An Internet-based intelligent irrigation system for uniform cultivation

Abstract

The invention relates to the technical field of agricultural irrigation, and in particular to an intelligent irrigation system for uniform cultivation based on the Internet, comprising: a data acquisition module, used for collecting growth environment data of crops during their growth, and determining the temperature, humidity, light and soil moisture content of the soil in which the crops grow; a state monitoring module, used for determining the spraying amount and the change of growth environment data corresponding to each cultivation cycle during the growth of the crops, and obtaining a correlation curve between the spraying amount and the growth environment data; a curve analysis module, used for analyzing the correlation curve, determining the growth model of the crops under each preset environmental condition, and judging the water demand of the current crops, and generating irrigation instructions corresponding to the water demand; an instruction execution module, used for executing the generated irrigation instructions, and monitoring the change value of the growth environment data of the crops after the irrigation instructions are executed, thereby improving the sprinkler irrigation efficiency and the production efficiency.

Description

Technical Field

[0001] The invention relates to the technical field of agricultural irrigation, and in particular to an intelligent irrigation system for uniform cultivation based on the Internet. Background Art

[0002] Agricultural irrigation methods can generally be divided into traditional surface irrigation, ordinary sprinkler irrigation and micro-irrigation. Traditional surface irrigation includes furrow irrigation, furrow irrigation, flooding irrigation and overspill irrigation, but these irrigation methods often consume a lot of water and have low water utilization efficiency, which is an unreasonable agricultural irrigation method. Ordinary sprinkler irrigation technology is a more common irrigation method in China's agricultural production, but the water utilization efficiency of ordinary sprinkler irrigation technology is not high. Modern agricultural micro-irrigation technology includes micro-sprinkler irrigation, drip irrigation, infiltration irrigation, etc. These irrigation technologies generally have good water-saving performance and higher water utilization rate than traditional irrigation methods.

[0003] For example, Chinese patent publication number CN111273591A discloses an intelligent agricultural irrigation system based on the Internet of Things, including an environmental parameter detection module, a soil moisture detection module, a soil temperature detection module, an environmental data preprocessing module, a management database, an irrigation parameter analysis module, a management server, a display terminal, and an irrigation control module. The intelligent agricultural irrigation system based on the Internet of Things provided by the present invention collects and processes the temperature, humidity, carbon dioxide concentration, soil moisture, and soil temperature in each collection time period in the greenhouse, analyzes the irrigation ratio coefficient of the soil in the greenhouse, and extracts the amount of irrigation water per square meter corresponding to each irrigation ratio coefficient according to the irrigation ratio coefficient of the soil, thereby obtaining the irrigation amount corresponding to the area occupied by the greenhouse.

[0004] Existing technologies collect and process temperature, humidity, carbon dioxide concentration, soil moisture and soil temperature to prevent the problem of excessive carbon dioxide concentration. However, existing technologies cannot adjust irrigation volume according to the needs of crops, which may lead to waste of water resources. At the same time, it is also necessary to determine the relationship between crops and corresponding environmental data to determine the adaptability of crops to environmental changes. Summary of the invention

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: an Internet-based intelligent irrigation system for uniform cultivation, including: a data acquisition module for collecting growth environment data during crop growth, and determining the temperature, humidity, light and soil moisture content of the soil in which the crops grow.

[0006] The state monitoring module is used to determine the changes in the spraying amount and growth environment data corresponding to each cultivation cycle during the growth of crops, and obtain a correlation curve between the spraying amount and the growth environment data.

[0007] The curve analysis module is used to analyze the correlation curve, determine the growth model of crops under each preset environmental condition, judge the current water demand of crops, and generate irrigation instructions corresponding to the water demand.

[0008] The instruction execution module is used to execute the generated watering instructions and monitor the change value of the growth environment data of the crops after the watering instructions are executed.

[0009] The feedback adjustment module is used to determine the final selected irrigation strategy according to the change value of the growth environment data and the current state of the crops.

[0010] The beneficial effects of the present invention are as follows: 1. The present invention can avoid over-irrigation or under-irrigation by real-time monitoring and accurate analysis of the water demand of crops, thereby achieving conservation and efficient use of water resources.

[0011] 2. The present invention provides suitable irrigation amount for crops, thus helping them to grow in the best condition and improving the yield and quality of crops.

[0012] 3. The present invention reduces the negative impact of agriculture on the environment by reducing the waste of water resources, while improving the adaptability of crops to the environment, which is conducive to achieving sustainable agriculture.

[0013] 4. Through automated data collection, analysis and decision-making, the present invention realizes intelligent management of agricultural irrigation, reduces the labor intensity of farmers and improves the efficiency of agricultural production. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0015] Figure 1 It is a system framework diagram of an Internet-based intelligent irrigation system for uniform cultivation.

[0016] Figure 2 It is a system flow chart of an intelligent irrigation system for uniform cultivation based on the Internet.

[0017] Figure 3 The present invention is a logical schematic diagram of correlation curve analysis of an intelligent irrigation system for uniform cultivation based on the Internet.

[0018] Figure 4 The present invention is a structural schematic diagram of the spraying area of ​​an Internet-based intelligent irrigation system for uniform cultivation. DETAILED DESCRIPTION

[0019] The embodiments of the present invention are described in detail below. The embodiments described below are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention. If no specific techniques or conditions are specified in the embodiments, the techniques or conditions described in the literature in the art or the product specifications are used.

[0020] See also Figure 1 , Figure 2 , an Internet-based intelligent irrigation system for uniform cultivation, including: a data acquisition module, a state monitoring module, a curve analysis module, an instruction execution module, and a feedback adjustment module; the data acquisition module collects the growth environment data of crops in real time through sensors arranged in the farmland; the sensors used are temperature sensors, humidity sensors, light sensors, and soil moisture sensors; the collected data are transmitted to the state monitoring module via wired or wireless means; the state monitoring module receives real-time data from the data acquisition module, and stores the spraying amount and growth environment data of each cultivation cycle; uses historical data and real-time data to analyze the correlation between the spraying amount and the growth environment data, and draws a correlation curve; the curve analysis module receives the relevant information generated by the state monitoring module The system can obtain relevant curve data; determine the growth model of crops under different environmental conditions through in-depth analysis of the curve; judge the current water demand of crops based on the growth model and real-time environmental data, and generate corresponding irrigation instructions; the instruction execution module receives the irrigation instructions from the curve analysis module, controls the irrigation system according to the instructions, performs corresponding irrigation operations, and continues to monitor the changes in the growth environment data after executing the irrigation instructions, and feeds these data back to the status monitoring module; the feedback adjustment module receives the change value of the growth environment data fed back by the instruction execution module; evaluates the irrigation effect in combination with the current growth status of crops, and adjusts the future irrigation strategy accordingly, and feeds the adjusted strategy back to the status monitoring module and the instruction execution module to achieve more accurate irrigation control.

[0021] The data acquisition module is used to collect the growth environment data of crops during their growth and determine the temperature, humidity, light and soil moisture content of the soil in which the crops grow.

[0022] The state monitoring module is used to determine the changes in the spraying amount and growth environment data corresponding to each cultivation cycle during the growth of crops, and obtain a correlation curve between the spraying amount and the growth environment data.

[0023] The curve analysis module is used to analyze the correlation curve, determine the growth model of crops under each preset environmental condition, judge the current water demand of crops, and generate irrigation instructions corresponding to the water demand.

[0024] The instruction execution module is used to execute the generated watering instructions and monitor the change value of the growth environment data of the crops after the watering instructions are executed.

[0025] The feedback adjustment module is used to determine the final selected irrigation strategy according to the change value of the growth environment data and the current state of the crops.

[0026] The implementation method of the correlation curve in the status monitoring module includes recording the specific dosage of each spraying, including the type of pesticides and fertilizers used and their dosage; determining the changes in temperature, humidity, light intensity and soil moisture content after each spraying, and using the corresponding data as the current output correlation curve.

[0027] At this time, the correlation curve is drawn according to the values ​​of the collected growth environment data in chronological order to determine the corresponding values ​​after each spraying. At the same time, the data after spraying will be recorded multiple times to compare the current set spraying amount.

[0028] like Figure 3 As shown, the implementation method of analyzing the correlation curve in the curve analysis module includes sequentially obtaining a first correlation coefficient between the spraying amount and temperature, a second correlation coefficient between the spraying amount and humidity, a third correlation coefficient between the spraying amount and light intensity, and a fourth correlation coefficient between the spraying amount and soil moisture content.

[0029] The first correlation coefficient, the second correlation coefficient, the third correlation coefficient and the fourth correlation coefficient are processed to obtain the correlation coefficients between the spraying amount and the temperature, humidity, light intensity and soil moisture content.

[0030] For example, the first correlation coefficient is obtained by dividing the spraying amount and the temperature into multiple groups of data and sequentially inputting them into a multiple regression model to obtain regression coefficients corresponding to multiple groups of the first correlation coefficients.

[0031] ;in, Indicates the spraying amount. , , , represents the regression coefficient between spraying amount and temperature, , , Indicates temperature, represents the error term corresponding to the spraying amount and temperature, Indicates the number of regression coefficients; at this time, the regression coefficients corresponding to different temperatures under each spraying amount used are determined, and the regression coefficient with the smallest difference between the predicted spraying amount and the actual spraying amount is marked.

[0032] The calculation method for the second correlation coefficient, the third correlation coefficient and the fourth correlation coefficient is the same as that for the first correlation coefficient. The obtained values ​​are all regression coefficients with the smallest difference between the predicted spraying amount and the actual spraying amount. The obtained regression coefficients are compared, and the correlation coefficients of the first correlation coefficient, the second correlation coefficient, the third correlation coefficient and the fourth correlation coefficient are calculated using the Pearson correlation coefficient.

[0033] By grouping the data and inputting them into a multiple regression model, the specific relationship between the spraying amount and various environmental factors such as temperature, humidity, light intensity and soil moisture content can be found more accurately; this grouping processing method helps to reduce data noise and improve the accuracy of the analysis.

[0034] By calculating and comparing the various correlation coefficients, we can clearly understand which environmental factors are most correlated with the spraying amount, thereby providing more accurate support for agricultural management decisions. For example, if the spraying amount is most correlated with humidity, then more attention should be paid to adjusting the spraying amount when the humidity changes.

[0035] For example, the correlation coefficient between the spraying amount and humidity is 0.85, indicating that there is a strong positive correlation between the two. At the same time, the correlation coefficient between the spraying amount and humidity is calculated to be 0.75, and the correlation coefficient between these two coefficients is 0.9. At this time, the relationship between humidity and temperature will be more obvious, so you need to pay special attention to these combined data.

[0036] For example, the correlation between the regression coefficients of the first correlation coefficient and the second correlation coefficient is first calculated.

[0037] ;in, represents the correlation coefficient corresponding to the first correlation coefficient and the second correlation coefficient, represents the i-th regression coefficient in the first correlation coefficient, represents the average of the regression coefficients in the first correlation coefficient, represents the i-th regression coefficient in the second correlation coefficient, represents the average value of the second correlation coefficient, represents the number of regression coefficients, ; At this time, the data used for calculation are normalized in advance to prevent inconsistent dimensions during calculation.

[0038] Then, the correlation coefficients corresponding to the first correlation coefficient and the third correlation coefficient are calculated in turn according to the calculation method of the correlation coefficients corresponding to the first correlation coefficient and the second correlation coefficient. , the correlation coefficients corresponding to the first correlation coefficient and the fourth correlation coefficient , the correlation coefficients corresponding to the second correlation coefficient and the third correlation coefficient , the correlation coefficients corresponding to the second correlation coefficient and the fourth correlation coefficient , the correlation coefficients corresponding to the third correlation coefficient and the fourth correlation coefficient ; A set of data corresponding to the maximum value of the weighted average of these six correlation coefficients is used as the target data for correlation curve analysis.

[0039] The target data selected at this time can reflect that there is a large correlation between the corresponding multiple types of values ​​in the currently collected growth environment data. These grouped distributed data can be processed centrally to discover the impact of the spraying amount set at this time and how to adjust the spraying amount to achieve overall optimization control.

[0040] The implementation method of determining the growth model of crops under each preset environmental condition in the curve analysis module includes: obtaining target data of the correlation curve, setting the interval between the two ends of the time point corresponding to the target data as the cultivation cycle, and taking the average value of the corresponding growth environment data in each cultivation cycle as the growth model of crops under each preset environmental condition.

[0041] The growth model is segmented according to the way plants grow at different times to determine whether the currently cultivated crops grow into the preset appearance. At this time, the growth model can compare the current appearance of the crops with the preset growth image to determine whether the crops grow normally under the current watering scenario. At this time, the data within a specific interval is used as the data to control the growth of the crops to determine the growth model used for the current crops.

[0042] First, the target data is obtained from the correlation curve, which reflects the growth of crops under different environmental conditions. Then, the interval between the two ends of the time point corresponding to the target data is set as the cultivation cycle. This is done to ensure that the environmental conditions are relatively stable within each cultivation cycle, so that the growth model can be established more accurately.

[0043] The cultivation cycle is a time period artificially set for research or management needs. In the curve analysis module, the cultivation cycle is set based on the target data of the correlation curve, aiming to capture the growth of crops under specific environmental conditions; it may not be completely equivalent to the natural growth cycle of crops, but it can help to more accurately understand the growth characteristics of crops under different environmental conditions; in each cultivation cycle, the average value of the corresponding growth environment data is calculated, and this average value represents the typical state of the environmental conditions in the cultivation cycle, which can be used as the basic data for the growth model of crops under the preset environmental conditions; based on these average value data, statistical methods or machine learning algorithms are used to establish a crop growth model; this model can predict the growth of crops under different environmental conditions and provide decision support for precision agriculture management.

[0044] Suppose you are studying the growth of a certain type of rice. From the correlation curve, you select a segment of target data that reflects the growth of rice under specific temperature, humidity and light conditions. Set the interval between the two ends of the time point corresponding to this segment of target data as a cultivation cycle, such as from the 30th day to the 60th day after sowing.

[0045] During this cultivation period, the average values ​​of temperature, humidity and light were calculated, which were 25°C, 60% and 6 hours of direct sunlight per day; based on these data, a rice growth model under this environmental condition was established; this model can help predict the growth of rice under similar environmental conditions, thereby guiding agricultural management activities such as irrigation and fertilization.

[0046] In this way, we can more accurately understand the growth characteristics of crops under different environmental conditions and improve the efficiency and quality of agricultural production.

[0047] The curve analysis module determines the current water demand of crops and generates irrigation instructions corresponding to the water demand, including: recording the change curve of the spraying amount in each cultivation cycle, determining the irrigation coefficient and irrigation ratio coefficient in each cultivation cycle; and setting the irrigation instructions according to the irrigation coefficient and irrigation ratio coefficient.

[0048] like Figure 4 As shown, the setting method for the irrigation coefficient is: divide the area that currently needs to be irrigated into multiple spraying areas, obtain the residual sum of squares and the total sum of squares of the spraying amount of the corresponding spraying area under the cultivation cycle in turn, and calculate the determination coefficient corresponding to the spraying amount, and adjust the determination coefficient according to the number of data points in the current cultivation cycle, and use the adjusted determination coefficient as the current irrigation coefficient.

[0049] The determination coefficient of the spraying amount is expressed as: ;in, represents the coefficient of determination, represents the residual sum of squares of the spraying amount in the jth spraying area, represents the standard value of the residual sum of squares of the spraying amount, represents the total square sum of the spraying amount in the jth spraying area, Represents the standard value of the total square sum of the spraying amount; at this time, the value range of j is 1 to 6. At this time, for the set spraying area, multiple collectors are set on the area that currently needs to be irrigated in the form of a Tyson polygon, and the entire area is divided into several areas according to the position of the collector, and each area corresponds to a group of collectors.

[0050] When using Thiessen polygons to construct the spraying area, all collectors are connected into triangles, and the perpendicular bisectors of these triangles are made. The intersection of the perpendicular bisectors is the center of the circumscribed circle, and these centers are connected to form a polygon, namely, Thiessen polygons. At this time, the collectors contained in these polygons are set as a group of data, and each Thiessen polygon is set as a spraying area. The area currently requiring sprinkler irrigation is iterated until the spraying area can completely cover the area requiring sprinkler irrigation; then for the irrigation coefficient of each spraying area, the area closest to this sprinkler area is obtained for calculation. At this time, six areas are selected, which are selected in the form of polygons, so that it can be understood whether the corresponding spraying amount set in the current area can be reasonably set.

[0051] The total sum of squares is the sum of squares of the differences between the measured values ​​and the mean of the measured values, and the residual sum of squares is the sum of squares of the differences between the measured values ​​and the predicted values.

[0052] The method for adjusting the coefficient of determination is: ;in, represents the adjusted coefficient of determination, represents the number of data points in the area that needs to be watered, Indicates the number of regression coefficients of data points in the area that needs to be irrigated. The number of regression coefficients of data points is calculated by finding the number of regression coefficients calculated when the spraying amount is obtained from the currently calculated data, and the number of all currently collected data points minus the number of regression coefficients to adjust the current determination coefficient.

[0053] The method for setting the irrigation proportion coefficient is to obtain the change curve of the spraying amount during the cultivation period, calculate the water distribution uniformity corresponding to the spraying amount during the cultivation period, and output the calculated water distribution uniformity as the irrigation proportion coefficient.

[0054] ;in, Indicates the uniformity of water distribution of the spraying amount, represents the standard deviation of all spraying amounts during the cultivation period, Represents the average of all spraying amounts.

[0055] The method of setting watering instructions is based on the watering coefficient and the watering ratio coefficient; the watering coefficient and the watering ratio coefficient of the current cultivation cycle are obtained, and the change values ​​of the watering coefficient and the watering ratio coefficient in the current cultivation cycle and the adjacent cultivation cycle are compared, and the spraying amount with the smallest change value of the watering coefficient and the watering ratio coefficient is used as the currently set watering instruction.

[0056] At this time, by calculating the determination coefficient and irrigation ratio coefficient of each spraying area, the spraying amount of each area can be accurately controlled to ensure that water resources are effectively used where needed and reduce waste; excessive or insufficient irrigation may have a negative impact on the growth of crops. By accurately controlling the amount of irrigation, the health of crops can be protected and the yield and quality can be increased; by considering the impact of environmental factors on crop growth, the irrigation strategy can be adjusted to adapt to different environmental conditions, thereby improving the environmental adaptability of crops.

[0057] Suppose there is a large plantation where crops need to be irrigated; the traditional irrigation method may be to water the entire plantation uniformly, but this method may result in over-irrigation in some areas and under-irrigation in other areas.

[0058] With the current settings, the plantation can be divided into multiple spraying areas, and the irrigation coefficient and irrigation ratio coefficient for each area can be calculated. Based on these data, a precise irrigation plan can be made to ensure that each area receives the appropriate amount of water resources. For example, for areas close to water sources, less irrigation may be required due to their higher soil moisture; while for areas far from water sources and with lower soil moisture, more irrigation may be required.

[0059] In this way, it can be ensured that every crop in the plantation receives the right amount of water, thereby increasing the growth rate, yield and fruit quality of the crops; at the same time, since the waste of water resources is reduced, the irrigation cost can also be reduced and the economic benefits can be improved.

[0060] The implementation method for determining the final selected watering strategy is as follows: judging the change value of the current growth environment data, when the change value of the growth environment data is within an acceptable range, using the current watering instruction as the output watering strategy; if the change value of the growth environment data is less than the lower limit of the acceptable range, using the watering strategy with the highest similarity between the last implemented watering instruction and the preset solution library as the output watering strategy; if the change value of the growth environment data is greater than the upper limit of the acceptable range, using the median value of the adjacent watering instructions of the current watering instruction as the output watering strategy.

[0061] Specifically, the Pearson correlation coefficient is calculated by using the data in the last implemented irrigation instruction and the data of the irrigation strategies in the preset solution library to obtain the similarity, and the irrigation strategy with the largest Pearson correlation coefficient value is used as the irrigation strategy with the highest similarity.

[0062] Suppose there is a vegetable greenhouse where a variety of vegetables are grown. The watering strategy needs to be determined based on the environmental data in the greenhouse. The environmental data in the greenhouse includes soil moisture, temperature, CO2 concentration, etc. These data are monitored in real time through sensors.

[0063] Set acceptable range of environmental data changes, such as the acceptable range of soil moisture changes is ±5%; establish a preset program library that includes irrigation strategies under different environmental conditions.

[0064] Monitor the environmental data in the greenhouse in real time and calculate the change value compared with the last monitored data; when it is found that the change value of soil moisture is within the acceptable range, for example, a change of 3%, continue to execute the current watering instruction; if the change value of soil moisture is lower than the lower limit of the acceptable range, for example, a change of -6%, select the watering strategy with the highest similarity to the current environmental conditions from the preset solution library for execution; if the change value of soil moisture is higher than the upper limit of the acceptable range, for example, a change of +7%, calculate the median value of the current watering instruction and the adjacent watering instruction as the new watering strategy.

[0065] Based on the above decisions, the corresponding watering strategy is implemented; environmental data is continuously monitored, and the watering strategy is adjusted in real time according to data changes to reduce the workload of managers and improve management efficiency.

[0066] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations on the present invention. A person skilled in the art may make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention and they are still covered by the protection scope of the present invention.

Claims

1. An Internet-based intelligent irrigation system for uniform cultivation, characterized in that: include: The data acquisition module is used to collect the growth environment data of crops during their growth and determine the temperature, humidity, light and soil moisture content of the soil in which the crops grow; A state monitoring module is used to determine the changes in the spraying amount and growth environment data corresponding to each cultivation cycle during the growth of crops, and obtain a correlation curve between the spraying amount and the growth environment data; The curve analysis module is used to analyze the correlation curve, determine the growth model of crops under each preset environmental condition, judge the current water demand of crops, and generate irrigation instructions corresponding to the water demand; The instruction execution module is used to execute the generated watering instructions and monitor the change value of the growth environment data of the crops after the watering instructions are executed; The feedback adjustment module is used to determine the final irrigation strategy according to the change value of the growth environment data and the current state of the crops; The method of determining the current water demand of crops and generating the irrigation instructions corresponding to the water demand includes: recording the change curve of the spraying amount in each cultivation cycle, determining the irrigation coefficient and the irrigation ratio coefficient in each cultivation cycle; setting the irrigation instructions according to the irrigation coefficient and the irrigation ratio coefficient; The area currently requiring irrigation is divided into multiple spraying areas, and the spraying areas are set in the form of a Tyson polygon. The residual sum of squares and the total sum of squares of the spraying amount of the corresponding spraying area under the cultivation cycle are obtained in turn, and the determination coefficient corresponding to the spraying amount is calculated, and the determination coefficient is adjusted according to the number of data points in the current cultivation cycle, and the adjusted determination coefficient is used as the current irrigation coefficient; The determination coefficient of the spraying amount is expressed as: ;in, represents the coefficient of determination, represents the residual sum of squares of the spraying amount in the jth spraying area, represents the standard value of the residual sum of squares of the spraying amount, represents the total square sum of the spraying amount in the jth spraying area, It represents the standard value of the total sum of squares of the spraying amount; The method for adjusting the coefficient of determination is: ;in, represents the adjusted coefficient of determination, represents the number of data points in the area that needs to be watered, Indicates the number of regression coefficients for data points in the area that needs watering; The method for setting the irrigation ratio coefficient is to obtain the variation curve of the spraying amount during the cultivation period, calculate the water distribution uniformity corresponding to the spraying amount during the cultivation period, and output the calculated water distribution uniformity as the irrigation ratio coefficient; ;in, Indicates the uniformity of water distribution of the spraying amount, represents the standard deviation of all spraying amounts during the cultivation period, It represents the average of all spraying amounts; Set multiple collectors on the area that currently needs to be irrigated, and divide the entire area that needs to be irrigated into several spraying areas according to the positions of the collectors. Each spraying area corresponds to a group of collectors. When using Taylor polygons to adjust and set the area that needs to be irrigated, the polygon formed is an irregular pentagon. For the irrigation coefficient of each spraying area, it is necessary to obtain the nearest spraying area to this spraying area for calculation. Therefore, six spraying areas are selected, that is, the value range of j is set to 1 to 6; How to set watering instructions; Get the irrigation coefficient and irrigation ratio coefficient of the current cultivation cycle, compare the change values ​​of the irrigation coefficient and irrigation ratio coefficient in the current cultivation cycle with those in the adjacent cultivation cycle, and take the spraying amount with the smallest change value of the irrigation coefficient and irrigation ratio coefficient as the currently set irrigation instruction.

2. The Internet-based uniform cultivation intelligent irrigation system according to claim 1, characterized in that: The implementation method of the correlation curve in the status monitoring module includes recording the specific dosage of each spraying, including the type of pesticides and fertilizers used and their dosage; determining the changes in temperature, humidity, light intensity and soil moisture content after each spraying, and using the corresponding data as the current output correlation curve.

3. The Internet-based uniform cultivation intelligent irrigation system according to claim 1, characterized in that: The implementation method of analyzing the correlation curve in the curve analysis module includes sequentially obtaining a first correlation coefficient between the spraying amount and temperature, a second correlation coefficient between the spraying amount and humidity, a third correlation coefficient between the spraying amount and light intensity, and a fourth correlation coefficient between the spraying amount and soil moisture content; The first correlation coefficient, the second correlation coefficient, the third correlation coefficient and the fourth correlation coefficient are processed to obtain the correlation coefficients between the spraying amount and the temperature, humidity, light intensity and soil moisture content.

4. The Internet-based uniform cultivation intelligent irrigation system according to claim 3, characterized in that: The first correlation coefficient is obtained by dividing the spraying amount and temperature into multiple groups of data and inputting them into the multiple regression model in turn to obtain the regression coefficients corresponding to multiple groups of first correlation coefficients: ； in, Indicates the spraying amount. , , , represents the regression coefficient between spraying amount and temperature, , , Indicates temperature, represents the error term corresponding to the spraying amount and temperature, represents the number of regression coefficients; The calculation method of the second correlation coefficient, the third correlation coefficient and the fourth correlation coefficient is the same as that of the first correlation coefficient, and the correlation coefficients of the first correlation coefficient, the second correlation coefficient, the third correlation coefficient and the fourth correlation coefficient are calculated using the Pearson correlation coefficient.

5. The Internet-based uniform cultivation intelligent irrigation system according to claim 4, characterized in that: Calculate the correlation between the regression coefficients of the first correlation coefficient and the second correlation coefficient: ； in, represents the correlation coefficient corresponding to the first correlation coefficient and the second correlation coefficient, represents the i-th regression coefficient in the first correlation coefficient, represents the average of the regression coefficients in the first correlation coefficient, represents the i-th regression coefficient in the second correlation coefficient, represents the average value of the second correlation coefficient, represents the number of regression coefficients, ; Then, the correlation coefficients corresponding to the first correlation coefficient and the third correlation coefficient are calculated in turn according to the calculation method of the correlation coefficients corresponding to the first correlation coefficient and the second correlation coefficient. , the correlation coefficients corresponding to the first correlation coefficient and the fourth correlation coefficient , the correlation coefficients corresponding to the second correlation coefficient and the third correlation coefficient , the correlation coefficients corresponding to the second correlation coefficient and the fourth correlation coefficient , the correlation coefficients corresponding to the third correlation coefficient and the fourth correlation coefficient ; A set of data corresponding to the maximum value of the weighted average of these six correlation coefficients is used as the target data for correlation curve analysis.

6. An Internet-based uniform cultivation intelligent irrigation system according to claim 5, characterized in that: The implementation methods for determining the growth model of crops under each preset environmental condition include: The target data of the correlation curve is obtained, and the interval between the two ends of the time point corresponding to the target data is set as the cultivation cycle. The average value of the corresponding growth environment data in each cultivation cycle is used as the growth model of the crop under each preset environmental condition.

7. The Internet-based uniform cultivation intelligent irrigation system according to claim 1, characterized in that: The implementation method of determining the final selected watering strategy is as follows: judging the change value of the current growth environment data, when the change value of the growth environment data is within an acceptable range, using the current watering instruction as the output watering strategy, if the change value of the growth environment data is less than the lower limit of the acceptable range, using the watering instruction implemented last time and the watering strategy with the highest similarity in the preset solution library as the output watering strategy; If the change value of the growth environment data is greater than the upper limit of the acceptable range value, the median value of the adjacent watering instructions of the current watering instruction is used as the output watering strategy; The Pearson correlation coefficient is calculated by using the data in the last implemented watering instruction and the data of the watering strategies in the preset solution library to obtain the similarity, and the watering strategy with the largest Pearson correlation coefficient value is used as the watering strategy with the highest similarity.

Images