Plant cultivation method, apparatus and system

Abstract

A plant cultivation method, apparatus and system, relating to the field of agricultural intelligent control. The method comprises: acquiring a first image, and inputting the first image into a first model to output a first height curved surface and first planting information; on the basis of the first height curved surface, determining a first reference height; inputting the first reference height, the first height curved surface, and the first planting information into a second model to output a first deviation value; on the basis of the first deviation value, longitudinally dividing the first height curved surface into multiple height regions, and determining a second height curved surface of each height region; inputting the first planting information and each second height curved surface into a third model to output a first cultivation plan, the first cultivation plan comprising a fertilization mode and a planned cultivation duration; and after the planned cultivation duration, re-executing a first cultivation operation. On the basis of the solution, in an unmanned farm, the height of a plant population can be controlled, so that a harvester can harvest normally. In addition, the cultivation operation is repeated regularly, so that a virtuous internal cycle of the unmanned farm is achieved.

Description

Plant cultivation method, device and system

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on September 20, 2023, with application number 202311213783.7 and invention name “Method, device and system for plant cultivation”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of agricultural intelligent control, and more specifically, to methods, devices and systems for plant cultivation. Background Art

[0003] With the advancement of agricultural automation, informatization, and intelligent technologies, unmanned farms are becoming increasingly important. As the technologies for unmanned farms mature, the scale of their cultivation is also expanding.

[0004] Agronomic experience shows that uneven crop heights in field crops can hinder harvesting with large harvesters and lead to uneven growth within the plant population, impacting overall yield. Therefore, properly controlling the height of field crops in unmanned farms is crucial, yet presents significant challenges.

[0005] In view of this, a method for plant cultivation applicable to unmanned farms is in urgent need of development.

[0006] Summary of the Invention

[0007] The present application provides a method, device and system for plant cultivation, which can determine whether the height difference of a plant group is reasonable in an unmanned farm scenario, and if the judgment result is unreasonable, determine and implement cultivation plans for plant groups of different heights.

[0008] In a first aspect, a method for plant cultivation is provided, which is applied to an unmanned farm, the method comprising: performing a first cultivation operation on a first plant group planted in a first area, the first cultivation operation comprising: acquiring a first image through an aerial patrol platform, inputting the first image into a first model, and outputting a first height surface and first planting information, wherein the aerial patrol platform comprises a drone or a tethered balloon, the first image comprises a first plant group, and the first planting information comprises the plant variety and planting density of the first plant group; determining a first reference height based on the first height surface, the first reference height being the mode in a first height set, the first height set comprising height values ​​corresponding to a plurality of points constituting the above-mentioned first height surface; inputting the first reference height, the first height surface, and the first planting information into a second model, and outputting a first deviation value, wherein the first deviation value is used to represent the first height of the first plant group. The expected value of the height range is determined, and the second model is configured with a first standard table, which includes a first correspondence between the first height surface, the first planting information and the first deviation value; when the first height range is greater than the first deviation value, the first height surface is longitudinally divided into multiple height areas according to the first deviation value to obtain a second height surface for each height area; the first planting information and the second height surface of each height area are input into the third model, and a first cultivation plan is output, which is used to control the first height range to be within the first deviation value, and the first cultivation plan includes a fertilization plan corresponding to the first plant group in each height area, and the fertilization plan includes an application method and a planned cultivation time, and the application method includes an aerial fertilization method based on a drone and / or a ground fertilization method based on a drip irrigation system; after the above-mentioned planned cultivation time, the above-mentioned first cultivation operation is re-executed.

[0009] For example, the first image may be a photo image or a video image, or the first image may be a multispectral image including information such as visible light and NDVI, an ultrasonic image, or a laser point cloud image.

[0010] For example, when the first height range is greater than the first deviation value, the height difference of the plant population is unreasonable, so a cultivation plan for plant populations of different heights is determined and implemented next.

[0011] For example, the first model can be a pre-trained neural network model. After the first image is input into the first model, the first model can extract multiple vertices of the first plant population in the first image, connect the multiple vertices to form the first height surface, and output the first height surface. In addition, the first model can also extract plant features and corresponding semantic information of the first plant population in the first image, thereby determining and outputting the planting density of the first plant population and the plant variety of the first plants, that is, determining and outputting the first planting information.

[0012] For example, the second model can be a pre-trained neural network model, which is trained based on the first standard table. The first standard table can be determined through historical cultivation experience. The historical cultivation experience includes: for planting scenarios with different plant varieties, different planting densities and different plant benchmark heights, the cultivation guidance information given by experts. The cultivation guidance information can be the height deviation value of the plant group in the planting scenario.

[0013] For example, the third model can be a pre-trained expert model, which performs multiple iterative cycles of calculation based on the input first planting information and the second height surface of each height area, and finally solves a convergence result, which can be used to indicate the corresponding cultivation plan.

[0014] For example, after re-executing the above-mentioned first cultivation operation, if it is determined that the first height range is less than or equal to the first deviation value, there is no need to further generate the corresponding first cultivation plan, and a preset ordinary cultivation plan can be adopted. The ordinary cultivation plan can be the cultivation plan determined at the beginning of planting. It can be seen that the first cultivation plan proposed in the embodiment of the present application is a response measure taken to the abnormal growth condition of the plant, so that the growth state of the plant can return to normal; if it is determined that the first height range is still greater than the first deviation value, the subsequent operations are continued until the first height range is less than or equal to the first deviation value.

[0015] Based on this technical solution, unmanned farms can effectively control the height of plant groups in designated areas, keeping their heights and height ranges within reasonable tolerances. This allows large harvesters to harvest the plants normally and allows the plants to grow normally, helping to increase the overall yield of the plant population. Cultivation operations are then repeated regularly, and new cultivation plans are developed based on the new growth conditions of the plants, achieving a virtuous internal cycle of plant cultivation on unmanned farms.

[0016] In combination with the first aspect, in certain implementations of the first aspect, a first prescription map is generated according to the first cultivation plan, where the first prescription map is used to indicate the amount of fertilizer required to be sprayed on the first plant population in each height zone.

[0017] Based on the above technical solution, the cultivation plan is quantified in the form of a prescription map, so that the automated equipment of the unmanned farm can be better controlled to implement the cultivation plan.

[0018] In combination with the first aspect, in certain implementations of the first aspect, when the application method includes an aerial fertilizer spreading method based on a drone, first control information is determined based on the first prescription map and the scope of the first area, and the first control information includes the starting point position of the drone, the spraying height, the flight speed during spraying, multiple waypoints reached in sequence, and the amount of fertilizer required to be sprayed in each navigation path; and the first control information is sent to the drone.

[0019] Based on the above technical solution, it is possible to determine the cultivation plan, determine the waypoints, fertilizer amount and other control quantities for the drone, and instruct the drone to perform corresponding cultivation work through control information, control the growth rate of the plant group in the specified sub-area, and then control the height of the plant group in the entire area, and make the height difference within the expected deviation.

[0020] In combination with the first aspect, in certain implementations of the first aspect, a valve area set corresponding to the dynamic rotation irrigation area of ​​the drip irrigation system is determined based on the first prescription map and the scope of the first area; second control information is determined based on the drip irrigation network capacity, water pump parameters and historical network-wide pressure distribution of the drip irrigation system, and the second control information includes the control amount and corresponding fertilizer concentration for each valve in the valve area set, so that the drip irrigation system performs rotation irrigation with the fertilizer concentration first high and then low; and the second control information is sent to the drip irrigation system.

[0021] Based on the above technical solution, it is possible to determine the control quantity for the valve set of the drip irrigation system based on the determined cultivation plan, and to instruct the drip irrigation system to perform corresponding cultivation work through control information, thereby controlling the growth rate of the plant group in the specified sub-area, and then controlling the height of the plant group in the entire area, and making the height difference within the expected deviation.

[0022] In a second aspect, a plant cultivation system is provided, which is applied to unmanned farms and includes:

[0023] A main control center is used to instruct the system to perform a first cultivation operation on a first plant population planted in a first area, and the main control center includes:

[0024] An aerial field inspection platform, configured to acquire a first image including a first plant population, wherein the aerial field inspection platform includes a drone or a tethered balloon;

[0025] A digital image processing device is used to input the first image into the first model, and output a first height surface and first planting information, wherein the first planting information includes plant varieties and planting density of the first plant population;

[0026] A data processing device, configured to determine a first reference height based on a first height surface, the first reference height being the mode in a first height set, the first height set including height values ​​corresponding to a plurality of points constituting the first height surface; further configured to input the first reference height, the first height surface, and first planting information into a second model, and output a first deviation value, the first deviation value being used to represent an expected value of a first height range of a first plant population, the second model being configured with a first standard table, the first standard table including a first correspondence between the first height surface, the first planting information, and the first deviation value; further configured to, when the first height range is greater than the first deviation value, longitudinally divide the first height surface into a plurality of height regions based on the first deviation value, thereby obtaining a second height surface for each height region;

[0027] an expert system, configured to input the first planting information and the second height surface of each height zone into a third model, and output a first cultivation plan, the first cultivation plan being for a first height range within a first deviation value, the first cultivation plan including a fertilization plan corresponding to the first plant population in each height zone, the fertilization plan including an application method and a planned cultivation duration, the application method including an aerial fertilization method based on a drone and / or a ground fertilization method based on a drip irrigation system;

[0028] The above-mentioned general control center is further used to re-execute the above-mentioned first cultivation operation after the above-mentioned planned cultivation time has passed.

[0029] In conjunction with the second aspect, in certain implementations of the second aspect, the expert system is further configured to:

[0030] According to the first cultivation plan, a first prescription map is generated, where the first prescription map is used to indicate the amount of fertilizer required to be sprayed on the first plant population in each height zone.

[0031] In conjunction with the second aspect, in certain implementations of the second aspect, the system further includes:

[0032] A remote control device is used to determine first control information based on the first prescription map and the scope of the first area when the above-mentioned application method includes an aerial fertilizer spreading method based on a drone, and the first control information includes the starting point position of the drone, the spraying height, the flight speed during spraying, multiple waypoints reached in sequence, and the amount of fertilizer required to be sprayed in each navigation path; and send the first control information to the drone.

[0033] In conjunction with the second aspect, in certain implementations of the second aspect, the remote control device is further configured to:

[0034] Based on the first prescription map and the scope of the first area, the valve area set corresponding to the dynamic rotation irrigation area of ​​the drip irrigation system is determined; based on the drip irrigation network capacity, water pump parameters and historical pressure distribution of the entire network of the drip irrigation system, second control information is determined, and the second control information includes the control amount and corresponding fertilizer concentration for each valve in the valve area set, so that the drip irrigation system performs rotation irrigation with the fertilizer concentration first high and then low; the second control information is sent to the drip irrigation system.

[0035] In a third aspect, a device for plant cultivation is provided, comprising a processor and a memory, wherein the processor and the memory are connected, wherein the memory is used to store program code, and the processor is used to call the program code to execute a method in any possible implementation of the method design of the first aspect above.

[0036] In a fourth aspect, a chip system is provided, which is applied to an electronic device; the chip system includes one or more interface circuits and one or more processors; the interface circuit and the processor are interconnected through lines; the interface circuit is used to echo a signal from the memory of the electronic device and send a signal to the processor, the signal including a computer instruction stored in the memory; when the processor executes the computer instruction, the electronic device executes a method in any possible implementation of the method design of the first aspect above.

[0037] In a fifth aspect, a computer-readable storage medium is provided, storing a computer program or instruction, which is used to implement the method in any possible implementation manner in the method design of the first aspect.

[0038] In a sixth aspect, a computer program product is provided, comprising a computer program or instructions, which, when executed on a computer, enables the computer to execute a method in any possible implementation of the method design of the first aspect above. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] FIG1 is a schematic block diagram of a plant cultivation system 100 provided in an embodiment of the present application.

[0040] FIG2 is a schematic block diagram of a method for cultivating plants provided in an embodiment of the present application.

[0041] FIG3 is a schematic diagram of dividing height areas provided in an embodiment of the present application.

[0042] FIG4 is a schematic block diagram of a method for implementing a fertilization scheme provided in an embodiment of the present application.

[0043] FIG5 is a schematic block diagram of another method for implementing a fertilization scheme provided in an embodiment of the present application.

[0044] FIG6 is a schematic block diagram of another plant cultivation system 600 provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is a kind of association relationship that describes associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In this application, "at least one" refers to one or more, and "more than one" refers to two or more. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0046] In the embodiments of this application, prefixes such as "first" and "second" are used only to distinguish different description objects and have no limiting effect on the position, order, priority, quantity, or content of the described objects. The use of prefixes such as ordinal numbers in the embodiments of this application to distinguish description objects does not constitute a limitation on the described objects. For a statement of the described objects, please refer to the description in the context of the claims or embodiments, and the use of such prefixes should not constitute an unnecessary limitation.

[0047] The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings.

[0048] An unmanned farm refers to an all-weather, full-process, and full-space unmanned production operation model that uses new-generation information technologies such as the Internet of Things, big data, artificial intelligence, fifth-generation (5G) communication systems, and robotics technology without the need for human intervention. It completes all farm production and management tasks through remote control of farm facilities, equipment, and machinery, or autonomous decision-making and operation by intelligent equipment and robots.

[0049] During plant cultivation, controlling the height differences between plants in the field is crucial. This is because large harvesters require high consistency in the height of the harvested objects. Furthermore, if the height differences between plants are too large, the shorter plants will not receive enough light, resulting in a significant difference in growth between the shorter plants and the normal-growing plants, which in turn affects the overall yield of the plant population.

[0050] In view of this, the embodiments of the present application propose a method, device and system for plant cultivation, which are applied to unmanned farms to obtain the growth height of a plant group planted in a designated area, and analyze it to generate a cultivation strategy for the plant group in the area, and instruct relevant equipment to execute the strategy.

[0051] FIG1 is a schematic block diagram of a plant cultivation system 100 provided in an embodiment of the present application.

[0052] In some possible embodiments, the system 100 includes: a data collection device 110, a data processing device 120, an intelligent decision-making device 130, and an automation device 140. These devices can be connected via a wireless network to enable data exchange between the devices.

[0053] The acquisition device 110 is mainly used to collect relevant data of the plant population and transmit the data to the data processing device 120 and the intelligent decision-making device 130. The acquisition device 110 includes: a monocular camera, a binocular camera, an aerial drone or a millimeter wave radar.

[0054] The data processing device 120 is mainly used to process and analyze data based on the relevant data of the plant group received from the acquisition device 110, determine the growth status of the plant group, such as the height difference of the plant group, the plant height surface information of the plant group, etc., and transmit the processing results to the decision device 130.

[0055] In some possible embodiments, the data processing device 120 may include a neural network model dedicated to digital image processing, and extract and analyze image features based on the neural network model. The analysis results are used to represent the growth status of the plant population.

[0056] The decision-making device 130 is mainly used to generate a cultivation plan for the current plant population based on the received data, and transmit the cultivation plan to the automation device 140 .

[0057] In some possible embodiments, the decision-making device 130 includes a neural network model dedicated to decision-making and stores a crop cultivation experience library, which stores plant cultivation plans corresponding to different planting scenarios.

[0058] The automated equipment 140 is mainly used to perform designated cultivation tasks based on the received cultivation plan, such as aerial fertilization, ground fertilization, etc. The automated equipment 140 includes agricultural machinery with designated functions, such as agricultural drones, irrigation systems, etc.

[0059] Based on the above system 100, an embodiment of the present application proposes a method for cultivating plants.

[0060] Figure 2 is a schematic block diagram of a cultivation method provided in an embodiment of the present application. The method can be applied to unmanned farms.

[0061] It should be understood that the unmanned farm is equipped with automated equipment for cultivating plants.

[0062] S210: Perform a first cultivation operation on the first plant group planted in the first area.

[0063] The process of the first cultivation operation is as follows:

[0064] S211: Acquire a first image through the aerial field inspection platform, input the first image into a first model, and output a first height surface and first planting information.

[0065] The aerial field inspection platform includes a drone or a tethered balloon, the first image includes a first plant group, and the first planting information includes plant varieties and planting density of the first plant group.

[0066] In some possible embodiments, the first image may be a photo image or a video image, or may be a multispectral image including information such as visible light and NDVI, an ultrasonic image, or a laser point cloud image.

[0067] It should be understood that plant height refers to the distance between the root neck and the top of the plant, where the top refers to the top of the main stem of the plant.

[0068] In some possible embodiments, the first model may be a pre-trained neural network model. After the first image is input into the first model, the first model may extract multiple vertices of the first plant population in the first image, connect the multiple vertices to form the first height surface, and output the first height surface. In addition, the first model may also extract plant features and corresponding semantic information of the first plant population in the first image, thereby determining and outputting the planting density of the first plant population and the plant variety of the first plants, that is, determining and outputting the first planting information.

[0069] In some possible embodiments, the heights of the plurality of first plants may be acquired by the acquisition device 110 in the system 100 .

[0070] S212: Determine a first reference height according to the first height curved surface.

[0071] The first reference height is the mode of a first height set, and the first height set includes height values ​​corresponding to a plurality of points constituting a first height surface.

[0072] It should be understood that the above-mentioned first reference height can be used to represent the expected height that the current first plant group should reach under normal growth conditions of the first plants.

[0073] S213: Input the first reference height, the first height curved surface, and the first planting information into the second model, and output a first deviation value.

[0074] Among them, the first deviation value is used to represent the expected value of the first height range of the first plant group, and the first height range is used to represent the height difference between the tallest plant and the shortest plant in the first plant group. The second model is configured with a first standard table, which includes a first correspondence between the first height surface, the first planting information and the first deviation value.

[0075] In some possible embodiments, the second model may be a pre-trained neural network model, which is trained based on the first standard table. The first standard table may be determined through historical cultivation experience. The historical cultivation experience includes: cultivation guidance information provided by experts for planting scenarios with different plant varieties, different planting densities, and different base heights of plants. The cultivation guidance information may be the height deviation value of the plant group in the planting scenario.

[0076] S214: When the first height range is greater than the first deviation value, the first height curved surface is longitudinally divided into a plurality of height regions according to the first deviation value to obtain a second height curved surface in each height region.

[0077] FIG3 is a schematic diagram of dividing height areas proposed in an embodiment of the present application.

[0078] In some possible embodiments, the interval length corresponding to the above-mentioned height area can be equal to the first deviation value, that is, referring to the example shown in Figure 3, it can also be a multiple of the first deviation value, which can be an integer multiple or a non-integer multiple compared to the first deviation value.

[0079] As shown in Figure 3, the first height surface is divided into three second height surfaces within three height regions. In other words, the second height surface within each height region corresponds to a portion of the first height surface. The interfaces between these three height regions are planes perpendicular to the direction of gravity, i.e., the cross-sections dividing the first height surface.

[0080] In some possible embodiments, when the first height range difference is less than or equal to the first deviation value, it indicates that the growth state of the first plant group is good, and there is no need to adopt a special cultivation plan for the first plant group for the time being. After the preset first time period has passed, the above S210 can be re-executed. It can be seen that the plant cultivation method proposed in the embodiment of the present application is a long-term and repeatable method. Based on this solution, the growth state of the plant group can be regularly observed, and whether the growth state of the plant group is good can be discovered in a relatively timely manner.

[0081] S215: Input the first planting information and the second height curved surface of each height area into the third model, and output a first cultivation plan.

[0082] Among them, the first cultivation plan is used to control the above-mentioned first height extreme difference within the first deviation value. The first cultivation plan includes a fertilization plan corresponding to the first plant group in each height area. The fertilization plan includes an application method and a planned cultivation time. The application method includes an aerial fertilization method based on a drone and / or a ground fertilization method based on a drip irrigation system.

[0083] In some possible embodiments, the above-mentioned third model can be a pre-trained expert model, which performs multiple iterative cycles of calculation based on the input first planting information and the second height surface of each height area, and finally solves a convergence result, which can be used to indicate the corresponding cultivation plan.

[0084] It should be understood that when the boundary line of the height area is determined, it also means that the height information of the boundary line of the height area is determined. The height information can be extracted by the third model and used as the basis for determining the first cultivation plan.

[0085] In addition, the boundary line of the above-mentioned height area also implies the lateral range area of ​​the height area corresponding to the first area, thereby being able to determine the first plant group corresponding to the lateral range area. Similarly, this information can also be extracted by the above-mentioned third model and used as the basis for determining the first cultivation plan.

[0086] In some possible embodiments, as shown in FIG3 , in the cultivation scene, the first height surface is divided into three height areas. For the convenience of description, these three height areas are recorded here in order from low to high as the first height area, the second height area and the third height area.

[0087] When the above-mentioned first reference height falls into the second height area, it can be said that the first plant located in the second height area is in good growth condition and has a reasonable plant height. Then, the first plant located in the first height area has a poor growth condition and is too short. The first plant located in the third height area has a poor growth condition and is too high. Therefore, in the first cultivation plan, for the first plant group corresponding to the first height area, it is necessary to appropriately increase the amount of fertilizer applied so that the height of these first plants reaches the standard height range; for the first plant group corresponding to the second height area, it is not necessary to adjust the amount of fertilizer applied so that these first plants maintain their current growth state and grow normally; for the first plant group corresponding to the third height area, it is necessary to appropriately reduce the amount of fertilizer applied, or appropriately increase the application of growth inhibitors corresponding to the crop variety, so that the height of these first plants returns to the standard height range.

[0088] When the above-mentioned first reference height falls into the first height area, based on the same principle as above, in the first cultivation plan, there is no need to adjust the amount of fertilizer applied for the first height area; the amount of fertilizer applied for the second height area needs to be reduced; and the amount of fertilizer applied for the third height area needs to be further reduced.

[0089] When the above-mentioned first reference height falls into the third height area, based on the same principle mentioned above, in the first cultivation plan, there is no need to adjust the amount of fertilizer applied for the third height area; the amount of fertilizer applied for the second height area needs to be increased; and the amount of fertilizer applied for the first height area needs to be further increased.

[0090] It should be understood that the above solution is also applicable when the first height curved surface is divided into N height regions.

[0091] At this point, the first cultivation operation proposed in S210 is completed, with the output of the first cultivation plan serving as a completion sign.

[0092] S220: After the planned cultivation time has passed, the first cultivation operation is re-executed.

[0093] In some possible embodiments, after re-executing the above-mentioned first cultivation operation, if it is determined that the first height extreme difference is less than or equal to the first deviation value, there is no need to further generate the corresponding first cultivation plan, and a preset ordinary cultivation plan can be adopted. The ordinary cultivation plan can be the cultivation plan determined at the beginning of planting. It can be seen that the first cultivation plan proposed in the embodiment of the present application is a response measure taken to the abnormal growth condition of the plant, so that the growth state of the plant can return to normal; if it is determined that the first height extreme difference is still greater than the first deviation value, the subsequent operations are continued until the first height extreme difference is less than or equal to the first deviation value.

[0094] Based on this technical solution, unmanned farms can effectively control the height of plant groups in designated areas, keeping their heights and height ranges within reasonable tolerances. This allows large harvesters to harvest the plants normally and allows the plants to grow normally, helping to increase the overall yield of the plant population. Cultivation operations are then repeated regularly, and new cultivation plans are developed based on the new growth conditions of the plants, achieving a virtuous internal cycle of plant cultivation on unmanned farms.

[0095] In some possible embodiments, after determining the first cultivation plan, it is also necessary to determine how to control the corresponding automated equipment, such as a drone or a drip irrigation system. The specific operations are as follows:

[0096] According to the first cultivation plan, a first prescription map is generated, and the first prescription map is used to indicate the amount of fertilizer required to be sprayed for the first plant group in each height area.

[0097] FIG4 is a schematic block diagram of a method for implementing a fertilization scheme proposed in an embodiment of the present application.

[0098] In some possible embodiments, when the application method in the above solution is an aerial fertilizer spreading method based on a drone, the following operations may be performed:

[0099] S410: Determine first control information according to the first prescription map and the range of the first area.

[0100] The first control information includes the starting point position of the UAV, the spraying height, the flight speed during spraying, the multiple waypoints reached in sequence, and the amount of fertilizer required to be sprayed in each navigation path.

[0101] In some possible embodiments, since the first height surface is divided into multiple height regions, the first region is correspondingly divided into multiple first sub-regions. Correspondingly, the first plant groups in each first sub-region also correspond to different height regions. Therefore, when the drone passes over different first sub-regions, the amount of fertilizer to be sprayed is different. For example, the drone needs to spray more fertilizer in the first sub-region where the first plant group is at a lower height region; and less fertilizer in the first sub-region where the first plant group is at a higher height region.

[0102] S420: Send the first control information to the drone.

[0103] Based on the above technical solution, it is possible to determine the cultivation plan, determine the waypoints, fertilizer amount and other control quantities for the drone, and instruct the drone to perform corresponding cultivation work through control information, control the growth rate of the plant group in the specified sub-area, and then control the height of the plant group in the entire area, and make the height difference within the expected deviation.

[0104] FIG5 is a schematic block diagram of another method for implementing a fertilization scheme proposed in an embodiment of the present application.

[0105] In some possible embodiments, when the application method of the above solution is a ground fertilization method based on a drip irrigation system, the following operations may be performed:

[0106] S510: Determine a valve zone set corresponding to a dynamic rotation irrigation zone of the drip irrigation system according to the first prescription map and the range of the first area.

[0107] It should be understood that the irrigation function of a drip irrigation system is controlled by multiple valves, which constitute valve zones. Because drip irrigation systems are typically deployed on a large scale, the first area mentioned above is usually a portion of the area covered by the drip irrigation system. Therefore, the valve zones corresponding to the portion of the drip irrigation system deployed in the first area constitute the valve zone set mentioned above.

[0108] S520: Determine second control information according to the drip irrigation pipe network capacity, water pump parameters, and historical pressure distribution of the entire network of the drip irrigation system.

[0109] The second control information includes the control amount and the corresponding fertilizer concentration for each valve in the valve zone set, so that the drip irrigation system performs rotation irrigation with the fertilizer concentration first high and then low.

[0110] It should be understood that the control amount of the valve can be a control amount of the valve opening to control the amount of fertilizer mixed into the water spray pipe per unit time, thereby controlling the fertilizer concentration.

[0111] In some possible embodiments, the above-mentioned historical network-wide pressure distribution may be the most recently detected network-wide pressure distribution.

[0112] In some possible embodiments, similar to the above-mentioned drone-based aerial fertilization method, for the first sub-area where the height of the first plant group is lower, the opening control amount of the corresponding valve of the drip irrigation system is larger, and the corresponding fertilizer concentration is also larger; for the first sub-area where the height of the first plant group is higher, the opening control amount of the corresponding valve of the drip irrigation system is smaller, and the corresponding fertilizer concentration is also smaller.

[0113] S530: Send the second control information to the drip irrigation system.

[0114] Based on the above technical solution, it is possible to determine the control quantity for the valve set of the drip irrigation system based on the determined cultivation plan, and to instruct the drip irrigation system to perform corresponding cultivation work through control information, thereby controlling the growth rate of the plant group in the specified sub-area, and then controlling the height of the plant group in the entire area, and making the height difference within the expected deviation.

[0115] In some possible embodiments, the first cultivation scheme may also combine the drone-based aerial fertilization method and the drip irrigation system-based ground fertilization method.

[0116] In some possible embodiments, when some valves in the drip irrigation system malfunction, the drip irrigation system identifies a first abnormal area. This first abnormal area is the portion of the first area that the drip irrigation system's irrigation range cannot cover. The drip irrigation system can then transmit the first prescription map and the first abnormal area to a drone, allowing the drone to complete the cultivation work in the abnormal area on behalf of the drip irrigation system. Simultaneously, the drip irrigation system can also transmit a first abnormality message to the command center of the unmanned farm. This first abnormality message indicates that some of the valves in the drip irrigation system have malfunctioned, allowing personnel at the command center to promptly take emergency repair measures.

[0117] Similarly, if the drone veers off course, it identifies a second abnormal area, which is the portion of the first area that the drone's current path cannot cover. The drone can then transmit the first prescription map and the second abnormal area to the drip irrigation system, allowing the drip irrigation system to complete the cultivation work in the abnormal area on behalf of the drone. Simultaneously, the drone can also transmit a second abnormality message to the unmanned farm's command center, indicating the yaw, so that personnel at the command center can take timely repair measures.

[0118] In some possible embodiments, when the drip irrigation system and the drone cannot complete the cultivation plan even if they cooperate with each other, the drip irrigation system or the drone can send an alarm message to the command center. The alarm message is used to indicate that the current application method cannot complete the current cultivation plan, so that the on-duty personnel of the command center can contact relevant personnel to troubleshoot the drip irrigation system and the drone. If no fault is found, the corresponding automated equipment is introduced to implement the cultivation plan.

[0119] Based on the above technical solution, a communication connection is established between the drone and the drip irrigation system. When a failure occurs in the process of executing the cultivation plan, the device on the other side can be instructed to assist it in completing the cultivation plan, which increases the robustness of the solution and helps avoid shutdowns caused by equipment failures.

[0120] In addition, embodiments of the present application also provide a system for implementing any of the above methods. FIG6 is a schematic block diagram of another plant cultivation system 600 provided in an embodiment of the present application. The system can be applied to an unmanned farm. As shown in FIG6 , the system 600 includes:

[0121] The main control center 610 is used to instruct the system to perform a first cultivation operation on a first plant population planted in a first area. The main control center 610 includes:

[0122] An aerial field inspection platform 611 is configured to acquire a first image, the first image including a first plant population, and the aerial field inspection platform includes a drone or a tethered balloon;

[0123] a digital image processing device 612 for inputting the first image into the first model, and outputting a first height surface and first planting information, wherein the first planting information includes plant varieties and planting density of the first plant population;

[0124] Data processing device 613 is configured to determine a first reference height based on the first height surface, the first reference height being the mode of a first height set, the first height set including height values ​​corresponding to a plurality of points constituting the first height surface; further configured to input the first reference height, the first height surface, and the first planting information into a second model, and output a first deviation value, the first deviation value being used to represent an expected value of a first height range of the first plant population, the second model being configured with a first standard table including a first correspondence between the first height surface, the first planting information, and the first deviation value; further configured to, when the first height range is greater than the first deviation value, longitudinally divide the first height surface into a plurality of height regions based on the first deviation value, to obtain a second height surface for each height region;

[0125] Expert system 614 is configured to input the first planting information and the second height surface of each height zone into a third model, and output a first cultivation plan, the first cultivation plan being for a first height range within a first deviation value, the first cultivation plan including a fertilization plan corresponding to the first plant population in each height zone, the fertilization plan including an application method and a planned cultivation duration, the application method including an aerial fertilization method using a drone and / or a ground fertilization method using a drip irrigation system;

[0126] The main control center 610 is further configured to re-execute the first cultivation operation after the planned cultivation time has elapsed.

[0127] In some possible embodiments, the expert system 614 is further configured to generate a first prescription map according to the first cultivation plan, where the first prescription map is configured to indicate the amount of fertilizer required to be sprayed on the first plant population in each height zone.

[0128] In some possible embodiments, the system 600 further includes:

[0129] The remote control device 620 is used to determine first control information based on the first prescription map and the scope of the first area when the above-mentioned application method includes an aerial fertilizer spreading method based on a drone; the first control information includes the starting point position of the drone, the spraying height, the flight speed during spraying, multiple waypoints reached in sequence, and the amount of fertilizer required to be sprayed in each navigation path; and send the first control information to the drone.

[0130] In some possible embodiments, the remote control device 620 is further used to determine the valve area set corresponding to the dynamic rotation irrigation area of ​​the drip irrigation system based on the first prescription map and the scope of the first area; determine the second control information based on the drip irrigation network capacity, water pump parameters and historical network-wide pressure distribution of the drip irrigation system, and the second control information includes the control amount and corresponding fertilizer concentration for each valve in the valve area set, so that the drip irrigation system performs rotation irrigation with the fertilizer concentration first high and then low; and send the second control information to the drip irrigation system.

[0131] This system effectively controls the height of plant clusters in a designated area, keeping their heights and height ranges within reasonable tolerances. This allows large harvesters to harvest the plants normally and allows them to grow normally, helping to increase overall yield. Cultivation operations are then repeated regularly, with new cultivation plans developed based on the plant's evolving growth patterns, achieving a virtuous cycle of plant cultivation within unmanned farms.

[0132] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0133] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0134] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0135] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0136] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0137] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory, a magnetic disk, or an optical disk.

[0138] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for plant cultivation, characterized in that: Applied to unmanned farms, the method includes: A first cultivation operation is performed on a first plant population planted in a first area, wherein the first cultivation operation includes: Acquire a first image through an aerial field inspection platform, input the first image into a first model, and output a first height surface and first planting information, wherein the aerial field inspection platform includes a drone or a tethered balloon, the first image includes the first plant population, and the first planting information includes plant varieties and planting density of the first plant population; Determine a first reference height according to the first height curved surface, where the first reference height is the mode in a first height set, and the first height set includes height values ​​corresponding to a plurality of points constituting the first height curved surface; Inputting the first reference height, the first height curved surface and the first planting information into a second model, outputting a first deviation value, wherein the first deviation value is used to represent an expected value of a first height range of the first plant population, wherein the second model is configured with a first standard table, wherein the first standard table includes a first corresponding relationship between the first height curved surface, the first planting information and the first deviation value; When the first height range is greater than the first deviation value, the first height curved surface is longitudinally divided into a plurality of height regions according to the first deviation value to obtain a second height curved surface in each height region; Input the first planting information and the second height surface of each height area into a third model, and output a first cultivation plan, wherein the first cultivation plan is used to control the first height range to be within the first deviation value, and the first cultivation plan includes a fertilization plan corresponding to the first plant population in each height area, and the fertilization plan includes an application method and a planned cultivation time, and the application method includes an aerial fertilization method based on a drone and / or a ground fertilization method based on a drip irrigation system; After the planned cultivation time has elapsed, the first cultivation operation is re-executed.

2. The method according to claim 1, characterized in that: The method further comprises: A first prescription map is generated according to the first cultivation plan, wherein the first prescription map is used to indicate the amount of fertilizer required to be sprayed on the first plant population in each of the height areas.

3. The method according to claim 2, characterized in that When the application method includes the drone-based aerial fertilizer spreading method, the method further includes: Determine first control information according to the first prescription map and the range of the first area, the first control information including the starting point position of the UAV, the spraying height, the flight speed during spraying, the multiple waypoints reached in sequence, and the amount of fertilizer required to be sprayed in each navigation path; The first control information is sent to the drone.

4. The method according to claim 2 or 3, characterized in that: When the application method includes the ground fertilization method based on the drip irrigation system, the method further includes: Determine a valve zone set corresponding to a dynamic irrigation zone of the drip irrigation system according to the first prescription map and the range of the first area; Determine second control information according to the drip irrigation network capacity, water pump parameters and historical pressure distribution of the entire network of the drip irrigation system, wherein the second control information includes a control amount and a corresponding fertilizer concentration for each valve in the valve zone set, so that the drip irrigation system performs rotation irrigation with a high fertilizer concentration first and a low fertilizer concentration later; The second control information is sent to the drip irrigation system.

5. A system for plant cultivation, characterized in that: Applied to unmanned farms, the system includes: A general control center is used to instruct the system to perform a first cultivation operation on a first plant population planted in a first area, and the general control center includes: An aerial field inspection platform, used for acquiring a first image, wherein the first image includes the first plant population, and the aerial field inspection platform includes a drone or a tethered balloon; A digital image processing device, used for inputting the first image into a first model, and outputting a first height surface and first planting information, wherein the first planting information includes plant varieties and planting density of the first plant population; A data processing device, for determining a first reference height according to the first height surface, the first reference height being the mode in a first height set, the first height set including height values ​​corresponding to a plurality of points constituting the first height surface; further for inputting the first reference height, the first height surface and the first planting information into a second model, and outputting a first deviation value, the first deviation value being used to represent an expected value of a first height range of the first plant population, the second model being configured with a first standard table, the first standard table including a first correspondence between the first height surface, the first planting information and the first deviation value; further for dividing the first height surface longitudinally into a plurality of height regions according to the first deviation value when the first height range is greater than the first deviation value, and obtaining a second height surface for each height region; An expert system, for inputting the first planting information and the second height surface of each height area into a third model, and outputting a first cultivation plan, wherein the first cultivation plan is used to control the first height range to be within the first deviation value, and the first cultivation plan includes a fertilization plan corresponding to the first plant population in each of the height areas, and the fertilization plan includes an application method and a planned cultivation time, and the application method includes an aerial fertilization method based on a drone and / or a ground fertilization method based on a drip irrigation system; The master control center is further configured to re-execute the first cultivation operation after the planned cultivation time has elapsed.

6. A plant cultivation device, characterized in that: The method comprises a processor and a memory, wherein the processor and the memory are connected, wherein the memory is used to store program codes, and the processor is used to call the program codes to execute the method according to any one of claims 1 to 4.

7. A chip system, characterized in that: The chip system is applied to an electronic device; the chip system includes one or more interface circuits and one or more processors; the interface circuit and the processor are interconnected via lines; the interface circuit is used to receive a signal from a memory of the electronic device and send the signal to the processor, the signal including a computer instruction stored in the memory; when the processor executes the computer instruction, the electronic device executes the method as described in any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 4.

9. A computer program product, characterized in that The method comprises computer program codes or instructions, which, when executed on a computer, cause the computer to perform the method according to any one of claims 1 to 4.

Images