CN116941483A

CN116941483A - Intelligent crop planting method and system

Info

Publication number: CN116941483A
Application number: CN202311006703.0A
Authority: CN
Inventors: 孙彤; 黄桂恒
Original assignee: Brick Suzhou Agricultural Internet Co ltd
Current assignee: Brick Suzhou Agricultural Internet Co ltd
Priority date: 2023-08-10
Filing date: 2023-08-10
Publication date: 2023-10-27
Anticipated expiration: 2043-08-10
Also published as: CN116941483B

Abstract

The embodiment of the specification provides an intelligent crop planting method, which is executed based on a processor and comprises the following steps: determining a planting density scheme based on soil structure data of the planting area; determining a planting adjustment scheme for crops in the planting area based on the planting characteristics of the crops in the planting area; controlling an automatic sowing device to sow the planting area according to a planting density scheme; at least one of the environmental conditioning equipment and the unmanned aerial vehicle is controlled to adjust the planting condition of crops in the planting area according to the planting adjustment scheme. Wherein, the planting adjustment scheme is determined by the following method: acquiring detection data acquired by a detection device deployed in a planting area; determining a planting characteristic of the crop in a planting area based on the detection data; the planting adjustment scheme is determined based on the planting characteristics.

Description

Intelligent crop planting method and system

Technical Field

The specification relates to the technical field of crop planting, in particular to an intelligent crop planting method and system.

Background

The traditional crop planting management is more dependent on human experience, and lacks scientific basis and systematic management methods. Along with the modernization of agricultural development, the application of warmhouse booth is more and more extensive, and the solution of planting problem needs to rely on intelligent management method more. For example, after greenhouse crops are planted, if the planting density of the crops is not proper, remedial measures are required to improve the survival rate, the yield and the quality of the crops. The manual adjustment has subjectivity, and is difficult to accurately judge proper planting density and environment parameters and an adjustment scheme of planting parameters.

In view of the above problems, CN112650337a provides a device and a method for automatically adjusting the crop environment, which monitor the crop growth environment in real time, compare the best parameters required for crop growth in cloud storage with the monitored data, and determine whether the crop needs to be subjected to environmental adjustment operation through data analysis. But this technique does not provide a method for determining optimal adjustment parameters based on the current conditions of the crop.

Therefore, it is desirable to provide an intelligent crop planting method, which can determine a planting scheme and an adjusting scheme according to the crop planting environment and the growth condition, so as to perform targeted optimization adjustment on the planting condition of crops.

Disclosure of Invention

One or more embodiments of the present specification provide a method for intelligent crop planting, the method being processor-based and comprising: determining a planting density scheme based on soil structure data of the planting area; determining a planting adjustment scheme for the crop of the planting area based on a planting characteristic of the crop of the planting area; controlling an automatic sowing device to sow the planting area according to the planting density scheme; controlling at least one of environment adjusting equipment and an unmanned aerial vehicle, and adjusting the planting condition of the crops in the planting area according to the planting adjusting scheme; wherein, the planting adjustment scheme is determined by the following method: acquiring detection data acquired by a detection device deployed in the planting area; determining the planting characteristics of the crop of the planting area based on the detection data; based on the planting characteristics, the planting adjustment scheme is determined.

One of the embodiments of the present disclosure provides an intelligent crop planting system, including a first determining module, a second determining module, a first control module, and a second control module: the first determining module is used for determining a planting density scheme based on soil structure data of a planting area; the second determining module is used for determining a planting adjustment scheme of the crops in the planting area based on the planting characteristics of the crops in the planting area; the first control module is used for controlling an automatic seeding device to seed the planting area according to the planting density scheme; the second control module is used for controlling at least one of environment adjusting equipment and an unmanned aerial vehicle, and adjusting the planting condition of the crops in the planting area according to the planting adjustment scheme; wherein the second determination module is further configured to: acquiring detection data acquired by a detection device deployed in the planting area; determining the planting characteristics of the crop of the planting area based on the detection data; based on the planting characteristics, the planting adjustment scheme is determined.

One or more embodiments of the present specification provide an intelligent crop planting device including a processor for performing an intelligent crop planting method.

One or more embodiments of the present specification provide a computer-readable storage medium storing computer instructions that, when read by a computer in the storage medium, the computer performs a method of intelligent crop planting.

Drawings

The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:

FIG. 1 is an exemplary block diagram of a crop intelligent planting system according to some embodiments of the present description;

FIG. 2 is an exemplary flow chart of a method of intelligent crop planting according to some embodiments of the present disclosure;

FIG. 3 is an exemplary schematic diagram of an image processing model shown in accordance with some embodiments of the present description;

FIG. 4 is an exemplary schematic diagram of determining a planting adjustment scheme according to some embodiments of the present description;

FIG. 5 is an exemplary schematic diagram of determining a second planting adjustment scheme, according to some embodiments of the present description.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.

It will be appreciated that "system," "apparatus," "unit" and/or "module" as used herein is one method for distinguishing between 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.

As used in this specification and the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.

In the process of intelligently adjusting the crop growth parameters, the adjustment based on preset parameter values (such as temperature and humidity) is simple and lacks pertinence due to different soil conditions for planting crops, different growth periods for the crops and different planting densities for the crops. In the method provided by CN112650337, crop monitoring data is compared with preset optimal parameters, and according to the comparison result, whether the crop needs to be subjected to environmental conditioning operation is determined. However, this scheme does not account for other data, other than irrigation parameters, for comparison, nor for determining adjustment parameters.

In some embodiments of the present disclosure, the initial planting density may be determined based on soil conditions, and then determined based on environmental data, crop growth conditions, and an optimized adjustment scheme is provided. Some embodiments of the present disclosure may provide for the targeted formulation of different adjustment schemes based on different growth conditions of the crop, resulting in an improvement in the overall growth condition of the crop.

FIG. 1 is an exemplary block diagram of a crop intelligent planting system according to some embodiments of the present description.

In some embodiments, the crop intelligent planting system 100 may include a first determination module 110, a second determination module 120, a first control module 130, and a second control module 140.

In some embodiments, the first determination module 110 is configured to determine a planting density scheme based on soil structure data of a planting area.

In some embodiments, the second determination module 120 is configured to determine a planting adjustment scheme for the crop of the planting area based on a planting characteristic of the crop of the planting area. Further, the second determining module may be further configured to obtain detection data collected by a detection device disposed in the planting area; determining planting characteristics of crops in a planting area based on the detection data; based on the planting characteristics, a planting adjustment scheme is determined. In some embodiments, the detection data includes a crop image, a plurality of sets of soil composition data; the planting features include growth features and nutrient absorption features.

In some embodiments, the second determination module 120 is further to: extracting crop growth characteristics based on at least one crop image; based on the sets of soil composition data, nutrient absorption characteristics are determined. Wherein, the multiple groups of soil component data correspond to the multiple groups of detection points.

In some embodiments, the second determination module 120 is further to: determining an adjustment type of the planting area based on the planting characteristics, the adjustment type including a first adjustment and a second adjustment (the first adjustment and the second adjustment being related to a planting density of the crop in the planting area); responsive to the adjustment type being a first adjustment, determining a first planting adjustment scheme based on the planting characteristics, the first planting adjustment scheme including a fertilization scheme; in response to the adjustment type being a second adjustment, a second planting adjustment scheme is determined based on the planting characteristics, the second planting adjustment scheme including an environmental adjustment scheme, a fertilization scheme.

In some embodiments, the second determination module 120 is further to: determining an environmental compensation zone based on the growth characteristics of the crop; determining a candidate environmental adjustment scheme based on the environmental compensation region; determining future growth characteristics of crops corresponding to the candidate environment adjustment scheme based on the evaluation model; the evaluation model is a machine learning model; selecting a candidate environment adjustment scheme with future growth characteristics meeting preset conditions as a target environment adjustment scheme of the second planting adjustment scheme; the fertilization scheme is determined based on nutrient absorption characteristics of the crop.

In some embodiments, the first control module 130 is used to control the automatic seeding device to seed the planting area in a planting density scheme.

In some embodiments, the second determination module is configured to determine 140 a planting adjustment scheme for the crop of the planting area based on a planting characteristic of the crop of the planting area.

In some embodiments, the above modules may be integrated into a processor and the above operations performed by the processor. In some embodiments, the processor may be configured as a GPU (Graphics Processing Units, graphics processor) or a Single-Board computer (Single-Board Computers), or the like.

For more details, reference may be made to the relevant descriptions of the other parts, which are not repeated here.

It should be understood that the system shown in fig. 1 and its modules may be implemented in a variety of ways.

It should be noted that the above description of the intelligent crop planting system and the modules thereof is for convenience of description only, and is not intended to limit the present description to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the principles of the system, various modules may be combined arbitrarily or a subsystem may be constructed in connection with other modules without departing from such principles. In some embodiments, the first determining module, the second determining module, the first control module and the second control module disclosed in fig. 1 may be different modules in one system, or may be one module to implement the functions of two or more modules. For example, each module may share one memory module, or each module may have a respective memory module. Such variations are within the scope of the present description.

Fig. 2 is an exemplary flow chart of a method for intelligent crop planting according to some embodiments of the present disclosure.

In some embodiments, the process 200 may be performed by a processor. As shown in fig. 2, the process 200 includes the steps of:

at step 210, a planting density plan is determined based on soil structure data of the planting area.

The planting area refers to an area where crops are planted.

Soil structure data refers to data characterizing the physical structure of the soil, such as temperature, humidity, PH, porosity, softness, etc. of the soil. In some embodiments, the processor may pre-sample the soil and obtain soil structure data via soil detection techniques.

The planting density scheme refers to a scheme related to the density of crop planting. In some embodiments, the planting density scheme can include planting distances of crops both laterally and longitudinally.

In some embodiments, the processor may construct the current feature vector based on the soil composition data, the soil structure data, and the environmental data; selecting a historical feature vector with the minimum vector distance from the current feature vector from the feature vector library as a reference feature vector; and taking the planting density scheme stored in association with the reference feature vector in the feature vector library as the planting density scheme corresponding to the current feature vector. The feature vector library may store a plurality of historical feature vectors constructed based on the historical soil composition data, the historical soil structure data, and the historical environmental data, and a planting density scheme corresponding to each of the historical feature vectors.

The soil composition data refers to data related to the composition contained in the soil, such as the content of each nutrient in the soil. Environmental data refers to data related to the environment in which the planting area is located, such as ambient temperature, humidity, illumination intensity, altitude, etc. In some embodiments, the processor may acquire soil composition data via a detection device deployed at a detection point of the planting area; environmental data is acquired by various types of sensors.

Step 220, determining a planting adjustment scheme for the crop in the planting area based on the planting characteristics of the crop in the planting area.

Planting characteristics refer to characteristics related to the planting of crops. In some embodiments, the planting features may include density features, growth features of crops, nutrient absorption features, and the like.

Density characteristics refer to characteristics that characterize the overall distribution gap of crops in a planting area, such as the coverage of the branches and leaves of crops, crop gaps, and the like. In some embodiments, the processor may identify the area of soil not planted with the crop from the crop image by a variety of techniques such as image recognition, edge detection, etc., divide the area of soil not planted with the crop by the total area of the planted area to obtain the idle ratio, and take the difference between 1 and the idle ratio as the density characteristic.

For further description of crop growth characteristics, nutrient absorption characteristics and crop images see the relevant description below.

The planting adjustment scheme refers to a scheme for adjusting the planting environment and/or fertilization condition of crops.

In some embodiments, the processor may acquire detection data acquired by a detection device deployed at the planting area; determining planting characteristics of crops in a planting area based on the detection data; based on the planting characteristics, a planting adjustment scheme is determined.

The detection device is a device for detecting a planting area. In some embodiments, the detection device may include a variety of sensors and image acquisition devices, and the detection device may be deployed at one or more preset detection points.

The detection data means data obtained by detecting the planting area by the detection device. In some embodiments, the detection data may include crop images and sets of soil composition data.

In some embodiments, the processor may capture an image of the crop by capturing the crop with the detection apparatus. In some embodiments, the plurality of sets of soil composition data correspond to the plurality of sets of detection points, and for further details regarding the soil composition data, reference may be made to the foregoing description.

In some embodiments, the processor may determine the planting characteristics in a variety of ways based on the detection data. For example, the processor may determine the planting characteristics by querying a first preset table. The first preset table may further include an association between the detection data and the planting feature. In some embodiments, the first preset table may be determined based on historical data.

In some embodiments, the processor may extract a growth characteristic of the crop based on the at least one crop image; based on the sets of soil composition data, nutrient absorption characteristics are determined.

The growth characteristics of crops are characteristics for representing the overall growth and development conditions of crops in a planting area, such as crop growth vigor, fruit development conditions and the like. In some embodiments, the growth characteristics of the crop may include a sequence of degrees of uniformity of fruit quality for a plurality of preset sub-regions and a degree of uniformity of fruit quality for the entire planting region. The sequence of the degree of consistency of the fruit quality of the plurality of preset sub-areas refers to a sequence formed by the degree of consistency of the fruit quality of the plurality of preset sub-areas. The degree of uniformity of the overall fruit quality of the planting area refers to an index for evaluating the degree of uniformity of the overall fruit quality of the planting area, and the manner of obtaining the same can be seen from the following related description. The preset sub-area refers to a plurality of sub-areas of preset shape and/or size into which the planting area is divided in advance.

In some embodiments, the processor analyzes the consistency degree of the fruit quality of each preset subarea, and the consistency degree of the fruit quality of the subarea is high, so that the overall growth and development conditions of crops in the subarea are proved to be good; the consistency degree is not high, and the conditions of the whole growth and development of the crops in the subregion are proved to be inconsistent, and the conditions of uneven illumination and nutrient substance intake exist.

In some embodiments, the processor may extract the appearance features of the fruit based on the crop image by manual recognition or techniques such as image recognition, edge detection, etc.; determining a quality score for the fruit based on the appearance characteristics; a standard deviation is calculated for quality scores of a plurality of fruits, and a degree of consistency of fruit quality is determined based on the standard deviation.

In some embodiments, the processor may determine a quality score based on the obtained appearance features by a preset correspondence of the appearance features to the quality scores, and calculate standard deviations of the quality scores of the plurality of fruits; and determining the degree of consistency based on the calculated standard deviation through the corresponding relation between the preset standard deviation and the degree of consistency, wherein the smaller the standard deviation is, the higher the degree of consistency is.

Appearance characteristics refer to characteristics related to the appearance of the fruit, such as fruit size, degree of shape standard, whether there is chapping, whether there is protrusion, etc.

In some embodiments, the appearance features may also include touch features.

The touch feature refers to a feature related to touch feedback of the fruit. In some embodiments, the touch features may include an elastic sequence and a deformation sequence.

The elastic sequence is a sequence composed of elastic feedback of fruit when the fruit is touched. The deformation sequence refers to a sequence consisting of deformation degrees caused by touching fruits.

The elasticity of the fruit is different, and the elasticity generated by touching the fruit is also different. Thus, in some embodiments, the processor may use a robot to hold different fruits with a preset force, collect the elastic sequence fed back by the pressure sensor and the multi-frame deformation image of the process. The processor can extract the deformation degree corresponding to each frame of deformation image through an image recognition technology, and a plurality of deformation degrees corresponding to a plurality of frames of deformation images form a deformation sequence. Wherein, the dynamics of manipulator default needs to be based on actual conditions and confirms, avoids the dynamics too big to pinch out the fruit.

According to some embodiments of the present disclosure, touch characteristics of the fruits are obtained by a mechanical hand, so that appearance characteristics of the fruits can be obtained more comprehensively and three-dimensionally, and further determination of growth characteristics of crops can be facilitated.

In some embodiments, the processor may extract growth characteristics of the crop based on the image processing model, for more see fig. 2 and its associated description.

The nutrient absorption characteristics refer to characteristics for representing absorption conditions (such as absorption rate and the like) of different nutrient substances of crops at a plurality of groups of detection points in a planting area. When the difference of the absorption rates of nutrient substances at different detection points is large, the nutrient substances of crops are represented to be unevenly contended, and the fertilization amount can be increased nearby the point with the slower absorption rate subsequently.

In some embodiments, the processor may calculate the nutrient absorption characteristics from the collected soil composition data. For example, for a certain detection point, the processor may acquire soil component data of the point detected by at least two detection devices adjacent to the historical moment (e.g., T1, T2), so as to calculate the nutrient absorption characteristic of the point. Taking nutrient m as an example, the nutrient absorption characteristic= (content of nutrient m at T1-content of nutrient m at T2)/(T2-T1) ×100%.

After the processor divides the planting area into a plurality of subregions, each subregion can correspond a set of testing point position, in some embodiments, the detection device that detects multiunit soil composition data can be set up to movable to according to actual demand to arbitrary position acquisition soil composition data, and then acquire the nutrient absorption characteristic of corresponding position.

Some embodiments of the present disclosure extract crop growth characteristics based on crop images and determine nutrient absorption characteristics based on multiple sets of soil composition data, helping to obtain more accurate specific planting characteristics in order to determine a planting adjustment scheme based on the planting characteristics.

In some embodiments, the processor may determine the planting adjustment scheme in a variety of ways based on the planting characteristics. For example, the processor may determine a planting adjustment scheme corresponding to a historical planting feature that is similar to the current planting feature as a planting adjustment scheme corresponding to the current planting feature by querying a second preset table based on the planting feature. The second preset table may include correspondence between different planting characteristics and planting adjustment schemes. In some embodiments, the second preset table may be determined based on historical data.

In some embodiments, the processor may determine the type of adjustment for the planting area based on the planting characteristics, and thus the planting adjustment scheme, for more reference to fig. 4 and its associated description.

And 230, controlling the automatic sowing device to sow the planting area according to the planting density scheme.

The automatic seeding apparatus refers to a device that can automatically perform seeding, such as an unmanned aerial vehicle, an automatic seeding robot, or the like.

In some embodiments, the processor may control the automatic seeding apparatus to seed in a variety of ways. For example, the processor may generate and issue control instructions containing a planting density scheme to the automated seeding device to control the automated seeding device to seed the planting area with the planting density scheme.

And step 240, controlling at least one of the environment adjusting equipment and the unmanned aerial vehicle to adjust the planting condition of crops in the planting area according to the planting adjustment scheme.

The environmental conditioning device refers to a device that conditions the environment of the planting area, such as a temperature control device, a humidity control device, a lighting device, a sunshade device, and the like. Wherein, temperature control device can adjust ambient temperature, and humidity control device can adjust ambient humidity, and lighting device and sunshade equipment can adjust the illumination intensity of environment, and lighting device is used for supplementing illumination, and sunshade equipment is used for reducing illumination.

In some embodiments, the processor may control the automatic seeding apparatus to seed in a variety of ways. For example, the processor may generate and issue control instructions containing a planting adjustment scheme to the environmental conditioning device and/or the drone to control the environmental conditioning device and/or the drone to plant the adjustment scheme to adjust the planting of the crop in the planting area.

According to some embodiments of the present disclosure, a planting density scheme is determined based on soil structure data of a planting area, and a planting adjustment scheme of crops in the planting area is determined based on planting characteristics of the crops in the planting area, so that the planting density suitable for the growth of the crops can be determined before sowing, and remedial measures are taken when the planting density of the planted crops is unsuitable, so as to meet basic growth requirements of the crops by adjusting the planting scheme, thereby realizing the intellectualization of crop planting.

It should be noted that the above description of the flow is only for the purpose of illustration and description, and does not limit the application scope of the present specification. Various modifications and changes to the flow may be made by those skilled in the art under the guidance of this specification. However, such modifications and variations are still within the scope of the present description.

Fig. 3 is an exemplary schematic diagram of an image processing model shown in accordance with some embodiments of the present description.

In some embodiments, the processor may extract the growth characteristics 340 of the crop through the image processing model 320 based on the crop image 310. For more on the crop image 310 and the growth characteristics 340 of the crop, see fig. 2 and its associated description.

The image processing model 320 may be a machine learning model. In some embodiments, the image processing model 320 may include a feature extraction layer 321 and a prediction layer 322.

In some embodiments, the feature extraction layer 321 may be used to extract multiple sets of object boxes 330 of at least one crop image 310.

The object frame 330 may refer to a frame that encloses objects when the objects are identified, where an object refers to a completely photographed fruit. Each group of object frames corresponds to a preset sub-region, and each object frame in each group of object frames represents a completely photographed fruit.

The input of the predictive layer 322 may include multiple sets of object boxes 330 and the output may include growth characteristics 340 of the crop corresponding to the crop image 310.

In some embodiments, feature extraction layer 321 and prediction layer 322 may be machine learning models of convolutional neural network models or other network structures.

In some embodiments, the feature extraction layer 321 and the prediction layer 322 of the image processing model 320 may be obtained by a first training sample joint training. Each set of training samples in the first training samples may include a sample crop image, and the first label may be a growth characteristic of the crop in the manually labeled sample crop image (may include a sequence of degrees of uniformity of fruit quality in a plurality of preset sub-regions and a degree of uniformity of fruit quality in an entirety of the planting region). The first training sample may be obtained based on historical detection data.

In some embodiments, the processor may calculate, for a plurality of object frames of one group of object frames corresponding to the sample crop image, a similarity between every two object frames, and take an average value of the plurality of similarity as a consistency degree of fruit quality of a sub-region corresponding to the group of object frames; repeating the calculation for each group of object frames corresponding to the sample crop image to obtain a consistent degree sequence of fruit quality of a plurality of preset subareas.

In some embodiments, the processor may randomly select the same number of object frames from each group of object frames corresponding to the sample crop image, calculate the similarity between every two selected object frames, and use the average value of the similarity as the consistency degree of the overall fruit quality of the planting area.

In some embodiments, the processor may input the sample crop image into the initial feature extraction layer, determining a plurality of sets of object frames for the sample crop image; inputting the output of the initial characteristic extraction layer into an initial prediction layer to obtain the predicted growth characteristics of crops; and constructing a loss function according to the output of the initial prediction layer and the first label. Updating the initial feature extraction layer and the initial prediction layer based on the loss function, and determining the trained feature extraction layer and the trained prediction layer through parameter updating.

In some embodiments of the present disclosure, the growth characteristics of crops are determined by an image processing model, and the self-learning capability of a machine learning model is utilized; the image processing model is set as the feature extraction layer and the prediction layer, corresponding data are processed based on different layers respectively, the data processing efficiency can be further improved, and the accuracy of the growth features of crops is improved.

FIG. 3 is an exemplary schematic diagram of determining a planting adjustment scheme according to some embodiments of the present description.

In some embodiments, the processor may determine an adjustment type 420 for the planting area based on the planting characteristics 410; responsive to the adjustment type being a first adjustment 431, determining a first planting adjustment scheme 440 based on the planting characteristics 410; in response to the adjustment type being a second adjustment 432, a second planting adjustment scheme 450 is determined based on the planting characteristics 410.

In some embodiments, the adjustment types may include a first adjustment 431 and a second adjustment 432.

In some embodiments, the first adjustment or the second adjustment is used to adjust the planting density of the crop relative to the planting area.

When the planting density of the crop in the planting area is too sparse, the processor may determine that the adjustment type is a first adjustment 431; when the crop planting density of the planting area is too dense, the processor may determine the adjustment type as a second adjustment 432. The planting density of the crop in the planting area may be determined based on density characteristics, such as when the density characteristics are below a preset density threshold, the planting density of the crop is considered too sparse. For more on density characteristics see fig. 2 and its associated description.

The first planting adjustment scheme 440 refers to a planting adjustment scheme corresponding to the first adjustment 431. In some embodiments, the first planting adjustment scheme may include a fertilization scheme 441.

The fertilization scheme 441 refers to a scheme related to fertilization of crops, such as fertilization frequency, fertilization times, and the like.

In some embodiments, the processor may determine the first planting adjustment scheme in a variety of ways. For example, the processor may construct a vector to be matched based on the planting features, search a vector database for a reference vector having a highest similarity to the vector to be matched, and use a first planting adjustment scheme corresponding to the reference vector as a first planting adjustment scheme corresponding to the vector to be matched. The vector database may include a plurality of sets of reference vectors formed by a plurality of historical planting features, and a first planting adjustment scheme corresponding to each set of reference vectors.

In some embodiments, the fertilization scheme may include a next fertilization time of the drone; the processor can calculate the estimated starvation time point of each nutrient based on the current soil composition data and nutrient absorption characteristics in the planting characteristics; and in response to the future time point meeting the insufficient nutrient category number exceeding a quantity threshold, determining the future time point as the next fertilization time.

The next fertilization time refers to the next fertilization time of crops by the unmanned aerial vehicle.

The estimated starvation time point refers to a time point when a certain nutrient in the soil of the planting area is deficient.

In some embodiments, the processor may calculate an estimated starvation time for each nutrient based on current soil composition data, nutrient absorption characteristics in the planting characteristics. For example, at the current time T0, the content of the nutrient m is a, the nutrient absorption rate of the nutrient m is b, and the estimated starvation time t=t0+ (a-c)/(b), where c is a threshold value of the content of the nutrient m, may be determined according to practical situations.

The future time point refers to a future time point, and may be determined based on a preset, for example, a next fertilization candidate time point is taken as the future time point.

The quantity threshold is a value that evaluates whether the quantity of the type of starved nutrient exceeds a certain range. The number threshold may be determined based on historical experience.

In some embodiments, the quantity threshold is related to a difference in absorption rates of different nutrients.

The difference in absorption rate of different nutrients refers to the difference between the maximum absorption rate and the minimum absorption rate of different nutrients. For a determination of the absorption rate of different nutrients, reference can be made to fig. 2 and the description related thereto.

In some embodiments, the greater the difference in the absorption rates of different nutrients, the smaller the quantity threshold.

In some embodiments of the present disclosure, in the case that the difference of the absorption rates of different nutrients is large and the number threshold is also large, the individual nutrients may be in an extremely deficient state, so that the survival rate of crops and the quality of fruits are improved by correlating the number threshold with the difference of the absorption rates of different nutrients, so that the situation that fertilization is performed only after the individual nutrients are extremely deficient is avoided.

In some embodiments, the processor may determine that the future point in time is equal to or later than the predicted point in time of starvation of the nutrient.

In some embodiments, the processor may determine the next fertilization time in a variety of ways. For example, the processor may directly take the future point in time when the number of types of starved nutrients exceeds the number threshold as the next fertilization time.

The second planting adjustment scheme 450 refers to a planting adjustment scheme corresponding to the second adjustment 432. In some embodiments, the second planting adjustment scheme can include a fertilization scheme 441 and an environmental adjustment scheme 451. For more details regarding the fertilization scheme 441, see the previous description.

The environment adjustment scheme 451 is a scheme for adjusting the environment of the planting area, and is related to adjustment of environmental parameters such as illumination, temperature, humidity, and the like.

In some embodiments, the processor may determine the second planting adjustment scheme in a variety of ways based on the planting characteristics. For example, the processor may determine, based on the planting characteristics, a second planting adjustment scheme corresponding to a current planting characteristic as a second planting adjustment scheme corresponding to the current planting characteristic by querying a third preset table. The third preset table may include correspondence between different planting characteristics and the second planting adjustment scheme. In some embodiments, the third preset table may be determined based on historical data.

For more details on determining the second planting adjustment scheme, see fig. 5 and its associated description.

According to some embodiments of the present disclosure, the adjustment type is determined according to the planting characteristics, and an appropriate planting adjustment scheme can be flexibly adopted in combination with the actual conditions of crops in the planting area, for example, only the adjustment of the fertilization scheme is involved in the case of sparse crops, and the adjustment of the environment and the fertilization scheme is involved in the case of dense crops, so that the targeted adjustment of the planting areas with different planting characteristics is facilitated, and the intelligence of the planting adjustment is improved.

In some embodiments, the processor may determine the environmental compensation zone 510 based on the growth characteristics 340 of the crop; determining a candidate environmental adjustment scheme 520 based on the environmental compensation region 510; determining future growth characteristics 540 of the crop corresponding to the candidate environmental adjustment 520 based on the assessment model 530; selecting a candidate environment adjustment scheme 520 with future growth characteristics 540 meeting preset conditions as a target environment adjustment scheme 560 of the second planting adjustment scheme; the fertilization scheme 441 is determined based on the nutrient absorption characteristics 550 of the crop.

The environment compensation area 510 is a sub-area in which compensation of environmental parameters is required, for example, a sub-area in which the fruit quality is low in uniformity.

In some embodiments, the processor may determine the sub-region of the crop growth characteristics where the degree of uniformity of fruit quality is below the uniformity threshold as the environmental compensation region. The consistency threshold may be set based on historical experience. For more details on the degree of consistency of fruit quality, see fig. 2 and its associated description.

Candidate environmental adjustment 520 refers to an alternative to adjust the planting area environment. In some embodiments, the candidate environmental adjustment scheme may include an adjustment amount for the temperature, humidity, illumination intensity, and adjustment execution time, etc., for each environmental compensation zone.

In some embodiments, the moving means may cause the environmental conditioning device to move to the environmental compensation zone, providing environmental compensation for the environmental compensation zone, for more details regarding the environmental conditioning device, see fig. 2 and the associated description.

In some embodiments, the processor may randomly generate a predetermined number of candidate environmental adjustment schemes within a predetermined range of environmental parameters.

In some embodiments, the evaluation model 530 may be a machine learning model, such as a neural network model, or the like.

In some embodiments, the input of the assessment model may include candidate environmental adjustment schemes, crop characteristics, soil structure data, environmental data; the output may include future growth characteristics 540 of the crop corresponding to the candidate environmental adjustment scheme. For more on soil structure data, environmental data see fig. 2 and its related description.

Crop characteristics refer to characteristics associated with crops, such as crop species, crop properties (e.g., happiness of the shade, happiness of the temperature, etc.), and the like.

Future growth characteristics 540 refer to growth characteristics of the crop at some point in the future, and more on the growth characteristics of the crop can be found in fig. 2 and its associated description.

In some embodiments, the assessment model may be trained from a plurality of second training samples with second labels. For example, a plurality of second training samples with second labels may be input into the evaluation model, a loss function is constructed through the second labels and the prediction results of the initial evaluation model, the initial evaluation model is updated based on the iteration of the loss function, and training is completed when the loss function of the initial evaluation model meets a preset condition, where the preset condition may be that the loss function converges, the number of iterations reaches a threshold value, and the like.

In some embodiments, the second training samples may include sample candidate environmental adjustment schemes, sample crop features, sample soil structure data, and sample environmental data for the first historical period of time. In some embodiments, the second training sample may be obtained based on historical data. The second signature may include a growth characteristic of the crop for a second historical period of time, and the determination of the growth characteristic of the crop may be found in fig. 2 and its associated description. Wherein the first historical time period is before the environmental adjustment and the second historical time period is after the environmental adjustment.

Some embodiments of the present disclosure, by processing candidate environmental adjustment schemes through an evaluation model, may find rules from a large amount of historical data, helping to more accurately determine future growth characteristics for subsequent determination of target environmental adjustment schemes.

The preset condition refers to a condition which is required to be met by the future growth characteristics when the preset candidate environment adjustment scheme can be used as the target environment adjustment scheme.

For example, the preset condition may be that the degree of uniformity of fruit quality for individual environmental compensation zones in the future growth characteristics is above a first threshold. As another example, the preset condition may be that the degree of uniformity of the overall fruit quality throughout the planting area is above a second threshold. The first threshold and the second threshold may be determined based on historical experience.

The target adjustment scheme is an environment adjustment scheme selected when the environment of the planting area is actually adjusted.

In some embodiments, the processor may determine the target environment adjustment scheme in a variety of ways. For example, when there is only one candidate environment adjustment scheme satisfying the preset condition, the processor may directly regard the candidate environment adjustment scheme as the target environment adjustment scheme. For another example, when there are a plurality of candidate environmental adjustment schemes satisfying the preset condition, the processor may select a candidate environmental adjustment scheme having the highest degree of consistency of the overall fruit quality of the entire planting area as the target adjustment scheme.

In some embodiments, the processor may determine the fertilization scheme in a variety of ways based on the nutrient absorption characteristics 550. The manner in which the processor determines the next time the drone is fertilized in the fertilisation scheme may be seen in fig. 4 and its associated description.

In some embodiments, the fertilization scheme 441 may also include a drone fertilization frequency and a time sequence of drone stay for a plurality of environmental compensation areas; the time series of unmanned aerial vehicle stay in the plurality of environment compensation areas can be determined based on nutrient absorption characteristics of crops.

The unmanned aerial vehicle fertilization frequency refers to the frequency of unmanned aerial vehicle fertilization to crops. In some embodiments, the unmanned aerial vehicle fertilization frequency may be determined by a preset relationship based on the planting characteristics, wherein the preset relationship may be: the greater the density characteristic of crops in the planting characteristics, the greater the unmanned aerial vehicle fertilization frequency.

The time sequence in which the unmanned aerial vehicle stays refers to a sequence of time in which the unmanned aerial vehicle stays in a plurality of environment compensation areas.

In some embodiments, the drone executes a preset fertilization path, and the processor may determine the time for each environmental compensation zone for the drone to stay based on the nutrient absorption characteristics of the crop, and determine a time sequence for the drone to stay in conjunction with the fertilization path. Wherein, unmanned aerial vehicle dwell time of other subregions except the environmental compensation district in the planting district defaults to 0.

In some embodiments, the time that each environmental compensation zone drone remains may be obtained through steps S1-S3.

Step S1, calculating the comprehensive absorption rate of the environment compensation area based on the nutrient absorption characteristics.

The integrated absorption rate refers to the rate at which crops in the environment-compensated area are integrated to absorb different nutrients. In some embodiments, the processor may average the absorption rates of different nutrients as a composite absorption rate.

And S2, determining a difference value between the comprehensive absorption rate and a reference rate threshold.

The reference rate threshold refers to a threshold that is a reference for the integrated absorption rate.

In some embodiments, the reference rate threshold may be a dynamic threshold, related to nutrient absorption characteristics of other sub-areas of the planting area than the environmental compensation area.

In some embodiments, the processor may weight sum the integrated absorption rates of the nutrients of the other sub-regions as a reference rate threshold.

In some embodiments, the weights at the time of weighted summation may be related to the degree of uniformity of fruit quality of other subregions.

In some embodiments, the greater the degree of uniformity of fruit quality for a sub-region, the greater the weight of the combined absorption rate for that sub-region.

According to the embodiment of the specification, the weighted weight is related to the consistency degree of the fruit quality of other subareas, so that the comprehensive absorption rate of the nutrient substances in the subareas with high consistency degree of the fruit quality can be more occupied in the determination of the reference rate threshold value, the determination of the reference rate threshold value can be more reasonable, and the calculation of the subsequent unmanned aerial vehicle residence time is facilitated.

Some embodiments of the present disclosure may enable the reference rate threshold to be adjusted with actual conditions by setting the reference rate threshold to be a dynamic threshold, with respect to nutrient absorption characteristics of other sub-areas other than the environmental compensation zone, which may help to more reasonably determine the reference rate threshold.

And step S3, determining the residence time of the unmanned aerial vehicle in each environment compensation area based on a preset relation comparison table.

The preset relation comparison table is a corresponding relation table between a preset difference value between the comprehensive absorption rate and the reference rate threshold value and the residence time of the unmanned aerial vehicle in the environment compensation area. In some embodiments, the preset relationship lookup table may be determined based on historical experience.

In some embodiments, the processor may query a preset relationship lookup table based on a difference between the integrated absorption rate and the reference rate threshold, and obtain a time for the unmanned aerial vehicle to stay corresponding to the difference.

According to some embodiments of the present disclosure, the time sequence of the unmanned aerial vehicle stay is determined through the nutrient absorption characteristics, so that the stay time of the unmanned aerial vehicle in the environment compensation area with low crop nutrient seed absorption rate can be prolonged appropriately, so as to ensure that more fertilizer is applied to the environment compensation area, and the fertilizer in each environment compensation area is fully compensated.

According to some embodiments of the present disclosure, an environment compensation area is determined according to growth characteristics of crops, a candidate environment adjustment scheme is determined based on the environment compensation area, a candidate environment adjustment scheme with future growth characteristics meeting preset conditions is selected as a target environment adjustment scheme, and a fertilization scheme is determined based on nutrient absorption characteristics of crops, so that efficient and accurate determination of a second planting adjustment scheme is facilitated, and the problem of uneven crop growth caused by improper crop density is solved.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations to the present disclosure may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this specification, and therefore, such modifications, improvements, and modifications are intended to be included within the spirit and scope of the exemplary embodiments of the present invention.

Meanwhile, the specification uses specific words to describe the embodiments of the specification. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present description. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present description may be combined as suitable.

Furthermore, the order in which the elements and sequences are presented in this specification, the use of numerical letters, or other designations, is not intended to limit the order in which the processes and systems of this specification are presented unless specifically recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present disclosure. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.

Likewise, it should be noted that in order to simplify the presentation disclosed in this specification and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the present description. Indeed, less than all of the features of a single embodiment disclosed above.

In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., referred to in this specification is incorporated herein by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the content of this specification, documents that are currently or later attached to this specification in which the broadest scope of the claims to this specification is limited are also. It is noted that, if the description, definition, and/or use of a term in an attached material in this specification does not conform to or conflict with what is described in this specification, the description, definition, and/or use of the term in this specification controls.

Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.

Claims

1. A method of intelligent crop planting, the method being performed on a processor basis, comprising:

determining a planting density scheme based on soil structure data of the planting area;

determining a planting adjustment scheme for the crop of the planting area based on a planting characteristic of the crop of the planting area;

controlling an automatic sowing device to sow the planting area according to the planting density scheme;

controlling at least one of environment adjusting equipment and an unmanned aerial vehicle, and adjusting the planting condition of the crops in the planting area according to the planting adjusting scheme;

wherein, the planting adjustment scheme is determined by the following method:

acquiring detection data acquired by a detection device deployed in the planting area;

Determining the planting characteristics of the crop of the planting area based on the detection data;

based on the planting characteristics, the planting adjustment scheme is determined.

2. The method of claim 1, the detection data comprising a crop image, a plurality of sets of soil composition data; the planting features include growth features, nutrient absorption features;

the determining the planting characteristics of the crop of the planting area based on the detection data includes:

extracting crop growth characteristics based on at least one of the crop images;

determining the nutrient absorption characteristics based on the plurality of sets of soil composition data; the plurality of groups of soil component data correspond to a plurality of groups of detection points.

3. The method of claim 1, the determining the planting adjustment scheme based on the planting characteristics comprising:

determining an adjustment type of the planting area based on the planting characteristics, the adjustment type including a first adjustment and a second adjustment, the first adjustment and the second adjustment being related to a planting density of the crop in the planting area;

determining the first planting adjustment scheme based on the planting characteristics in response to the adjustment type being the first adjustment, the first planting adjustment scheme including a fertilization scheme;

And determining a second planting adjustment scheme based on the planting characteristics in response to the adjustment type being a second adjustment, the second planting adjustment scheme including an environmental adjustment scheme, a fertilization scheme.

4. The method of claim 3, the determining the second planting adjustment scheme based on the planting characteristics in response to the adjustment type being a second adjustment comprising:

determining an environmental compensation zone based on the growth characteristics of the crop;

determining a candidate environmental adjustment scheme based on the environmental compensation region;

determining future growth characteristics of the crop corresponding to the candidate environmental adjustment scheme based on an evaluation model; the evaluation model is a machine learning model;

selecting the candidate environment adjustment scheme with the future growth characteristics meeting preset conditions as a target environment adjustment scheme of the second planting adjustment scheme;

the fertilization scheme is determined based on nutrient absorption characteristics of the crop.

5. An intelligent crop planting system comprises a first determining module, a second determining module, a first control module and a second control module;

the first determining module is used for determining a planting density scheme based on soil structure data of a planting area;

The second determining module is used for determining a planting adjustment scheme of the crops in the planting area based on the planting characteristics of the crops in the planting area;

the first control module is used for controlling an automatic seeding device to seed the planting area according to the planting density scheme;

the second control module is used for controlling at least one of environment adjusting equipment and an unmanned aerial vehicle, and adjusting the planting condition of the crops in the planting area according to the planting adjustment scheme;

wherein the second determination module is further configured to:

6. The system of claim 5, the detection data comprising a crop image, a plurality of sets of soil composition data; the planting features include growth features, nutrient absorption features;

the second determination module is further to:

extracting growth characteristics of the crop based on at least one image of the crop;

7. The system of claim 5, the second determination module further to:

8. The system of claim 7, the second determination module further to:

9. An intelligent crop planting device comprising a processor for performing the intelligent crop planting method of any one of claims 1-4.

10. A computer readable storage medium storing computer instructions which, when read by a computer in the storage medium, the computer performs the intelligent crop planting method of any one of claims 1 to 4.