Indoor environment monitoring method and system combined with big data

Abstract

The application discloses an indoor environment monitoring method and system combined with big data, and relates to the technical field of indoor environment monitoring. The method comprises the following steps: according to a preset demand characteristic definition, extracting a monitoring demand characteristic set of a target scene; based on big data, obtaining excess historical monitoring logs, and analyzing the excess historical monitoring logs to obtain a typical monitoring demand characteristic set and a typical environment monitoring scheme set; taking the typical monitoring demand characteristic set and the typical environment monitoring scheme set as targets, statistically analyzing the excess historical monitoring logs, and establishing a demand-scheme distribution matrix according to the statistical analysis result; traversing the monitoring demand characteristic set, matching corresponding typical environment monitoring schemes in the demand-scheme distribution matrix, and obtaining an environment monitoring scheme sequence corresponding to a monitoring demand characteristic sequence; and based on the environment monitoring scheme sequence, performing indoor environment monitoring of the target scene. The application solves the technical problem of poor indoor environment monitoring effect in the prior art.

Description

Technical Field

[0001] This invention relates to the field of indoor environmental monitoring technology, and specifically to an indoor environmental monitoring method and system that combines big data. Background Technology

[0002] Indoor environmental quality directly impacts human health and work efficiency, making accurate environmental monitoring an essential part of daily life. Current indoor environmental monitoring systems generally employ static monitoring schemes with pre-installed sensor networks and fixed thresholds.

[0003] Existing technologies mainly rely on manual experience to configure monitoring equipment and alarm rules, which has significant drawbacks. Static solutions cannot adapt to dynamic changes in multiple scenarios, making it difficult to generate accurate monitoring strategies. This results in poor indoor environmental monitoring performance and may lead to inaccurate monitoring results or redundant monitoring resources. Summary of the Invention

[0004] This application provides an indoor environmental monitoring method and system that combines big data, which is used to address the technical problem of poor performance of existing indoor environmental monitoring technologies.

[0005] In view of the above problems, this application provides an indoor environmental monitoring method and system that combines big data.

[0006] Firstly, this application provides an indoor environmental monitoring method that incorporates big data, the method comprising:

[0007] Based on the pre-defined requirements, extract the set of monitoring requirements features for the target scenario.

[0008] Based on big data, excess historical monitoring logs are obtained and analyzed to obtain a set of typical monitoring needs characteristics and a set of typical environmental monitoring solutions.

[0009] Using the typical monitoring demand feature set and the typical environmental monitoring scheme set as targets, statistical analysis is performed on the excess historical monitoring logs, and a demand-scheme distribution matrix is ​​established based on the statistical analysis results.

[0010] Traverse the monitoring demand feature set, match the corresponding typical environmental monitoring schemes in the demand-scheme distribution matrix, and obtain the environmental monitoring scheme sequence corresponding to the monitoring demand feature sequence.

[0011] The indoor environmental monitoring operation for the target scenario is executed based on the environmental monitoring scheme sequence.

[0012] Secondly, this application provides an indoor environmental monitoring system that incorporates big data, including:

[0013] The information extraction module is used to extract the monitoring requirement feature set of the target scenario based on the preset requirement feature definition.

[0014] The historical analysis module is used to obtain excess historical monitoring logs based on big data, and to analyze the excess historical monitoring logs to obtain a set of typical monitoring demand features and a set of typical environmental monitoring solutions.

[0015] The statistical analysis module is used to perform statistical analysis on the excess historical monitoring logs using the typical monitoring demand feature set and the typical environmental monitoring scheme set as targets, and to establish a demand-scheme distribution matrix based on the statistical analysis results.

[0016] The scheme matching module is used to traverse the monitoring demand feature set, match the corresponding typical environmental monitoring schemes in the demand-scheme distribution matrix, and obtain the environmental monitoring scheme sequence corresponding to the monitoring demand feature sequence.

[0017] The environmental monitoring module is used to perform indoor environmental monitoring operations for the target scenario based on the environmental monitoring scheme sequence.

[0018] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0019] This application proposes an indoor environmental monitoring method and system that integrates big data. By constructing a demand-scheme distribution matrix, it achieves dynamic matching of monitoring strategies, significantly improving the scenario adaptability and decision-making accuracy of indoor environmental monitoring. Compared with traditional methods, the technical solution provided in this application significantly overcomes the rigidity of static configuration. It utilizes the potential patterns in historical monitoring logs to establish an intelligent mapping relationship between demand characteristics and monitoring schemes, automatically generating a sequence of monitoring schemes tailored to the target scenario without manual intervention, thus achieving the technical effect of precise indoor environmental monitoring.

[0020] This application uses big data to drive indoor environmental monitoring, simultaneously reducing monitoring blind spots and resource redundancy. It is especially suitable for scenarios that need to balance complex environmental parameters and privacy protection, and provides scalable technical support for accurate indoor environmental monitoring in multi-source heterogeneous environments. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating an indoor environmental monitoring method that incorporates big data, as provided in an embodiment of this application.

[0023] Figure 2 This is a schematic diagram of an indoor environmental monitoring system that incorporates big data, provided as an embodiment of this application.

[0024] The components represented by each number in the attached diagram are explained below:

[0025] The system includes an information extraction module (100 modules), a historical analysis module (200 modules), a statistical analysis module (300 modules), a scheme matching module (400 modules), and an environmental monitoring module (500 modules). Detailed Implementation

[0026] This application provides an indoor environmental monitoring method and system that combines big data to address the technical problem of poor performance of existing indoor environmental monitoring technologies.

[0027] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0028] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0029] Example 1, as Figure 1 As shown, this application provides an indoor environmental monitoring method that combines big data, wherein the method includes:

[0030] S10: Extract the monitoring requirement feature set of the target scenario based on the preset requirement feature definition.

[0031] Traditional monitoring solutions rely on manually defined fixed parameters during the initialization phase, making it impossible to dynamically integrate multi-dimensional features. When faced with complex variables including user behavior habits and external weather interference, manual configuration is prone to overlooking key required features or violating privacy constraints, resulting in a mismatch between the monitoring solution and the actual needs of the scenario.

[0032] Step S10 in the method provided in this application embodiment includes:

[0033] By combining preset privacy constraints, the intrinsic features and behavioral feature sequences of the object are obtained.

[0034] Based on indoor environmental reference data, intrinsic indoor features are extracted and obtained.

[0035] Interact with external data sources to obtain outdoor environmental feature sequences.

[0036] The definition of demand characteristics includes a list of invariant demand characteristics and a list of variable demand characteristics.

[0037] In this embodiment, with the informed consent of the subject, subject information is extracted, and the subject's intrinsic characteristics and behavioral characteristic sequences are obtained. The subject's intrinsic information includes basic subject information and the subject's basic requirements for target environment monitoring, such as basic characteristics like age and the required target scene temperature range, such as 24°C to 28°C. The subject's behavioral characteristic sequence includes information such as when the subject requires monitoring results of the target environment each week.

[0038] Based on indoor environmental reference data, intrinsic indoor features are extracted. For example, the indoor area is extracted in square meters, and basic information such as the number of windows is extracted.

[0039] Interact with external data sources, such as weather forecasts, to obtain outdoor environmental feature sequences, such as outdoor temperature and humidity.

[0040] The pre-defined requirements feature definitions include a list of invariant requirements features and a list of variable requirements features. For example, invariant requirements include intrinsic characteristics of the object and intrinsic characteristics of the indoor environment, while variable requirements include sequences of object behavioral characteristics and sequences of outdoor environmental characteristics.

[0041] By pre-defining demand features, this method automatically extracts user intrinsic and behavioral characteristics, indoor intrinsic features, and outdoor environmental feature sequences, constructing a monitoring demand feature set covering privacy security and multi-source data. The method provided in this application overcomes the limitations of human experience, ensuring that the personalized needs and dynamic environmental factors of the target object are captured in a structured manner, providing a complete input foundation for subsequent intelligent matching.

[0042] S20: Obtain excess historical monitoring logs based on big data, and parse the excess historical monitoring logs to obtain a set of typical monitoring demand features and a set of typical environmental monitoring solutions.

[0043] Historical monitoring logs lack intelligent filtering mechanisms, making it difficult to directly use the raw data for decision-making. Existing technologies use fixed rules to filter samples, failing to adaptively extract representative demand characteristics and solution patterns, and thus unable to meet the diverse needs.

[0044] Step S20 in the method provided in this application embodiment includes:

[0045] Based on the geographic location information of the target scenario and the preset call window constraints, the excess historical monitoring logs are extracted.

[0046] Feature engineering is performed on the excess historical monitoring logs to extract a monitoring demand feature sample set and an environmental monitoring scheme sample set.

[0047] Cluster analysis is performed on the monitoring demand feature sample set and the environmental monitoring scheme sample set respectively to obtain the typical monitoring demand feature set and the typical environmental monitoring scheme set.

[0048] Specifically, cluster analysis is performed on the monitoring demand feature sample set and the environmental monitoring scheme sample set to obtain the typical monitoring demand feature set and the typical environmental monitoring scheme set, including:

[0049] By combining the elbow method, the target number M for demand clustering and the target number N for solution clustering are determined, and cluster analysis is performed accordingly to obtain the first cluster analysis result and the second cluster analysis result.

[0050] Select the M points with the highest density from the M clusters in the first cluster analysis results, and output them as the typical monitoring requirement feature set.

[0051] The method of selecting the M points with the highest density from the M clusters in the first cluster analysis results and outputting them as the typical monitoring demand feature set also includes:

[0052] Traverse each cluster and identify multiple density maxima.

[0053] Determine the geometric cluster center of each cluster, and calculate the center distance of the multiple density maxima.

[0054] Using the normalized center distance as an adjustment coefficient, the density values ​​of multiple density maxima are corrected, and the density maximum point is determined based on the density value correction results.

[0055] Select the N points with the highest density from the N clusters in the second cluster analysis results, and output them as the typical environmental monitoring scheme set.

[0056] Where M > N > 1, and M ∈ Z, N ∈ Z.

[0057] In this embodiment, excess historical monitoring logs are extracted based on the geographic location information of the target scene and a preset call window constraint. The geographic information of the target scene can be obtained through GPS positioning of the target scene; different geographic locations affect outdoor environmental conditions, which in turn affect indoor monitoring results. The preset time window is a pre-set time window; for example, setting the preset time window to summer 2024, data extracted from the same period in a more recent time window may be closer to current data. Excess historical monitoring logs are extracted based on the geographic location information of the target scene and the preset call window constraint; these excess historical monitoring logs refer to logs in the historical logs that are outside the monitoring scope.

[0058] Feature engineering is performed on the excess historical monitoring logs. Specifically, monitoring requirement feature samples are extracted, such as the highest temperature being 40℃. These are integrated into a monitoring requirement feature sample set, and environmental monitoring schemes are extracted, such as monitoring three times a day, with all sensors activated on the first day, only temperature monitored on the second day, and all sensors activated on the third day. These are then integrated into an environmental monitoring scheme sample set.

[0059] By combining the elbow method, the target number M for demand clustering and the target number N for solution clustering are determined, and corresponding cluster analysis is performed to obtain the first and second cluster analysis results. The elbow method is a calculation rule that derives the significant inflection point by calculating the average change of the K value under different conditions, which can solve the problem of partially determining the number of nearest clusters. For example, by combining the elbow method and using the K-means algorithm, the sum of squares within each k value of the demand feature sample set is calculated, the elbow curve is plotted, and the number corresponding to the inflection point is selected as the target number M for demand clustering. The same method is used to determine the target number N for solution clustering. Based on the target number M for demand clustering and the target number N for solution clustering, cluster analysis is performed to obtain the first and second cluster analysis results. The first cluster analysis result is the cluster analysis result for monitoring demand, and the second cluster analysis result is the cluster analysis result for monitoring solution.

[0060] Select M clusters from the first cluster analysis results, traverse each cluster, and determine multiple density maxima.

[0061] Determine the geometric cluster center for each cluster, for example, by calculating the mean of the coordinates of each point in the cluster as the geometric cluster center, and then calculating the center distance of multiple density maxima.

[0062] Using the normalized center distance as an adjustment coefficient, the density values ​​of multiple density maxima are corrected, and the density maximum point is determined based on the density value correction result. For example, the corrected density = original density × (1 - normalized center distance).

[0063] Select the N points with the highest density from the N clusters in the second cluster analysis results, and output them as a set of typical environmental monitoring schemes.

[0064] Where M > N > 1, and M ∈ Z, N ∈ Z.

[0065] Based on the elbow method, the target number of clusters is dynamically determined. Feature engineering and cluster analysis are performed on excess historical logs to extract typical monitoring demand feature sets and environmental monitoring scheme sets. On the one hand, this eliminates redundant data interference and retains the most representative feature-scheme patterns; on the other hand, clustering adaptively captures demand differences, laying a statistical foundation for the construction of the distribution matrix.

[0066] S30: Using the typical monitoring demand feature set and the typical environmental monitoring scheme set as targets, perform statistical analysis on the excess historical monitoring logs, and establish a demand-scheme distribution matrix based on the statistical analysis results.

[0067] The correlation between demand characteristics and monitoring schemes implicit in historical data has not been quantitatively modeled, and traditional methods rely solely on human experience to set scheme selection rules. When similar demand characteristics correspond to multiple feasible schemes, human experience-based decision-making cannot objectively determine the optimal scheme.

[0068] Step S30 in the method provided in this application embodiment includes:

[0069] One of the typical monitoring requirement features is randomly selected from the set of features to be the first monitoring requirement feature.

[0070] Using the first monitoring requirement feature as the analysis object, the excess historical monitoring logs are traversed and related logs are filtered to obtain the first historical monitoring log.

[0071] Traverse the first historical monitoring log, use the set of typical environmental monitoring schemes as the matching target to perform matching and marking, and establish the first monitoring scheme distribution based on the matching and marking results.

[0072] Iteratively obtain the distribution of multiple monitoring schemes, and construct the demand-scheme distribution matrix by combining the first monitoring scheme distribution.

[0073] In this matrix, each row of the demand-scheme distribution matrix corresponds to a typical monitoring demand characteristic, and the matrix elements included in each row correspond to the distribution coefficients of each typical environmental monitoring scheme.

[0074] In this embodiment of the application, one of the typical monitoring requirement features is randomly selected as the first monitoring requirement feature from the set of typical monitoring requirement features.

[0075] Taking the first monitoring requirement feature as the analysis object, traverse the excess historical monitoring logs and filter related logs. For example, if the first monitoring requirement feature is that the temperature exceeds 40℃, then filter multiple logs in the excess historical monitoring logs that have a temperature exceeding 40℃ as related logs to obtain the first historical monitoring log.

[0076] The first historical monitoring log is traversed, and matching is performed using the typical environmental monitoring scheme set as the matching target. A first monitoring scheme distribution is then established based on the matching results. The schemes in the first monitoring distribution include multiple monitoring schemes from the first historical monitoring log that match the typical environmental monitoring scheme set. For example, each log entry in the first historical monitoring log is traversed, and the actual execution scheme recorded in the log is extracted. The closest scheme is matched in the typical environmental monitoring scheme set. For instance, schemes with temperatures exceeding 40℃ are matched first, followed by schemes with humidity between 40% and 60%. The number of times the same scheme appears in each condition is counted and used as the distribution coefficient of that scheme. The distribution coefficient = number of times the scheme appears ÷ total number of schemes in the typical environmental monitoring scheme set.

[0077] Iteratively obtain the distribution of multiple monitoring schemes, and combine the first monitoring scheme distribution to construct a demand-scheme distribution matrix.

[0078] In the demand-scheme distribution matrix, each row corresponds to a typical monitoring demand characteristic, and the matrix elements included in each row correspond to the distribution coefficients of each typical environmental monitoring scheme. Each matrix row corresponds to a typical monitoring demand characteristic, and the row elements represent the proportion of environmental monitoring schemes. The distribution matrix is ​​used to represent the proportion of different schemes selected under different monitoring demand characteristics.

[0079] By statistically analyzing the co-occurrence relationship between typical demand characteristics and typical solutions in historical logs, a demand-solution distribution matrix is ​​constructed. This transforms fuzzy correlations into computable probability models, shifting solution decisions from subjective choices to data-driven objective distributions, thereby enhancing the scientific nature and interpretability of strategies.

[0080] S40: Traverse the monitoring demand feature set, match the corresponding typical environmental monitoring schemes in the demand-scheme distribution matrix, and obtain the environmental monitoring scheme sequence corresponding to the monitoring demand feature sequence.

[0081] In this embodiment, the monitoring demand feature set is traversed, and multiple typical environmental monitoring schemes are matched in the demand-scheme distribution matrix and integrated to obtain an environmental monitoring scheme sequence corresponding to the monitoring demand feature sequence. The sequence is sorted from high to low according to the distribution of environmental monitoring schemes.

[0082] S50: Execute indoor environmental monitoring operations for the target scenario based on the environmental monitoring scheme sequence.

[0083] In this embodiment, indoor environmental monitoring operations for the target scenario are performed based on a sequence of environmental monitoring schemes. For example, the environmental monitoring scheme ranked first in the sequence is executed first, with other schemes in the sequence serving as alternatives. If the monitoring effect is unsatisfactory, the next alternative scheme in the sequence is used for monitoring. The monitoring schemes include multi-source data acquisition monitoring schemes that integrate multiple sensors, such as temperature sensors, humidity sensors, and air quality sensors, to collect multi-source data. After acquisition, optionally, the collected data is uploaded to a cloud platform for data analysis to obtain an indoor environmental analysis report, which is then sent to the target location as the monitoring result.

[0084] Example 2, as Figure 2 As shown, based on the same inventive concept as the indoor environmental monitoring method combining big data provided in Embodiment 1, this embodiment of the invention also provides an indoor environmental monitoring system combining big data, including:

[0085] The information extraction module 100 is used to extract the monitoring requirement feature set of the target scene according to the preset requirement feature definition.

[0086] The historical analysis module 200 is used to obtain excess historical monitoring logs based on big data, and to analyze the excess historical monitoring logs to obtain a set of typical monitoring demand features and a set of typical environmental monitoring schemes.

[0087] The statistical analysis module 300 is used to perform statistical analysis on the excess historical monitoring logs using the typical monitoring demand feature set and the typical environmental monitoring scheme set as targets, and to establish a demand-scheme distribution matrix based on the statistical analysis results.

[0088] The scheme matching module 400 is used to traverse the monitoring demand feature set, match the corresponding typical environmental monitoring schemes in the demand-scheme distribution matrix, and obtain the environmental monitoring scheme sequence corresponding to the monitoring demand feature sequence.

[0089] The environmental monitoring module 500 is used to perform indoor environmental monitoring operations for the target scenario based on the environmental monitoring scheme sequence.

[0090] In one embodiment, the information extraction module 100 is further configured to:

[0091] By combining preset privacy constraints, the intrinsic features and behavioral feature sequences of the object are obtained.

[0092] Based on indoor environmental reference data, intrinsic indoor features are extracted and obtained.

[0093] Interact with external data sources to obtain outdoor environmental feature sequences.

[0094] The definition of demand characteristics includes a list of invariant demand characteristics and a list of variable demand characteristics.

[0095] In one embodiment, the history parsing module 200 is further configured to:

[0096] Based on the geographic location information of the target scenario and the preset call window constraints, the excess historical monitoring logs are extracted.

[0097] Feature engineering is performed on the excess historical monitoring logs to extract a monitoring demand feature sample set and an environmental monitoring scheme sample set.

[0098] Cluster analysis is performed on the monitoring demand feature sample set and the environmental monitoring scheme sample set respectively to obtain the typical monitoring demand feature set and the typical environmental monitoring scheme set.

[0099] Specifically, cluster analysis is performed on the monitoring demand feature sample set and the environmental monitoring scheme sample set to obtain the typical monitoring demand feature set and the typical environmental monitoring scheme set, including:

[0100] By combining the elbow method, the target number M for demand clustering and the target number N for solution clustering are determined, and cluster analysis is performed accordingly to obtain the first cluster analysis result and the second cluster analysis result.

[0101] Select the M points with the highest density from the M clusters in the first cluster analysis results, and output them as the typical monitoring requirement feature set.

[0102] The method of selecting the M points with the highest density from the M clusters in the first cluster analysis results and outputting them as the typical monitoring demand feature set also includes:

[0103] Traverse each cluster and identify multiple density maxima.

[0104] Determine the geometric cluster center of each cluster, and calculate the center distance of the multiple density maxima.

[0105] Using the normalized center distance as an adjustment coefficient, the density values ​​of multiple density maxima are corrected, and the density maximum point is determined based on the density value correction results.

[0106] Select the N points with the highest density from the N clusters in the second cluster analysis results, and output them as the typical environmental monitoring scheme set.

[0107] Where M > N > 1, and M ∈ Z, N ∈ Z.

[0108] In one embodiment, the statistical analysis module 300 is further configured to:

[0109] One of the typical monitoring requirement features is randomly selected from the set of features to be the first monitoring requirement feature.

[0110] Using the first monitoring requirement feature as the analysis object, the excess historical monitoring logs are traversed and related logs are filtered to obtain the first historical monitoring log.

[0111] Traverse the first historical monitoring log, use the set of typical environmental monitoring schemes as the matching target to perform matching and marking, and establish the first monitoring scheme distribution based on the matching and marking results.

[0112] Iteratively obtain the distribution of multiple monitoring schemes, and construct the demand-scheme distribution matrix by combining the first monitoring scheme distribution.

[0113] In this matrix, each row of the demand-scheme distribution matrix corresponds to a typical monitoring demand characteristic, and the matrix elements included in each row correspond to the distribution coefficients of each typical environmental monitoring scheme.

[0114] In summary, the embodiments of this application have at least the following technical effects:

[0115] This application proposes an indoor environmental monitoring method and system that integrates big data. By constructing a demand-scheme distribution matrix, it achieves dynamic matching of monitoring strategies, significantly improving the scenario adaptability and decision-making accuracy of indoor environmental monitoring. Compared with traditional methods, the technical solution provided in this application significantly overcomes the rigidity of static configuration. It utilizes the potential patterns in historical monitoring logs to establish an intelligent mapping relationship between demand characteristics and monitoring schemes, automatically generating a sequence of monitoring schemes tailored to the target scenario without manual intervention, thus achieving the technical effect of precise indoor environmental monitoring.

[0116] This application achieves optimal monitoring results through a big data-driven approach. First, it extracts typical demand characteristics and solutions based on cluster analysis, ensuring efficient knowledge extraction from historical data and avoiding the subjective limitations of human experience. Second, it quantifies the correlation strength between characteristics and solutions through a demand-solution distribution matrix, enabling monitoring strategies to adaptively adjust to dynamic factors such as behavioral characteristics and changes in the outdoor environment. Third, by combining privacy constraints and intrinsic feature extraction, it effectively responds to personalized monitoring needs while ensuring data security. Finally, through the automatic generation and execution of solution sequences, it simultaneously reduces monitoring blind spots and resource redundancy, making it particularly suitable for scenarios that require balancing complex environmental parameters and privacy protection, providing scalable technical support for accurate indoor environmental monitoring in multi-source heterogeneous environments.

[0117] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0118] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0119] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A method for indoor environmental monitoring that combines big data, characterized in that, The method comprises the following steps: According to the preset demand feature definition, extract the monitoring demand feature set of the target scene; Based on the geographical location information of the target scene and the preset calling window constraint, extract the excess historical monitoring log; Perform feature engineering processing on the excess historical monitoring log to extract the monitoring demand feature sample set and the environmental monitoring scheme sample set; Respectively perform clustering analysis on the monitoring demand feature sample set and the environmental monitoring scheme sample set to obtain the typical monitoring demand feature set and the typical environmental monitoring scheme set, including: Determine the demand clustering target number M and the scheme clustering target number N by combining the elbow method, and correspondingly perform clustering analysis to obtain the first clustering analysis result and the second clustering analysis result; Select M density maximum points of M cluster clusters in the first clustering analysis result as the typical monitoring demand feature set; Select N density maximum points of N cluster clusters in the second clustering analysis result as the typical environmental monitoring scheme set; Wherein, M>N>1, and M∈Z, N∈Z; Take the typical monitoring demand feature set and the typical environmental monitoring scheme set as the target to perform statistical analysis on the excess historical monitoring log, and establish a demand-scheme distribution matrix according to the statistical analysis result; Traverse the monitoring demand feature set to match the corresponding typical environmental monitoring scheme in the demand-scheme distribution matrix to obtain the environmental monitoring scheme sequence corresponding to the monitoring demand feature sequence; Based on the environmental monitoring scheme sequence, perform indoor environmental monitoring operation on the target scene; Wherein, the demand-scheme distribution matrix is established, including: Randomly select one from the typical monitoring demand feature set as the first monitoring demand feature; Take the first monitoring demand feature as the analysis object, traverse the excess historical monitoring log to filter the associated log, and obtain the first historical monitoring log; Traverse the first historical monitoring log, match and mark the typical environmental monitoring scheme set, and establish the first monitoring scheme distribution according to the matching mark result; Iteratively obtain multiple monitoring scheme distributions, and combine the first monitoring scheme distribution to construct the demand-scheme distribution matrix. 2.The indoor environment monitoring method of claim 1, wherein, According to the preset demand feature definition, extract the monitoring demand feature set of the target scene, including: Combine the preset privacy constraint to obtain the object intrinsic feature and the object behavior feature sequence; Based on the indoor environment reference material, extract the indoor intrinsic feature; Interact with the external data source to obtain the outdoor environment feature sequence; Wherein, the demand feature definition includes the invariant demand feature list and the variable demand feature list. 3.The indoor environment monitoring method of claim 2, wherein, Select M density maximum points of M cluster clusters in the first clustering analysis result as the typical monitoring demand feature set, also including: Traverse each cluster to determine multiple density maximum points; Determine the geometric clustering center of each cluster, and correspondingly calculate the center distance of multiple density maximum points; Take the normalized center distance as the adjustment coefficient to correct the density value of multiple density maximum points, and determine the density maximum point according to the density value correction result. 4.The indoor environment monitoring method of claim 3, wherein, Each matrix row in the demand-scheme distribution matrix corresponds to a typical monitoring demand feature, and the included matrix elements of each matrix row correspond to the distribution coefficients of each typical environmental monitoring scheme.

5. An indoor environment monitoring system incorporating big data, characterized by, A system for implementing the indoor environmental monitoring method of any one of claims 1 to 4, the system comprising: an information extraction module configured to extract a set of monitoring demand features of a target scene according to a preset demand feature definition; a historical analysis module configured to obtain excess historical monitoring logs based on big data, and analyze the excess historical monitoring logs to obtain a set of typical monitoring demand features and a set of typical environmental monitoring schemes; a statistical analysis module configured to perform statistical analysis on the excess historical monitoring logs with the set of typical monitoring demand features and the set of typical environmental monitoring schemes as subjects, and establish a demand-scheme distribution matrix according to the statistical analysis results; a scheme matching module configured to traverse the set of monitoring demand features, match corresponding typical environmental monitoring schemes in the demand-scheme distribution matrix, and obtain a sequence of environmental monitoring schemes corresponding to a sequence of monitoring demand features; an environmental monitoring module configured to perform indoor environmental monitoring operations of the target scene based on the sequence of environmental monitoring schemes.

Images