Intelligent fertilization method for crops

Abstract

An embodiment of the present specification provides a method for intelligent fertilization of crops, the method comprising: acquiring monitoring data of a planting unit based on a monitoring unit, the monitoring unit comprising at least a soil detection unit, and the monitoring data comprising at least soil data; determining soil characteristics corresponding to the planting unit based on the soil data; determining that the planting unit is a unit to be fertilized in response to the soil characteristics of the unit to be fertilized satisfying fertilization conditions; determining fertilizer requirement characteristics of the unit to be fertilized based on the soil characteristics of the unit to be fertilized; determining a fertilization path of a fertilizer applicator according to the fertilizer requirement characteristics of the unit to be fertilized; and controlling the fertilizer applicator to fertilize at least one unit to be fertilized based on the fertilization path.

Description

Technical Field

[0001] The present invention relates to the field of fertilizer distribution, and in particular to a method for intelligent fertilization of crops. Background Art

[0002] In current agricultural production, crop planting and management are extensive and there are many types of crops. In the process of fertilizing and watering crops, manual operation is often required, which is labor-intensive for workers and the operation is complicated and tedious. In addition, the existing automatic fertilization and watering devices do not consider the intelligent ratio of fertilizer application, which reduces the overall fertilization efficiency and makes it difficult to ensure the fertilization effect.

[0003] In response to the problem of intelligent fertilizer ratio, CN108684278B proposes an intelligent fertilizer ratio method, device and system. The application focuses on calculating the fertilizer formula and fertilizer amount based on the soil nutrient supply of the current plot and the nutrient demand of crops, as well as the pH value, terrain, fertilization habits, etc. However, the time of fertilization is also very important for the fertilization effect. There may be differences in the fertilization effect brought about by fertilization at different time points. However, this application does not consider the impact of the time of fertilization on crops, which will lead to reduced fertilization effect.

[0004] Therefore, it is hoped to provide an intelligent fertilization method for crops, so as to carry out fertilization more reasonably and ensure the fertilization effect. Summary of the invention

[0005] One of the embodiments of the present specification provides an intelligent fertilization method for crops, characterized in that it is executed based on a processor and includes: acquiring monitoring data of a planting unit based on a monitoring unit, the monitoring unit at least including a soil detection unit, and the monitoring data at least including soil data; determining soil characteristics corresponding to the planting unit based on the soil data; determining that the planting unit is a unit to be fertilized in response to the soil characteristics of the planting unit satisfying fertilization conditions; determining fertilizer requirement characteristics of the unit to be fertilized based on the soil characteristics of the unit to be fertilized; determining a fertilization path of a fertilizer applicator according to the fertilizer requirement characteristics of the unit to be fertilized; and controlling the fertilizer applicator to fertilize the at least one unit to be fertilized based on the fertilization path.

[0006] One of the embodiments of the present specification provides an intelligent fertilization system for crops, including an acquisition module, a first determination module, a second determination module, a third determination module, a fourth determination module and a control module; the acquisition module is used to acquire monitoring data of a planting unit based on a monitoring unit, the monitoring unit at least includes a soil detection unit, and the monitoring data at least includes soil data; the first determination module is used to determine soil characteristics corresponding to the planting unit based on the soil data; the second determination module is used to determine that the planting unit is a unit to be fertilized in response to the soil characteristics of the planting unit satisfying fertilization conditions; the third determination module is used to determine the fertilizer requirement characteristics of the unit to be fertilized based on the soil characteristics of the unit to be fertilized; the fourth determination module is used to determine a fertilization path of a fertilizer applicator according to the fertilizer requirement characteristics of the unit to be fertilized; and the control module is used to control the fertilizer applicator to fertilize at least one unit to be fertilized based on the fertilization path.

[0007] One of the embodiments of the present specification provides an intelligent crop fertilization device, characterized in that it includes a processor, and the processor is used to execute the aforementioned intelligent crop fertilization method.

[0008] One of the embodiments of the present specification provides a computer-readable storage medium, characterized in that the storage medium stores computer instructions, and when a computer reads the computer instructions in the storage medium, the computer executes the aforementioned intelligent fertilization method for crops. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0010] Figure 1 is an exemplary module diagram of a smart fertilization system for crops according to some embodiments of this specification;

[0011] Figure 2 is an exemplary flow chart of a method for intelligent fertilization of crops according to some embodiments of this specification;

[0012] Figure 3 is a schematic diagram of determining fertilizer demand characteristics according to some embodiments of this specification;

[0013] Figure 4 It is a schematic diagram of determining a fertilization path according to some embodiments of this specification. DETAILED DESCRIPTION

[0014] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0015] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0016] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0017] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0018] In order to solve the problem of intelligent fertilizer ratio, the existing technology calculates the fertilizer formula and fertilizer amount based on the soil nutrient supply, the nutrient demand of crops, pH value, terrain, fertilization habits, etc., and uses this as the basis for fertilizer allocation and fertilization. The impact of the time of fertilization on crops is often not considered. For example, fertilization before rainfall will cause a large loss of nutrients in the fertilizer. After rainfall, the soil conditions will change, and the fertilization effect will naturally change accordingly. If the time factor is not considered, even with a reasonable fertilizer ratio, the fertilization effect may not be ideal due to inappropriate timing of fertilization.

[0019] In view of this, some embodiments of the present specification provide an intelligent fertilization method for crops, which determines the fertilization time and fertilization path of the fertilizer applicator based on the soil characteristics and fertilizer demand characteristics of different planting units, taking into account the influence of weather and time, which is conducive to obtaining better fertilization effects.

[0020] Figure 1 It is an exemplary module diagram of the intelligent fertilization system for crops shown in some embodiments of this specification.

[0021] like Figure 1 As shown, the intelligent crop fertilization system 100 includes an acquisition module 110 , a first determination module 120 , a second determination module 130 , a third determination module 140 , a fourth determination module 150 and a control module 160 .

[0022] The acquisition module 110 is used to acquire monitoring data of at least one planting unit based on a monitoring unit, wherein the monitoring unit at least includes a soil detection unit, and the monitoring data at least includes soil data.

[0023] The first determination module 120 is used to determine soil characteristics corresponding to at least one planting unit based on the soil data.

[0024] The second determination module 130 may be configured to determine at least one unit to be fertilized from at least one planting unit according to soil characteristics and fertilization conditions.

[0025] The third determination module 140 is used to determine the fertilizer requirement characteristics of the unit to be fertilized according to the soil characteristics of the unit to be fertilized.

[0026] In some embodiments, the third determination module 140 is also used to obtain predicted weather data for a future time period based on a weather monitoring unit; in response to the predicted weather data meeting a first weather condition, determine fertilizer demand characteristics based on target soil component characteristics, wherein the first weather condition includes the absence of rainfall in the future time period; in response to the predicted weather data meeting a second weather condition, predict soil characteristics after rain of the unit to be fertilized, wherein the second weather condition includes the presence of rainfall in the future time period; determine the dissolution rate of different nutrients based on the soil characteristics after rain; determine fertilizer demand characteristics based on the soil characteristics after rain, target soil characteristics, and the dissolution rates of different nutrients.

[0027] In some embodiments, the third determination module 140 is further configured to determine the dissolution rates of different nutrients through a prediction model based on soil characteristics after rain.

[0028] The fourth determination module 150 may be used to determine a fertilization path of the fertilizer applicator based on the fertilizer demand characteristics of the unit to be fertilized.

[0029] In some embodiments, the fourth determination module 150 is also used to generate at least one candidate fertilization path; for each of the at least one candidate fertilization path, the fertilization cost of the candidate fertilization path is determined based on the fertilizer demand characteristics and the remaining power of the fertilizer applicator; and the candidate fertilization path whose fertilization cost meets the preset conditions is used as the target fertilization path.

[0030] The control module 160 may be configured to control the fertilizer applicator to fertilize at least one fertilization unit based on a fertilization path.

[0031] For more information about the aforementioned modules and their functions, see Figure 2-4 and related instructions.

[0032] It should be noted that the above description of the intelligent crop fertilization system and its modules is only for convenience of description and cannot limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. In some embodiments, Figure 1 The modules disclosed in the system may be different modules in one system, or one module may realize the functions of two or more modules mentioned above.

[0033] Figure 2 is an exemplary flow chart of a method for intelligent fertilization of crops according to some embodiments of this specification. In some embodiments, process 200 may be executed by a processor. Figure 2 As shown, process 200 includes the following steps:

[0034] Step 210: Acquire monitoring data of the planting unit based on the monitoring unit.

[0035] The monitoring unit refers to a device or component that monitors the planting unit to obtain monitoring data, such as a temperature sensor, a humidity sensor, etc. The monitoring unit can be deployed at a preset monitoring point in the planting unit. In some embodiments, the monitoring unit can include a soil detection unit and a weather monitoring unit.

[0036] A soil detection unit is a device or component used to detect soil data, such as a pH meter, conductivity sensor, etc.

[0037] The weather monitoring unit is a device or component for monitoring weather data of at least one future period, such as a weather observation instrument, a rain gauge, a solar radiation sensor, etc. In some embodiments, the weather monitoring unit may also include a communication component for obtaining weather forecasts through the network to determine weather information for the future period.

[0038] A planting unit refers to a unit with a certain spatial range within a planting area. For example, the planting area may be divided into multiple spaces, and one planting unit may correspond to one space within the planting area.

[0039] Monitoring data refers to monitoring data related to the planting unit. In some embodiments, the monitoring data may include soil data and weather data.

[0040] Soil data refers to data related to the soil within the planting unit, such as soil conductivity, soil moisture content, and the content of different nutrients in the soil.

[0041] Weather data refers to data related to the weather at the planting unit, such as weather type, wind speed, air humidity, etc. In some embodiments, weather data can be used to determine fertilizer demand characteristics. For more information, see Figure 3 and its related description.

[0042] In some embodiments, the processor may obtain monitoring data from one or more monitoring units in at least one planting unit deployed in the target area.

[0043] Step 220, determining soil characteristics corresponding to the planting unit based on the soil data.

[0044] Soil characteristics refer to characteristics related to the soil in the planting unit. In some embodiments, soil characteristics may include soil component characteristics and soil structure characteristics. Generally, soil per unit area in a uniform planting unit has the same soil component characteristics and soil structure characteristics.

[0045] Soil composition characteristics refer to characteristics related to the components contained in the soil. For example, soil composition can include the content of nutrients and trace elements in the soil.

[0046] Soil structure characteristics refer to characteristics related to soil structure. For example, soil structure characteristics can include soil looseness, moisture, temperature, pH value, etc.

[0047] In some embodiments, the processor may analyze and process the acquired soil data to determine the soil characteristics corresponding to the planting unit. For example, the processor may represent the soil characteristics in the form of a sequence of {A, B, C, D, ...} based on the soil data, where A and B may be used to represent soil component characteristics, and C and D may be used to represent soil structure characteristics.

[0048] Step 230: In response to the soil characteristics of the planting unit satisfying the fertilization conditions, the planting unit is determined to be a unit to be fertilized.

[0049] The fertilization condition refers to a judgment condition for evaluating whether the planting unit needs to be fertilized. In some embodiments, if the soil characteristics of the planting unit meet at least one fertilization condition, the planting unit can be determined as a unit to be fertilized.

[0050] In some embodiments, the fertilization condition may include that the content of each nutrient in the soil is lower than the corresponding content threshold.

[0051] In some embodiments, the fertilization condition may include a ratio of different nutrient contents in the soil exceeding a range threshold.

[0052] In some embodiments, the content threshold and range threshold may be preset based on historical experience.

[0053] The unit to be fertilized refers to a planting unit that needs to be fertilized. In some embodiments, the unit to be fertilized may include at least one planting unit that needs to be fertilized.

[0054] In some embodiments, the processor may determine whether the soil characteristics of the planting unit meet the fertilization conditions, and determine the planting unit that meets the fertilization conditions as the unit to be fertilized.

[0055] For example, the processor can compare the soil component characteristics in the soil characteristics corresponding to the planting unit with the preset content threshold and / or range threshold to determine whether the fertilization conditions are met. Exemplarily, the content threshold corresponding to nitrogen in the soil is 1.3g / kg. When the nitrogen content in the soil component characteristics of the planting unit is lower than 1.3g / kg, the fertilization conditions are met. For another example, the preset ratio of nitrogen, phosphorus and potassium content in the soil is 1:2:2. When the ratio of nitrogen, phosphorus and potassium content in the soil is within the range threshold of the preset ratio, the fertilization conditions are not met. On the contrary, when it exceeds the range threshold of the preset ratio, the fertilization conditions are met.

[0056] Step 240, determining the fertilizer requirement characteristics of the unit to be fertilized based on the soil characteristics of the unit to be fertilized.

[0057] The fertilizer requirement characteristics refer to the characteristics used to reflect the fertilizer requirement of the soil in the unit to be fertilized, such as the content ratio of different nutrients in the fertilizer, etc. In some embodiments, the soil in the same unit to be fertilized has the same fertilizer requirement characteristics.

[0058] In some embodiments, the processor may determine the fertilizer requirement characteristics in a variety of ways based on the soil characteristics of at least one unit to be fertilized. For example, the processor may determine the fertilizer requirement characteristics corresponding to the historical soil characteristics similar to the current soil characteristics as the fertilizer requirement characteristics corresponding to the current soil characteristics by querying a preset table based on the soil characteristics of at least one unit to be fertilized. The preset table may include the correspondence between different soil characteristics and fertilizer requirement characteristics. In some embodiments, the preset table may be determined based on historical data.

[0059] In some embodiments, the processor may determine the fertilizer demand characteristics of the unit to be fertilized based on the predicted weather data for the future period. For more information, see Figure 3 and its related description.

[0060] Step 250, determining a fertilization path of the fertilizer applicator according to the fertilizer demand characteristics of the unit to be fertilized.

[0061] The fertilization path refers to the path along which the fertilizer applicator applies fertilizer to the units to be fertilized. In some embodiments, the fertilization path may include the order in which the fertilizer applicator applies fertilizer to the units to be fertilized.

[0062] In some embodiments, the processor may determine the fertilization path of the fertilizer applicator in a variety of ways based on the fertilizer demand characteristics of the unit to be fertilized. For example, the processor may determine the unit to be fertilized that needs to be fertilized based on the fertilizer demand characteristics of the unit to be fertilized, and use a path planning algorithm to select the path with the least fertilization time as the fertilization path.

[0063] In some embodiments, the processor can determine the fertilization path based on the fertilizer demand characteristics and the remaining power of the fertilizer applicator. For more information, see Figure 4 and its related description.

[0064] Step 260: Control the fertilizer applicator to fertilize at least one unit to be fertilized based on the fertilization path.

[0065] A fertilizer applicator refers to a device for applying fertilizer. In some embodiments, the fertilizer applicator can be implemented based on a drone.

[0066] In some embodiments, the processor can control the fertilizer applicator to fertilize at least one unit to be fertilized based on the fertilization path in a variety of ways. For example, the processor can generate a fertilization path control instruction and send it to the fertilizer applicator to control the fertilizer applicator to fertilize according to the fertilization path control instruction.

[0067] Some embodiments of the present specification analyze and process monitoring data to determine the units to be fertilized, and determine the fertilization path based on the fertilizer demand characteristics of the units to be fertilized. This can quickly and efficiently determine the fertilization path suitable for fertilization by the fertilizer applicator, thereby realizing intelligent fertilization of crops.

[0068] Figure 3 FIG. 1 is a schematic diagram of determining fertilizer demand characteristics according to some embodiments of this specification. Figure 3 As shown, the process 300 of determining fertilizer demand characteristics includes at least the following.

[0069] In some embodiments, the processor can obtain predicted weather data for a future time period based on a weather monitoring unit; in response to the predicted weather data meeting a first weather condition, determine fertilizer demand characteristics based on target soil component characteristics; in response to the predicted weather data meeting a second weather condition, predict post-rain soil characteristics of the unit to be fertilized; determine the dissolution rates of different nutrients based on the post-rain soil characteristics; determine fertilizer demand characteristics based on the post-rain soil characteristics, target soil component characteristics, and the dissolution rates of different nutrients.

[0070] The predicted weather data refers to the predicted weather data for a future period. Generally, when the planting unit meets the fertilization conditions, fertilization can be arranged for the planting unit the next day. Therefore, in some embodiments, the predicted weather data may include the weather data for the next day.

[0071] In some embodiments, the processor may perform meteorological analysis on the weather data obtained by the weather monitoring unit to obtain the predicted weather data. In some embodiments, the processor may also obtain weather forecast data through the weather monitoring unit, and determine the predicted weather data based on the weather forecast data.

[0072] In some embodiments, the first weather condition may include that the probability of rainfall in the future period is less than a probability threshold, wherein the probability threshold may be set based on actual production experience.

[0073] The target soil composition characteristics refer to the soil composition characteristics of the unit to be fertilized after fertilization. In some embodiments, the target soil composition characteristics may include the content and proportion of different nutrients in the soil. In some embodiments, the target soil composition can be obtained based on historical planting experience. The target soil composition characteristics of multiple units to be fertilized for planting the same crop are the same, and the target soil composition characteristics of multiple units to be fertilized for planting different crops are different.

[0074] For an explanation of the characteristics of fertilizer requirements, see Figure 2 In some embodiments, the fertilizer requirement characteristic may also include a fertilizer requirement amount.

[0075] The fertilizer demand refers to the demand for fertilizer by the unit to be fertilized. In some embodiments, the fertilizer demand can be calculated based on the content of different nutrients in the fertilizer of the fertilizer demand characteristics. In some embodiments, the processor can add the content of different nutrients in the fertilizer to obtain the initial fertilizer demand, and then adjust the initial fertilizer demand based on the sum of the difference between the content of different nutrients in the soil composition characteristics of the unit to be fertilized and the corresponding content threshold, so as to obtain the fertilizer demand. For more information about the content threshold, please refer to Figure 2 and its related description.

[0076] In some embodiments, the fertilizer demand may be the product of the initial fertilizer demand and the adjustment coefficient. The processor may preset the relationship between the sum of the differences between the contents of different nutrients and the corresponding content thresholds in the soil composition characteristics of the unit to be fertilized and the adjustment coefficient. For example, the preset relationship may be: the greater the sum of the differences, the greater the adjustment coefficient.

[0077] In some embodiments, the fertilizer demand may be related to the fertilizer diffusion rate between adjacent units to be fertilized.

[0078] The fertilizer diffusion rate refers to the rate at which fertilizer diffuses from a unit to be fertilized to an adjacent unit to be fertilized. In some embodiments, the fertilizer diffusion rate can be obtained based on the statistics of historical data. The fertilizer diffusion rate has a direction. The fertilizer will diffuse from a unit to be fertilized with a high concentration to a unit to be fertilized with a low concentration. For example, if the fertilizer concentration of unit A to be fertilized is greater than the fertilizer concentration of unit B to be fertilized, the fertilizer will diffuse from unit A to be fertilized to the adjacent unit to be fertilized B. At this time, the fertilizer diffusion rate of A is a negative value, and the fertilizer diffusion rate of B is a positive value. The unit to be fertilized with a negative fertilizer diffusion rate has fertilizer loss, and the unit to be fertilized with a positive fertilizer diffusion rate has fertilizer absorption.

[0079] In some embodiments, the processor may adjust the fertilizer demand based on the fertilizer diffusion rate. For example, if the fertilizer diffusion rate between adjacent units to be fertilized A and B is negative for A and positive for B, the processor may appropriately increase the fertilizer demand of unit A to be fertilized and appropriately reduce the fertilizer demand of unit B to be fertilized.

[0080] In some embodiments, the processor may adjust the fertilizer demand based on the average diffusion rate of the fertilizer between the unit to be fertilized and the adjacent fertilization unit. The average diffusion rate may be the average value of the fertilizer diffusion rate between the unit to be fertilized and the adjacent fertilization unit. For example, the units to be fertilized adjacent to the unit to be fertilized A are B, C, and D, and there are fertilizer diffusion rates 1, 2, and 3 between A and B, C, and D, respectively. Then, the average diffusion rate of the fertilizer between the unit to be fertilized A and the adjacent fertilization unit = (fertilizer diffusion rate 1 + fertilizer diffusion rate 2 + fertilizer diffusion rate 3) ÷ 3. In some embodiments, the processor may preset the relationship between the average diffusion rate of the fertilizer and the adjustment amount of the fertilizer demand, and adjust the fertilizer demand based on the corresponding relationship and the average diffusion rate.

[0081] In some embodiments of the present specification, the fertilizer demand is adjusted by the fertilizer diffusion rate between adjacent units to be fertilized, so as to avoid the problem that the soil component characteristics in the planting unit after fertilization are inconsistent with the target soil component characteristics due to fertilizer diffusion between adjacent units to be fertilized, thereby ensuring the fertilization effect of the units to be fertilized.

[0082] In some embodiments, the processor may determine the fertilizer requirement characteristics in a variety of ways based on the target soil component characteristics. For example, the processor may directly use the content and ratio of different nutrients in the target soil component characteristics as the content and ratio of corresponding nutrients in the fertilizer requirement characteristics of the unit to be fertilized.

[0083] In some embodiments, the second weather condition may include a probability of rainfall in the future period being not less than a probability threshold.

[0084] Post-rainfall soil characteristics refer to the soil characteristics of the unit to be fertilized after rainfall.

[0085] In some embodiments, the processor may predict the soil characteristics after rain in a variety of ways. For example, the processor may perform statistical analysis on historical soil characteristics after rain, determine the changing pattern of soil characteristics after rain, and predict the soil characteristics after rain based on the changing pattern.

[0086] The dissolution rate of different nutrients refers to the dissolution rate of different nutrients in the soil of the unit to be fertilized after rainfall.

[0087] In some embodiments, the processor can construct a current feature vector based on the post-rain soil structure characteristics in the post-rain soil characteristics of the unit to be fertilized, select at least one reference feature vector that is closest to the current feature vector from the vector database, and take the weighted average of the dissolution rates of different nutrients stored in association with the reference feature vector as the dissolution rates of different nutrients corresponding to the current feature vector, wherein the weight of the weighted average can be related to the reliability of the dissolution rates of different nutrients stored in association with the reference feature vector, and the greater the reliability, the greater the corresponding weight. In some embodiments, the aforementioned reliability can be determined based on the confidence of the output of the prediction model, and more information about the prediction model can be found in the relevant description below.

[0088] In some embodiments, the vector database may include multiple reference feature vectors, and each reference feature vector has at least the dissolution rate of the corresponding different nutrients stored in association. The reference feature vector may be constructed based on the post-rain soil structure feature in the historical post-rain soil feature of the unit to be fertilized.

[0089] In some embodiments, the processor can determine the dissolution rate of different nutrients under the post-rain soil structure in the historical post-rain soil characteristics of the unit to be fertilized based on the soil characteristics in the historical data. For example, the processor can obtain soil component characteristics at least two historical moments (such as T1 and T2) under the post-rain soil structure in the historical post-rain soil characteristics of the unit to be fertilized, and calculate the dissolution rate of each nutrient in the soil component characteristics. Taking nutrient A as an example, its dissolution rate = (content of A at T1 - content of A at T2) ÷ (T2-T1) × 100%.

[0090] In some embodiments, the processor may determine the dissolution rates of different nutrients through a predictive model based on soil characteristics after rain.

[0091] In some embodiments, the prediction model may be a machine learning model, such as a convolutional neural network model (CNN).

[0092] The input of the prediction model may include the soil structure characteristics after rain of at least one unit to be fertilized; and the output may include the dissolution rate of different nutrients.

[0093] In some embodiments, the output of the prediction model further includes the confidence level of the aforementioned dissolution rate, which can characterize the reliability of the dissolution rate determined by the prediction model.

[0094] In some embodiments, the prediction model can be obtained by training multiple first training samples with first labels. For example, multiple first training samples with first labels can be input into the prediction model, a loss function can be constructed by the first label and the prediction result of the initial prediction model, the initial prediction model can be updated based on the iteration of the loss function, and the training is completed when the loss function of the initial prediction model meets the end condition, wherein the end condition can be the convergence of the loss function, the number of iterations reaches a threshold, etc.

[0095] In some embodiments, the first training sample may include the soil structure characteristics of the unit to be fertilized after historical rain, and the first label may be the dissolution rate of the corresponding different nutrients. The acquisition of the first label is similar to the calculation of the dissolution rate of different nutrients in the above text, and can refer to the above related description.

[0096] In some embodiments of the present specification, the dissolution rates of different nutrients are determined by a prediction model. The self-learning ability of the machine learning model can be used to find patterns in the dissolution rates of different nutrients corresponding to the post-rain soil structure characteristics of a large number of units to be fertilized, which helps to obtain more accurate dissolution rates of different nutrients and facilitates more accurate acquisition of fertilizer demand characteristics later.

[0097] In some embodiments, the processor can adjust the content and proportion of different nutrients in the target soil composition based on the dissolution rates of different nutrients to obtain updated target soil composition characteristics; and use the added amounts and proportions of different nutrients in the updated target soil composition characteristics as the content and proportions of corresponding nutrients in the fertilizer demand characteristics of the unit to be fertilized.

[0098] In some embodiments, the processor can preset the correspondence between the dissolution rates of different nutrients of different types of crops and the contents and proportions of different nutrients, and adjust the contents and proportions of different nutrients in the target soil components based on the correspondence, thereby obtaining updated target soil component characteristics.

[0099] In some embodiments, the processor may determine a fertilization path of the fertilizer applicator and a fertilizer spraying rate and a travel speed of the fertilizer applicator at each point on the fertilization path according to the fertilizer demand characteristics.

[0100] The fertilizer spraying rate refers to the speed at which the fertilizer applicator sprays fertilizer over the unit to be fertilized.

[0101] The travel speed of the fertilizer applicator refers to the speed at which the fertilizer applicator travels over the unit to be fertilized.

[0102] In some embodiments, the processor may determine the fertilizer spraying rate and the fertilizer applicator travel speed based on a preset relationship between the fertilizer demand characteristic and the fertilizer spraying rate and the fertilizer applicator travel speed, wherein the preset relationship may be that the greater the fertilizer demand, the faster the fertilizer spraying rate and the slower the fertilizer applicator travel speed.

[0103] In some embodiments of the present specification, the fertilizer spraying rate and the travel speed of the fertilizer applicator are determined by the fertilizer demand, so that the fertilizer applicator can stay longer and spray at a higher rate in the unit to be fertilized with a large fertilizer demand, so as to ensure that the fertilizer applicator completes fertilizing the unit to be fertilized, thereby improving the fertilization efficiency.

[0104] In some embodiments of the present specification, by judging the weather conditions satisfied by the predicted weather data, the fertilizer requirement characteristics are determined based on the target soil composition characteristics when there is no rainfall in the future period, thereby improving the efficiency of determining the fertilizer requirement characteristics; when there is rainfall in the future period, the target soil composition characteristics are updated based on the soil characteristics after the rain and the dissolution rates of different nutrients, and then the fertilizer requirement characteristics are determined, which helps to avoid the problem of nutrient loss due to rainfall.

[0105] Figure 4 FIG. 1 is a schematic diagram of determining a fertilization path according to some embodiments of this specification. Figure 4 As shown, the process 400 of determining a fertilization path may at least include the following contents.

[0106] In some embodiments, the processor can generate multiple candidate fertilization paths; for the candidate fertilization paths, the fertilization cost of the candidate fertilization paths is determined based on the remaining power of the fertilizer applicator and the fertilizer demand characteristics; and the candidate fertilization path whose fertilization cost meets the preset conditions is used as the target fertilization path.

[0107] The candidate fertilization path refers to the order in which the available fertilizer applicators fertilize the units to be fertilized.

[0108] In some embodiments, the candidate fertilization paths may be randomly generated based on a plurality of units to be fertilized. For example, for four units to be fertilized, A, B, C, and D, the candidate fertilization paths may be ABCD, BCAD, and so on.

[0109] Fertilization cost refers to the cost spent by the fertilizer applicator to complete fertilization. Fertilization cost may include at least one of the time cost, material cost, and other costs. Among them, time cost refers to the total time from the fertilizer applicator starting from the station to the time it completes fertilization and returns to the station. Material cost at least includes the power consumption of the fertilizer applicator, the loss of the fertilizer applicator itself, and the like. Among them, material cost is related to time cost. Generally speaking, the longer the fertilization time of the fertilizer applicator is, the higher the corresponding material cost is.

[0110] The target fertilization path refers to the candidate fertilization path finally determined for fertilization.

[0111] In some embodiments, the processor may use the candidate fertilization path whose fertilization cost meets the preset conditions as the target fertilization path, and control the fertilizer applicator to fertilize the unit to be fertilized based on the target fertilization path.

[0112] In some embodiments, the preset conditions may include that the fertilization cost is minimum and / or the fertilization cost is not greater than a cost threshold, wherein the cost threshold may be determined based on production experience and / or actual demand.

[0113] In some embodiments, the processor may calculate at least one fertilization cost (eg, fertilization cost 1, ..., fertilization cost N) corresponding to at least one candidate fertilization path (eg, candidate fertilization path 1, ..., candidate fertilization path N).

[0114] In some embodiments, the fertilization cost can be obtained by the following formula (1):

[0115] C=a×T0+b×T2+c×T3 (1)

[0116] Among them, C represents the fertilizer cost of the fertilizer applicator, T0 represents the fertilizer time of the fertilizer applicator, T2 represents the charging time of the fertilizer applicator, and T3 represents the moving time of the fertilizer applicator when it is not fertilizing. a and b are weights.

[0117] The moving time at least includes the transfer time of the fertilizer applicator between two non-adjacent units to be fertilized and the round-trip time when the fertilizer applicator is charged.

[0118] Fertilization time refers to the time it takes for the fertilizer applicator to complete fertilization of all units to be fertilized.

[0119] In some embodiments, the processor can calculate the fertilization time of the fertilizer applicator based on the distance length sequence corresponding to the fertilization number sequence and the travel speed of the fertilizer applicator at each point on the candidate fertilization path. For example, the processor can determine the fertilization time of the fertilizer applicator based on the fertilization time of each unit to be fertilized and the time taken to travel from the current unit to be fertilized to the next unit to be fertilized, where the fertilization time of a single unit to be fertilized can be calculated according to the following formula (2):

[0120] T1 = N × L1 ÷ V1 (2)

[0121] Wherein, T1 represents the fertilization time of a unit to be fertilized, N represents the number of fertilization times of the unit to be fertilized, L1 represents the distance length corresponding to the number of fertilization times of the unit to be fertilized, and V1 represents the travel speed of the fertilizer applicator in the unit to be fertilized.

[0122] The fertilization frequency sequence is a sequence of the fertilization frequency of each unit to be fertilized arranged in the order of fertilization in the candidate fertilization path. For example, for the four units to be fertilized, A, B, C, and D, the candidate fertilization path can be ABCD, and the fertilization frequency sequence is (2, 3, 1, 2), where 2, 3, 1, and 2 correspond to the fertilization frequency of the units A, B, C, and D to be fertilized, respectively.

[0123] The distance length sequence corresponding to the fertilization frequency sequence refers to the sequence composed of the unilateral fertilization distance length of the unit to be fertilized according to the order of fertilization in the candidate fertilization path. The unilateral fertilization distance length refers to the distance length from one side of the unit to be fertilized to another side. For example, for the four units to be fertilized A, B, C, and D, the candidate fertilization path can be ABCD, and the fertilization frequency sequence is (2, 3, 1, 2), where the unilateral average distance lengths corresponding to 2, 3, 1, 2 are S1, S2, S3, S4, and the distance length sequence is (S1, S2, S3, S4). In some embodiments, the fertilization frequency sequence can be determined by obtaining manual input.

[0124] In some embodiments, the number of fertilization times of the unit to be fertilized can be determined based on the area of ​​the unit to be fertilized and the preset effective fertilization width. For example, if the area of ​​unit A to be fertilized is 60 units and the preset effective fertilization width is 20 units, the number of fertilization times of unit A to be fertilized is 3 times (60÷20=3).

[0125] In some embodiments, the effective fertilization width may be related to the fertilization height plan, and the fertilization height plan may be related to weather data for a future period of time.

[0126] The effective fertilization width refers to the horizontal width that the fertilizer can cover in a direction perpendicular to the fertilization direction when the fertilizer applicator performs a single fertilization from one end of the unit to be fertilized to the other end. In some embodiments, the effective fertilization width can be manually determined based on experience and the performance of the fertilizer applicator.

[0127] In some embodiments, the fertilization altitude plan may be determined based on weather data for a future period.

[0128] In some embodiments, the weather data for the future period may include the wind speed of the environment where the unit to be fertilized is located. In some embodiments, the weather data for the future period may be acquired by a weather monitoring unit.

[0129] In some embodiments, the fertilization height planning can be related to the wind speed in the future period. When the drone fertilizes, different fertilization heights will be considered. If the wind speed in the future period increases, the fertilizer will be blown away, thus affecting the fertilization effect. Therefore, the faster the wind speed in the future period, the lower the flight height of the drone and the lower the fertilization height.

[0130] In some embodiments, the effective fertilization width can be related to the fertilization height planning. The planting unit can be regarded as a rectangle, and the lower the flying altitude of the drone, the narrower the effective width of the drone that can fertilize in a single time.

[0131] In some embodiments, the effective fertilization width is also related to the fertilizer spraying rate of the fertilizer applicator.

[0132] In some embodiments, the planting unit is generally rectangular, and the greater the fertilizer spraying rate of the fertilizer applicator and the farther the fertilizer is sprayed, the greater the effective width of the fertilization.

[0133] Generally speaking, under the premise that the fertilizer spraying rate and travel speed of the fertilizer applicator are the same, the larger the effective fertilization width, the larger the area that the fertilizer applicator can complete fertilization in unit time, and the lower the time cost required to complete fertilization. However, due to the fertilization capacity of the fertilizer applicator, the effective fertilization width cannot be increased indefinitely, and at the same spraying rate, an excessively large effective fertilization width will reduce the amount of fertilizer sprayed per unit area, thereby requiring an increase in the number of fertilizations. Therefore, it is necessary to set a reasonable effective fertilization width to obtain higher fertilization efficiency and save time costs for fertilization while ensuring the quality of fertilization.

[0134] In some embodiments of the present specification, the preset effective fertilization width can be adjusted according to the fertilizer spraying rate to obtain a more accurate preset effective fertilization width, and then obtain a more accurate number of fertilization times for the unit to be fertilized, thereby improving the accuracy of the drone fertilization time.

[0135] In some embodiments of the present specification, the fertilization height plan can be determined based on weather data in the future period, and then the preset effective fertilization width can be adjusted, thereby obtaining an effective fertilization width with better fertilization effect.

[0136] In some embodiments, the charging time of the fertilizer applicator can be determined based on the number of charging times. For example, the charging time can be calculated according to the following formula (3):

[0137] T2=E1×E2 (3)

[0138] Wherein, T2 represents the charging time of the fertilizer applicator, E1 represents the number of charging times, and E2 represents the single charging time of the fertilizer applicator.

[0139] In some embodiments, the number of charging times can be determined based on the remaining power of the fertilizer applicator and the reference power of the fertilizer applicator. For example, in response to the remaining power of the fertilizer applicator being less than the reference power of the fertilizer applicator, the processor determines that the fertilizer applicator needs to return for charging midway, and the number of charging times can be calculated according to the following formula (4):

[0140] E1=1+(E3-E4)÷E5

[0141] Among them, E1 represents the number of charging times, E3 represents the reference power of the fertilizer applicator, E4 represents the remaining power of the fertilizer applicator, and E5 represents the maximum storage power of the fertilizer applicator.

[0142] In some embodiments, the reference power of the fertilizer applicator can be calculated according to the following formula (5):

[0143] E3=W×T0

[0144] Among them, W represents the power consumption of the drone per unit time, and T0 represents the fertilization time.

[0145] In the process of fertilizing the fertilization unit, the fertilizer spraying and charging and discharging process are required, and batteries, parts and components will be consumed in the process. If the fertilization can be completed in a shorter time, the consumption of the fertilizer applicator itself can be reduced to a certain extent, so that the fertilizer applicator can complete more fertilization operations. Therefore, in some embodiments, the processor can use the candidate fertilization path with the minimum fertilization cost and / or the fertilization cost not greater than the cost threshold as the target fertilization path.

[0146] In some embodiments of the present specification, the processor can generate multiple candidate fertilization paths, and determine the fertilization costs of the candidate fertilization paths based on the remaining power of the fertilizer applicator and the fertilizer demand characteristics, and use the candidate fertilization paths whose fertilization costs meet preset conditions as the target fertilization paths, thereby ensuring that the fertilization efficiency is improved and better fertilization effects are obtained.

[0147] Some embodiments of the present specification provide a smart crop fertilization device, including a processor, and the processor is used to execute the above-mentioned smart crop fertilization method.

[0148] Some embodiments of the present specification provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the aforementioned intelligent fertilization method for crops.

[0149] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0150] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0151] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and laminar flow hoods in this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0152] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0153] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0154] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0155] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for intelligent fertilization of crops, characterized in that: Processor-based execution, including: Acquiring monitoring data of the planting unit based on the monitoring unit, wherein the monitoring unit includes at least a soil detection unit and a weather monitoring unit, and the monitoring data includes at least soil data and predicted weather data for a future period; Based on the soil data, determining soil characteristics corresponding to the planting unit; In response to the soil characteristics of the planting unit satisfying a fertilization condition, determining the planting unit as a unit to be fertilized; In response to the predicted weather data meeting a first weather condition, determining a fertilizer requirement characteristic based on a target soil component characteristic, wherein the first weather condition includes that there is no rainfall in the future period, and the fertilizer requirement characteristic includes a content ratio of different nutrients in the fertilizer and a fertilizer requirement; wherein determining the fertilizer requirement includes: Adding the contents of different nutrients in the fertilizers of the fertilizer requirement characteristic to obtain an initial fertilizer requirement; Determining an adjustment coefficient based on the sum of the differences between the contents of different nutrients in the soil component characteristics of the unit to be fertilized and the corresponding content thresholds; Based on the adjustment coefficient, the initial fertilizer requirement is adjusted to obtain the fertilizer requirement; Based on the fertilizer diffusion rate of the unit to be fertilized to each adjacent unit to be fertilized, determine the average diffusion rate between the unit to be fertilized and the adjacent units to be fertilized, wherein the fertilizer diffusion rate refers to the rate at which the fertilizer diffuses from the unit to be fertilized to the adjacent units to be fertilized, the fertilizer diffusion rate is related to the fertilizer concentration of the unit to be fertilized and the adjacent units to be fertilized, and the average diffusion rate is the average value of the fertilizer diffusion rate between the unit to be fertilized and the adjacent units to be fertilized; adjusting the fertilizer requirement based on the average diffusion rate; In response to the predicted weather data meeting a second weather condition, predicting soil characteristics of the unit to be fertilized after rain, the second weather condition including the presence of rainfall in the future period; A current feature vector is constructed based on the post-rain soil structure feature in the post-rain soil feature of the unit to be fertilized, at least one reference feature vector that is closest to the current feature vector is selected from a vector database, and the dissolution rates of different nutrients stored in association with the reference feature vectors are weighted averaged as the dissolution rates of different nutrients corresponding to the current feature vector, wherein the weight of the weighted average is related to the reliability of the dissolution rates of different nutrients stored in association with the reference feature vector, and the reliability is determined based on the confidence of the output of a prediction model, the input of the prediction model includes the post-rain soil structure feature of at least one unit to be fertilized, the output of the prediction model includes the confidence of the dissolution rates of different nutrients, and the prediction model is a machine learning model; Determining the fertilizer requirement characteristics based on the post-rain soil characteristics, the target soil characteristics, and the dissolution rates of the different nutrients; generating multiple candidate fertilization paths; For the candidate fertilization path, the number of fertilization times of the unit to be fertilized is determined based on the area of ​​the unit to be fertilized and a preset effective fertilization width; the effective fertilization width is related to the fertilization height planning or the fertilizer spraying rate of the fertilizer applicator, and the fertilizer applicator is implemented based on a drone; the fertilization height planning is related to the wind speed in the future period; The fertilization time of the fertilizer is calculated based on the distance length sequence corresponding to the fertilization frequency sequence and the travel speed of the fertilizer at each point on the candidate fertilization path; the fertilization frequency sequence is a sequence consisting of the fertilization frequency of each unit to be fertilized arranged in the order of fertilization in the candidate fertilization path; The fertilization cost of the fertilizer applicator is determined based on the fertilization time of the fertilizer applicator, the charging time of the fertilizer applicator, and the moving time of the fertilizer applicator when not fertilizing by the formula C=a×T0+b×T2+c×T3, wherein C represents the fertilization cost of the fertilizer applicator, T0 represents the fertilization time of the fertilizer applicator, T2 represents the charging time of the fertilizer applicator, T3 represents the moving time of the fertilizer applicator when not fertilizing, and a, b, and c are weights; Taking the candidate fertilization path whose fertilization cost meets the preset condition as the target fertilization path; The fertilizer applicator is controlled to fertilize the at least one unit to be fertilized based on the target fertilization path.

2. A crop intelligent fertilization system, comprising an acquisition module, a first determination module, a second determination module, a third determination module, a fourth determination module and a control module; The acquisition module is used to acquire monitoring data of the planting unit based on the monitoring unit, the monitoring unit at least includes a soil detection unit and a weather monitoring unit, and the monitoring data at least includes soil data and predicted weather data for a future period; The first determination module is used to determine the soil characteristics corresponding to the planting unit based on the soil data; The second determination module is used for determining that the planting unit is a unit to be fertilized in response to the soil characteristics of the planting unit satisfying the fertilization condition; The third determination module is used to determine the fertilizer demand characteristics based on the target soil component characteristics in response to the predicted weather data meeting the first weather condition, wherein the first weather condition includes the absence of rainfall in the future period, and the fertilizer demand characteristics include the content ratio of different nutrients in the fertilizer and the fertilizer demand; wherein, Determining the fertilizer requirement includes: adding the contents of different nutrients in the fertilizer of the fertilizer requirement characteristic to obtain an initial fertilizer requirement; determining an adjustment coefficient based on the sum of the differences between the contents of different nutrients in the soil composition characteristics of the unit to be fertilized and the corresponding content thresholds; adjusting the initial fertilizer requirement based on the adjustment coefficient to obtain the fertilizer requirement; determining an average diffusion rate between the unit to be fertilized and the adjacent units to be fertilized based on the fertilizer diffusion rate from the unit to be fertilized to each adjacent unit to be fertilized, wherein the fertilizer diffusion rate refers to the rate at which the fertilizer diffuses from the unit to be fertilized to the adjacent units to be fertilized, the fertilizer diffusion rate is related to the fertilizer concentration of the unit to be fertilized and the adjacent units to be fertilized, and the average diffusion rate is the average value of the fertilizer diffusion rate between the unit to be fertilized and the adjacent units to be fertilized; adjusting the fertilizer requirement based on the average diffusion rate; in response to the predicted weather data meeting the second weather conditions, Predicting the post-rain soil characteristics of the unit to be fertilized, wherein the second weather condition includes the presence of rainfall in the future period; constructing a current feature vector based on the post-rain soil structure characteristics in the post-rain soil characteristics of the unit to be fertilized, selecting at least one reference feature vector closest to the current feature vector from a vector database, and taking the weighted average of the dissolution rates of different nutrients stored in association with the reference feature vector as the dissolution rates of the different nutrients corresponding to the current feature vector, wherein the weight of the weighted average is related to the reliability of the dissolution rates of the different nutrients stored in association with the reference feature vector, and the reliability is determined based on the confidence of the output of a prediction model, the input of the prediction model includes the post-rain soil structure characteristics of at least one unit to be fertilized, and the output of the prediction model includes the confidence of the dissolution rates of different nutrients, and the prediction model is a machine learning model; determining the fertilizer demand characteristics based on the post-rain soil characteristics, the target soil characteristics, and the dissolution rates of the different nutrients; The fourth determination module is used to generate a plurality of candidate fertilization paths; for the candidate fertilization paths, the number of fertilizations of the unit to be fertilized is determined based on the area of ​​the unit to be fertilized and the preset effective fertilization width; the effective fertilization width is related to the fertilization height planning or the fertilizer spraying rate of the fertilizer applicator, and the fertilizer applicator is implemented based on a drone; the fertilization height planning is related to the wind speed in the future period; the fertilization time of the fertilizer applicator is calculated based on the distance length sequence corresponding to the fertilization number sequence and the travel speed of the fertilizer applicator at each point on the candidate fertilization path; the fertilization number sequence is arranged according to the order of fertilization in the candidate fertilization path. A sequence is formed by the fertilization times of each unit to be fertilized in the column; based on the fertilization time of the fertilizer applicator, the charging time of the fertilizer applicator, and the moving time of the fertilizer applicator when not fertilizing, the fertilization cost of the fertilizer applicator is determined by the formula C=a×T0+b×T2+c×T3, wherein C represents the fertilization cost of the fertilizer applicator, T0 represents the fertilization time of the fertilizer applicator, T2 represents the charging time of the fertilizer applicator, T3 represents the moving time when the fertilizer applicator is not fertilizing, and a, b, and c are weights; the candidate fertilization path whose fertilization cost meets the preset conditions is taken as the target fertilization path; The control module is used to control the fertilizer applicator to fertilize the at least one unit to be fertilized based on the target fertilization path.

3. An intelligent crop fertilization device, comprising a processor, wherein the processor is used to execute the intelligent crop fertilization method described in claim 1.

4. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the intelligent fertilization method for crops as described in claim 1.

Images