volatile storage medium having a program stored thereon, which implements a method for determining a building environment state when the program is executed by a processor.

[0139] An embodiment of the present application provides an electronic device, comprising a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: obtaining current measurement values ​​corresponding to a plurality of environmental parameters of a building, and historical measurement values ​​corresponding to the plurality of environmental parameters, wherein a measurement error between the historical measurement value and the current measurement value is less than a preset error threshold, and the measurement error indicates the degree of similarity between the environmental state corresponding to the current measurement value and the environmental state corresponding to the historical measurement value; filtering based on the current measurement values ​​corresponding to the plurality of environmental parameters to determine first correction values ​​corresponding to the plurality of environmental parameters; determining the probabilities corresponding to a plurality of candidate environmental states under the condition of the first correction values ​​corresponding to the plurality of environmental parameters; determining an environmental state with a probability greater than a preset probability threshold among the plurality of candidate environmental states as a second set of candidate environmental states, and determining a target environmental state of the building from the second set of candidate environmental states based on the historical measurement values ​​corresponding to the plurality of environmental parameters. The device herein may be a server, a PC, or the like.

[0140] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program initialized with the following method steps: obtaining current measurement values ​​corresponding to multiple environmental parameters of a building, and historical measurement values ​​corresponding to multiple environmental parameters, wherein a measurement error between the historical measurement value and the current measurement value is less than a preset error threshold, and the measurement error indicates the degree of similarity between the environmental state corresponding to the current measurement value and the environmental state corresponding to the historical measurement value; filtering based on the current measurement values ​​corresponding to the multiple environmental parameters, and determining first correction values ​​corresponding to the multiple environmental parameters; under the condition of the first correction values ​​corresponding to the multiple environmental parameters, determining the probabilities corresponding to multiple candidate environmental states; taking the environmental state with a probability greater than a preset probability threshold among the multiple candidate environmental states as a second candidate environmental state set, and determining the target environmental state of the building from the second candidate environmental state set based on the historical measurement values ​​corresponding to the multiple environmental parameters.

[0141] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0142] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0143] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0144] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0145] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0146] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0147] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0148] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0149] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0150] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for determining a building environment state, characterized in that: include: Obtaining current measurement values ​​corresponding to a plurality of environmental parameters of the building, and historical measurement values ​​corresponding to the plurality of environmental parameters, wherein a measurement error between the historical measurement value and the current measurement value is less than a preset error threshold, and the measurement error indicates a degree of similarity between an environmental state corresponding to the current measurement value and an environmental state corresponding to the historical measurement value; Filtering based on current measurement values ​​corresponding to the multiple environmental parameters respectively, to determine first correction values ​​corresponding to the multiple environmental parameters respectively; determining the probabilities corresponding to the plurality of candidate environmental states respectively under the condition of the first correction values ​​respectively corresponding to the plurality of environmental parameters; The environmental states with probabilities greater than a preset probability threshold among the multiple candidate environmental states are taken as a second candidate environmental state set, and the target environmental state of the building is determined from the second candidate environmental state set based on the historical measurement values ​​corresponding to the multiple environmental parameters.

2. The method according to claim 1, characterized in that The filtering based on the current measurement values ​​respectively corresponding to the multiple environmental parameters to determine the first correction values ​​respectively corresponding to the multiple environmental parameters includes: Obtaining historical correction values ​​corresponding to the plurality of environmental parameters; Filtering respectively the current measurement values ​​and the historical correction values ​​corresponding to the multiple environmental parameters to determine the second correction values ​​corresponding to the multiple environmental parameters; Data drift correction is performed based on the second correction values ​​respectively corresponding to the multiple environmental parameters, and first correction values ​​respectively corresponding to the multiple environmental parameters are determined.

3. The method according to claim 1, characterized in that The method further comprises: A health index representing a sensor that collects the multiple environmental parameters is determined based on differences between the first correction values ​​corresponding to the multiple environmental parameters and the second correction values ​​corresponding to the multiple environmental parameters.

4. The method according to claim 1, wherein The method further comprises: encrypting the first correction value using a predetermined encryption algorithm to obtain an encrypted first correction value; The encrypted first correction value is transmitted to a data processing server, wherein the data processing server is used to parse the encrypted first correction value of the building.

5. The method according to claim 1, wherein The determining the target environmental state of the building from the second candidate environmental state set based on the historical measurement values ​​corresponding to the multiple environmental parameters respectively includes: Based on the historical measurement values ​​corresponding to the multiple environmental parameters, a pre-trained environmental state prediction model is used to obtain the historical environmental state of the building, wherein the environmental state prediction model pre-learns the corresponding relationship between the measurement values ​​of the multiple environmental parameters of the building and the environmental state; Comparing the plurality of candidate environmental states included in the second candidate environmental state set with the historical environmental state respectively, and determining errors corresponding to the plurality of candidate environmental states included in the second candidate environmental state set respectively; The candidate environment state with the smallest error among the multiple candidate environment states included in the second candidate environment state set is used as the target environment state.

6. The method according to claim 1, characterized in that Before selecting the environmental states having probabilities greater than a preset probability threshold among the multiple candidate environmental states as the second candidate environmental state set, the method further includes: Obtaining weather information for the area where the building is located; The probability threshold is determined based on the weather information and the historical measurement values ​​corresponding to the multiple environmental parameters.

7. A building environment status determination system, characterized in that: include: Multi-parameter sensor module, data processing and fusion module, including: The multi-parameter sensor module is used to obtain current measurement values ​​corresponding to multiple environmental parameters of the building, as well as historical measurement values ​​corresponding to the multiple environmental parameters, wherein a measurement error between the historical measurement value and the current measurement value is less than a preset error threshold, and the measurement error indicates a degree of similarity between the environmental state corresponding to the current measurement value and the environmental state corresponding to the historical measurement value; The data processing and fusion module is connected to the multi-parameter sensor module, and is used to perform filtering based on the current measurement values ​​corresponding to the multiple environmental parameters, and determine the first correction values ​​corresponding to the multiple environmental parameters; under the conditions of the first correction values ​​corresponding to the multiple environmental parameters, use data fusion to determine the probabilities corresponding to multiple candidate environmental states; take the environmental states with probabilities greater than a pre-set probability threshold among the multiple candidate environmental states as a second candidate environmental state set, and determine the target environmental state of the building from the second candidate environmental state set based on the historical measurement values ​​corresponding to the multiple environmental parameters.

8. The system according to claim 7, characterized in that The multi-parameter sensor module includes: a temperature sensor unit, a humidity sensor unit, a carbon dioxide sensor unit, a fine particulate matter concentration PM2.5 sensor unit, a volatile organic compound sensor unit, and a light sensor unit, wherein: The temperature sensor unit is used to measure a temperature parameter of the building, wherein the temperature parameter is used to adjust a temperature device that maintains the temperature of the building; The humidity sensor unit is used to measure a humidity parameter in the air, wherein the humidity parameter is used to adjust a humidity device that maintains the humidity of the building; The carbon dioxide sensor unit is used to measure a carbon dioxide concentration parameter in the air, wherein the carbon dioxide concentration parameter is used to adjust ventilation equipment to maintain the air quality of the building; The PM2.5 sensor unit is used to measure the concentration of fine particles in the air. The volatile organic compound sensor unit is used to measure a predetermined type of volatile organic compound gas in the air; The light sensor unit is used to measure the natural light intensity of the building, wherein the natural light intensity is used to adjust indoor lighting equipment to maintain the light intensity of the building.

9. The system according to claim 8, characterized in that The multi-parameter sensor module further includes: a noise sensor unit and a magnetic field sensor unit, wherein: the noise sensor unit is configured to measure noise intensity of the building, wherein the noise intensity is used to adjust a noise reduction device for maintaining a noise level in the building; The magnetic field sensor unit is used to measure the magnetic field strength of the building, wherein the magnetic field strength is used to adjust a magnetic field adjustment device that maintains the magnetic field strength of the building.

10. The system according to claim 7, wherein: The system further comprises: a self-calibration and self-diagnosis module, wherein the self-calibration and self-diagnosis module comprises: an automatic calibration unit, a self-diagnosis unit, wherein: The automatic calibration unit is configured to perform data drift correction based on second correction values ​​corresponding to the plurality of environmental parameters, and determine first correction values ​​corresponding to the plurality of environmental parameters, wherein the second correction values ​​corresponding to the plurality of environmental parameters are historical correction values ​​corresponding to the plurality of environmental parameters obtained by the data processing and fusion module, and are obtained by filtering the current measurement values ​​and the historical correction values ​​corresponding to the plurality of environmental parameters respectively; The self-diagnosis unit is connected to the automatic calibration unit and is configured to determine a health index representing a health condition of the sensor based on a difference between the first correction value and the second correction value.

11. The system according to claim 7, wherein: The system further includes a communication module, which includes a communication protocol support unit, a data encryption unit, and a data transmission unit, wherein: The communication protocol support unit is used to provide a communication protocol between the communication module and the data processing server; The data encryption unit is connected to the communication protocol support unit and is used to encrypt the first correction value using a predetermined encryption algorithm to obtain an encrypted first correction value; The data transmission unit is connected to the data encryption unit, and is used to transmit the encrypted first correction value to a data processing server, wherein the data processing server is used to parse the encrypted first correction value of the building.

12. The system according to claim 7, wherein: The system further comprises: a power management module, the power management module comprising: a clean power generation unit, a battery power supply unit, wherein: The clean power generation unit is used to supply power to the building; The battery power supply unit is used to switch the clean power generation unit to the battery power supply unit when the power generation of the clean power generation unit is less than the minimum power, wherein the minimum power is the minimum power required to maintain normal operation of the building.

13. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the building environment status determination method according to any one of claims 1 to 6.

Images