Water valve operation control method and device based on Internet of Things and computer equipment

Abstract

The invention relates to a water valve operation control method and device based on the Internet of Things and computer equipment, and aims to improve the efficiency and flexibility of an agricultural irrigation system. According to the method, detailed irrigation plan data and weather information are firstly obtained, then the irrigation requirement of the day is dynamically adjusted based on the data so as to deal with weather changes, the system can generate optimized irrigation data by analyzing rainfall, temperature, humidity, wind speed and other factors in real time, a control instruction is generated accordingly, and finally, the irrigation plan data and the weather information are obtained. The instructions are sent to the electronic control valves of the irrigation areas, accurate water valve operation is achieved, and the method not only improves automation and adaptability of irrigation, but also effectively reduces waste of water resources, improves the crop growth environment and improves farmland productivity.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a water valve operation control method, device and computer equipment based on the Internet of Things. Background Art

[0002] The development of IoT technology has brought new opportunities to agricultural irrigation systems. Traditional irrigation methods usually rely on manual operation, which is inefficient and cannot accurately control irrigation time and water volume, resulting in serious waste of water resources. In addition, due to the inability to obtain and analyze environmental data in real time, it is difficult to dynamically adjust the irrigation process according to actual needs, which may lead to over-irrigation or under-irrigation, affecting the growth of crops and the overall productivity of farmland.

[0003] Although some automated irrigation systems currently available on the market can pre-set irrigation plans, most of these systems rely on fixed programs and lack flexibility, making it difficult to adapt to different weather conditions and changes in farmland needs. Especially when faced with complex farmland environments and multi-region irrigation needs, the existing systems’ insufficient response speed and accuracy may result in untimely or inaccurate irrigation in some areas, which in turn affects the yield and quality of crops.

[0004] In this context, the water valve operation control method based on the Internet of Things has gradually become a research hotspot. This method can accurately control the operation of water valves in each irrigation area by acquiring irrigation plan data in real time and generating control instructions. However, current research still has problems with imperfect data processing and control algorithms. How to improve the flexibility and adaptability of the system while ensuring irrigation efficiency is still a key technical problem that needs to be solved. Summary of the invention

[0005] The main purpose of the present invention is to provide a water valve operation control method, device and computer equipment based on the Internet of Things, so as to solve how to realize an efficient, flexible agricultural irrigation system that can adapt to different environmental conditions by optimizing data processing and control algorithms with the support of the Internet of Things technology, so as to solve the problems of inefficiency and waste of water resources in traditional irrigation methods.

[0006] To achieve the above-mentioned purpose, the present invention provides a water valve operation control method based on the Internet of Things, comprising the following steps: obtaining irrigation plan data sent by a target device, wherein the irrigation plan data at least includes: multiple irrigation areas, and irrigation parameters corresponding to each of the irrigation areas, and the irrigation parameters at least include: irrigation frequency, irrigation duration and irrigation flow; determining the irrigation data of the day based on the irrigation plan data, and obtaining weather information, wherein the weather information includes: weather data of a preset number of days before and after the day, and the weather data at least includes: rainfall, temperature, humidity and wind speed; adjusting the irrigation data of the day based on the weather information to obtain updated irrigation data; generating a control instruction based on the updated irrigation data, and sending the control instruction to the irrigation electronic control valves corresponding to the multiple irrigation areas, wherein the irrigation electronic control valve is used to open / close the faucet in response to the control instruction to irrigate the multiple irrigation areas.

[0007] Furthermore, before adjusting the irrigation data of the day based on the weather information to obtain updated irrigation data, the method also includes: determining each data point in the weather data in the weather information, and determining the size of the neighborhood corresponding to each data point; calculating the distance value from each data point to the nearest neighborhood, and calculating the local density estimate of the data point based on the distance value; calculating the relative density difference between each data point and other data points in the neighborhood based on the local density estimate; determining in turn whether the relative density difference of each data point is greater than a preset threshold, and eliminating data points in the weather information whose relative density difference is greater than the preset threshold.

[0008] Furthermore, based on the weather information, the irrigation data of the day is adjusted to obtain updated irrigation data, including: inputting the data value of each weather data in the weather information into the corresponding preset membership function, and calculating the membership of each data value in each fuzzy set; calculating and processing the membership of each data value in each fuzzy set according to preset fuzzy rules to obtain the influence factors corresponding to each data value in each fuzzy set; calculating the combined influence factors corresponding to each data value based on the membership and influence factors of each data value in each fuzzy set; integrating the combined influence factors corresponding to each data value to obtain the comprehensive influence factors, and adjusting the irrigation data of the day based on the comprehensive influence factors to obtain updated irrigation data.

[0009] Furthermore, the data value of each weather data in the weather information is input into the corresponding preset membership function, the membership of each data value in each fuzzy set is calculated, and based on the membership and influence factor of each data value in each fuzzy set, the combined influence factor corresponding to each data value is calculated, including: using a linear normalization formula to standardize the data value of each weather data in the weather information, mapping the data values ​​of weather data of different scales to a preset interval to obtain converted data values; extracting a first type of data value, a second type of data value, a third type of data value and a fourth type of data value from the converted data values, wherein the first type of data value is associated with the rainfall, the second type of data value is associated with the temperature, the third type of data value is associated with the humidity, and the fourth type of data value is associated with the wind speed; inputting the first type of data value into the rainfall corresponding membership function. The membership function corresponding to the temperature is used to generate the membership of the first type of data value in the first type of fuzzy set, and the membership is integrated into the first type of membership matrix, wherein the first type of fuzzy set is associated with the rainfall; the second type of data value is input into the membership function corresponding to the temperature, the membership of the second type of data value in the second type of fuzzy set is generated, and the membership is integrated into the second type of membership matrix, wherein the second type of fuzzy set is associated with the temperature; the third type of data value is input into the membership function corresponding to the humidity, the membership of the third type of data value in the third type of fuzzy set is generated, and the membership is integrated into the third type of membership matrix, wherein the third type of fuzzy set is associated with humidity; the fourth type of data value is input into the membership function corresponding to the wind speed, the membership of the fourth type of data value in the fourth type of fuzzy set is generated, and the membership is integrated into the fourth type of membership matrix, wherein the fourth type of fuzzy set is associated with the wind speed.

[0010] Furthermore, according to the preset fuzzy rules, the membership of each data value in each fuzzy set is calculated and processed to obtain the influence factors corresponding to each data value in each fuzzy set, including: determining the fuzzy rules matching the first-class membership matrix in the preset fuzzy rules, and activating the determined fuzzy rules; assigning weights to each activated fuzzy rule, and calculating the conditional part of each activated fuzzy rule based on the first-class membership matrix to obtain the first-class overall membership; using the calculated first-class overall membership as the weight value, combining each of the activated The result part of the activated fuzzy rules is calculated and processed to generate a first preliminary influencing factor, and integrated into a first type of preliminary influencing factor matrix; the preset fuzzy rules are reset, and in the reset fuzzy rules, the fuzzy rules matching the second type of membership matrix are determined, and the determined fuzzy rules are activated; a weight is assigned to each activated fuzzy rule, and the condition part of each activated fuzzy rule is calculated and processed based on the second type of membership matrix to obtain a second type of overall membership; the calculated second type of overall membership is used as a weight value, and is combined with the result part of each activated fuzzy rule to calculate Processing, generating a second preliminary influencing factor, and integrating it into a second preliminary influencing factor matrix; resetting the preset fuzzy rules, and determining the fuzzy rules that match the third membership matrix in the reset fuzzy rules, and activating the determined fuzzy rules; assigning weights to each activated fuzzy rule, and calculating and processing the conditional part of each activated fuzzy rule based on the third membership matrix to obtain the third overall membership; using the calculated third overall membership as a weight value, and calculating and processing in combination with the result part of each activated fuzzy rule, generating a third preliminary influencing factor, and Integrate into a third type of preliminary influencing factor matrix; reset the preset fuzzy rules, and determine the fuzzy rules that match the fourth type of membership matrix in the reset fuzzy rules, and activate the determined fuzzy rules; assign weights to each activated fuzzy rule, and calculate the conditional part of each activated fuzzy rule based on the fourth type of membership matrix to obtain the fourth type of overall membership; use the calculated fourth type overall membership as the weight value, combine it with the result part of each activated fuzzy rule to calculate and process, generate a fourth preliminary influencing factor, and integrate into a fourth type of preliminary influencing factor matrix.

[0011] Furthermore, the combined influencing factors corresponding to the various data values ​​are integrated to obtain a comprehensive influencing factor, including: normalizing the first category of preliminary influencing factor matrix, the second category of preliminary influencing factor matrix, the third category of preliminary influencing factor matrix and the fourth category of preliminary influencing factor matrix respectively to obtain the normalized first category of preliminary influencing factor matrix, the second category of preliminary influencing factor matrix, the third category of preliminary influencing factor matrix and the fourth category of preliminary influencing factor matrix; performing weighted averaging on the normalized first category of preliminary influencing factor matrix, the second category of preliminary influencing factor matrix, the third category of preliminary influencing factor matrix and the fourth category of preliminary influencing factor matrix to obtain the comprehensive influencing factor.

[0012] Furthermore, based on the comprehensive influencing factor, the irrigation data of the day is adjusted to obtain updated irrigation data, including: determining sensitive values ​​of different irrigation parameters in the irrigation data, wherein the sensitive values ​​represent the relative importance of different irrigation parameters in the irrigation data to the irrigation effect; determining an adjustment coefficient corresponding to each of the irrigation parameters based on the sensitive values ​​of the different irrigation parameters and the comprehensive influencing factor; and adjusting different irrigation parameters in the irrigation data of the day based on the adjustment coefficient corresponding to each irrigation parameter to obtain updated irrigation data.

[0013] The present invention also provides a water valve operation control device based on the Internet of Things, comprising the following steps: a first acquisition unit, used to acquire irrigation plan data sent by a target device, wherein the irrigation plan data at least includes: multiple irrigation areas, and irrigation parameters corresponding to each of the irrigation areas, and the irrigation parameters at least include: irrigation frequency, irrigation duration and irrigation flow; a second acquisition unit, used to determine the irrigation data of the day based on the irrigation plan data, and acquire weather information, wherein the weather information includes: weather data of a preset number of days before and after the day, and the weather data at least includes: rainfall, temperature, humidity and wind speed; an adjustment unit, used to adjust the irrigation data of the day based on the weather information to obtain updated irrigation data; a sending unit, used to generate a control instruction based on the updated irrigation data, and send the control instruction to the irrigation electronic control valves corresponding to the multiple irrigation areas, wherein the irrigation electronic control valve is used to open / close the faucet in response to the control instruction to irrigate the multiple irrigation areas.

[0014] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0015] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0016] The water valve operation control method, device and computer equipment based on the Internet of Things provided by the present invention, by obtaining detailed irrigation plan data sent by the target device, including multiple irrigation areas and their corresponding irrigation parameters (such as irrigation frequency, duration and flow), ensures that the operation of each irrigation area can be accurately configured according to specific needs. Secondly, combined with the weather information (such as rainfall, temperature, humidity and wind speed) of the preset days before and after the day, the method can dynamically adjust the irrigation data of the day. Through this adjustment, the system can effectively respond to the impact of weather changes on irrigation demand, avoid the problem of over-irrigation or insufficient irrigation, and significantly improve the utilization efficiency of water resources. Furthermore, the control instructions generated based on the updated irrigation data can accurately control the water valves of each irrigation area, ensuring that each area is irrigated according to the optimized plan, thereby improving the overall irrigation efficiency and effect. This method not only improves the automation level and response speed of the irrigation system, but also enhances the adaptability of the system in a complex farmland environment, ultimately improving the growth environment of crops, and improving the productivity and resource utilization efficiency of farmland. In summary, the technical solution of the present invention realizes precise control of the agricultural irrigation process by comprehensively utilizing Internet of Things technology and real-time data analysis, and solves the problems of inefficiency and waste of resources in traditional irrigation methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of the steps of a water valve operation control method based on the Internet of Things in one embodiment of the present invention; Figure 2 This is a structural block diagram of a water valve operation control device based on the Internet of Things in one embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0018] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] Reference Figure 1 The embodiment of the present application provides a water valve operation control method based on the Internet of Things, comprising the following steps: S1, obtaining irrigation plan data sent by a target device, wherein the irrigation plan data at least includes: multiple irrigation areas, and irrigation parameters corresponding to each of the irrigation areas, and the irrigation parameters at least include: irrigation frequency, irrigation duration and irrigation flow.

[0021] S2, determining the irrigation data for the day based on the irrigation plan data, and acquiring weather information, wherein the weather information includes: weather data of a preset number of days before and after the day, and the weather data includes at least: rainfall, temperature, humidity and wind speed.

[0022] S3, adjusting the irrigation data of the day based on the weather information to obtain updated irrigation data.

[0023] S4, generating a control instruction based on the updated irrigation data, and sending the control instruction to the irrigation electronic control valves corresponding to the multiple irrigation areas, wherein the irrigation electronic control valve is used to open / close the faucet in response to the control instruction to irrigate the multiple irrigation areas.

[0024] That is, in the embodiment of the present application, the water valve operation control method based on the Internet of Things realizes accurate and flexible irrigation control through a series of steps, especially when facing complex farmland environments and multi-region irrigation needs, it shows high adaptability and efficiency. The implementation process of the method is explained in detail below, and is illustrated with specific examples.

[0025] First, step S1 involves obtaining the irrigation plan data sent by the target device. The irrigation plan data is the basic information source of the system, which includes multiple irrigation areas and their corresponding irrigation parameters. Irrigation parameters are key factors in determining the irrigation effect, and usually include irrigation frequency, irrigation duration, and irrigation flow. For example, in a farmland with multiple crop planting areas, different crops have different water requirements, so the irrigation parameters of each irrigation area may be different. One area may need to be irrigated twice a day, each irrigation lasting 30 minutes, and the flow rate is set to 100 liters per hour, while another area may only need to be irrigated once a day, each irrigation lasting 15 minutes, and the flow rate is set to 50 liters per hour. These parameters will directly affect the operation of the irrigation system and determine the effect of irrigation.

[0026] Next, in step S2, the system determines the irrigation data for the day based on the acquired irrigation plan data, and obtains weather information. Weather information is an important basis for dynamic adjustment of the irrigation plan. Traditional irrigation systems often lead to rigid irrigation plans and cannot be adjusted according to actual conditions due to the lack of real-time analysis of weather information. However, this system can more accurately evaluate the environmental conditions of the day by acquiring weather data including rainfall, temperature, humidity and wind speed. For example, if heavy rain is predicted on that day, the system may reduce or completely cancel the irrigation operation of that day according to the amount of rainfall to avoid waste of water resources. At the same time, changes in temperature and humidity will also affect the evaporation rate of soil moisture, thereby affecting the crop's demand for water. Therefore, real-time acquisition and analysis of weather information is the basis for ensuring the flexibility and accuracy of the irrigation system.

[0027] In step S3, based on the weather information obtained, the system will adjust the irrigation data for the day. This step is an important part of achieving irrigation flexibility. By combining weather information with irrigation plan data, the system can optimize and adjust the irrigation plan according to real-time conditions. For example, if a certain area is expected to have a high wind speed, the system may consider increasing the irrigation frequency or extending the irrigation time in that area to compensate for the evaporation caused by the increased wind speed. Conversely, if the temperature is expected to be low and the humidity is high on that day, the system may reduce the amount of irrigation to avoid damage to the crop roots caused by excessive irrigation. The adjusted irrigation data will be closer to actual needs, thereby better promoting the healthy growth of crops.

[0028] Step S4 is to generate control instructions and send them to the corresponding irrigation electronic control valve. The control instructions are operation instructions generated after the aforementioned data processing, which determine the specific operation of each irrigation area. The system generates instructions based on the updated irrigation data, such as "the control valve of area A is opened between 9:00 and 9:30, and the flow rate is set to 100 liters / hour", and sends these instructions to the electronic control valves in each irrigation area. After receiving the instructions, the electronic control valve will open or close the faucet according to the set parameters to complete the irrigation operation of the designated area. It is worth mentioning that these control instructions can realize automated and precise operations, greatly reducing the errors and burdens of manual operations. For example, in the case of irrigation in multiple areas, the system can send different control instructions to the control valves in different areas at the same time to ensure that each area receives the right amount of irrigation at the most appropriate time.

[0029] Through the above steps, the water valve operation control method based on the Internet of Things provided by the embodiment of the present application can realize efficient, accurate and flexible irrigation operations in a complex farmland environment. It not only reduces the waste of water resources, but also ensures the best growth environment for crops and improves the overall productivity of farmland through the acquisition and processing of real-time data. For example, assuming that a large farmland is divided into several irrigation areas and a variety of different crops are planted, the system can automatically generate corresponding irrigation plans by obtaining irrigation plan data and real-time weather information in different areas. For example, area A is planted with rice that requires more water, while area B is planted with drought-resistant corn. The system will adjust according to the weather forecast to ensure that the irrigation of each area achieves the best effect. In this way, even in the same farmland, each crop area can be irrigated accurately and timely, thereby improving the production efficiency of the overall farmland.

[0030] In one example, before adjusting the irrigation data of the day based on the weather information to obtain updated irrigation data, the method also includes: determining each data point in the weather data in the weather information, and determining the size of the neighborhood corresponding to each data point; calculating the distance value from each data point to the nearest neighborhood, and calculating the local density estimate of the data point based on the distance value; calculating the relative density difference between each data point and other data points in the neighborhood based on the local density estimate; determining in turn whether the relative density difference of each data point is greater than a preset threshold, and eliminating data points in the weather information whose relative density difference is greater than the preset threshold.

[0031] That is, in the embodiment of the present application, the process of adjusting the irrigation data based on weather information is further refined, and a series of data processing steps are added to improve the accuracy and reliability of irrigation decisions. These steps involve density analysis and outlier removal of weather data to ensure that the irrigation plan generated is more accurate and effective. The implementation process of these steps is explained in detail below and illustrated by specific examples.

[0032] First, before adjusting the irrigation data for the day, the acquired weather information needs to be analyzed in depth. Weather information usually includes multiple data points, such as rainfall, temperature, humidity, and wind speed, which reflect environmental changes in the next few days. However, due to the complexity of weather data and the possible existence of noise or outliers, directly using this data to adjust the irrigation plan may lead to inaccurate results. To overcome this problem, each data point in the weather information must first be identified, and the neighborhood size corresponding to each data point must be further determined. The neighborhood size can be understood as the influence range of the data point in the data space, which is usually defined by setting a certain distance threshold. For example, when analyzing rainfall data, if the neighborhood size of a data point is set to 10 kilometers, this means that the influence range of the data point covers the rainfall within 10 kilometers around it.

[0033] Next, the system needs to calculate the distance value from each data point to the nearest neighbor. This distance value reflects the relationship between data points. The shorter the distance, the stronger the correlation between data points. Taking wind speed as an example, suppose that the wind speed data point A in a certain area is only 2 kilometers away from the nearest neighbor data point B, which means that the two are geographically close and may be affected by similar environmental conditions. Therefore, the data at point A will have a greater impact on irrigation decisions within the neighborhood. In this way, the importance of each data point within its neighborhood can be determined.

[0034] After obtaining the distance value, the system will further calculate the local density estimate for each data point. The local density estimate is calculated based on the distance distribution between the data point and other data points in its neighborhood, and it reflects the density state of a data point in the entire data set. For example, if there are a large number of dense data points around the temperature data point C in a certain area, then the local density estimate of C will be high, indicating that the temperature change in this area may be relatively stable and representative. Conversely, if there are only sparse data points around the temperature data point D in a certain area, then the local density estimate of D will be low, indicating that the temperature data in this area may be greatly affected by noise or outliers.

[0035] After obtaining the local density estimate, the system then needs to calculate the relative density difference between each data point and other data points in the neighborhood. The relative density difference is used to measure the degree of abnormality of a data point in its neighborhood. For example, when analyzing humidity data, assuming that the local density estimate of data point E is significantly different from most of the data points in its neighborhood, then the relative density difference of point E will be large. This may mean that the data at point E is abnormal, such as being affected by sudden weather changes or sensor failures.

[0036] Based on the calculated relative density difference, the system will determine in turn whether the relative density difference of each data point is greater than the preset threshold. If the relative density difference of a data point exceeds the preset threshold, the data point will be regarded as an anomaly and removed from the weather information. This elimination process is crucial because it can effectively filter out unreliable data caused by noise or abnormal phenomena, thereby improving the accuracy of subsequent irrigation data adjustments. For example, in rainfall data processing, if the relative density difference of data point F is much higher than the threshold, it indicates that the rainfall at this point is abnormal. For example, if a local extreme rainfall event occurs, the data at point F will be eliminated to prevent the abnormal data from misleading the overall irrigation plan.

[0037] Through the above steps, the system has comprehensively analyzed and processed the weather information before adjusting the irrigation data for the day. This process ensures that only verified and screened high-quality data is used to generate a more accurate irrigation plan. For example, suppose a farm is divided into multiple irrigation areas, and the weather information obtained by the system shows that in the next few days, the wind speed data in area G will fluctuate abnormally. Through density estimation and outlier removal, the system identifies that these abnormal fluctuations may be caused by local climate anomalies or equipment failures, so these abnormal data points are removed, and ultimately excessive or insufficient irrigation caused by erroneous data is avoided when adjusting the irrigation plan. In this way, not only the accuracy of irrigation is improved, but also it ensures that crops grow under optimal conditions, thereby improving the productivity of farmland.

[0038] In one example, based on the weather information, the irrigation data of the day is adjusted to obtain updated irrigation data, including: inputting the data value of each weather data in the weather information into the corresponding preset membership function, and calculating the membership of each data value in each fuzzy set; calculating and processing the membership of each data value in each fuzzy set according to preset fuzzy rules to obtain the influence factors corresponding to each data value in each fuzzy set; calculating the combined influence factors corresponding to each data value based on the membership and influence factors of each data value in each fuzzy set; integrating the combined influence factors corresponding to each data value to obtain the comprehensive influence factors, and adjusting the irrigation data of the day based on the comprehensive influence factors to obtain updated irrigation data.

[0039] In the embodiment of the present application, the process of adjusting the irrigation data of the day based on weather information is further refined, and the specific method involves combining weather data with fuzzy logic control to adjust irrigation parameters more accurately and flexibly. This method not only considers the individual impact of each weather data, but also comprehensively analyzes their interactive impact through fuzzy logic processing, thereby optimizing irrigation decisions. The implementation of this process is explained in detail below, and its application is illustrated by specific examples.

[0040] First, the data values ​​of the acquired weather information, such as rainfall, temperature, humidity and wind speed, are input into the corresponding preset membership functions. The membership function is the core part of fuzzy logic control, which is used to convert accurate weather data into membership in fuzzy sets. This process enables the system to handle uncertainty and complexity. For example, for temperature data, a membership function can be preset to divide the temperature into three fuzzy sets: "low temperature", "medium temperature" and "high temperature". Assuming that the current temperature is 28°C, the temperature may have a certain membership in both the "medium temperature" and "high temperature" fuzzy sets, such as a membership of 0.7 in the "medium temperature" set and a membership of 0.3 in the "high temperature" set. This membership calculation enables the temperature data to be fuzzy processed, thereby reflecting its degree of influence under different climate conditions.

[0041] Next, the system calculates the membership of each data value in different fuzzy sets according to the preset fuzzy rules to obtain the corresponding influence factors of each data value in each fuzzy set. Fuzzy rules are usually preset by the expert system and adjusted according to different irrigation needs and climatic conditions. For example, suppose the irrigation system sets a fuzzy rule: "If the temperature is high and the humidity is low, increase the irrigation amount." In this case, when the temperature and humidity data of a certain area are fuzzified, the system will calculate the corresponding influence factors based on the membership, reflecting the weight of the influence of these data on the irrigation decision.

[0042] The system then calculates the combined influence factor for each data value based on its membership and influence factors in each fuzzy set. The combined influence factor is the result of the interaction of the weather data through fuzzy logic, which takes into account the combined influence of multiple meteorological conditions. For example, in the temperature and humidity example above, suppose that on a certain day, the temperature has a membership of 0.6 in the "high temperature" set and the humidity has a membership of 0.8 in the "low humidity" set. After calculation through fuzzy rules, these memberships may generate a higher combined influence factor, indicating that the area needs to increase irrigation on that day.

[0043] Finally, the system integrates the combined influencing factors corresponding to each data value to obtain a comprehensive influencing factor. The comprehensive influencing factor is the result of a comprehensive analysis of all relevant weather conditions and is directly used to adjust the irrigation plan. Based on this comprehensive influencing factor, the system can dynamically adjust irrigation parameters, such as irrigation time and water volume, to generate updated irrigation data. For example, if the system calculates a comprehensive influencing factor of 0.75 for a certain farmland area after comprehensively considering temperature, humidity, wind speed and rainfall, this means that the area needs to increase irrigation volume on that day to cope with high temperature and low humidity weather conditions. Therefore, the irrigation system will adjust the irrigation duration and water flow according to this influencing factor to ensure that the crops can get enough water on that day.

[0044] In this way, the irrigation system can not only adjust according to real-time weather information, but also respond flexibly to different weather conditions, avoiding insufficient or excessive irrigation due to fluctuations in a single factor. The application of this fuzzy logic control greatly improves the accuracy and adaptability of irrigation decisions, thereby effectively improving the productivity of farmland and the efficiency of water resource utilization.

[0045] In one example, the data value of each weather data in the weather information is input into a corresponding preset membership function, the membership of each data value in each fuzzy set is calculated, and based on the membership and influence factor of each data value in each fuzzy set, the combined influence factor corresponding to each data value is calculated, including: using a linear normalization formula to standardize the data value of each weather data in the weather information, mapping the data values ​​of weather data of different scales to a preset interval to obtain converted data values; extracting a first type of data value, a second type of data value, a third type of data value and a fourth type of data value from the converted data values, wherein the first type of data value is associated with the rainfall, the second type of data value is associated with the temperature, the third type of data value is associated with the humidity, and the fourth type of data value is associated with the wind speed; inputting the first type of data value into the rainfall In the corresponding membership function, the membership of the first type of data value in the first type of fuzzy set is generated and integrated into a first type of membership matrix, wherein the first type of fuzzy set is associated with the rainfall; the second type of data value is input into the membership function corresponding to the temperature, the membership of the second type of data value in the second type of fuzzy set is generated, and integrated into a second type of membership matrix, wherein the second type of fuzzy set is associated with the temperature; the third type of data value is input into the membership function corresponding to the humidity, the membership of the third type of data value in the third type of fuzzy set is generated, and integrated into a third type of membership matrix, wherein the third type of fuzzy set is associated with humidity; the fourth type of data value is input into the membership function corresponding to the wind speed, the membership of the fourth type of data value in the fourth type of fuzzy set is generated, and integrated into a fourth type of membership matrix, wherein the fourth type of fuzzy set is associated with the wind speed.

[0046] That is, in the embodiments of the present application, it is explained in detail how to adjust the irrigation data of the day based on weather information, which specifically involves data standardization, fuzzy processing and calculation of influencing factors. This process converts weather data of different scales into a unified interval and applies fuzzy logic control to generate accurate irrigation adjustment parameters to ensure the scientificity and adaptability of irrigation decisions. The following explains in detail how to implement these steps and illustrates them through specific examples.

[0047] First, the data values ​​in the weather information need to be standardized. Since different weather data (such as rainfall, temperature, humidity, wind speed) have different dimensions and scales, directly using these data for calculations may lead to errors. Therefore, the purpose of standardization is to map these data to a preset uniform interval, such as [0, 1], for subsequent processing. The linear normalization formula is usually used for this purpose. Through the formula, all weather data are converted to values ​​between 0 and 1, thereby eliminating the impact of dimensional differences.

[0048] Next, four categories of data values ​​are extracted from the converted data values: the first category of data values ​​is associated with rainfall, the second category of data values ​​is associated with temperature, the third category of data values ​​is associated with humidity, and the fourth category of data values ​​is associated with wind speed. Assume that the data values ​​after standardization are as follows: rainfall is 0.7, temperature is 0.5, humidity is 0.4, and wind speed is 0.6. These data values ​​will be assigned to the corresponding categories and processed separately.

[0049] These categorical data values ​​are then input into the corresponding membership functions for fuzzification. The membership function is used to calculate the degree of membership of each data value in its associated fuzzy set. The degree of membership indicates the degree to which a data value belongs to a fuzzy set, usually between 0 and 1. For example, for the fuzzy set of rainfall, three sets of "low rainfall", "medium rainfall" and "high rainfall" can be set. If the standardized rainfall data value is 0.7, then it may have a membership of 0.8 in the "high rainfall" set and a membership of 0.2 in the "medium rainfall" set. Similarly, the data values ​​of temperature, humidity and wind speed will also be fuzzified.

[0050] These memberships are integrated into corresponding membership matrices. The first membership matrix is ​​obtained by organizing the membership calculation results of rainfall. The second, third and fourth membership matrices are generated similarly, corresponding to the data of temperature, humidity and wind speed respectively. These membership matrices will be used as inputs of fuzzy rules in subsequent processing to help calculate the influencing factors of each weather data.

[0051] The membership matrix is ​​processed by fuzzy rules to calculate the impact factor of each data value. The impact factor reflects the specific degree of impact of each data value on the irrigation plan. For example, suppose the fuzzy rule stipulates that "if the temperature is high and the humidity is low, the irrigation amount needs to be increased." In this case, the system will combine the membership matrices of temperature and humidity to calculate the corresponding impact factor. Assuming that the high membership of temperature is 0.6 and the low membership of humidity is 0.4, after weighted processing based on fuzzy rules, a comprehensive impact factor, such as 0.5, can be obtained, which means that the irrigation amount needs to be relatively increased on that day.

[0052] Finally, the influencing factors of each weather data are integrated to obtain the comprehensive influencing factor. The comprehensive influencing factor is the result of comprehensive consideration of all relevant weather conditions and is used to adjust the irrigation data for the day. Assume that after the integration process, the system obtains a comprehensive influencing factor of 0.65, indicating that the amount of water needs to be increased in the irrigation plan for the day to adapt to the high temperature and low humidity conditions.

[0053] For example, when the rainfall in a farmland area is 0.7, the temperature is 0.5, the humidity is 0.4, and the wind speed is 0.6, after standardization, fuzzy processing, and calculation of influencing factors, the system will obtain the specific adjustment parameters that need to increase the irrigation amount. Through this comprehensive processing, the irrigation system can more accurately adjust the irrigation time and water volume, thereby ensuring that the crops can obtain appropriate moisture on the day, avoiding excessive or insufficient irrigation, and improving the production efficiency of the farmland and the growth environment of the crops.

[0054] In one example, according to preset fuzzy rules, the membership of each data value in each fuzzy set is calculated and processed to obtain the influence factors corresponding to each data value in each fuzzy set, including: determining the fuzzy rules matching the first-class membership matrix in the preset fuzzy rules, and activating the determined fuzzy rules; assigning weights to each activated fuzzy rule, and calculating the conditional part of each activated fuzzy rule based on the first-class membership matrix to obtain the first-class overall membership; using the calculated first-class overall membership as the weight value, combined with each of the The result part of the activated fuzzy rules is calculated and processed to generate a first preliminary influencing factor, and integrated into a first type of preliminary influencing factor matrix; the preset fuzzy rules are reset, and in the reset fuzzy rules, the fuzzy rules matching the second type of membership matrix are determined, and the determined fuzzy rules are activated; a weight is assigned to each activated fuzzy rule, and the condition part of each activated fuzzy rule is calculated and processed based on the second type of membership matrix to obtain a second type of overall membership; the calculated second type of overall membership is used as a weight value, and is combined with the result part of each activated fuzzy rule to calculate The method further comprises: performing calculation processing to generate a second preliminary influencing factor and integrating it into a second preliminary influencing factor matrix; resetting the preset fuzzy rules, and determining the fuzzy rules matching the third membership matrix in the reset fuzzy rules, and activating the determined fuzzy rules; assigning a weight to each activated fuzzy rule, and calculating the conditional part of each activated fuzzy rule based on the third membership matrix to obtain a third overall membership; using the calculated third overall membership as a weight value, and performing calculation processing in combination with the result part of each activated fuzzy rule to generate a third preliminary influencing factor, And integrated into the third type of preliminary influencing factor matrix; reset the preset fuzzy rules, and in the reset fuzzy rules, determine the fuzzy rules that match the fourth type of membership matrix, and activate the determined fuzzy rules; assign weights to each activated fuzzy rule, and calculate the conditional part of each activated fuzzy rule based on the fourth type of membership matrix to obtain the fourth type of overall membership; use the calculated fourth type overall membership as the weight value, combine with the result part of each activated fuzzy rule to calculate and process, generate a fourth preliminary influencing factor, and integrate into the fourth type of preliminary influencing factor matrix.

[0055] That is, when implementing the content described in the above claims, we need to process various types of weather data and calculate their impact factors through detailed steps. These steps include the application of fuzzy rules, the calculation of impact factors, and the integration of impact factors. The following will describe in detail how to complete these steps and illustrate them with specific examples.

[0056] First, we start by identifying fuzzy rules that match the first-class membership matrix. The first-class membership matrix is ​​generated by the standardized data values ​​of rainfall, which contains the membership of rainfall data in various fuzzy sets. For example, suppose our fuzzy rules involve "if rainfall is high, increase irrigation." In these rules, the fuzzy rules can be activated based on the specific value of rainfall, such as "high rainfall" as the activation condition.

[0057] Next, each activated fuzzy rule is assigned a weight. Weights are usually assigned based on the specific conditions of the fuzzy rule and its impact on the system. For example, suppose the rule "if rainfall is high" is assigned a weight of 0.7, while "if rainfall is moderate" is assigned a weight of 0.3. Based on these weights, the conditional part of each activated fuzzy rule is calculated to obtain the overall membership. The overall membership is a measure of the degree to which the rule conditions are satisfied, and the calculation method may involve a weighted sum of the membership values ​​of all activated rules.

[0058] The calculated overall membership is used as a weight value, combined with the result part of each activated fuzzy rule, to generate the first preliminary impact factor. For example, if the overall membership is 0.5 and the rule result part (such as the increased water volume) is 2 units, then the preliminary impact factor may be 0.5 × 2 = 1 unit. These impact factors are integrated into the first type of preliminary impact factor matrix for subsequent processing and decision-making.

[0059] Repeat the above steps and perform similar processing for the second, third, and fourth categories of data values. First, reset the fuzzy rules to determine the rules that match the second category membership matrix (temperature related). These rules may include "if the temperature is high, reduce the amount of irrigation." Similarly, assign weights to these rules and calculate the overall membership to generate the second category of preliminary influencing factors. Each step in this process, including rule activation, weight assignment, and calculation processing, provides a basis for adjusting irrigation data.

[0060] The third and fourth categories of data (humidity and wind speed) are processed similarly. For humidity data, the rule may be "if humidity is low, increase irrigation", while for wind speed, it may be "if wind speed is high, reduce irrigation". The activation of these rules, the weight assignment, and the calculation of the overall membership will result in the corresponding influence factor matrix.

[0061] For example, if the overall membership is 0.6 when processing humidity data, and the rule result is to increase the water volume by 3 units, the preliminary impact factor is 1.8 units. Similarly, the processing of wind speed will also obtain its corresponding preliminary impact factor. These impact factor matrices will be summarized and integrated to form a comprehensive impact factor, which will be used to finally adjust the irrigation data for the day.

[0062] The final result of the above processing will be a comprehensive influencing factor that fully considers rainfall, temperature, humidity and wind speed. This factor can accurately reflect the comprehensive impact of all relevant weather conditions on irrigation demand, thereby guiding actual irrigation adjustments and ensuring that the irrigation system can operate effectively under various weather conditions. This method improves the flexibility and adaptability of the system through fuzzy logic control, avoiding the adverse effects of uncertainty caused by weather changes on crop growth.

[0063] In one example, the combined influencing factors corresponding to the various data values ​​are integrated to obtain a comprehensive influencing factor, including: normalizing the first category preliminary influencing factor matrix, the second category preliminary influencing factor matrix, the third category preliminary influencing factor matrix, and the fourth category preliminary influencing factor matrix, respectively, to obtain the normalized first category preliminary influencing factor matrix, the second category preliminary influencing factor matrix, the third category preliminary influencing factor matrix, and the fourth category preliminary influencing factor matrix; performing weighted averaging on the normalized first category preliminary influencing factor matrix, the second category preliminary influencing factor matrix, the third category preliminary influencing factor matrix, and the fourth category preliminary influencing factor matrix to obtain the comprehensive influencing factor.

[0064] That is, when implementing the calculation of the comprehensive impact factor in the IoT-based irrigation control system, it is first necessary to process the preliminary impact factor matrix of various weather data, and then integrate these matrices into a comprehensive impact factor. This process involves several key steps: normalization of the preliminary impact factor, weighted average processing, and the final generation of the comprehensive impact factor. The following is an explanation of how to implement these steps in detail.

[0065] First, the first type of preliminary influencing factor matrix (related to rainfall), the second type of preliminary influencing factor matrix (related to temperature), the third type of preliminary influencing factor matrix (related to humidity), and the fourth type of preliminary influencing factor matrix (related to wind speed) are normalized. The purpose of normalization is to map the data values ​​in each preliminary influencing factor matrix into a unified range, so as to eliminate the influence caused by different data dimensions, thereby ensuring the fairness of various influencing factors in the comprehensive calculation.

[0066] Normalization usually uses a linear normalization method to adjust each data value to a preset interval, such as [0, 1]. Taking the preliminary influencing factor matrix of rainfall as an example, we first find the maximum and minimum values ​​in the matrix, and then normalize each data value. In this way, all data values ​​are converted to the range of [0, 1], ensuring the compatibility between different influencing factor matrices.

[0067] After all four preliminary impact factor matrices are normalized, we obtain the normalized first category preliminary impact factor matrix, second category preliminary impact factor matrix, third category preliminary impact factor matrix, and fourth category preliminary impact factor matrix. These normalized matrices have the same data range, which is convenient for subsequent weighted average processing.

[0068] Next, we perform weighted averaging on these normalized matrices. The purpose of weighted averaging is to combine the relative importance of various weather factors and obtain a comprehensive influencing factor through weighted calculation. The weight distribution is usually set according to the degree of influence of each weather factor on irrigation demand. For example, suppose we believe that temperature has the greatest impact on irrigation demand, and its weight is set to 0.4, while the weights of rainfall, humidity, and wind speed are set to 0.3, 0.2, and 0.1, respectively. The calculation steps of weighted averaging are as follows: For each region or time point, first calculate the weighted average of the normalized matrix. Specifically, we multiply each data value in the normalized preliminary influencing factor matrix by its corresponding weight, and then sum all weighted data values ​​to obtain the comprehensive influencing factor for the region or time point.

[0069] For example, assuming that at a specific time point, the normalized preliminary impact factor of rainfall is 0.5, that of temperature is 0.7, that of humidity is 0.6, and that of wind speed is 0.4, according to the set weights (rainfall 0.3, temperature 0.4, humidity 0.2, wind speed 0.1), we calculate the weighted average as follows: Comprehensive impact factor = (0.5 × 0.3) + (0.7 × 0.4) + (0.6 × 0.2) + (0.4 × 0.1) =0.15+0.28+0.12+0.04=0.59 This comprehensive impact factor of 0.59 represents the need for irrigation adjustment under current weather conditions. By performing similar calculations for all time points or areas, we obtain a comprehensive impact factor matrix that fully reflects the impact of weather.

[0070] Ultimately, the resulting comprehensive impact factors can be used to adjust the settings of the irrigation system to optimize the use of water resources. For example, if the comprehensive impact factors show that the amount of irrigation needs to be increased, the system will adjust the opening of the water valve or extend the irrigation time accordingly, thereby achieving more accurate and efficient irrigation control.

[0071] Through the above steps, we have realized the calculation of multi-factor comprehensive influencing factors based on weather data, ensuring that the irrigation system can dynamically adjust to changing weather conditions, and improving the intelligence level and resource utilization efficiency of agricultural irrigation.

[0072] In one example, based on the comprehensive influencing factor, the irrigation data of the day is adjusted to obtain updated irrigation data, including: determining sensitive values ​​of different irrigation parameters in the irrigation data, wherein the sensitive values ​​represent the relative importance of different irrigation parameters in the irrigation data to the irrigation effect; determining an adjustment coefficient corresponding to each of the irrigation parameters based on the sensitive values ​​of the different irrigation parameters and the comprehensive influencing factor; and adjusting different irrigation parameters in the irrigation data of the day based on the adjustment coefficient corresponding to each irrigation parameter to obtain updated irrigation data.

[0073] That is, in the process of adjusting irrigation data based on comprehensive influencing factors, we first need to determine the sensitive values ​​of each irrigation parameter in the irrigation data, which represent the relative importance of different irrigation parameters to the irrigation effect. Then, we will use these sensitive values ​​and comprehensive influencing factors to calculate the adjustment coefficient, and finally adjust the parameters in the irrigation data according to the adjustment coefficient to obtain the updated irrigation data.

[0074] First of all, the determination of sensitive values ​​is the starting point of the whole process. Each irrigation parameter, such as irrigation frequency, irrigation duration and irrigation flow, has different degrees of influence on the irrigation effect. The setting of sensitive values ​​usually relies on the analysis of historical data or expert experience. For example, by analyzing past irrigation records, we can determine that under specific weather conditions, some parameters may have a more significant impact on crop growth than other parameters. Suppose through analysis, it is found that irrigation flow has the greatest impact on crop growth, followed by irrigation frequency, and irrigation duration has the least impact. Then, the sensitive value of irrigation flow may be set to 0.5, irrigation frequency to 0.3, and irrigation duration to 0.2. These sensitive values ​​reflect the importance of each parameter to the final irrigation effect and will be used in calculations during the adjustment process.

[0075] After determining the sensitivity of each irrigation parameter, we then calculate the adjustment coefficient of each irrigation parameter based on the comprehensive impact factor. The comprehensive impact factor is calculated by weighting the impact of various weather factors, and it represents the degree of influence of the overall weather conditions on the irrigation demand. Assume that on a certain day, the calculated comprehensive impact factor is 0.7, which indicates that the overall weather conditions on that day require an increase in irrigation. The calculation of the adjustment coefficient is determined based on the sensitivity of each parameter. For example, if the comprehensive impact factor is 0.7, and the sensitivity value of the irrigation flow is 0.5, the sensitivity value of the irrigation frequency is 0.3, and the sensitivity value of the irrigation duration is 0.2, then the adjustment coefficient of each parameter can be calculated by the following formula: Adjustment coefficient = comprehensive impact factor × sensitivity value. For example, for irrigation flow, the adjustment coefficient is 0.7×0.5=0.35, for irrigation frequency it is 0.7×0.3=0.21, and for irrigation duration it is 0.7×0.2=0.14.

[0076] Next, we apply these adjustment coefficients to the irrigation data for the day to obtain updated irrigation data. Assume that the initial irrigation data for the day is: irrigation flow is 1000 liters, irrigation frequency is 2 times, and irrigation duration is 30 minutes. We use the calculated adjustment coefficients to adjust these data values. For irrigation flow, the updated irrigation volume will be the initial value plus the change caused by the adjustment coefficient, that is, 1000+1000×0.35=1350 liters. For irrigation frequency, the updated frequency is 2+2×0.21=2.42 times. For irrigation duration, the updated duration is 30+30×0.14=34.2 minutes. These updated parameter values ​​are the new irrigation plans, which are adjusted according to the guidance of the comprehensive influencing factors and the sensitivity values ​​of each parameter to better adapt to the weather conditions of the day.

[0077] Through this processing, we can not only dynamically adjust irrigation data according to real-time weather information, but also ensure that the operation of the irrigation system matches the actual needs of the crops, thereby improving the efficiency of water resource utilization and the growth effect of crops. This method enables the irrigation system to respond to environmental changes more intelligently and achieve precise and efficient agricultural irrigation.

[0078] Reference Figure 2 The embodiment of the present application provides a water valve operation control device based on the Internet of Things, comprising the following steps: The first acquisition unit 1 is used to acquire the irrigation plan data sent by the target device, wherein the irrigation plan data at least includes: multiple irrigation areas, and irrigation parameters corresponding to each of the irrigation areas, and the irrigation parameters at least include: irrigation frequency, irrigation duration and irrigation flow.

[0079] The second acquisition unit 2 is used to determine the irrigation data of the day based on the irrigation plan data and acquire weather information, wherein the weather information includes: weather data of a preset number of days before and after the day, and the weather data includes at least: rainfall, temperature, humidity and wind speed.

[0080] The adjustment unit 3 is used to adjust the irrigation data of the day based on the weather information to obtain updated irrigation data.

[0081] The sending unit 4 is used to generate a control instruction based on the updated irrigation data, and send the control instruction to the irrigation electronic control valves corresponding to the multiple irrigation areas, wherein the irrigation electronic control valve is used to open / close the faucet in response to the control instruction to irrigate the multiple irrigation areas.

[0082] In this embodiment, for the specific implementation of each unit in the above device embodiment, please refer to the above method embodiment, which will not be repeated here.

[0083] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0084] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0085] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0086] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0087] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0088] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A water valve operation control method based on the Internet of Things, characterized in that: The following steps are involved: Acquire irrigation plan data sent by the target device, wherein the irrigation plan data at least includes: multiple irrigation areas, and irrigation parameters corresponding to each of the irrigation areas, and the irrigation parameters at least include: irrigation frequency, irrigation duration, and irrigation flow; Determine the irrigation data of the day based on the irrigation plan data, and obtain weather information, wherein the weather information includes: weather data of a preset number of days before and after the day, and the weather data includes at least: rainfall, temperature, humidity and wind speed; Based on the weather information, adjusting the irrigation data of the day to obtain updated irrigation data; A control instruction is generated based on the updated irrigation data, and the control instruction is sent to the irrigation electronic control valves corresponding to the multiple irrigation areas, wherein the irrigation electronic control valve is used to open / close the faucet in response to the control instruction to irrigate the multiple irrigation areas.

2. The water valve operation control method according to claim 1, characterized in that: Before adjusting the irrigation data of the day based on the weather information to obtain updated irrigation data, the method further includes: Determine each data point in the weather data in the weather information, and determine the size of a neighborhood corresponding to each data point; Calculate the distance value from each data point to the nearest neighbor, and calculate the local density estimate of the data point based on the distance value; Calculate the relative density difference between each data point and other data points in the neighborhood based on the local density estimate; It is determined in turn whether the relative density difference of each data point is greater than a preset threshold, and data points in the weather information whose relative density difference is greater than the preset threshold are eliminated.

3. The water valve operation control method according to claim 1, characterized in that: Based on the weather information, the irrigation data of the day is adjusted to obtain updated irrigation data, including: Inputting the data value of each weather data in the weather information into the corresponding preset membership function, and calculating the membership degree of each data value in each fuzzy set; According to the preset fuzzy rules, the membership of each data value in each fuzzy set is calculated and processed to obtain the influence factor corresponding to each data value in each fuzzy set; Based on the membership and influence factors of the respective data values ​​in the respective fuzzy sets, calculating the combined influence factors corresponding to the respective data values; The combined influencing factors corresponding to the various data values ​​are integrated to obtain a comprehensive influencing factor, and based on the comprehensive influencing factor, the irrigation data of the day is adjusted to obtain updated irrigation data.

4. The water valve operation control method according to claim 3, characterized in that: Inputting the data value of each weather data in the weather information into the corresponding preset membership function, calculating the membership of each data value in each fuzzy set, and calculating the combined influence factor corresponding to each data value based on the membership and influence factor of each data value in each fuzzy set, including: Using a linear normalization formula, the data values ​​of each weather data in the weather information are normalized, and the data values ​​of the weather data of different scales are mapped into a preset interval to obtain converted data values; Extracting a first type of data value, a second type of data value, a third type of data value and a fourth type of data value from the converted data values, wherein the first type of data value is associated with the rainfall, the second type of data value is associated with the temperature, the third type of data value is associated with the humidity, and the fourth type of data value is associated with the wind speed; Inputting the first-category data value into the membership function corresponding to the rainfall, generating the membership of the first-category data value in the first-category fuzzy set, and integrating them into a first-category membership matrix, wherein the first-category fuzzy set is associated with the rainfall; Inputting the second type of data value into the membership function corresponding to the temperature, generating the membership of the second type of data value in the second type of fuzzy set, and integrating them into a second type of membership matrix, wherein the second type of fuzzy set is associated with the temperature; Inputting the third type of data value into the membership function corresponding to humidity, generating the membership of the third type of data value in the third type of fuzzy set, and integrating them into a third type of membership matrix, wherein the third type of fuzzy set is associated with humidity; The fourth type of data value is input into the membership function corresponding to the wind speed, the membership of the fourth type of data value in the fourth type of fuzzy set is generated, and integrated into a fourth type of membership matrix, wherein the fourth type of fuzzy set is associated with the wind speed.

5. The water valve operation control method according to claim 4, characterized in that: According to the preset fuzzy rules, the membership of each data value in each fuzzy set is calculated and processed to obtain the influence factors corresponding to each data value in each fuzzy set, including: Determine, among the preset fuzzy rules, a fuzzy rule that matches the first type of membership matrix, and activate the determined fuzzy rule; Assigning a weight to each activated fuzzy rule, and calculating the conditional part of each activated fuzzy rule based on the first-class membership matrix to obtain a first-class overall membership; The calculated first-category overall membership is used as a weight value, combined with the result part of each activated fuzzy rule to perform calculation processing, generate a first preliminary influencing factor, and integrate it into a first-category preliminary influencing factor matrix; Resetting the preset fuzzy rules, and determining a fuzzy rule matching the second type of membership matrix among the reset fuzzy rules, and activating the determined fuzzy rule; Assigning a weight to each activated fuzzy rule, and calculating the conditional part of each activated fuzzy rule based on the second-class membership matrix to obtain a second-class overall membership; The calculated second-category overall membership is used as a weight value, combined with the result part of each of the activated fuzzy rules to perform calculation processing, generate a second preliminary influencing factor, and integrate it into a second-category preliminary influencing factor matrix; Resetting the preset fuzzy rules, and determining a fuzzy rule matching the third type of membership matrix among the reset fuzzy rules, and activating the determined fuzzy rule; Assigning a weight to each activated fuzzy rule, and calculating the conditional part of each activated fuzzy rule based on the third-class membership matrix to obtain the third-class overall membership; The calculated third category overall membership is used as a weight value, combined with the result part of each activated fuzzy rule to perform calculation processing, generate a third preliminary impact factor, and integrate it into a third category preliminary impact factor matrix; Resetting the preset fuzzy rules, and determining a fuzzy rule matching the fourth type of membership matrix among the reset fuzzy rules, and activating the determined fuzzy rule; Assigning a weight to each activated fuzzy rule, and calculating and processing the conditional part of each activated fuzzy rule based on the fourth type of membership matrix to obtain a fourth type of overall membership; The calculated fourth category overall membership is used as a weight value, combined with the result part of each activated fuzzy rule to perform calculation processing, generate a fourth preliminary influencing factor, and integrate it into a fourth category preliminary influencing factor matrix.

6. The water valve operation control method according to claim 5, characterized in that: Integrate the combined impact factors corresponding to the various data values ​​to obtain a comprehensive impact factor, including: Normalizing the first preliminary impact factor matrix, the second preliminary impact factor matrix, the third preliminary impact factor matrix, and the fourth preliminary impact factor matrix respectively to obtain the first preliminary impact factor matrix, the second preliminary impact factor matrix, the third preliminary impact factor matrix, and the fourth preliminary impact factor matrix after normalization; The first type of preliminary impact factor matrix, the second type of preliminary impact factor matrix, the third type of preliminary impact factor matrix and the fourth type of preliminary impact factor matrix that have been normalized are weighted averaged to obtain the comprehensive impact factor.

7. The water valve operation control method according to claim 3, characterized in that: Based on the comprehensive influencing factors, the irrigation data of the day is adjusted to obtain updated irrigation data, including: Determining sensitivity values ​​of different irrigation parameters in the irrigation data, wherein the sensitivity values ​​represent the relative importance of different irrigation parameters in the irrigation data to the irrigation effect; Determining an adjustment coefficient corresponding to each of the irrigation parameters based on the sensitivity values ​​of the different irrigation parameters and the comprehensive influencing factors; Based on the adjustment coefficient corresponding to each irrigation parameter, different irrigation parameters in the irrigation data of the day are adjusted to obtain updated irrigation data.

8. A water valve operation control device based on the Internet of Things, characterized in that: The following steps are involved: A first acquisition unit is used to acquire irrigation plan data sent by a target device, wherein the irrigation plan data at least includes: a plurality of irrigation areas, and irrigation parameters corresponding to each of the irrigation areas, and the irrigation parameters at least include: irrigation frequency, irrigation duration, and irrigation flow rate; A second acquisition unit is used to determine the irrigation data of the day based on the irrigation plan data, and acquire weather information, wherein the weather information includes: weather data of a preset number of days before and after the day, and the weather data includes at least: rainfall, temperature, humidity and wind speed; An adjustment unit, configured to adjust the irrigation data of the day based on the weather information to obtain updated irrigation data; A sending unit is used to generate a control instruction based on the updated irrigation data, and send the control instruction to the irrigation electronic control valves corresponding to the multiple irrigation areas, wherein the irrigation electronic control valve is used to open / close the faucet in response to the control instruction to irrigate the multiple irrigation areas.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images