A multi-sensor fusion greenhouse environment data monitoring method and platform

Abstract

The present application relates to the technical field of greenhouse monitoring, and particularly relates to a multi-sensor fusion greenhouse environment data monitoring method and platform. Soil environment monitoring time sequence information, air environment monitoring time sequence information and crop growth information of a target area are received; initial time soil environment information of the air environment monitoring time sequence information is extracted from environment monitoring historical information; the initial time soil environment information is taken as an initial soil state constraint, the air environment monitoring time sequence information and the crop growth information are taken as soil state influence constraints, a soil state monitoring sample set is collected, and soil environment prediction time sequence information is counted; when the soil environment prediction time sequence information and the soil environment monitoring time sequence information are inconsistent, suspicious identification is performed on the soil environment monitoring time sequence information and the air environment monitoring time sequence information, and the suspicious identification is sent to a user end. Technical effects of improving the stability and reliability of greenhouse environment data monitoring are achieved.

Description

Technical Field

[0001] This invention relates to the field of greenhouse monitoring technology, and in particular to a method and platform for monitoring greenhouse environmental data using multi-sensor fusion. Background Technology

[0002] Traditional greenhouse environmental data monitoring involves taking multiple samples from the same location and averaging them as the final result to avoid errors from a single measurement. However, this method fails to account for potential sensor malfunctions, which can introduce errors regardless of the number of measurements taken. Furthermore, the accuracy of sensor errors is difficult to monitor, resulting in inconsistent stability in greenhouse environmental data monitoring. Summary of the Invention

[0003] This invention addresses the technical problem of difficulty in ensuring the stability of greenhouse environment data detection in existing technologies by providing a multi-sensor fusion method and platform for greenhouse environment data monitoring.

[0004] The technical solution of the present invention to solve the above-mentioned technical problems is as follows:

[0005] In a first aspect, the present invention provides a multi-sensor fusion method for monitoring greenhouse environmental data, comprising: receiving soil environmental monitoring time-series information, air environmental monitoring time-series information, and crop growth information of a target area, wherein the crop growth information characterizes the degree of crop growth within the environmental monitoring time window; extracting soil environmental information at the initial moment of the air environmental monitoring time-series information from historical environmental monitoring information; collecting a soil state monitoring sample set using the initial moment soil environmental information as an initial soil state constraint, and using the air environmental monitoring time-series information and the crop growth information as soil state influence constraints, and statistically analyzing soil environmental prediction time-series information; and when the soil environmental prediction time-series information and the soil environmental monitoring time-series information are inconsistent, marking the soil environmental monitoring time-series information and the air environmental monitoring time-series information as suspicious and sending them to a user terminal.

[0006] Optionally, using the initial soil environmental information as the initial soil state constraint, and the air environment monitoring time series information and the crop growth information as soil state influence constraints, a soil state monitoring sample set is collected, and soil environment prediction time series information is statistically analyzed. This includes: performing spatial clustering on the initial soil environmental information to obtain the initial soil environmental information of the first region up to the initial soil environmental information of the Nth region; partitioning the air environment monitoring time series information based on the first region up to the Nth region to obtain the air environment monitoring time series information of the first region up to the Nth region; performing spatiotemporal clustering on the air environment monitoring time series information of the first region up to the Nth region to obtain the air environment spatiotemporal clustering results of the first region up to the Nth region; and using the initial soil environmental information of the first region as the initial soil state constraint, and the crop growth information and the air environment spatiotemporal clustering results of the first region as soil state influence constraints, a first soil state monitoring sample set is collected, and soil environment prediction time series information of the first region is statistically analyzed.

[0007] Until the initial soil environment information of the Nth region is used as the initial soil state constraint, and the crop growth information and the spatiotemporal clustering results of the air environment of the Nth region are used as the soil state influence constraint, the Nth soil state monitoring sample set is collected, and the soil environment prediction time series information of the Nth region is statistically analyzed; the soil environment prediction time series information of the first region up to the soil environment prediction time series information of the Nth region is added to the soil environment prediction time series information.

[0008] The process of traversing the air environment monitoring time-series information of the first region up to the air environment monitoring time-series information of the Nth region and performing spatiotemporal clustering to obtain the air environment spatiotemporal clustering results of the first region up to the Nth region includes: performing spatial clustering on the air environment monitoring time-series information of the first region to obtain the air environment monitoring time-series information of the first sub-region up to the Mth sub-region; performing temporal clustering on the air environment monitoring time-series information of the first sub-region to obtain the air environment information of the first time zone up to the Yth time zone up to the Mth sub-region; performing temporal clustering on the air environment monitoring time-series information of the Mth sub-region to obtain the air environment information of the first time zone up to the Zth time zone up to the Mth sub-region; and adding the air environment information of the first time zone up to the Yth time zone up to the Mth sub-region up to the Zth time zone up to the air environment information of the Mth sub-region to the spatiotemporal clustering results of the first region.

[0009] Specifically, the process involves using the initial soil environmental information of the first region as the initial soil state constraint, and the crop growth information and the spatiotemporal clustering results of the air environment in the first region as soil state influence constraints. A first soil state monitoring sample set is collected, and the predicted time-series information of the soil environment in the first region is statistically analyzed. This includes: extracting air environment information from the first sub-region's first time zone up to the Y-th time zone of the first sub-region from the spatiotemporal clustering results of the air environment in the first region, up to the Z-th time zone of the M-th sub-region; extracting crop planting duration and crop variety from the crop growth information; and collecting a first sub-soil state monitoring sample set using the initial soil environmental information of the first region as the initial soil state constraint, and the crop planting duration, crop variety, and the air environment information of the first sub-region's first time zone as constraints, and statistically analyzing the final time of the first sub-region's first time zone. Soil environmental prediction information; until the soil environmental prediction information at the end of the Y-1 time zone of the first sub-region is used as the initial soil state constraint, and the crop planting time, the crop variety, and the air environment information of the Y time zone of the first sub-region are used as constraints, the Y-th sub-region soil state monitoring sample set is collected, and the soil environmental prediction information at the end of the Y time zone of the first sub-region is statistically analyzed; the soil environmental prediction information at the end of the first time zone of the first sub-region up to the end of the Y time zone of the first sub-region is added to the soil environmental prediction time series information of the first sub-region; until the soil environmental prediction information at the end of the first time zone of the M-th sub-region up to the end of the Z time zone of the M-th sub-region is obtained, the soil environmental prediction time series information of the M-th sub-region is added to the soil environmental prediction time series information of the M-th sub-region; the soil environmental prediction time series information of the first sub-region up to the soil environmental prediction time series information of the M-th sub-region is added to the soil environmental prediction time series information of the first region.

[0010] Optionally, when the soil environmental prediction time series information and the soil environmental monitoring time series information are inconsistent, the soil environmental monitoring time series information and the air environmental monitoring time series information are marked as suspicious, including: extracting soil environmental prediction time series information for a first region from the soil environmental prediction time series information, wherein the first region soil environmental prediction time series information includes soil environmental prediction time series information for a first sub-region up to the Mth sub-region soil environmental prediction time series information; extracting soil environmental monitoring time series information for a first region from the soil environmental monitoring time series information, wherein the first region soil environmental monitoring time series information includes soil environmental monitoring time series information for a first sub-region up to the Mth sub-region soil environmental monitoring time series information; marking the first sub-region soil environmental prediction time series information and the first region soil environmental monitoring time series information as suspicious, including: extracting soil environmental prediction time series information for a first region from the soil environmental monitoring time series information, wherein the first region soil environmental monitoring time series information includes soil environmental monitoring time series information for a first sub-region up to the Mth sub-region soil environmental monitoring time series information; marking the first sub-region soil environmental prediction time series information and the first region soil environmental monitoring time series information as suspicious, including: extracting soil environmental prediction time series information for a first region from the soil environmental prediction ... region up to the Mth sub-region soil environmental monitoring time series information; marking the first sub-region soil environmental prediction time series information and the first region soil environmental monitoring time series information as suspicious, including: extracting soil environmental prediction time series information for a first region from the soil environmental prediction time series information, wherein the first region soil environmental prediction time series information includes soil environmental monitoring time series information for a first region up to the Mth sub-region soil environmental monitoring time series information; marking the first sub-region soil environmental prediction Similarity analysis is performed on the time-series information of soil environmental monitoring in sub-regions to obtain the soil environmental similarity of the first sub-region; similarity analysis is then performed on the predicted time-series information of soil environment in the Mth sub-region and the soil environmental monitoring time-series information of the Mth sub-region to obtain the soil environmental similarity of the Mth sub-region; a consistency comparison rule is constructed: when the soil environmental similarity is greater than a similarity threshold, it is considered that the soil environment is consistent, otherwise it is considered that it is inconsistent; based on the consistency comparison rule, the soil environmental similarity of the first sub-region is processed up to the soil environmental similarity of the Mth sub-region to obtain inconsistent sub-regions; based on the inconsistent sub-regions, the soil environmental monitoring time-series information and the air environmental monitoring time-series information are marked as suspicious to obtain suspicious marking data for the first region, which is added to the suspicious marking data for the whole region.

[0011] This also includes: calculating the proportion of inconsistent sub-regions to the total number of sub-regions in the first region, and setting this as the inconsistency proportion of the first region; when the inconsistency proportion of the first region is greater than the inconsistency proportion threshold, identifying the soil environmental monitoring time series information and the air environmental monitoring time series information as suspicious based on the inconsistent sub-regions; and when the inconsistency proportion of the first region is less than or equal to the inconsistency proportion threshold, identifying the air environmental monitoring time series information as suspicious.

[0012] The process involves performing similarity analysis on the predicted soil environment time series information and the monitored soil environment time series information of the first sub-region to obtain the soil environment similarity of the first sub-region. This includes: extracting the predicted soil environment value at a first moment from the predicted soil environment time series information of the first sub-region; extracting the monitored soil environment value at a first moment from the monitored soil environment time series information of the first sub-region; calculating the same attribute standard deviation for the predicted soil environment value and the monitored soil environment value at the first moment to obtain several attribute standard deviations; performing dimensionless processing on the several attribute standard deviations to obtain several deviation feature values; and calculating the Euclidean distance using the several deviation feature values ​​as several-dimensional distance parameters, and then taking the reciprocal to obtain the soil environment similarity of the first sub-region.

[0013] Secondly, the present invention provides a multi-sensor fusion greenhouse environment data monitoring platform, comprising:

[0014] The monitoring information acquisition module is used to receive soil environmental monitoring time series information, air environmental monitoring time series information, and crop growth information of the target area, wherein the crop growth information represents the degree of crop growth within the environmental monitoring time window;

[0015] The environmental information extraction module is used to extract the initial soil environmental information from the air environmental monitoring time series information from historical environmental monitoring information;

[0016] The prediction information statistics module is used to collect a soil state monitoring sample set and statistically analyze the soil environment prediction time series information, using the soil environment information at the initial time as the initial soil state constraint, the air environment monitoring time series information and the crop growth information as soil state influence constraints.

[0017] The monitoring information identification module is used to identify the soil environment monitoring time series information and the air environment monitoring time series information as suspicious when they are inconsistent, and then send the information to the user terminal.

[0018] By implementing this invention, it is possible to receive time-series information on soil environmental monitoring, air environmental monitoring, and crop growth in a target area. The crop growth information characterizes the degree of crop growth within the environmental monitoring time window, enabling a comprehensive understanding of the greenhouse environment and providing fundamental data support for subsequent data analysis and prediction. The integration of multi-dimensional data can more comprehensively reflect the environmental conditions for crop growth, avoiding the limitations of single data sources.

[0019] By implementing this invention, it is possible to extract initial soil environmental information from historical environmental monitoring data, providing an initial reference point for soil environmental prediction. This gives the prediction process a clear starting point, improving the accuracy and rationality of the prediction. Extracting the initial state based on historical information leverages accumulated past data to enhance the reliability of the prediction.

[0020] By implementing this invention, it is possible to use the initial soil environmental information as the initial soil state constraint, and the air environment monitoring time series information and crop growth information as soil state influence constraints. A soil state monitoring sample set is collected, and soil environment prediction time series information is statistically analyzed. Through comprehensive consideration of multiple constraints, soil environment prediction becomes more scientific and accurate. Partitioning and clustering processing can adapt to the differences in the environment of different areas within the greenhouse, improving the targeting and detail of the prediction, and providing a reliable predictive basis for subsequent consistency judgments.

[0021] By implementing this invention, when the soil environment prediction time series information and the soil environment monitoring time series information are inconsistent, the soil environment monitoring time series information and the air environment monitoring time series information are marked as suspicious and sent to the user terminal. This can promptly detect potentially abnormal data, prompt the user to check the relevant sensors or monitoring data, and help to troubleshoot sensor hardware malfunctions and other problems as early as possible, thus ensuring the stability and accuracy of greenhouse environment data monitoring.

[0022] In summary, by implementing this invention, the technical effect of improving the stability and reliability of greenhouse environmental data detection can be achieved. Attached Figure Description

[0023] Figure 1 A flowchart illustrating a multi-sensor fusion method for monitoring greenhouse environmental data provided by the present invention;

[0024] Figure 2 This is a schematic diagram of the structure of a greenhouse environment data monitoring platform with multi-sensor fusion provided by the present invention.

[0025] In the attached diagram, the components represented by each number are as follows:

[0026] The monitoring information acquisition module 11, the environmental information extraction module 12, the prediction information statistics module 13, and the monitoring information identification module 14 are all included. Detailed Implementation

[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0029] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0030] Example 1, as Figure 1 As shown, this embodiment of the invention provides a method and platform for monitoring greenhouse environmental data through multi-sensor fusion, including:

[0031] S100: Receive soil environmental monitoring time-series information, air environmental monitoring time-series information, and crop growth information for the target area, wherein the crop growth information characterizes the degree of crop growth within the environmental monitoring time window;

[0032] S200: Extract the initial soil environmental information from the historical environmental monitoring information of the air environmental monitoring time series information;

[0033] S300: Using the initial soil environment information as the initial soil state constraint, and the air environment monitoring time series information and the crop growth information as soil state influence constraints, collect a soil state monitoring sample set and statistically analyze the soil environment prediction time series information.

[0034] S400: When the soil environment prediction time series information and the soil environment monitoring time series information are inconsistent, the soil environment monitoring time series information and the air environment monitoring time series information are marked as suspicious and sent to the user terminal.

[0035] In step S100 of this embodiment, it is necessary to receive soil environmental monitoring time-series information, air environmental monitoring time-series information, and crop growth information of the target area. The purpose is to provide comprehensive and multi-dimensional basic data support for greenhouse environmental data monitoring and analysis. By integrating the dynamic information of soil, air, and crop growth, a complete environment-crop correlation data system is constructed, laying the data foundation for subsequent steps such as soil environmental prediction and anomaly identification.

[0036] The soil environmental monitoring time series information and air environmental monitoring time series information can be obtained through a certain type of intelligent observation instrument.

[0037] Among them, the collection of soil environmental monitoring time series information can be obtained by using soil sensors extended by intelligent observation instruments. These sensors can measure parameters such as soil temperature (°C), volumetric water content (RH), electrical conductivity (μS / cm), and pH value, and record time series data at a set frequency, such as once per hour.

[0038] Air environment monitoring time-series information can be collected by the sensors of the intelligent observation instrument itself, including temperature (°C), humidity (RH), light intensity (Lux), CO2 concentration (ppm), etc., and transmitted to the cloud in real time via 4G or StarNet to form time-series information.

[0039] Crop growth information can be obtained manually, such as recording crop planting time and variety, or using equipment extension modules, such as growth images captured by cameras or chlorophyll content analyzed by spectrometers, to characterize the crop's growth stage and vigor within a specific time window. For example, a set of crop growth information could be: {Monitoring time window: 2025-07-20; Crop variety: tomato; Planting time: 45 days; Plant height: 65.2 cm; Number of leaves: 18; Fruit development stage: flowering}.

[0040] Then, the soil and air environment monitoring time-series information collected by the sensors is transmitted to the cloud platform via 4G Cat.1 or StarFlash communication, while receiving crop growth information manually entered or uploaded by the extended module.

[0041] The cloud platform timestamps and aligns multi-source data to ensure that soil and air data are correlated with crop growth information within the same time window, forming a structured dataset that provides a unified data input format for subsequent steps.

[0042] In step S200 of this embodiment, it is necessary to extract the initial soil environmental information from the historical environmental monitoring information to provide an initial baseline state for soil environmental prediction. By extracting the soil environmental data corresponding to the starting time of the air environmental monitoring time series information, a time starting point anchor point for the prediction model is established. This initial state is the basis for subsequent analysis of soil environmental changes, eliminating the ambiguity of having no baseline reference during the prediction process, and ensuring that soil state prediction based on air environment and crop growth information has a clear starting point, thereby improving the scientific nature and accuracy of the prediction.

[0043] Specifically, the first timestamp of the air environment monitoring data can be used as the benchmark. For example, if the smart observation instrument starts collecting air data at 08:00 on 2025-07-20, then this time point can be defined as the "initial moment".

[0044] Then, historical monitoring data related to the target area of ​​the greenhouse is extracted from the cloud platform, including past soil environmental monitoring time series information and air environmental monitoring time series information. This historical data must include timestamps and cover the monitoring period prior to the initial moment.

[0045] Next, from the historical soil environmental monitoring time series information, the soil environmental monitoring time series information that is exactly the same as or closest to the initial time of the air environment monitoring, such as 2025-07-20 08:00, is selected as the "initial time soil environmental information". For example:

[0046] If air environment monitoring starts from 2025-07-20 08:00, then parameters such as soil temperature, humidity, electrical conductivity, and pH value at that time point are extracted from historical environmental monitoring time series information, such as the soil environmental monitoring time series information for 2025-07-20 08:00 in the dataset example above.

[0047] Step S200 aligns the starting point of air environment monitoring with the initial state of the soil environment through timestamp alignment, providing specific input values ​​for the soil environment prediction constrained by the initial soil state in step S300. For example, if subsequent air environment monitoring shows a sudden increase in light intensity, combined with the initial soil moisture, the trend of humidity change caused by soil moisture evaporation can be predicted more accurately. In other words, the clarity of the initial state directly affects the reliability of this type of prediction.

[0048] In step S300 of this application embodiment, the initial soil environmental information is used as the initial soil state constraint, and the air environment monitoring time series information and the crop growth information are used as soil state influence constraints. A soil state monitoring sample set is collected, and soil environment prediction time series information is statistically analyzed, including:

[0049] Spatial clustering is performed on the initial soil environmental information to obtain the initial soil environmental information of the first region up to the initial soil environmental information of the Nth region.

[0050] Based on the first region up to the Nth region, the air environment monitoring time series information is divided into regions to obtain the air environment monitoring time series information from the first region up to the Nth region;

[0051] The air environment monitoring time series information of the first region is traversed up to the air environment monitoring time series information of the Nth region, and spatiotemporal clustering is performed to obtain the spatiotemporal clustering results of the air environment in the first region up to the spatiotemporal clustering results of the air environment in the Nth region;

[0052] Using the soil environment information of the first region at the initial moment as the initial soil state constraint, and the crop growth information and the spatiotemporal clustering results of the air environment of the first region as the soil state influence constraint, a first soil state monitoring sample set is collected, and the predicted time series information of the soil environment of the first region is statistically analyzed.

[0053] Until the initial soil environment information of the Nth region is used as the initial soil state constraint, and the crop growth information and the spatiotemporal clustering results of the air environment of the Nth region are used as the soil state influence constraint, the Nth soil state monitoring sample set is collected, and the predicted time series information of the Nth region soil environment is statistically analyzed.

[0054] The soil environment prediction time series information from the first region up to the soil environment prediction time series information of the Nth region is added to the soil environment prediction time series information.

[0055] In step S300 of this application embodiment, the soil environmental information at the initial time is subjected to spatial clustering. The purpose is to refine the target area of ​​the greenhouse into several sub-regions through spatial division and data matching, so that the soil environmental prediction is upgraded from overall fuzzy estimation to precise analysis of zones.

[0056] Specifically, the initial soil environmental information first needs to be spatially clustered to obtain the initial soil environmental information of the first region up to the initial soil environmental information of the Nth region. Spatial clustering can be based on the spatial distribution characteristics of soil moisture, electrical conductivity, etc., of the initial soil environmental information, and clustering algorithms such as K-means can be used to divide the target area of ​​the greenhouse into N highly homogeneous sub-regions.

[0057] Specifically, soil environmental parameters, such as soil temperature and air humidity, are collected from multiple monitoring points inside the greenhouse. Each point includes spatial coordinates, such as x=1m and y=2m, and specific parameter values, such as soil temperature 22℃.

[0058] Suppose there are 5 monitoring points inside the greenhouse, with the following coordinates and soil temperatures: A(1,1), 22℃; B(1,3), 23℃; C(3,1), 18℃; D(3,3), 19℃; E(2,2), 21℃. These features are combined into an eigenvector for calculating Euclidean distance. For example, A(1,1), 22℃ is combined into [1,1,22].

[0059] Then, the Euclidean distance is used to calculate the comprehensive difference between the two points. The calculation formula is, for example, Dij = √[(Xi-Xj)² + (Yi-Yj)² + (Pi-Pj)²]. Where X and Y are spatial coordinates, P is an environmental parameter value, such as temperature, and i and j represent the two sets of feature vectors to be calculated.

[0060] The Euclidean distance between A and B is calculated to be 2.24 using the above formula, the Euclidean distance between A and C is 4.47, and so on. Then, the K-means clustering algorithm is used to divide the greenhouse target area into N highly homogeneous sub-regions based on the Euclidean distances of the feature vectors between the sub-regions. The K-means clustering algorithm is existing technology and will not be elaborated upon here.

[0061] For example, if the soil moisture inside the greenhouse exhibits a spatial distribution that is higher on the east side and lower on the west side, clustering can create "Region 1 (East)" and "Region 2 (West)," etc. Each region corresponds to a set of initial soil state data, i.e., "Initial soil environmental information of Region 1" up to "Initial soil environmental information of Region N." For example, the initial soil environmental information of Region 1 could be that the initial soil moisture on the east side of the greenhouse is 65%, and the initial temperature is 22℃, etc. Spatial distribution data can be obtained by installing the aforementioned intelligent observation instruments at different locations within the greenhouse, providing raw samples for spatial clustering.

[0062] Furthermore, it is necessary to partition the air environment monitoring time series information based on the first region up to the Nth region to obtain the air environment monitoring time series information from the first region up to the Nth region.

[0063] Specifically, the overall air environment monitoring time series information needs to be divided into N regions as spatial boundaries, so that each region corresponds only to the air environment data within its own area. For example, the air environment monitoring time series information for the first region (east side) only includes data such as temperature, humidity, and light intensity monitored by sensors within that region. This forms air environment data that corresponds one-to-one with the soil zoning, i.e., "air environment monitoring time series information for the first region" up to "air environment monitoring time series information for the Nth region".

[0064] In step S300 of this application embodiment, traversing the air environment monitoring time series information of the first region up to the air environment monitoring time series information of the Nth region and performing spatiotemporal clustering to obtain the air environment spatiotemporal clustering results of the first region up to the Nth region includes:

[0065] The air environment monitoring time series information of the first region is spatially clustered to obtain the air environment monitoring time series information of the first sub-region up to the Mth sub-region.

[0066] Perform time-domain clustering on the air environment monitoring time series information of the first sub-region to obtain the air environment information of the first time zone of the first sub-region up to the air environment information of the Yth time zone of the first sub-region;

[0067] The process continues until time-domain clustering is performed on the air environment monitoring time series information of the Mth sub-region to obtain the air environment information of the first time zone of the Mth sub-region up to the air environment information of the Zth time zone of the Mth sub-region.

[0068] The air environment information of the first sub-region in the first time zone up to the air environment information of the first sub-region in the Y time zone, up to the air environment information of the first time zone in the M sub-region up to the air environment information of the Z time zone in the M sub-region, are added to the spatiotemporal clustering result of the air environment of the first region.

[0069] In this embodiment, the above steps are the core of "spatiotemporal clustering." The core purpose is to break down the air environment monitoring time series information of each region into smaller-scale spatiotemporal units through spatial subdivision and temporal segmentation, thereby achieving a "refined characterization" of air environment changes. Specifically, the spatial region is further divided into sub-regions, and then the time is divided into time zones, transforming the air environment data from a "regional-level time series stream" into gridded data blocks of "sub-region-time zone." This provides more detailed constraints for subsequent accurate prediction of soil environment changes, avoiding prediction biases caused by coarse spatiotemporal scales.

[0070] First, spatial clustering needs to be performed on the air environment monitoring time series information of the first region to obtain the air environment monitoring time series information of the first sub-region up to the Mth sub-region.

[0071] Within the first defined region, secondary spatial clustering is performed based on spatial differences in air environment parameters such as temperature, humidity, and light intensity. For example, a density clustering algorithm can be used to subdivide the first region into M more homogeneous sub-regions. For instance, if there is a difference in humidity near the vent and in the corners within the first region, it can be divided into a "first sub-region" (the area near the vent) and a "second sub-region" (the corner), and so on.

[0072] Using the above method, air environment monitoring time-series information from the first sub-region to the Mth sub-region is obtained. Each sub-region corresponds to the time-varying data of air parameters within its range, such as hourly temperature and humidity records for the first sub-region. This process continues until the Yth time zone of the first sub-region is obtained.

[0073] Next, time-domain clustering needs to be performed on the air environment monitoring time series information of the first sub-region to obtain the air environment information of the first time zone up to the Yth time zone of the first sub-region. For the air environment monitoring time series information of each sub-region, time-domain clustering is performed according to the parameter change characteristics in the time dimension, such as the temperature fluctuation pattern between day and night, and the diurnal difference in light intensity. Sliding window clustering can be used to divide the continuous time into Z time zones. The specific time-domain clustering method is the same as the aforementioned spatial clustering method. Alternatively, the air environment monitoring time series information features of multiple sub-regions can be vectorized, and then the Euclidean distance can be calculated. K-means time-domain clustering can then be performed based on the Euclidean distance. This will not be elaborated here.

[0074] For example, the first sub-region can be divided into two time zones based on "daytime (8:00-18:00)" and "nighttime (18:00-8:00 the next day)," or divided into multiple time zones based on parameter stability every 6 hours.

[0075] Through the above steps, the air environment monitoring time series information for each sub-region is broken down into air environment information for multiple time zones, such as the air environment information data for the first time zone (8:00-14:00) and the second time zone (14:00-20:00) of the first sub-region. Ultimately, air environment information for the first time zone of the Mth sub-region up to the Zth time zone of the Mth sub-region is obtained.

[0076] Finally, the air environment information of the first sub-region in the first time zone up to the air environment information of the first sub-region in the Y time zone, up to the air environment information of the first sub-region in the M time zone up to the air environment information of the Z time zone in the M time zone, needs to be added to the spatiotemporal clustering result of the air environment of the first region.

[0077] That is, the air environment information of all time zones from the first sub-region to the Mth sub-region is integrated to form the spatiotemporal clustering result of the air environment in the first region. For example, the spatiotemporal clustering result of the first region includes air environment information data blocks of "first sub-region - first time zone", "first sub-region - second time zone"... "Mth sub-region - Zth time zone".

[0078] By analogy, the same processing is performed on regions 2 through 3 to obtain the spatiotemporal clustering results of the air environment for all regions.

[0079] In step S300 of this application embodiment, the soil environmental information of the first region at the initial time is used as the initial soil state constraint, and the crop growth information and the spatiotemporal clustering results of the air environment in the first region are used as the soil state influence constraint. A first soil state monitoring sample set is collected, and the predicted time series information of the soil environment in the first region is statistically analyzed, including:

[0080] From the spatiotemporal clustering results of the air environment in the first region, extract the air environment information of the first time zone of the first sub-region up to the air environment information of the Y time zone of the first sub-region, until extract the air environment information of the first time zone of the M sub-region up to the air environment information of the Z time zone of the M sub-region;

[0081] From the crop growth information, the crop planting duration and crop variety are extracted;

[0082] Using the initial soil environment information of the first region as the initial soil state constraint, and the crop planting time, crop variety and air environment information of the first time zone of the first sub-region as constraints, a first sub-soil state monitoring sample set is collected, and soil environment prediction information of the first sub-region at the end of the first time zone is statistically analyzed.

[0083] Until the soil environment prediction information at the end of the Y-1 time zone of the first sub-region is used as the initial soil state constraint, and the crop planting time, the crop variety and the air environment information of the Y time zone of the first sub-region are used as constraints, the Y-th sub-soil state monitoring sample set is collected, and the soil environment prediction information at the end of the Y time zone of the first sub-region is statistically analyzed.

[0084] Add the soil environment prediction information of the first sub-region up to the soil environment prediction information of the first sub-region up to the end time of the Yth time zone of the first sub-region into the soil environment prediction time series information of the first sub-region.

[0085] Until the soil environment prediction information of the first time zone end time of the Mth sub-region is obtained, until the soil environment prediction information of the Zth time zone end time of the Mth sub-region is obtained, add it to the soil environment prediction time series information of the Mth sub-region.

[0086] The soil environment prediction time series information of the first sub-region up to the soil environment prediction time series information of the Mth sub-region is added to the soil environment prediction time series information of the first region.

[0087] In this embodiment, the purpose of statistically analyzing soil environmental prediction time-series information is to predict soil environmental changes in each sub-region in stages based on refined spatiotemporal constraints, and ultimately integrate them to form regional-level soil environmental prediction time-series information. By combining initial soil conditions, crop varieties, crop planting duration, and subdivided spatiotemporal characteristics of the air environment, dynamic prediction from the "initial state" to the "end state of each time zone" is achieved, ensuring that the prediction results accurately reflect the differences in soil environment in different sub-regions and at different times, providing a high-precision reference benchmark for comparison with actual monitoring data in subsequent step S400.

[0088] First, it is necessary to extract the air environment information of the first sub-region's first time zone up to the Yth time zone from the spatiotemporal clustering results of the first region's air environment, and so on, up to the Mth sub-region's first time zone up to the Zth time zone. The air environment information includes temperature, humidity, light intensity, CO2 concentration, etc. For example, the air environment information data for the first sub-region's first time zone (8:00-14:00) is "temperature 28-32℃, humidity 60%~65%, light intensity 60000-80000Lux".

[0089] Then, it is necessary to extract the crop planting duration and crop variety from the crop growth information, for example, if the crop variety is tomato and the planting duration is 45 days. These parameters directly affect the soil's nutrient consumption and water requirements.

[0090] Then, the initial soil environmental information of the first region at the initial moment needs to be used as the initial soil state constraint. For example, the initial soil environmental information at that moment is: soil temperature 22.5℃, humidity 65.2%. The crop planting duration, crop variety, and air environmental information of the first sub-region at the first time zone are used as constraints to collect a first sub-soil state monitoring sample set, and statistically predict the soil environment at the end of the first time zone of the first sub-region. The first sub-soil state monitoring sample set is the soil change data under similar conditions in the same historical period, used to predict the soil environment at the end of the first time zone of the first sub-region, such as the predicted soil humidity value at 14:00.

[0091] Next, rolling time series forecasting is required. For subsequent time zones of the same sub-region, the forecast result of the previous time zone endpoint is used as the new initial constraint. Combined with the air environment information and crop characteristics of the corresponding time zone, the forecast continues.

[0092] For example, the initial constraint for the second time zone (14:00-20:00) of the first sub-region is the predicted soil value at the end of the first time zone. Combined with the air environment information data for that period, such as temperature 30-26℃, humidity 50-65%, and light intensity 10000-50000Lux, the soil environment at 20:00 is predicted. This means that the soil environment prediction information at the end of the Y-1 time zone of the first sub-region is used as the initial soil state constraint, and the crop planting time, crop variety, and air environment information of the Y time zone of the first sub-region are used as constraints. The Y-th sub-region soil state monitoring sample set is collected, and the soil environment prediction information at the end of the Y time zone of the first sub-region is statistically analyzed.

[0093] Repeat the above steps to complete the soil environment prediction for all sub-regions from the first to the Mth time zone in the first region, until the soil environment prediction information for the end time of the first time zone of the Mth sub-region is obtained, up to the end time of the Zth time zone of the Mth sub-region, and add it to the soil environment prediction time series information of the Mth sub-region.

[0094] Finally, the soil environmental prediction information for each time zone's endpoint in each sub-region is arranged chronologically to form a sub-region-level soil environmental prediction time series, such as the 6-hour soil moisture prediction time series for the first sub-region from 8:00 to 8:00 the next day. The soil environmental prediction time series of all sub-regions are then integrated to form the soil environmental prediction time series information for the first region, fully reflecting the dynamic changes of the soil environment within that region over time.

[0095] In step S400 of this application embodiment, when the soil environment prediction time series information and the soil environment monitoring time series information are inconsistent, the soil environment monitoring time series information and the air environment monitoring time series information are marked as suspicious, including:

[0096] From the soil environment prediction time series information, extract the soil environment prediction time series information of the first region, wherein the soil environment prediction time series information of the first region includes the soil environment prediction time series information of the first sub-region up to the soil environment prediction time series information of the Mth sub-region.

[0097] From the soil environmental monitoring time series information, extract the soil environmental monitoring time series information of the first region, wherein the soil environmental monitoring time series information of the first region includes the soil environmental monitoring time series information of the first sub-region up to the soil environmental monitoring time series information of the Mth sub-region;

[0098] A similarity analysis was performed on the soil environment prediction time series information and the soil environment monitoring time series information of the first sub-region to obtain the soil environment similarity of the first sub-region.

[0099] The similarity of the soil environment in the Mth sub-region is obtained by performing a similarity analysis on the predicted time series information of the soil environment in the Mth sub-region and the monitored time series information of the soil environment in the Mth sub-region.

[0100] Establish consistency comparison rules: when the soil environment similarity is greater than the similarity threshold, the soil environment is considered consistent; otherwise, it is considered inconsistent.

[0101] Based on the consistency comparison rule, the soil environment similarity of the first sub-region is processed up to the soil environment similarity of the Mth sub-region to obtain inconsistent sub-regions;

[0102] Based on the inconsistent sub-regions, suspicious identification is performed on the soil environmental monitoring time series information and the air environmental monitoring time series information to obtain suspicious identification data for the first region, which is then added to the suspicious identification data for the entire region.

[0103] In this embodiment, extracting the predicted soil environmental time-series information and the monitored soil environmental time-series information of the first region is the basic data processing step for suspicious identification. The core purpose is to split and accurately match the predicted and monitored soil environmental monitoring data according to the "region-sub-region" hierarchy, providing a structured comparison unit for subsequent judgment on whether the two are consistent. By focusing on the time-series data of each sub-region within the first region, it is ensured that anomaly identification can be located at the smallest spatial unit, avoiding the obscuring of differences in local sub-regions due to overall region comparison, thereby improving the accuracy of anomaly detection.

[0104] Specifically, the first step is to extract the soil environmental monitoring time series information for the first region from the aforementioned soil environmental monitoring time series information. That is, from the global soil environmental prediction time series information generated in step S300, the prediction time series belonging to the first region is selected, such as the prediction data sequence for the eastern area of ​​a greenhouse. Then, it is further divided into sub-regions, and the prediction time series information for all sub-regions within the first region is extracted. For example, the first sub-region is "near the ventilation opening," and the second sub-region is "corner," obtaining the time series information for these sub-regions. This sub-region prediction time series information contains the predicted values ​​of soil parameters at the end of each time zone, such as humidity, temperature, and electrical conductivity, and corresponds one-to-one with the sub-regions divided in step S300.

[0105] For example, data such as "The predicted soil moisture value at the end of the time zone from 8:00 to 14:00 in the first sub-region is 63%" and "The predicted soil moisture value at the end of the time zone from 14:00 to 20:00 in the first sub-region is 61%" can be extracted from the soil environmental prediction time series of the first region. The same method can be used to extract soil environmental prediction time series information from the first sub-region up to the Mth sub-region.

[0106] Next, it is necessary to extract the soil environmental monitoring time-series information for the first region from the aforementioned soil environmental monitoring time-series information. That is, the soil environmental monitoring time-series information for the first region is selected from the soil environmental monitoring time-series information actually monitored by the aforementioned intelligent observation instrument.

[0107] Soil environmental monitoring time series information is split into sub-regions, and the measured soil environmental monitoring time series information of each sub-region is extracted. The data comes from the soil sensors in the smart observation instruments deployed in the sub-region, such as the measured values ​​of humidity, temperature and other parameters uploaded by the sensors in the first sub-region every 6 hours.

[0108] For example, data such as "the measured soil moisture value at the end of the time zone from 8:00 to 14:00 in the first sub-region is 58%" and "the measured soil moisture value at the end of the time zone from 14:00 to 20:00 in the first sub-region is 56%" can be extracted from the soil environmental monitoring time series information of the first sub-region. The same method can be used to extract soil environmental monitoring time series information from the first sub-region up to the Mth sub-region.

[0109] In step S400 of this application embodiment, a similarity analysis is performed on the soil environment prediction time series information and the soil environment monitoring time series information of the first sub-region to obtain the soil environment similarity of the first sub-region, including:

[0110] Extract the predicted soil environment value at the first moment from the predicted time series information of the soil environment in the first sub-region;

[0111] Extract the soil environmental monitoring value at the first moment from the soil environmental monitoring time series information of the first sub-region;

[0112] The standard deviations of the same attribute are calculated for the predicted soil environmental value and the monitored soil environmental value at the first time point to obtain the standard deviations of several attributes.

[0113] The standard deviations of the aforementioned attributes are traversed and dimensionless to obtain several deviation characteristic values.

[0114] Using the aforementioned deviation feature values ​​as several dimensional distance parameters, the Euclidean distance is calculated, and then the reciprocal is taken to obtain the soil environment similarity of the first sub-region.

[0115] In this embodiment of the application, the purpose of the above steps is to quantitatively evaluate the degree of matching between the predicted and measured values ​​of the soil environment in the same sub-region, and to provide an objective basis for judging whether the two are consistent by calculating the soil environment similarity.

[0116] Specifically, the first step is to extract the predicted soil environment value and the monitored soil environment value at the first moment from the predicted time series information of the soil environment in the first sub-region.

[0117] For the predicted soil environment value at the first moment, a specific moment can be selected from the predicted soil environment time series information of the first sub-region, such as the predicted soil environment value at 14:00 in the previous example, which covers all the monitoring parameters of the sub-region at that moment, such as soil temperature 24.1℃, humidity 63.8%, electrical conductivity 118.7μS / cm, and pH value 6.7.

[0118] For the soil environmental monitoring values ​​at the first moment, the measured values ​​at the same moment can be extracted from the real-time monitoring of the soil environmental time series information of the first sub-region, such as soil temperature 23.5℃, humidity 59.2%, electrical conductivity 125.3μS / cm, and pH value 6.8, to ensure that the parameter types completely correspond to the predicted soil environmental values.

[0119] Then, it is necessary to calculate the standard deviation of the soil environment prediction value and the soil environment monitoring value at the first time point, and obtain the standard deviation of several attributes.

[0120] The standard deviation of the predicted and measured values ​​for each attribute, such as temperature and humidity, is calculated to reflect the dispersion of the single-dimensional parameter. For example, the standard deviation between the predicted temperature of 24.1℃ and the measured value of 23.5℃ is 0.6℃; the standard deviation between the predicted humidity of 63.8% and the measured value of 59.2% is 4.6%, and so on, to obtain the standard deviations of all attributes, thus obtaining the standard deviations of several attributes.

[0121] Then, the standard deviations of the various attributes are iterated and dimensionless to obtain several deviation characteristic values. Since different attributes have different units and magnitudes (e.g., temperature is in °C, humidity is in %), directly comparing standard deviations will result in bias. Standardization is needed to convert them into dimensionless deviation characteristic values. For example, dividing the standard deviation by the reasonable range of values ​​for the attribute yields the following values: temperature deviation characteristic value = 0.6 / (120-(-40)) = 0.00375, humidity deviation characteristic value = 4.6 / (100-0) = 0.046, allowing direct comparison of differences across dimensions. The reasonable range of values ​​can be determined by the sensor's maximum range or by the range of values ​​observed during actual measurement. The values ​​used here are merely examples and not representative.

[0122] Then, using the aforementioned deviation feature values ​​as distance parameters for several dimensions, the Euclidean distance is calculated, and its reciprocal is taken to obtain the soil environmental similarity of the first sub-region. That is, the dimensionless deviation feature values ​​are used as coordinates in a multi-dimensional space, such as temperature, humidity, conductivity, and pH value corresponding to four dimensions. The Euclidean distance between the predicted and measured values ​​in this space is calculated to comprehensively reflect the overall difference across multiple dimensions. The larger the Euclidean distance, the more significant the overall difference. For example, if the deviation feature values ​​of the four attributes in the above example are 0.00375, 0.046, 0.032, and 0.01 respectively, then the Euclidean distance is √(0.00375²+0.046²+0.032²+0.01²)≈0.057.

[0123] Then, the reciprocal of the Euclidean distance is taken, such as 1 / 0.057 ≈ 17.5, to obtain the soil environment similarity of the first sub-region. The smaller the Euclidean distance and the larger the reciprocal, the higher the soil environment similarity of the first sub-region, which intuitively reflects the degree of matching between the predicted and measured values.

[0124] Furthermore, based on the above method, a similarity analysis needs to be performed on the predicted time series information of the soil environment in the Mth sub-region and the monitored time series information of the soil environment in the Mth sub-region to obtain the soil environment similarity of the Mth sub-region.

[0125] Then, a consistency comparison rule is constructed: when the soil environment similarity is greater than the similarity threshold, it is considered that the soil environment is consistent; otherwise, it is considered that it is inconsistent.

[0126] Specifically, a uniform soil environment similarity threshold can be set, such as 0.8. The similarity threshold can be adjusted according to the type of greenhouse crop and the accuracy requirements of the sensors. The consistency comparison rule is clearly defined as follows: when the soil environment similarity of a sub-region is greater than the threshold, the predicted and monitored data of that sub-region are determined to be "consistent," that is, the data is reliable; when the similarity is less than or equal to the threshold, it is determined to be "inconsistent," that is, the data may be abnormal.

[0127] The similarity threshold setting also needs to be combined with the characteristics of the monitoring equipment to ensure that the rules can both identify real anomalies, such as deviations caused by sensor hardware failures, and tolerate reasonable measurement errors, such as minor deviations caused by environmental fluctuations.

[0128] Furthermore, based on the consistency comparison rules, it is necessary to process the soil environment similarity of the first sub-region up to the soil environment similarity of the Mth sub-region to obtain inconsistent sub-regions.

[0129] Specifically, the soil environment similarity of the first to the Mth sub-regions can be compared with the threshold. For example: the soil environment similarity of the first sub-region is 0.85 > 0.8 (consistent), the soil environment similarity of the second sub-region is 0.72 < 0.8 (inconsistent), the soil environment similarity of the third sub-region is 0.83 > 0.8 (consistent) ... the soil environment similarity of the Mth sub-region is 0.79 < 0.8 (inconsistent).

[0130] Summarize all "inconsistent" sub-regions, such as the second sub-region and the Mth sub-region, to form a list of abnormal sub-regions within the first region, clearly marking their spatial location, such as "corner sub-region" or "sub-region near the west fence".

[0131] In step S400 of the embodiment of this application, the following is also included:

[0132] The percentage of inconsistent sub-regions in the first region is defined as the proportion of inconsistent sub-regions in the first region.

[0133] When the proportion of inconsistency in the first region is greater than the inconsistency proportion threshold, the soil environmental monitoring time series information and the air environmental monitoring time series information are marked as suspicious based on the inconsistent sub-regions;

[0134] When the proportion of non-consistency in the first region is less than or equal to the non-consistency proportion threshold, the air environment monitoring time series information is marked as suspicious.

[0135] In this embodiment, the purpose of the above steps is to differentiate the possible sources of data anomalies based on the distribution ratio of abnormal areas, thereby selectively marking suspicious data. By statistically analyzing the proportion of inconsistent sub-regions within a region (i.e., the aforementioned non-consistency ratio) and comparing it with a preset non-consistency ratio threshold, local anomalies and systemic anomalies are distinguished. When the non-consistency ratio is too high, it may indicate problems with both soil and air environmental monitoring data; when the non-consistency ratio is too low, it is more likely due to errors in the air environmental monitoring data used as a predictive constraint, thus improving the accuracy of suspicious data identification and reducing invalid investigations.

[0136] First, we need to calculate the percentage of inconsistent sub-regions in the first region relative to the total number of sub-regions, and call this the inconsistency percentage of the first region. That is, we calculate the number of inconsistent sub-regions in the first region. For example, if there are two sub-regions (e.g., the second and fifth sub-regions), then we calculate the ratio of the number of inconsistent sub-regions to the total number of sub-regions in that region. If the total number of sub-regions in that region is M=5, then the inconsistency percentage = 2 / 5 = 40%.

[0137] Next, it is necessary to preset the non-consistency percentage threshold, which can be set according to the stability requirements of the greenhouse environment, such as 30%, as the boundary for judging local anomalies and systemic anomalies.

[0138] Then compare the non-consistency rate of the first region with the non-consistency rate threshold: if the non-consistency rate of the first region is 40%, 40% > 30%, it is judged as "high risk of systemic anomaly"; if the non-consistency rate of the first region is 20%, 20% < 30%, it is judged as "high risk of local anomaly".

[0139] When the proportion of inconsistencies exceeds the threshold, it can be considered that both soil and air environmental monitoring data may be abnormal. Based on the inconsistent sub-regions, the soil environmental monitoring time series information and air environmental monitoring time series information of these sub-regions are marked as suspicious, such as marking "data abnormal - sensor needs to be checked" on the cloud platform.

[0140] When the proportion of inconsistencies is less than or equal to the threshold, the anomaly is more likely to originate from air environment monitoring data. Only the air environment monitoring time series information of the first region is marked as suspicious, such as "air data may be distorted - affecting soil prediction", to reduce unnecessary investigation of soil monitoring data.

[0141] Using the above method, suspicious identification is performed on the soil environmental monitoring time series information and the air environmental monitoring time series information to obtain suspicious identification data for the first region, which is then added to the suspicious identification data for the entire region.

[0142] Finally, the suspicious identification results are pushed to the user terminal through the cloud platform, clearly indicating the abnormal area and the type of parameter to be checked, thus completing the greenhouse environment data monitoring through multi-sensor fusion.

[0143] Example 2, as Figure 2 As shown, based on the same inventive concept as the multi-sensor fusion greenhouse environment data monitoring method provided in Embodiment 1, this embodiment of the invention also provides a multi-sensor fusion greenhouse environment data monitoring platform, including:

[0144] The monitoring information acquisition module 11 is used to receive soil environmental monitoring time series information, air environmental monitoring time series information and crop growth information of the target area, wherein the crop growth information represents the degree of crop growth within the environmental monitoring time window;

[0145] The environmental information extraction module 12 is used to extract the initial soil environmental information of the air environmental monitoring time series information from the historical environmental monitoring information;

[0146] Prediction information statistics module 13 is used to collect a soil state monitoring sample set and statistically analyze soil environment prediction time series information, using the initial soil environment information as the initial soil state constraint, the air environment monitoring time series information and the crop growth information as soil state influence constraints.

[0147] The monitoring information identification module 14 is used to identify the soil environment monitoring time series information and the air environment monitoring time series information as suspicious when the soil environment prediction time series information and the soil environment monitoring time series information are inconsistent, and send them to the user terminal.

[0148] Furthermore, the predictive information statistics module 13 includes the following execution steps:

[0149] Spatial clustering is performed on the initial soil environmental information to obtain the initial soil environmental information of the first region up to the initial soil environmental information of the Nth region.

[0150] Based on the first region up to the Nth region, the air environment monitoring time series information is divided into regions to obtain the air environment monitoring time series information from the first region up to the Nth region;

[0151] The air environment monitoring time series information of the first region is traversed up to the air environment monitoring time series information of the Nth region, and spatiotemporal clustering is performed to obtain the spatiotemporal clustering results of the air environment in the first region up to the spatiotemporal clustering results of the air environment in the Nth region;

[0152] Using the soil environment information of the first region at the initial moment as the initial soil state constraint, and the crop growth information and the spatiotemporal clustering results of the air environment of the first region as the soil state influence constraint, a first soil state monitoring sample set is collected, and the predicted time series information of the soil environment of the first region is statistically analyzed.

[0153] Until the initial soil environment information of the Nth region is used as the initial soil state constraint, and the crop growth information and the spatiotemporal clustering results of the air environment of the Nth region are used as the soil state influence constraint, the Nth soil state monitoring sample set is collected, and the predicted time series information of the Nth region soil environment is statistically analyzed.

[0154] The soil environment prediction time series information from the first region up to the soil environment prediction time series information of the Nth region is added to the soil environment prediction time series information.

[0155] Specifically, the process involves traversing the air environment monitoring time-series information of the first region up to the air environment monitoring time-series information of the Nth region, performing spatiotemporal clustering, and obtaining the spatiotemporal clustering results of the air environment in the first region up to the Nth region, including:

[0156] The air environment monitoring time series information of the first region is spatially clustered to obtain the air environment monitoring time series information of the first sub-region up to the Mth sub-region.

[0157] Perform time-domain clustering on the air environment monitoring time series information of the first sub-region to obtain the air environment information of the first time zone of the first sub-region up to the air environment information of the Yth time zone of the first sub-region;

[0158] The process continues until time-domain clustering is performed on the air environment monitoring time series information of the Mth sub-region to obtain the air environment information of the first time zone of the Mth sub-region up to the air environment information of the Zth time zone of the Mth sub-region.

[0159] The air environment information of the first sub-region in the first time zone up to the air environment information of the first sub-region in the Y time zone, up to the air environment information of the first time zone in the M sub-region up to the air environment information of the Z time zone in the M sub-region, are added to the spatiotemporal clustering result of the air environment of the first region.

[0160] Specifically, the soil environmental information of the first region at the initial moment is used as the initial soil state constraint, and the crop growth information and the spatiotemporal clustering results of the air environment in the first region are used as the soil state influence constraint. A first soil state monitoring sample set is collected, and the predicted time series information of the soil environment in the first region is statistically analyzed, including:

[0161] From the spatiotemporal clustering results of the air environment in the first region, extract the air environment information of the first time zone of the first sub-region up to the air environment information of the Y time zone of the first sub-region, until extract the air environment information of the first time zone of the M sub-region up to the air environment information of the Z time zone of the M sub-region;

[0162] From the crop growth information, the crop planting duration and crop variety are extracted;

[0163] Using the initial soil environment information of the first region as the initial soil state constraint, and the crop planting time, crop variety and air environment information of the first time zone of the first sub-region as constraints, a first sub-soil state monitoring sample set is collected, and soil environment prediction information of the first sub-region at the end of the first time zone is statistically analyzed.

[0164] Until the soil environment prediction information at the end of the Y-1 time zone of the first sub-region is used as the initial soil state constraint, and the crop planting time, the crop variety and the air environment information of the Y time zone of the first sub-region are used as constraints, the Y-th sub-soil state monitoring sample set is collected, and the soil environment prediction information at the end of the Y time zone of the first sub-region is statistically analyzed.

[0165] Add the soil environment prediction information of the first sub-region up to the soil environment prediction information of the first sub-region up to the end time of the Yth time zone of the first sub-region into the soil environment prediction time series information of the first sub-region.

[0166] Until the soil environment prediction information of the first time zone end time of the Mth sub-region is obtained, until the soil environment prediction information of the Zth time zone end time of the Mth sub-region is obtained, add it to the soil environment prediction time series information of the Mth sub-region.

[0167] The soil environment prediction time series information of the first sub-region up to the soil environment prediction time series information of the Mth sub-region is added to the soil environment prediction time series information of the first region.

[0168] Furthermore, the monitoring information identification module 14 includes the following execution steps:

[0169] From the soil environment prediction time series information, extract the soil environment prediction time series information of the first region, wherein the soil environment prediction time series information of the first region includes the soil environment prediction time series information of the first sub-region up to the soil environment prediction time series information of the Mth sub-region.

[0170] From the soil environmental monitoring time series information, extract the soil environmental monitoring time series information of the first region, wherein the soil environmental monitoring time series information of the first region includes the soil environmental monitoring time series information of the first sub-region up to the soil environmental monitoring time series information of the Mth sub-region;

[0171] A similarity analysis was performed on the soil environment prediction time series information and the soil environment monitoring time series information of the first sub-region to obtain the soil environment similarity of the first sub-region.

[0172] The similarity of the soil environment in the Mth sub-region is obtained by performing a similarity analysis on the predicted time series information of the soil environment in the Mth sub-region and the monitored time series information of the soil environment in the Mth sub-region.

[0173] Establish consistency comparison rules: when the soil environment similarity is greater than the similarity threshold, the soil environment is considered consistent; otherwise, it is considered inconsistent.

[0174] Based on the consistency comparison rule, the soil environment similarity of the first sub-region is processed up to the soil environment similarity of the Mth sub-region to obtain inconsistent sub-regions;

[0175] Based on the inconsistent sub-regions, suspicious identification is performed on the soil environmental monitoring time series information and the air environmental monitoring time series information to obtain suspicious identification data for the first region, which is then added to the suspicious identification data for the entire region.

[0176] This also includes:

[0177] The percentage of inconsistent sub-regions in the first region is defined as the proportion of inconsistent sub-regions in the first region.

[0178] When the proportion of inconsistency in the first region is greater than the inconsistency proportion threshold, the soil environmental monitoring time series information and the air environmental monitoring time series information are marked as suspicious based on the inconsistent sub-regions;

[0179] When the proportion of non-consistency in the first region is less than or equal to the non-consistency proportion threshold, the air environment monitoring time series information is marked as suspicious.

[0180] Specifically, a similarity analysis is performed on the predicted time-series information of the soil environment in the first sub-region and the monitored time-series information of the soil environment in the first sub-region to obtain the soil environment similarity of the first sub-region, including:

[0181] Extract the predicted soil environment value at the first moment from the predicted time series information of the soil environment in the first sub-region;

[0182] Extract the soil environmental monitoring value at the first moment from the soil environmental monitoring time series information of the first sub-region;

[0183] The standard deviations of the same attribute are calculated for the predicted soil environmental value and the monitored soil environmental value at the first time point to obtain the standard deviations of several attributes.

[0184] The standard deviations of the aforementioned attributes are traversed and dimensionless to obtain several deviation characteristic values.

[0185] Using the aforementioned deviation feature values ​​as several dimensional distance parameters, the Euclidean distance is calculated, and then the reciprocal is taken to obtain the soil environment similarity of the first sub-region.

[0186] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0187] Those skilled in the art will understand that embodiments of the present invention can provide methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0188] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0189] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0190] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0191] Although preferred embodiments of the invention have been described, those skilled in the art, once they have learned the basic inventive concept, can make other changes and modifications to these embodiments.

[0192] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for monitoring greenhouse environmental data using multi-sensor fusion, characterized in that, include: The system receives soil environmental monitoring time-series information, air environmental monitoring time-series information, and crop growth information for the target area, wherein the crop growth information characterizes the degree of crop growth within the environmental monitoring time window. Extract the initial soil environmental information from historical environmental monitoring information; Using the initial soil environmental information as the initial soil state constraint, and the air environment monitoring time series information and the crop growth information as soil state influence constraints, a soil state monitoring sample set is collected, and soil environment prediction time series information is statistically analyzed. When the soil environment prediction time series information and the soil environment monitoring time series information are inconsistent, the soil environment monitoring time series information and the air environment monitoring time series information are marked as suspicious and sent to the user terminal. Specifically, the soil environmental information at the initial time is used as the initial soil state constraint, and the air environment monitoring time series information and the crop growth information are used as soil state influence constraints. A soil state monitoring sample set is collected, and soil environment prediction time series information is statistically analyzed, including: Spatial clustering is performed on the initial soil environmental information to obtain the initial soil environmental information of the first region up to the initial soil environmental information of the Nth region. Based on the first region up to the Nth region, the air environment monitoring time series information is divided into regions to obtain the air environment monitoring time series information from the first region up to the Nth region; The air environment monitoring time series information of the first region is traversed up to the air environment monitoring time series information of the Nth region, and spatiotemporal clustering is performed to obtain the spatiotemporal clustering results of the air environment in the first region up to the spatiotemporal clustering results of the air environment in the Nth region; Using the soil environment information of the first region at the initial moment as the initial soil state constraint, and the crop growth information and the spatiotemporal clustering results of the air environment of the first region as the soil state influence constraint, a first soil state monitoring sample set is collected, and the predicted time series information of the soil environment of the first region is statistically analyzed. Until the initial soil environment information of the Nth region is used as the initial soil state constraint, and the crop growth information and the spatiotemporal clustering results of the air environment of the Nth region are used as the soil state influence constraint, the Nth soil state monitoring sample set is collected, and the predicted time series information of the Nth region soil environment is statistically analyzed. The soil environment prediction time series information from the first region up to the soil environment prediction time series information of the Nth region is added to the soil environment prediction time series information.

2. The method as described in claim 1, characterized in that, The air environment monitoring time series information of the first region up to the air environment monitoring time series information of the Nth region is traversed and spatiotemporal clustered to obtain the spatiotemporal clustering results of the air environment in the first region up to the Nth region, including: The air environment monitoring time series information of the first region is spatially clustered to obtain the air environment monitoring time series information of the first sub-region up to the Mth sub-region. Perform time-domain clustering on the air environment monitoring time series information of the first sub-region to obtain the air environment information of the first time zone of the first sub-region up to the air environment information of the Yth time zone of the first sub-region; The process continues until the air environment monitoring time series information of the Mth sub-region is clustered in the time domain to obtain the air environment information of the first time zone of the Mth sub-region up to the air environment information of the Zth time zone of the Mth sub-region. The air environment information of the first sub-region in the first time zone up to the air environment information of the first sub-region in the Y time zone, up to the air environment information of the first time zone in the M sub-region up to the air environment information of the Z time zone in the M sub-region, are added to the spatiotemporal clustering result of the air environment of the first region.

3. The method as described in claim 2, characterized in that, Using the initial soil environmental information of the first region as the initial soil state constraint, and the crop growth information and the spatiotemporal clustering results of the air environment in the first region as the soil state influence constraint, a first soil state monitoring sample set is collected, and the predicted time series information of the soil environment in the first region is statistically analyzed, including: From the spatiotemporal clustering results of the air environment in the first region, extract the air environment information of the first time zone of the first sub-region up to the air environment information of the Y time zone of the first sub-region, until extract the air environment information of the first time zone of the M sub-region up to the air environment information of the Z time zone of the M sub-region; From the crop growth information, the crop planting duration and crop variety are extracted; Using the initial soil environment information of the first region as the initial soil state constraint, and the crop planting time, crop variety and air environment information of the first time zone of the first sub-region as constraints, a first sub-soil state monitoring sample set is collected, and soil environment prediction information of the first sub-region at the end of the first time zone is statistically analyzed. Until the soil environment prediction information at the end of the Y-1 time zone of the first sub-region is used as the initial soil state constraint, and the crop planting time, the crop variety and the air environment information of the Y time zone of the first sub-region are used as constraints, the Y-th sub-soil state monitoring sample set is collected, and the soil environment prediction information at the end of the Y time zone of the first sub-region is statistically analyzed. Add the soil environment prediction information of the first sub-region up to the soil environment prediction information of the first sub-region up to the end time of the Yth time zone of the first sub-region into the soil environment prediction time series information of the first sub-region. Until the soil environment prediction information of the first time zone end time of the Mth sub-region is obtained, until the soil environment prediction information of the Zth time zone end time of the Mth sub-region is obtained, add it to the soil environment prediction time series information of the Mth sub-region. The soil environment prediction time series information of the first sub-region up to the soil environment prediction time series information of the Mth sub-region is added to the soil environment prediction time series information of the first region.

4. The method as described in claim 1, characterized in that, When the soil environment prediction time series information and the soil environment monitoring time series information are inconsistent, the soil environment monitoring time series information and the air environment monitoring time series information are marked as suspicious, including: From the soil environment prediction time series information, extract the soil environment prediction time series information of the first region, wherein the soil environment prediction time series information of the first region includes the soil environment prediction time series information of the first sub-region up to the soil environment prediction time series information of the Mth sub-region. From the soil environmental monitoring time series information, extract the soil environmental monitoring time series information of the first region, wherein the soil environmental monitoring time series information of the first region includes the soil environmental monitoring time series information of the first sub-region up to the soil environmental monitoring time series information of the Mth sub-region; A similarity analysis was performed on the soil environment prediction time series information and the soil environment monitoring time series information of the first sub-region to obtain the soil environment similarity of the first sub-region. The similarity of the soil environment in the Mth sub-region is obtained by performing a similarity analysis on the predicted time series information of the soil environment in the Mth sub-region and the monitored time series information of the soil environment in the Mth sub-region. Establish consistency comparison rules: when the soil environment similarity is greater than the similarity threshold, the soil environment is considered consistent; otherwise, it is considered inconsistent. Based on the consistency comparison rule, the soil environment similarity of the first sub-region is processed up to the soil environment similarity of the Mth sub-region to obtain inconsistent sub-regions; Based on the inconsistent sub-regions, suspicious identification is performed on the soil environmental monitoring time series information and the air environmental monitoring time series information to obtain suspicious identification data for the first region, which is then added to the suspicious identification data for the entire region.

5. The method as described in claim 4, characterized in that, Also includes: The percentage of inconsistent sub-regions in the first region is defined as the proportion of inconsistent sub-regions in the first region. When the proportion of inconsistency in the first region is greater than the inconsistency proportion threshold, the soil environmental monitoring time series information and the air environmental monitoring time series information are marked as suspicious based on the inconsistent sub-regions; When the proportion of non-consistency in the first region is less than or equal to the non-consistency proportion threshold, the air environment monitoring time series information is marked as suspicious.

6. The method as described in claim 4, characterized in that, A similarity analysis was performed on the predicted time-series information of the soil environment in the first sub-region and the monitored time-series information of the soil environment in the first sub-region to obtain the soil environment similarity of the first sub-region, including: Extract the predicted soil environment value at the first moment from the predicted time series information of the soil environment in the first sub-region; Extract the soil environmental monitoring value at the first moment from the soil environmental monitoring time series information of the first sub-region; The standard deviations of the same attribute are calculated for the predicted soil environmental value and the monitored soil environmental value at the first time point to obtain the standard deviations of several attributes. The standard deviations of the aforementioned attributes are traversed and dimensionless to obtain several deviation characteristic values. Using the aforementioned deviation feature values ​​as several dimensional distance parameters, the Euclidean distance is calculated, and then the reciprocal is taken to obtain the soil environment similarity of the first sub-region.

7. A greenhouse environment data monitoring platform integrating multiple sensors, characterized in that, For implementing the method as described in any one of claims 1 to 6, comprising: The monitoring information acquisition module is used to receive soil environmental monitoring time series information, air environmental monitoring time series information, and crop growth information of the target area, wherein the crop growth information represents the degree of crop growth within the environmental monitoring time window; The environmental information extraction module is used to extract the initial soil environmental information from the air environmental monitoring time series information from historical environmental monitoring information; The prediction information statistics module is used to collect a soil state monitoring sample set and statistically analyze the soil environment prediction time series information, using the soil environment information at the initial time as the initial soil state constraint, the air environment monitoring time series information and the crop growth information as soil state influence constraints. The monitoring information identification module is used to identify the soil environment monitoring time series information and the air environment monitoring time series information as suspicious when they are inconsistent, and then send the information to the user terminal.

Images