Earthworm breeding room environment monitoring system and method based on multi-source data

Abstract

The invention provides an earthworm breeding room environment monitoring system and method based on multi-source data, and relates to the technical field of earthworm breeding room environment monitoring, a breeding room is uniformly divided into a plurality of grids, a plurality of sensors are arranged to collect historical environment data in the breeding room, and the historical environment data are preprocessed to form a historical sample set. And training an environment prediction model by adopting a linear regression model so as to predict future environment data. And preprocessing environment data at the current moment, inputting the preprocessed environment data into the model, predicting environment parameters at the next moment, comparing the predicted environment parameters with a suitable range, and marking an abnormal grid. And calculating an environment index of the abnormal grid, comparing the environment index with a preset threshold value, and if the environment index is lower than the threshold value, giving out an early warning. According to the method, the environment condition of the earthworm breeding room can be effectively monitored, the suitability of breeding conditions is ensured, the breeding efficiency and yield are improved, and the method has important application value and popularization potential.

Description

Technical Field

[0001] The present invention relates to the technical field of earthworm breeding room environment monitoring, and in particular to an earthworm breeding room environment monitoring system and method based on multi-source data. Background Art

[0002] As an emerging ecological agricultural model, earthworm farming has attracted widespread attention due to its efficient organic waste conversion capacity and high-quality soil improvement effect. With people's attention to sustainable development and organic agriculture, earthworm farming has gradually become an important means to improve soil fertility and reduce environmental pollution. However, the growth and reproduction of earthworms have strict requirements on environmental conditions, including temperature, soil moisture, soil Values, oxygen concentrations, carbon dioxide concentrations, and light intensity. Changes in these factors not only affect the growth rate and reproductive capacity of earthworms, but may also lead to disease and death, which in turn affects the economic benefits of breeding. Therefore, it is particularly important to establish a scientific and effective environmental monitoring system. By real-time monitoring and analyzing environmental data in the breeding room, breeders can detect abnormal conditions in a timely manner and take corresponding adjustment measures to ensure the best growth environment for earthworms. At the same time, the development of modern information technology, such as the Internet of Things, data analysis, and artificial intelligence, has provided new solutions for environmental monitoring, enabling breeders to manage the breeding environment more accurately.

[0003] In recent years, with the increasing attention paid to ecological agriculture and environmentally friendly breeding, earthworm breeding has gradually received attention. However, the growth and reproduction of earthworms are affected by many environmental factors, such as temperature, soil moisture, soil Values, oxygen and carbon dioxide concentrations, etc. These factors are often difficult to maintain within an appropriate range during the breeding process, resulting in the inhibition of earthworm growth and even affecting their survival. Therefore, how to effectively monitor and adjust these environmental factors to create an ideal breeding condition has become a technical problem that needs to be solved in the current earthworm breeding field.

[0004] The prior art has the following deficiencies: First, data collection often relies on a small number of sensors, which cannot fully cover all important environmental variables, resulting in incomplete monitoring data. In addition, many traditional systems have low real-time update frequencies and cannot reflect environmental changes in a timely manner, increasing aquaculture risks. Data analysis capabilities are also relatively limited, and it is impossible to fully utilize big data and intelligent algorithms for in-depth analysis, affecting the accuracy of environmental forecasts. At the same time, some systems lack effective early warning mechanisms and fail to identify abnormal environmental conditions in a timely manner. These factors have a combined impact on aquaculture efficiency and sustainable development. Summary of the invention

[0005] The object of the present invention is to provide a system and method for monitoring the environment of an earthworm breeding room based on multi-source data to solve the problems raised in the above-mentioned background technology.

[0006] An earthworm breeding room environment monitoring system based on multi-source data, comprising: The environmental data acquisition module is used to evenly divide the breeding room into multiple grids, collect the historical environmental data of each grid, pre-process the historical environmental data, and integrate the pre-processed environmental data into a historical sample set according to the timestamp. The historical environmental data includes temperature, soil humidity, soil values, oxygen concentration, carbon dioxide concentration and light intensity; The environment prediction model building module is used to divide the historical sample set into a training set and a test set, take the environment data at a certain moment in the training set as input, and the environment data at the next moment as a label, and build an environment prediction model based on a linear regression model; The real-time environmental monitoring module is used to obtain the environmental data of each grid at the current moment, input it into the trained environmental prediction model, and analyze the environmental data predicted at the next moment. When any environmental data predicted in the grid is not within the preset suitable range, the grid is marked as an abnormal grid; The environmental index analysis and early warning module is used to analyze the predicted environmental data in the abnormal grid, calculate the environmental index of the grid, and compare it with the preset environmental index threshold, and issue an early warning for the grid whose environmental index is lower than the environmental index threshold.

[0007] Furthermore, the specific logic for collecting historical environmental data for each grid is as follows: The earthworm breeding room is The size of the grid is evenly divided into multiple grids, and temperature and humidity sensors, soil Sensors, oxygen concentration sensors, carbon dioxide concentration sensors and light intensity sensors are used to collect temperature, soil moisture, soil Value, oxygen concentration, carbon dioxide concentration and light intensity. The preprocessing operation includes removing outliers, calculating the Z-score of each data, and when the absolute value of the Z-score of the data When the data is considered as an outlier, it is removed. After the outlier is removed, the missing value is filled by the mean filling method, and then the Min-Max normalization is used to make the data Within the scope, the preprocessed data is integrated into a historical sample set based on the timestamp.

[0008] Furthermore, the specific logic for building the environmental prediction model is as follows: The historical sample set is divided into a training set and a test set with a division ratio of 7:3. The environmental data from the first timestamp is used as input, and the environmental data at the next moment is used as the label. The linear regression model is selected to train the environmental prediction model. After the training is completed, the test set is input into the trained environmental prediction model for testing. The root mean square error and mean absolute error are selected as the loss function. When the change range of the loss function value in five consecutive trainings is less than 0.1, it indicates that the training of the environmental prediction model is completed.

[0009] Furthermore, the specific logic for marking abnormal grids is as follows: The environmental data of each grid at the current moment is collected, preprocessed and input into the trained environmental prediction model to obtain the prediction of the environmental data at the next moment. The predicted environmental data is compared with the preset suitable range of each environmental data. The suitable range of temperature is [15,30], in °C, and the suitable range of soil moisture is [60%, 85%]. The suitable range of values ​​is [6.0, 7.5], the suitable range of oxygen concentration is [5%, 21%], the suitable range of carbon dioxide concentration is [0.03%, 1%], and the suitable range of light intensity is [100, 500]. The unit is Lux. If any environmental data predicted by the model at the next moment exceeds the suitable range, the grid is marked as abnormal.

[0010] Furthermore, the specific logic for determining whether to issue an abnormal warning to the grid is as follows: The formula for calculating the environmental index of a grid with anomalies is: ; in, is the environmental index, are temperature, soil moisture, value, oxygen concentration, carbon dioxide concentration and light intensity, is the weight of the temperature suitability function value, is the weight of the soil moisture suitability function value, For soil The weight of the suitability function value, is the weight of the oxygen concentration suitability function value, is the weight of the carbon dioxide concentration suitability function value, is the weight of the light intensity suitability function value, ,and ; Obtain the suitability function of each environmental factor. The temperature suitability function is: ; in, Represents the temperature at the next moment predicted by the model; The soil moisture suitability function is: ; in, Indicates the humidity at the next moment predicted by the model; soil The value suitability function is: ; in, Represents the soil at the next moment predicted by the model value; The oxygen concentration suitability function is: ; in, Represents the oxygen concentration at the next moment predicted by the model; The carbon dioxide concentration suitability function is: ; in, represents the carbon dioxide concentration at the next moment predicted by the model; The light intensity suitability function is: ; in, Represents the light intensity at the next moment predicted by the model; If the current grid environmental index is higher than the preset environmental index threshold, the grid will continue to be monitored. If the current grid environmental index is lower than the preset environmental index threshold, the grid will issue an abnormal warning.

[0011] The present invention further provides an earthworm breeding room environment monitoring method based on multi-source data, the earthworm breeding room environment monitoring method based on multi-source data is executed by the earthworm breeding room environment monitoring system based on multi-source data, and the specific steps include: Step 1: Divide the breeding room into multiple grids evenly, collect historical environmental data of each grid, pre-process the historical environmental data, and integrate the pre-processed environmental data into a historical sample set according to the timestamp. The historical environmental data includes temperature, soil humidity, soil values, oxygen concentration, carbon dioxide concentration and light intensity; Step 2: Divide the historical sample set into a training set and a test set, use the environmental data at a certain moment in the training set as input, and the environmental data at the next moment as labels, and build an environmental prediction model based on the linear regression model; Step 3: Obtain the environmental data of each grid at the current moment, input it into the trained environmental prediction model, and analyze the environmental data for the next moment. When any environmental data predicted in the grid is not within the preset suitable range, mark the grid as an abnormal grid; Step 4: Analyze the environmental data in the abnormal grid, calculate the environmental index of the grid, and compare it with the preset environmental index threshold, and issue an early warning for the grid whose environmental index is lower than the environmental index threshold.

[0012] In the above technical solution, the technical effects and advantages provided by the present invention are: The present invention realizes comprehensive and real-time monitoring of the breeding environment by integrating information from different sensors and data sources. This method has significant technical effects and can provide more accurate and comprehensive environmental data analysis to help breeders grasp temperature, soil moisture, soil At the same time, this method uses data fusion and intelligent algorithms to improve the early warning capability of environmental abnormalities and reduce breeding risks. It has strong real-time performance and can respond to environmental changes in a timely manner, thereby effectively preventing potential problems. It is also highly intelligent and can automatically identify and process data to provide scientific decision-making support for breeders. Finally, the system is highly adaptable and can be flexibly adjusted according to different breeding conditions to meet personalized needs. These advantages make this method of great significance in improving the efficiency and sustainable development of earthworm breeding. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a schematic diagram of the system structure of the present invention; Figure 2 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0014] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0015] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0016] Example: See also Figure 1 The present invention provides an earthworm breeding room environment monitoring system based on multi-source data, comprising: The environmental data acquisition module is used to evenly divide the breeding room into multiple grids, collect the historical environmental data of each grid, pre-process the historical environmental data, and integrate the pre-processed environmental data into a historical sample set according to the timestamp. The historical environmental data includes temperature, soil humidity, soil Value, oxygen concentration, carbon dioxide concentration and light intensity, temperature, oxygen concentration and carbon dioxide concentration also refer to the temperature, oxygen concentration and carbon dioxide concentration in the soil; In this embodiment, the specific logic for collecting the historical environmental data of each grid is as follows: The earthworm breeding room is The size of the grid is evenly divided into multiple grids, and temperature and humidity sensors, soil Sensors, oxygen concentration sensors, carbon dioxide concentration sensors and light intensity sensors are used to collect temperature, soil moisture, soil Value, oxygen concentration, carbon dioxide concentration and light intensity. The preprocessing operation includes removing outliers, calculating the Z-score of each data, and when the absolute value of the Z-score of the data When the data is considered as an outlier, it is removed. After the outlier is removed, the missing value is filled by the mean filling method, and then the Min-Max normalization is used to make the data Within the scope, the preprocessed data is integrated into a historical sample set based on the timestamp.

[0017] By dividing the breeding room evenly into several The grid is formed and multiple sensors are arranged in the center of each grid, which can realize the detailed monitoring of the breeding environment. This grid layout ensures the comprehensiveness and representativeness of data collection, so that the environmental conditions of each area can be fully recorded, thus providing a rich foundation for subsequent data analysis. The step of removing outliers can effectively identify and exclude extreme values ​​that do not conform to the normal range by calculating the Z-score of each data, thereby improving the reliability of the data. The removal of outliers can reduce data noise and ensure the accuracy of subsequent analysis. In addition, the method of using the mean to fill missing values ​​not only ensures the integrity of the data, but also avoids the analysis bias caused by missing data. Min-Max normalization is then used to standardize the data to the range of [0,1], so that data of different dimensions and ranges can be effectively compared and fused. This processing step enhances the stability and interpretability of the model in subsequent analysis, makes the relationship between different environmental variables clearer, and lays a good foundation for data mining and intelligent analysis.

[0018] The environment prediction model building module is used to divide the historical sample set into a training set and a test set, take the environment data at a certain moment in the training set as input, and the environment data at the next moment as a label, and build an environment prediction model based on a linear regression model; In this embodiment, the specific logic for constructing the environment prediction model is: The historical sample set is divided into a training set and a test set with a division ratio of 7:3. The environmental data from the first timestamp is used as input, and the environmental data at the next moment is used as the label. The linear regression model is selected to train the environmental prediction model. After the training is completed, the test set is input into the trained environmental prediction model for testing. The root mean square error and mean absolute error are selected as the loss function. When the change range of the loss function value in five consecutive trainings is less than 0.1, it indicates that the training of the environmental prediction model is completed.

[0019] The real-time environmental monitoring module is used to obtain the environmental data of each grid at the current moment, input it into the trained environmental prediction model, and analyze the environmental data predicted at the next moment. When any environmental data predicted in the grid is not within the preset suitable range, the grid is marked as an abnormal grid; In this embodiment, the specific logic for marking abnormal grids is as follows: The environmental data of each grid at the current moment is collected, preprocessed and input into the trained environmental prediction model to obtain the prediction of the environmental data at the next moment. The predicted environmental data is compared with the preset suitable range of each environmental data. The suitable range of temperature is [15,30], in °C, and the suitable range of soil moisture is [60%, 85%]. The suitable range of values ​​is [6.0, 7.5], the suitable range of oxygen concentration is [5%, 21%], the suitable range of carbon dioxide concentration is [0.03%, 1%], and the suitable range of light intensity is [100, 500]. The unit is Lux. If any environmental data predicted by the model at the next moment exceeds the suitable range, the grid is marked as abnormal.

[0020] The environmental index analysis and early warning module is used to analyze the predicted environmental data in the abnormal grid, calculate the environmental index of the grid, and compare it with the preset environmental index threshold, and issue an early warning for the grid whose environmental index is lower than the environmental index threshold.

[0021] In this embodiment, the specific logic for determining whether to issue an abnormal warning to a grid is: The formula for calculating the environmental index of a grid with anomalies is: ; in, is the environmental index, Temperature, soil moisture, soil value, oxygen concentration, carbon dioxide concentration and light intensity, is the weight of the temperature suitability function value, is the weight of the soil moisture suitability function value, For soil The weight of the value suitability function value, is the weight of the oxygen concentration suitability function value, is the weight of the carbon dioxide concentration suitability function value, is the weight of the light intensity suitability function value, ,and ; Obtain the suitability function of each environmental factor. The temperature suitability function is: ; in, It represents the temperature at the next moment predicted by the model, and 25℃ is the best temperature value; The soil moisture suitability function is: ; in, It indicates the humidity at the next moment predicted by the model, and 80% is the optimal humidity value; soil The value suitability function is: ; in, Represents the soil at the next moment predicted by the model Value, 7.5 is the best value; The oxygen concentration suitability function is: ; in, It represents the oxygen concentration at the next moment predicted by the model, and 21% is the optimal oxygen concentration value; The carbon dioxide concentration suitability function is: ; in, represents the carbon dioxide concentration at the next moment predicted by the model; The light intensity suitability function is: ; in, Indicates the light intensity at the next moment predicted by the model, 500Lux is the optimal light intensity value; If the current grid environmental index is higher than the preset environmental index threshold, the grid will continue to be monitored. If the current grid environmental index is lower than the preset environmental index threshold, the grid will issue an abnormal warning.

[0022] In the suitable range, temperature, soil moisture, soil The closer the values ​​of oxygen concentration and light intensity are to the optimal parameter values, the larger the value of the suitability function is, and the more suitable it is for earthworms to survive. Environmental parameters and suitability function This means that if the suitability of an environmental parameter (such as temperature, soil moisture, etc. other than carbon dioxide concentration) increases (i.e., its value is closer to the ideal value), the corresponding suitability function value will increase, which will lead to an increase in the environmental index. When the carbon dioxide concentration is higher than 0.5%, although the environmental conditions are suitable, the carbon dioxide concentration is in the range of [0.03%, 0.5%], which is the most suitable environment for earthworm breeding, and the carbon dioxide concentration suitability function value is the highest. In the range of [0.5%, 1%), the suitability function value gradually decreases with the increase of concentration. Soil Both factors, soil temperature and CO2 concentration, are equally important in vermiculture and are therefore given equal weight. Too high or too low values ​​will affect the survival of earthworms, and high concentrations of carbon dioxide will cause hypoxia and affect the growth of earthworms. Light is also an important factor affecting the growth of earthworms. Although earthworms are soil organisms and are usually not directly exposed to strong light, suitable light can affect the temperature and humidity of the soil, thereby indirectly affecting the growth environment of earthworms. In addition, light will also affect microbial activity, which is crucial to the food supply of earthworms. The temperature and humidity of the soil are the basic environmental conditions that affect the growth of earthworms. The suitable range is wide, so the weight is relatively high. Oxygen is necessary for the survival of earthworms. The appropriate oxygen concentration can promote their respiration and growth. The hypoxic environment will directly lead to the death of earthworms. Temperature is a key factor affecting the metabolic rate of earthworms. The appropriate temperature range can promote the reproduction and activity of earthworms. Therefore, the suitability of temperature is crucial to the success of breeding. Soil moisture directly affects the survival and reproduction of earthworms. Earthworms need to maintain a certain humidity to prevent dehydration. Too high or too low humidity will threaten their survival. Therefore, the light intensity, oxygen concentration, temperature and soil moisture are given the same weight, and higher than the soil values ​​and weights of carbon dioxide concentrations.

[0023] See also Figure 2 The present invention also provides a method for monitoring the environment of an earthworm breeding room based on multi-source data. The method for monitoring the environment of an earthworm breeding room based on multi-source data is executed by the above-mentioned system for monitoring the environment of an earthworm breeding room based on multi-source data. The specific steps include: Step 1: Divide the breeding room into multiple grids evenly, collect historical environmental data of each grid, pre-process the historical environmental data, and integrate the pre-processed environmental data into a historical sample set according to the timestamp. The historical environmental data includes temperature, soil humidity, soil values, oxygen concentration, carbon dioxide concentration and light intensity; Step 2: Divide the historical sample set into a training set and a test set, use the environmental data at a certain moment in the training set as input, and the environmental data at the next moment as labels, and build an environmental prediction model based on the linear regression model; Step 3: Obtain the environmental data of each grid at the current moment, input it into the trained environmental prediction model, and analyze the environmental data for the next moment. When any environmental data predicted in the grid is not within the preset suitable range, mark the grid as an abnormal grid; Step 4: Analyze the predicted environmental data in the abnormal grid, calculate the environmental index of the grid, and compare it with the preset environmental index threshold, and issue an early warning for the grid whose environmental index is lower than the environmental index threshold.

[0024] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0025] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0026] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0027] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An earthworm breeding room environment monitoring system based on multi-source data, characterized in that: include: The environmental data acquisition module is used to evenly divide the breeding room into multiple grids, collect the historical environmental data of each grid, pre-process the historical environmental data, and integrate the pre-processed environmental data into a historical sample set according to the timestamp. The historical environmental data includes temperature, soil humidity, soil values, oxygen concentration, carbon dioxide concentration and light intensity; The environment prediction model building module is used to divide the historical sample set into a training set and a test set, take the environment data at a certain moment in the training set as input, and the environment data at the next moment as a label, and build an environment prediction model based on a linear regression model; The real-time environmental monitoring module is used to obtain the environmental data of each grid at the current moment, input it into the trained environmental prediction model, and analyze the environmental data predicted at the next moment. When any environmental data predicted in the grid is not within the preset suitable range, the grid is marked as an abnormal grid; The environmental index analysis and early warning module is used to analyze the predicted environmental data in the abnormal grid, calculate the environmental index of the grid, and compare it with the preset environmental index threshold, and issue an early warning for the grid whose environmental index is lower than the environmental index threshold.

2. The earthworm breeding room environment monitoring system based on multi-source data according to claim 1 is characterized in that: The specific logic for collecting historical environmental data for each grid is: The earthworm breeding room is The size of the grid is evenly divided into multiple grids, and temperature and humidity sensors, soil Sensors, oxygen concentration sensors, carbon dioxide concentration sensors and light intensity sensors are used to collect temperature, soil moisture, soil Value, oxygen concentration, carbon dioxide concentration and light intensity. The preprocessing operation includes removing outliers, calculating the Z-score of each data, and when the absolute value of the Z-score of the data When the data is considered as an outlier, it is removed. After the outlier is removed, the missing value is filled by the mean filling method, and then the Min-Max normalization is used to make the data Within the scope, the preprocessed data is integrated into a historical sample set based on the timestamp.

3. The earthworm breeding room environment monitoring system based on multi-source data according to claim 2 is characterized in that: The specific logic for building the environmental prediction model is: The historical sample set is divided into a training set and a test set with a division ratio of 7:

3. The environmental data from the first timestamp is used as input, and the environmental data at the next moment is used as the label. The linear regression model is selected to train the environmental prediction model. After the training is completed, the test set is input into the trained environmental prediction model for testing. The root mean square error and mean absolute error are selected as the loss function. When the change range of the loss function value in five consecutive trainings is less than 0.1, it indicates that the training of the environmental prediction model is completed.

4. The earthworm breeding room environment monitoring system based on multi-source data according to claim 3 is characterized in that: The specific logic for marking abnormal grids is as follows: The environmental data of each grid at the current moment is collected, preprocessed and input into the trained environmental prediction model to obtain the prediction of the environmental data at the next moment. The predicted environmental data is compared with the preset suitable range of each environmental data. The suitable range of temperature is [15,30], in °C, and the suitable range of soil moisture is [60%, 85%]. The suitable range of values ​​is [6.0, 7.5], the suitable range of oxygen concentration is [5%, 21%], the suitable range of carbon dioxide concentration is [0.03%, 1%], and the suitable range of light intensity is [100, 500]. The unit is Lux. If any environmental data predicted by the model at the next moment exceeds the suitable range, the grid is marked as abnormal.

5. The earthworm breeding room environment monitoring system based on multi-source data according to claim 4 is characterized in that: The specific logic for judging the abnormal warning of the grid is as follows: The formula for calculating the environmental index of a grid with anomalies is: ； in, is the environmental index, Temperature, soil moisture, soil value, oxygen concentration, carbon dioxide concentration and light intensity, is the weight of the temperature suitability function value, is the weight of the soil moisture suitability function value, For soil The weight of the suitability function value, is the weight of the oxygen concentration suitability function value, is the weight of the carbon dioxide concentration suitability function value, is the weight of the light intensity suitability function value, ,and ; Obtain the suitability function of each environmental factor. The temperature suitability function is: ； in, Indicates the temperature at the next moment predicted by the model; The soil moisture suitability function is: ； in, Indicates the humidity at the next moment predicted by the model; soil The value suitability function is: ； in, Represents the soil at the next moment predicted by the model value; The oxygen concentration suitability function is: ； in, Represents the oxygen concentration at the next moment predicted by the model; The carbon dioxide concentration suitability function is: ； in, represents the carbon dioxide concentration at the next moment predicted by the model; The light intensity suitability function is: ； in, Represents the light intensity at the next moment predicted by the model; If the environmental index of the grid at the current moment is higher than the preset environmental index threshold, the grid will continue to be monitored. If the environmental index of the grid at the current moment is lower than the preset environmental index threshold, the grid will issue an abnormal warning.

6. A method for monitoring the environment of an earthworm breeding room based on multi-source data, characterized in that: The method for monitoring the environment of an earthworm breeding room based on multi-source data is performed by the system for monitoring the environment of an earthworm breeding room based on multi-source data according to any one of claims 1 to 5, and the specific steps include: Step 1: Divide the breeding room into multiple grids evenly, collect historical environmental data of each grid, pre-process the historical environmental data, and integrate the pre-processed environmental data into a historical sample set according to the timestamp. The historical environmental data includes temperature, soil humidity, soil values, oxygen concentration, carbon dioxide concentration and light intensity; Step 2: Divide the historical sample set into a training set and a test set, use the environmental data at a certain moment in the training set as input, and the environmental data at the next moment as labels, and build an environmental prediction model based on the linear regression model; Step 3: Obtain the environmental data of each grid at the current moment, input it into the trained environmental prediction model, and analyze the environmental data for the next moment. When any environmental data predicted in the grid is not within the preset suitable range, mark the grid as an abnormal grid; Step 4: Analyze the predicted environmental data in the abnormal grid, calculate the environmental index of the grid, and compare it with the preset environmental index threshold, and issue an early warning for the grid whose environmental index is lower than the environmental index threshold.

Images