CN114066033A

CN114066033A - Intelligent agriculture optimization method and system

Info

Publication number: CN114066033A
Application number: CN202111326220.XA
Authority: CN
Inventors: 张淼; 赵晨
Original assignee: Qingdao Agricultural University
Current assignee: Qingdao Agricultural University
Priority date: 2021-11-10
Filing date: 2021-11-10
Publication date: 2022-02-18

Abstract

The embodiment of the specification provides an intelligent agriculture optimization method and system, and the method comprises the steps of collecting a near infrared spectrum of an agricultural product based on infrared collection equipment, and determining maturity information of the agricultural product; based on the light transmission coefficient of the leaves of the agricultural products acquired by the light transmission acquisition equipment, determining the nutrition information of the leaves; detecting a substrate for cultivating agricultural products based on substrate detection equipment, and determining substrate detection information; and determining a water and fertilizer adjustment plan based on the maturity information, the leaf nutrition information and the matrix detection information.

Description

Intelligent agriculture optimization method and system

Technical Field

The specification relates to the field of intelligent agriculture, in particular to an intelligent agriculture optimization method and system.

Background

With the continuous development of agricultural internet of things technology, modern agriculture is on a large scale, and a standardized planting mode is becoming a trend. Through intelligent planting, can grow seedlings more easily, improve the survival rate and the quality of growing seedlings greatly. After intelligent seedling raising, in order to guarantee high yield and high efficiency of agricultural production, farm products need to be intelligently managed, so that the most appropriate growth environment is provided for agricultural products, and the growth of crops is promoted to the maximum extent.

Therefore, it is necessary to provide an intelligent agricultural optimization method to intelligently control and manage the growth of agricultural products.

Disclosure of Invention

One embodiment of the present specification provides an intelligent agriculture optimization method, including: acquiring a near infrared spectrum of an agricultural product based on infrared acquisition equipment in a movable acquisition device, and determining maturity information of the agricultural product; determining the nutrition information of the leaves based on the light transmittance of the leaves of the agricultural products acquired by the light transmittance acquisition equipment in the movable acquisition device; detecting a substrate for cultivating the agricultural product based on a substrate detection device in the mobile acquisition device, and determining substrate detection information; and determining a water and fertilizer adjustment plan based on the maturity information, the leaf nutrition information and the matrix detection information.

One of the embodiments of the present specification provides an intelligent agricultural optimization system, which includes: the infrared acquisition module is used for acquiring the near infrared spectrum of the agricultural product based on infrared acquisition equipment in the movable acquisition device and determining the maturity information of the agricultural product; the light transmission acquisition module is used for acquiring the light transmission coefficient of the blade of the agricultural product based on light transmission acquisition equipment in the movable acquisition device and determining the blade nutrition information of the agricultural product; the base body detection module is used for detecting a base body for cultivating the agricultural product based on a base body detection device in the movable acquisition device and determining base body detection information; and the water and fertilizer adjustment plan determining module is used for determining a water and fertilizer adjustment plan based on the maturity information, the leaf nutrition information and the matrix detection information.

One of the embodiments of the present specification provides an intelligent agricultural optimization device, which includes: the infrared acquisition equipment is used for acquiring the near infrared spectrum of the agricultural product and determining the maturity information of the agricultural product; the light transmission acquisition equipment is used for acquiring the light transmission coefficient of the leaves of the agricultural products and determining the nutrition information of the leaves of the agricultural products; the substrate detection equipment is used for detecting a substrate for cultivating the agricultural product and determining substrate detection information; a memory for storing program code; a processor for executing the program code to implement the intelligent agriculture optimization method according to any of the above embodiments.

One of the embodiments of the present disclosure provides a computer-readable storage medium storing computer instructions, wherein when the computer instructions in the storage medium are read by a computer, the computer performs the method for optimizing intelligent agriculture according to any one of the above embodiments.

Drawings

The present description will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:

FIG. 1 is a schematic diagram of an application scenario of a smart agriculture optimization system according to some embodiments of the present disclosure;

FIG. 2 is an exemplary block diagram of a smart agriculture optimization system according to some embodiments herein;

FIG. 3 is an exemplary flow chart of a method for determining a water fertilizer adjustment plan in accordance with some embodiments of the present disclosure;

FIG. 4 is an exemplary flow chart illustrating controlling a mobile gathering device to gather information about an agricultural product according to some embodiments of the present description;

fig. 5 is an exemplary flow diagram for determining a water fertilizer adjustment plan using a water fertilizer demand prediction model 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 disclosure, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only examples or embodiments of the present description, and that for a person skilled in the art, the present description can also be applied to other similar scenarios on the basis of these drawings without inventive effort. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system", "apparatus", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this specification and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

Fig. 1 is a schematic diagram of an application scenario of an intelligent agricultural optimization system according to some embodiments of the present disclosure.

As shown in fig. 1, an application scenario 100 according to an embodiment of the present disclosure may include a server 110, a network 120, a user terminal 130, a storage device 140, and a movable capturing apparatus 150.

In some embodiments, the intelligent agricultural optimization system may implement the work of determining a water and fertilizer adjustment plan by implementing the methods and/or processes disclosed herein.

The server 110 may be configured to obtain information collected by the movable collecting device 150, process the obtained information, and determine a water and fertilizer adjustment plan of the agricultural product. In some embodiments, the server 110 may be used to obtain location information for the mobile acquisition device 150. In some embodiments, the server 110 may determine a route for the mobile gathering device 150 to the agricultural product and control the mobile gathering device 150 to travel to an area related to the agricultural product based on the acquired location information and a preset map.

In some embodiments, the server 110 may include a processor 112. Processor 112 may process data, information, and/or processing results obtained from other devices or system components and execute program instructions based on the data, information, and/or processing results to perform one or more of the functions described herein.

The network 120 may provide a conduit for the exchange of information. In some embodiments, information may be exchanged between the server 110, the user terminal 130, the storage device 140, and the removable collection 150 via the network 120. For example, the server 110 may receive data information (e.g., near infrared spectrum, transmittance, substrate detection information, etc.) about the agricultural product 160 collected by the movable collection device 150 via the network 120. As another example, server 110 may read data stored by storage device 140 over network 120. In some embodiments, network 120 may include one or more network access points. For example, the network 120 may include wired or wireless network access points, such as base stations and/or network switching points 120-1, 120-2, …, through which one or more components of the smart agriculture optimization system may connect to the network 120 to exchange data and/or information.

User terminal 130 refers to one or more terminal devices or software used by a user. In some embodiments, the user terminal 130 may be one or any combination of a mobile device 130-1, a tablet computer 130-2, a laptop computer 130-3, a desktop computer 130-4, etc., or other device having input and/or output capabilities. In some embodiments, the user terminal 130 may be a data receiving device and a display terminal of a data receiving party, for receiving and displaying the received data information. In some embodiments, the user terminal 130 may be configured to obtain and display data and/or information, working status, and the like collected by the movable collecting device 150 via the network 120, and may also be configured to obtain and display a water and fertilizer adjustment plan processed by the server 110 via the network 120. The above examples are intended only to illustrate the broad scope of the user terminal 130 device and not to limit its scope.

Storage device 140 may be used to store data and/or instructions. In some embodiments, storage device 140 may be used to store data and/or instructions obtained from, for example, server 110, user terminal 130, removable acquisition apparatus 150, and/or the like. In some embodiments, storage device 140 may store data and/or instructions used by server 110 to perform or use to perform the exemplary methods described in this specification.

The mobile gathering device 150 may be used to gather information related to the agricultural product 160. In some embodiments, the movable collection device 150 may be used to collect near infrared spectra of the agricultural product 160, the transmittance of the leaves, matrix detection information, and the like. In some embodiments, the movable capture device 150 may be moved under the control of the server 110. In some embodiments, the movable harvesting device 150 may also harvest the agricultural products 160.

The agricultural product 160 may be a plant produced in agriculture. In some embodiments, agricultural product 160 may include one or more plants. For example, agricultural products may include sorghum, rice, peanut, corn, wheat, and the like.

FIG. 2 is an exemplary block diagram of processor 112 shown in accordance with some embodiments of the present description.

As shown in fig. 2, in some embodiments, the smart agriculture optimization system 200 may include an infrared acquisition module 210, a light transmittance acquisition module 220, a substrate detection module 230, a liquid manure adjustment plan determination module 240, a positioning information acquisition module 250, a route determination module 260, a first control module 270, and a second control module 280.

The infrared collection module 210 may be configured to collect a near infrared spectrum of the agricultural product and determine maturity information of the agricultural product. For more details regarding determining maturity information for agricultural products, reference may be made to fig. 3 and its associated description.

The light transmission acquisition module 220 can be used for acquiring the light transmission coefficient of the leaves of the agricultural products and determining the nutrition information of the leaves. For more details on determining leaf nutrition information, reference may be made to fig. 3 and its associated description.

The substrate detection module 230 may be configured to detect substrates for cultivating agricultural products and determine substrate detection information. For more details on determining the substrate detection information, reference may be made to fig. 3 and its associated description.

The liquid manure adjustment plan determining module 240 may determine the liquid manure adjustment plan based on the maturity information, the leaf nutrition information, and the substrate detection information. For more details on determining the water and fertilizer adjustment plan, reference may be made to fig. 3 and its associated description.

The positioning information acquisition module 250 may be used to acquire positioning information of a movable acquisition device. For more details on obtaining positioning information, reference may be made to fig. 4 and its associated description.

The route determination module 260 may determine a route for the mobile gathering device to travel from the current location to the agricultural produce based on the preset map and positioning information. For more details regarding determining the route, reference may be made to fig. 4 and its associated description.

The first control module 270 may control the movable collection device to travel to an area associated with the agricultural produce based on the route. For more details regarding controlling the movable collection device to travel to the area associated with the agricultural produce, reference is made to fig. 4 and its associated description.

The second control module 280 may be configured to control the infrared collection device, the transmittance collection device, or the substrate detection device to collect in a relevant area to obtain near infrared spectrum, transmittance, or substrate detection information. In some embodiments, the second control module 280 may be further configured to control the infrared collection device, the light transmission collection device, or the substrate detection device to be separated from the main body device, and control the separated infrared collection device, light transmission collection device, or substrate detection device to collect in the relevant area. For more details regarding controlling the acquisition of the infrared acquisition device, the transmission acquisition device or the substrate detection device in the relevant area, reference may be made to fig. 4 and its associated description.

It should be understood that the system and its modules shown in FIG. 2 may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the above described methods and systems may be implemented using computer executable instructions and/or embodied in processor control code. The system and its modules of the present application may be implemented not only by hardware circuits of a programmable hardware device such as a very large scale integrated circuit or a gate array, but also by software executed by various types of processors, for example, and by a combination of the above hardware circuits and software (for example, firmware).

It should be noted that the above description of the modules is for convenience only and is not intended to limit the present disclosure to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the teachings of the present system, any combination of modules or sub-system configurations may be used to connect to other modules without departing from such teachings. In some embodiments, the first control module 270 and the second control module 280 disclosed in fig. 2 may be different modules in a system, or may be a module that implements the functionality of two or more of the modules described above. For example, each module may share one memory module, and each module may have its own memory module. Such variations are within the scope of the present disclosure.

Fig. 3 is an exemplary flow chart of a method for determining a water fertilizer adjustment plan according to some embodiments of the present disclosure. As shown in fig. 3, the process 300 includes the following steps. In some embodiments, the process 300 may be performed by the processor 112.

And 310, acquiring the near infrared spectrum of the agricultural product based on infrared acquisition equipment in the movable acquisition device, and determining the maturity information of the agricultural product. In some embodiments, this step 310 may be performed by the infrared acquisition module 210.

The agricultural product may be a plant produced in agriculture. For example, the agricultural product may be sorghum, rice, peanut, corn, wheat, and the like.

The movable gathering device may be a device for gathering information related to the agricultural product. In some embodiments, the movable collection device may include an infrared collection device, a transmission collection device, and a substrate detection device. In some embodiments, the mobile harvesting device may further comprise a body apparatus. The main body equipment can refer to the main body structure of the movable acquisition device.

In some embodiments, the movable harvesting device may also be used to harvest produce.

The infrared collection device may be a device for acquiring a near infrared spectrum. In some embodiments, the near infrared spectrum of the agricultural product may be collected by an infrared collection device. In some embodiments, the infrared collection device may be any of a variety of devices that can acquire near infrared spectra, for example, the infrared collection device may be a spectral detector.

In some embodiments, the content of each component in the agricultural product can be detected by analyzing the near infrared spectrum of the agricultural product. For example, the sugar content of the agricultural product can be analyzed according to different peak positions, peak numbers and peak intensities in the near infrared spectrum. In some embodiments, other information about the agricultural product, such as the type of agricultural product, whether the agricultural product is rotten, size of the agricultural product, hardness, shape, color, etc., may also be determined by analyzing the near infrared spectrum of the agricultural product.

The maturity information may be information indicating the maturity of the agricultural product. In some embodiments, the maturity of the agricultural product may be expressed in a maturity rating. For example, the maturity rating of the produce may include four ratings of unripe, semi-ripe, and over-ripe.

In some embodiments, the maturity information of the agricultural product may be determined by the content of each component in the agricultural product based on a preset rule. For example, the preset rule may be: when the agricultural product is strawberry, when the sugar content of the strawberry is 0-2%, the ripening grade of the strawberry is immature; when the sugar content of the strawberries is 2-4%, the ripening grade of the strawberries is half-ripe; when the sugar content of the strawberries is 4-7%, the ripening grade of the strawberries is ripening; when the sugar content of the strawberry is more than 7%, the ripening grade of the strawberry is over-ripening.

In some embodiments, the maturity information of the agricultural product may also be determined from other related information of the agricultural product. For example, maturity information for an agricultural product may be determined based on a comparison of the size, hardness, and color of the agricultural product to the size, hardness, and color of the agricultural product as it matures.

In some embodiments, maturity information for the agricultural product may also be determined by laser vibrometry techniques. For example, the ripeness information of the agricultural product is determined by generating vibration on the surface of the agricultural product using laser light and measuring the hardness of the agricultural product according to the resonance frequency. In some embodiments, the ripeness information of the agricultural product may also be determined according to other methods, for example, the ripeness information of the agricultural product may be determined using a fruit durometer, without limitation.

The method can be used for rapidly, nondestructively and accurately detecting the agricultural products, and can not influence the agricultural products while acquiring the information related to the agricultural products.

And 320, acquiring the light transmittance coefficient of the leaves of the agricultural products based on the light transmittance acquisition equipment, and determining the leaf nutrition information of the agricultural products. In some embodiments, this step 320 may be performed by the transmission collection module 220.

The transmission coefficient of a leaf may refer to an index of the ability of light to transmit through a leaf of an agricultural product. In some embodiments, the light transmittance can range from 0 to 1, wherein when the light transmittance is 0, light cannot penetrate the agricultural product leaves completely; when the light transmission coefficient is 1, light can completely transmit the agricultural product leaves. In some embodiments, the light transmittance of the leaves may reflect the photosynthesis capacity of the leaves. For example, when the light transmittance of the leaf is large, the photosynthesis capability thereof is weak.

The light transmission collection device may be a device for collecting a light transmission coefficient of the blade. In some embodiments, the light transmission collection device may include, but is not limited to, a plant chlorophyll meter, a plant nutrient detector, and the like. The light transmission collection device can emit light with two different wavelengths (for example, the wavelength of the light can be 650nm and 940nm) to irradiate the leaves of the agricultural product, and the light transmission coefficient of the leaves of the agricultural product can be determined by measuring the intensity of the light transmitted through the leaves.

The leaf nutrition information may refer to information indicating the nutritional status of the leaf. In some embodiments, the leaf nutritional information may include chlorophyll content and its synthesis rate, nitrogen content, leaf temperature and humidity, and the like, or any combination thereof.

In some embodiments, based on preset rules, the leaf nutrition information of the agricultural product can be determined through the light transmittance coefficient of the agricultural product leaves acquired by the light transmittance acquisition device. For example, when the light transmittance is 0.8, the chlorophyll content of the leaves of agricultural products can be determined to be 3.0SPAD based on a preset rule.

In some embodiments, based on leaf nutrition information, the fertilizer that needs to be applied may be determined. For example, when the agricultural product is cucumber, if the chlorophyll content of the cucumber leaf is low, the leaf may turn yellow or white, and a magnesium-containing fertilizer needs to be supplemented.

And 330, detecting a matrix for cultivating agricultural products based on the matrix detection equipment, and determining matrix detection information. In some embodiments, this step 330 may be performed by the matrix detection module 230.

The substrate can be used for cultivating agricultural products. The substrate may include solid media (e.g., soil, etc.), liquid media, semi-solid media, and dehydrated media, among others.

The substrate detection device can be used for detecting the components and the corresponding contents of the substrate so as to obtain the detection result of the substrate. In some embodiments, the substrate detection apparatus may include a soil detector, a media analyzer, and the like. In some embodiments, the detection results of the substrate may include pH, nitrogen content, phosphorus content, potassium content, humidity, temperature, and the like.

The substrate detection information may be used to reflect information about the substrate. In some embodiments, the substrate detection module 230 may determine the substrate detection information in a variety of ways, for example, the substrate detection module 230 may use the detection result of the substrate detection apparatus as the substrate detection information. For another example, the substrate detection module 230 may pre-process the detection result of the substrate detection device, and use the processed detection result as the substrate detection information. For example, the abnormal value in the detection result is eliminated by preprocessing.

And step 340, determining a water and fertilizer adjustment plan based on the maturity information, the leaf nutrition information and the matrix detection information. In some embodiments, this step 340 may be performed by the liquid manure adjustment plan determination module 240.

The water and fertilizer adjustment plan can be a plan for fertilizing the agricultural products to meet the requirements of the agricultural products for various nutrients. In some embodiments, the water and fertilizer adjustment plan may include fertilizer type, fertilization times, fertilization time, and fertilization amount per time. In some embodiments, the water and fertilizer adjustment plan may be determined according to the development cycle of the agricultural product. For example, nitrogen fertilizer is applied in the seedling stage to promote the seedlings to grow rapidly and robustly; and phosphate fertilizer is applied in the bud stage to promote the growth of buds and the like.

In some embodiments, the development period of the agricultural product can be determined based on the maturity information of the agricultural product, and the water and fertilizer adjustment amount is determined based on the difference between the nutrient requirement of each development period and the actually detected base body detection information and the difference between the leaf nutrition information corresponding to each development period and the actually detected leaf nutrition information, so that the water and fertilizer adjustment plan can be determined.

In some embodiments, the water and fertilizer adjustment plan may also be determined in other ways. For example, by obtaining a plurality of candidate water and fertilizer information, processing maturity information at a plurality of time points, leaf nutrition information at a plurality of time points, base detection information at a plurality of time points and the plurality of candidate water and fertilizer information based on a water and fertilizer demand prediction model, determining growth prediction information corresponding to the agricultural product under different candidate water and fertilizer information, and determining a water and fertilizer adjustment plan of the agricultural product based on the growth prediction information. For more details on the water and fertilizer demand prediction model, refer to fig. 5 and its related description.

Fig. 4 is an exemplary flow chart illustrating controlling a mobile gathering device to gather information about an agricultural product according to some embodiments of the present disclosure.

Step 410, acquiring positioning information of the movable acquisition device. In some embodiments, this step 410 may be performed by the positioning information acquisition module 250.

The positioning information may refer to the current position of the movable acquisition device. In some embodiments, the server 110 may obtain location information of the mobile acquisition device via a location system. The positioning system may include a Global Positioning System (GPS), a global navigation satellite system (GLONASS), a COMPASS navigation system (COMPASS), a beidou navigation satellite system, a galileo positioning system, a quasi-zenith satellite system (QZSS), and the like.

And step 420, determining a route for the movable collecting device to go to the agricultural products from the current position based on the preset map and the positioning information. In some embodiments, this step 420 may be determined by the route determination module 260.

The preset map may be a map of a certain area preset in advance. In some embodiments, the preset map may be a map of a mobile harvesting device work area. E.g., orchards, farms, etc. In some embodiments, the predetermined map may include locations of agricultural products, obstacles (e.g., ditches, soil bags, etc.), and the like. In some embodiments, the preset map may be directly obtained through a network (e.g., network 120).

In some embodiments, the route from the current position to the agricultural product of the movable collecting device can be determined according to the position of the agricultural product, the obstacle and the like in the preset map and the positioning information of the movable collecting device. In some embodiments, when there are no obstacles in the prediction map, the current position of the mobile gathering device may be connected to a line of positions of the agricultural products, with the line being taken as a route for the mobile gathering device to travel from the current position to the agricultural products. In some embodiments, the path for the mobile gathering device to travel from the current location to the agricultural produce may also be determined in other ways. For example, a route for the movable collection device to go from the current position to the agricultural product can be determined by a preset algorithm based on the position of the agricultural product, the obstacle, etc. in a preset map and the positioning information of the movable collection device.

Based on the route, the mobile gathering device is controlled to travel to an area associated with the agricultural produce, step 430. In some embodiments, this step 430 may be performed by the first control module 270.

The area associated with the agricultural product may be an area at a predetermined distance near the location of the agricultural product. For example, the area associated with the agricultural produce may be an area within 2 meters in diameter near where the agricultural produce is located.

In some embodiments, a mobile component is mounted in the mobile harvesting device through which the mobile harvesting device can travel to an area associated with the agricultural produce. For example, a mobile harvesting device may have a crawler mounted therein, through which the mobile harvesting device may be moved to an area associated with agricultural produce.

In some embodiments, the processor may generate the connection and movement instructions based on the location of the agricultural product to be processed and the particular processing that is required to be performed on the agricultural product to be processed (e.g., collecting data for the agricultural product or picking the agricultural product). The movable acquisition device can move based on the movement instruction. Each component of the movable acquisition device can be connected or disconnected based on the connection instruction, which is described in detail in connection with step 440 and will not be described herein again. For more details on determining the position of the agricultural product to be processed and the specific processing to be performed on the agricultural product to be processed, refer to fig. 5 and the related description thereof, and details are not repeated here.

In some embodiments, the processor may also control the movable acquisition device to move and acquire based on a preset acquisition mode. For example, the user moves from plot a to plot b and plot c … … in sequence, and determines a connected module according to the type information of agricultural products in each plot.

Step 440, controlling the infrared acquisition device, the light transmission acquisition device or the substrate detection device to acquire in the relevant area so as to acquire the near infrared spectrum, the light transmission coefficient or the substrate detection information. In some embodiments, this step 440 may be performed by the second control module 280.

In some embodiments, the processor may generate the acquisition instruction based on the information to be acquired (e.g., maturity information of the agricultural product, leaf nutrition information, and substrate detection information), and control the infrared acquisition device, the light transmission acquisition device, or the substrate detection device to acquire the information to be acquired in the relevant area. In some embodiments, controlling the infrared collection device, the transmission collection device, or the substrate detection device to collect in the relevant area may also be performed using the methods described in steps 441, 442, below.

And step 441, controlling the infrared acquisition equipment, the light transmission acquisition equipment and the matrix detection equipment to be separated from the main body equipment.

In some embodiments, the infrared collection device, the transmission collection device, and the substrate detection device are removably coupled to the body device.

In some embodiments, the means of detachable connection may include a snap connection and a jack connection. The clamping connection is realized by detachably connecting detachable equipment (namely the infrared acquisition equipment, the light transmission acquisition equipment and the substrate detection equipment) with main body equipment through a reserved clamping groove and a reserved fixed baffle. The jack connection is realized through the plug of the detachable equipment, the jack reserved by the main body equipment and the elastic clamping piece in the jack. In some embodiments, the detachable device and the main device may be connected by other detachable connection methods, which are not limited herein.

In some embodiments, the processor may generate connection instructions based on the information to be collected, thereby controlling the infrared collection device, the light transmission collection device, or the substrate detection device to be separated from or connected to the main body device. In some embodiments, when the detachable device is detachably connected to the main device based on a snap connection, the separation or connection between the detachable device and the main device may be controlled by controlling the position of the fixing flap. In some embodiments, when the detachable device is detachably connected to the main device based on the jack connection, the separation or connection between the detachable device and the main device may be controlled by controlling the position of the elastic clip. In some embodiments, the information that needs to be collected may be determined according to user needs. For example, when a user wants to know the nutritional status of an agricultural product, the information to be collected may be leaf nutritional information of the agricultural product.

Step 442, controlling the separated infrared acquisition equipment, light transmission acquisition equipment or matrix detection equipment to acquire in the related area so as to acquire the near infrared spectrum, the light transmission coefficient or the matrix detection information.

In some embodiments, the movable collection device may further comprise a robotic arm. In some embodiments, the robotic arm may be used to control a separate infrared acquisition device, transmission acquisition device, or substrate detection device to acquire in the area of interest. In some embodiments, the processor may determine the agricultural product requiring information to be collected based on image recognition, thereby controlling the mechanical arm to move to the position of the agricultural product requiring information to be collected for collection.

In some embodiments, the infrared collection device, the light transmission collection device, or the substrate detection device may be controlled to collect in the relevant area by other means to obtain near infrared spectrum, light transmission coefficient, or substrate detection information. For example, the infrared acquisition device, the light transmission acquisition device or the substrate detection device can be fixedly arranged on the movable acquisition device, and when the device is used, the agricultural products and the substrate are simultaneously detected so as to acquire the near infrared spectrum, the light transmission coefficient and the substrate detection information.

Through confirming the agricultural product that needs the information of gathering and the kind of the information that needs the collection to confirm the position of gathering and the removable device that needs to use, can realize the resource utilization maximize, improve equipment utilization and reduce equipment cost, can also improve detection efficiency simultaneously.

It should be noted that the above description related to the flow 400 is only for illustration and description, and does not limit the applicable scope of the present specification. Various modifications and changes to flow 400 will be apparent to those skilled in the art in light of this description. However, such modifications and variations are intended to be within the scope of the present description.

Fig. 5 is an exemplary flow diagram for determining a water fertilizer adjustment plan using a water fertilizer demand prediction model according to some embodiments of the present description. As shown in fig. 5, the process 500 may include the following steps:

and step 510, acquiring a plurality of candidate water and fertilizer information.

The candidate water and fertilizer information can be preset fertilizer information for adjusting the composition of each nutrient in the matrix. In some embodiments, the candidate water fertilizer information may include the type of nutrient and its corresponding content. In some embodiments, the candidate water and fertilizer information may be set manually or determined by historical candidate water and fertilizer information. For example, the candidate water and fertilizer information can be artificially set to be nitrogen fertilizers 1KG, 2KG and 3KG respectively.

And step 520, processing maturity information of multiple time points, leaf nutrition information of multiple time points, matrix detection information of multiple time points and multiple candidate water and fertilizer information based on the water and fertilizer demand prediction model, and determining corresponding growth prediction information of the agricultural product under different candidate water and fertilizer information.

The plurality of time points may be a plurality of time points adjacent before the time point at which the acquisition is performed. In some embodiments, the plurality of time points may be continuous or may be spaced. For example, the sampling time point is 15:00, and the plurality of time points may be 14:50, 14:40, 14:30, …, and the like.

The growth prediction information may be predicted growth information of the agricultural product after a preset time. In some embodiments, the preset time may be 20 days after fertilization, when the agricultural product is mature, and the like. In some embodiments, the growth prediction information may include a size, weight, shape, color, etc. of the agricultural product.

In some embodiments, the water and fertilizer demand prediction model may determine corresponding growth prediction information of the agricultural product under different candidate water and fertilizer information based on the input maturity information at multiple time points, the leaf nutrition information at multiple time points, the base detection information at multiple time points, and multiple candidate water and fertilizer information.

Illustratively, can be

And a nitrogen fertilizer 1KG input water and fertilizer demand prediction model, wherein the matrix represents collected information (such as maturity information, leaf nutrition information, matrix detection information and the like) of the agricultural product at a plurality of time points, the maturity information of the first row agricultural product in the matrix, and '1' represents that the maturity level of the agricultural product is immature; the leaf nutrition information of the second action agricultural product leaf in the matrix, wherein the expression of 3, 3.2 and 3.5, indicates that the chlorophyll content of the agricultural product is 3SPAD, 3.2SPAD and 3.5SPAD respectively; the third row in the matrix is matrix detection information of a matrix where the agricultural product is located, and 0.12 represents that the nitrogen content of the matrix is 0.12%; different columns in the matrix represent different time points, when the current time is 2030, 10, 4, and 06: 00, the first to third columns in the matrix represent respectively 2030, 10, 1, and 06: 00. year 2030, month 10, day 2, day 06: 00. year 2030, month 10, day 3 06: 00, the column of each element in the matrix represents the time point corresponding to the element. The output of the water and fertilizer demand prediction model can be that the weight of the agricultural products at maturity is 200 g.

In some embodiments, the water and fertilizer demand prediction model may be implemented by a Recurrent Neural Network (RNN) model and a Deep Neural Network (DNN) model.

In some embodiments, the water and fertilizer demand prediction model may be composed of a feature extraction layer and a prediction layer. In some embodiments, the feature extraction layer may be constructed based on the RNN model, and input into maturity information at multiple time points, leaf nutrition information at multiple time points, and matrix detection information at multiple time points, and output as a water and fertilizer requirement feature of the agricultural product (e.g., a nutrient type and content required for the agricultural product to reach a mature state). In some embodiments, the prediction layer may be constructed based on a DNN model, and the input is a water and fertilizer demand characteristic of the agricultural product (i.e., an output of the characteristic extraction layer) and one candidate water and fertilizer information, and the output is growth prediction information corresponding to the candidate water and fertilizer information. In some embodiments, the multiple candidate water and fertilizer information are predicted through the water and fertilizer demand prediction model, and growth prediction information corresponding to the multiple candidate water and fertilizer information can be obtained.

In some embodiments, the feature extraction layer and the prediction layer may be derived based on joint training. In some embodiments, the training samples may include sample maturity information for a plurality of historical sample time points, sample leaf nutrition information for a plurality of historical sample time points, sample matrix detection information for a plurality of historical sample time points, and a plurality of sample water and fertilizer information. In some embodiments, the way of obtaining the training sample may be based on historical data, and the historical data may include information related to the development of the historical agricultural products to the maturity (i.e., the maturity information, the leaf nutrition information, and the matrix detection information), and historical water and fertilizer information. In some embodiments, the label may be actual growth information of the agricultural product at a historical time point corresponding to the plurality of sample candidate water and fertilizer information, wherein the historical time point is located after the historical sample time point. In some embodiments, the tags may be obtained by manual measurement.

In some embodiments, the sample maturity information, the sample leaf nutrition information and the sample matrix detection information are input into a feature extraction layer in a water and fertilizer demand prediction model, the water and fertilizer demand features of the agricultural products and the sample water and fertilizer information output by the feature extraction layer are input into a prediction layer in the water and fertilizer demand prediction model, a loss function is constructed based on the output of the prediction layer and a label, and the parameters of the feature extraction layer and the prediction layer are updated iteratively based on the loss function at the same time until the preset conditions are met and training is completed. And after the training is finished, parameters of a characteristic extraction layer in the water and fertilizer demand prediction model can also be determined. The parameters of the feature extraction layer are obtained through the training mode, the problem that labels are difficult to obtain when the feature extraction layer is trained independently is solved, the feature extraction layer can well reflect the current nutrition condition of agricultural products, and the prediction layer can more accurately predict the growth prediction information of the agricultural products.

In some embodiments, the water and fertilizer demand prediction model may be composed of a feature determination layer and a treatment layer.

In some embodiments, the feature determination layer may be constructed based on a GNN model, with input of information for a plurality of acquisition points and a relationship between each acquisition point, and output of water and fertilizer demand features for each acquisition point. See below for more details on GNNs.

In some embodiments, the processing layer may be constructed based on a DNN model, and input the water and fertilizer demand characteristics for each acquisition point and one candidate water and fertilizer information, and output the growth prediction information for each acquisition point corresponding to the candidate water and fertilizer information. It can be understood that if there are a plurality of candidate water and fertilizer information, each candidate water and fertilizer information can obtain the growth prediction information of each corresponding collection point through the water and fertilizer demand prediction model.

In some embodiments, the collection point may be a location of the agricultural product for which information is desired to be collected. In some embodiments, the produce in the collection site may be planted and/or fertilized at a close time (e.g., same day, same morning of day, etc.). For example, the collection site may be a plot a or b as exemplified above, wherein the current time is 2030 and 10 months and 10 days, the agricultural products in plot a are planted 2030 and 8 months and 10 days, and the agricultural products in plot b are fertilized 2030 and 9 months and 20 days in 20 am.

The input to the feature determination layer may be data features of individual acquisition points represented in a graph in a theoretical sense, as well as data features of relationships between individual acquisition points. The graph is a data structure composed of nodes and edges, and may include a plurality of nodes and a plurality of edges connecting the plurality of nodes. The nodes correspond to all the acquisition points, and the edges correspond to the position relation among all the acquisition points.

The attributes of the nodes may be information of each collection point, including collected information (e.g., maturity information, leaf nutrition information, substrate detection information, etc.) corresponding to each collection point, and a collection time difference. The acquisition time difference may be the difference of the acquisition time of the different acquisition points with respect to a standard time. In some embodiments, the acquisition time difference may be in hours. For example, if the standard time is 14:00, the actual sampling time is 14:00, 16:00, 21:30, the difference in the sampling time is 0, 2, 7.5 (in hours). In some embodiments, the acquisition time difference may also be in units of days. In some embodiments, the acquisition time difference may also be expressed in other ways, which are not limited herein.

The attributes of the edges may include positional relationships (e.g., distance, wind direction information, altitude difference information, etc.) between the various acquisition points. For example, two collection points exist in a certain area, one collection point a is taken as a central point, the other collection point B is located at 50cm of the due north direction of the solar power generation device a, and the due north direction 50cm can be taken as an edge of a node.

The attributes of the nodes and the edges are used as the input of the GNN in a graph mode, so that the output data of each node can be obtained, and more specifically, the water and fertilizer requirement characteristics of the acquisition points corresponding to each node can be obtained. The graph neural network is a neural network directly acting on the graph, and can enable each node in the graph to exchange attribute information with each other through edges based on an information propagation mechanism, so that the node information of the node is continuously updated until a stopping condition is met. And outputting the water and fertilizer demand characteristics of the acquisition points corresponding to the nodes based on the updated node information of the nodes corresponding to each acquisition point.

In some embodiments, the feature determination layer and the processing layer may be derived based on joint training. In some embodiments, the training sample comprises information collected at a plurality of sample collection points, a time difference between the collection, a positional relationship between the plurality of sample collection points, and a plurality of sample liquid manure information. In some embodiments, the training sample may be obtained based on historical data, and the historical data may include information related to the development of the agricultural product in the historical collection points from maturity (i.e., the above maturity information, leaf nutrition information, and substrate detection information) and the relationship between the collection points, and historical water and fertilizer information. In some embodiments, the label may be actual growth information of the agricultural product in the collection point at a historical time point after the plurality of sample collection points apply the plurality of sample candidate water and fertilizer information, wherein the historical time point is located after the historical sample time point. In some embodiments, the tags may be acquired by manual measurement.

In some embodiments, information collected by a plurality of sample collection points, collection time difference for collection, and position relation among the plurality of sample collection points are input into a characteristic determination layer in a water and fertilizer demand prediction model, water and fertilizer demand characteristics of the collection points and sample water and fertilizer information output by the characteristic determination layer are input into a processing layer in the water and fertilizer demand prediction model, a loss function is constructed based on output of the processing layer and a label, and parameters of the characteristic determination layer and the processing layer are updated iteratively based on the loss function at the same time until preset conditions are met and training is completed. And after the training is finished, parameters of a characteristic determination layer in the water and fertilizer demand prediction model can also be determined. In some embodiments, the output of the water and fertilizer demand prediction model may also include the expected maturity time of the agricultural product in the collection site. Correspondingly, when the water and fertilizer demand prediction model is trained, the labels in the training data can also comprise the maturation time of agricultural products in the collection point besides the growth information described above. Wherein, the maturation time can be obtained by historical data.

The predicted ripening time may refer to the predicted time for the agricultural product to reach a state of maturity. For example, an expected ripening time for an agricultural product is 3 days, meaning that the agricultural product will ripen after 3 days.

In some embodiments, the processor may determine the time and location of the produce to be headed by the mobile gathering device based on the expected ripening time of the produce. For example, by comparing a preset time threshold with the expected ripening time, it is determined whether the mobile harvesting device is to treat the agricultural product. When the predicted maturity time of the agricultural product is smaller than the preset time threshold, the movable collecting device goes to the area related to the agricultural product to process the agricultural product, and when the predicted maturity time of the agricultural product is larger than or equal to the preset time threshold, the agricultural product is not processed temporarily. For example, when the preset time threshold is 3 days and the expected ripening time of an agricultural product is 2 days later, the movable collecting device can go to the area related to the agricultural product to pick the agricultural product. In some embodiments, upon determining that the mobile gathering device needs to travel to an area associated with the agricultural product for processing of the agricultural product, the processor may generate movement instructions to determine a route for the mobile gathering device to travel from the current location to the agricultural product and control the mobile gathering device to move to the area associated with the agricultural product. For more details on controlling the movement of the movable capture device, reference may be made to fig. 4 and its associated description.

The time and the position of the agricultural product to which the movable collecting device is going are determined according to the expected maturity time of the agricultural product, and the movable collecting device can be controlled to process the agricultural product more accurately and efficiently (for example, collect information, pick and the like), so that unnecessary collecting operation is reduced.

In some embodiments, the processor may generate the detection instruction according to a predicted maturity time of the agricultural product, wherein the detection instruction may be configured to control the movable collection device to travel to an area associated with the agricultural product and control the infrared collection device, the transmittance collection device, or the substrate detection device to acquire the near infrared spectrum, the transmittance coefficient, or the substrate detection information, respectively, in the associated area.

When information is collected, each collection point has greater contingency, but the growth condition of the agricultural product has certain universality and relevance, so that the data of the multiple collection points is comprehensively predicted based on a machine learning model, and the collection result for subsequent processing can be more accurate. Due to the influence of various conditions, the position relation and other influence relations (such as humidity, temperature and the like) of each acquisition point can be changed, and when each acquisition point is determined, the acquisition information of each acquisition point, the sampling time difference and the relation information among the acquisition points can be better combined based on the edge characteristics by utilizing the GNN model, so that the prediction result is more accurate.

And step 530, determining a water and fertilizer adjustment plan of the agricultural product based on the growth prediction information.

In some embodiments, the multiple candidate water and fertilizer information may be predicted by the water and fertilizer demand prediction model, and the growth prediction information corresponding to each of the multiple candidate water and fertilizer information may be determined. In some embodiments, the growth condition prediction information satisfying a condition (e.g., optimal) may be determined from the plurality of growth condition prediction information, and the candidate water and fertilizer information corresponding to the growth condition information satisfying the condition may be determined as the water and fertilizer adjustment plan of the agricultural product. The optimal growth prediction information may refer to the largest size, largest weight, the most full shape, etc. of the agricultural product at maturity. The optimal growth prediction information can be judged manually.

As described above, the growth prediction information of each acquisition point can be obtained through the growth prediction model. In some embodiments, the water and fertilizer adjustment plan of each collection point can be determined based on the growth prediction information of each collection point. It can be understood that the water and fertilizer adjustment plans of the collection points may be different according to local conditions.

In some embodiments, an overall water and fertilizer adjustment plan may also be determined, which is applicable to all collection points, in other words, the water and fertilizer adjustment plans for all collection points are the same. For example, the growth prediction information of each acquisition point corresponding to each candidate water and fertilizer information is fused, and the candidate water and fertilizer information corresponding to the fused growth prediction information meeting the requirements is taken as the whole water and fertilizer adjustment plan.

In some embodiments, the water and fertilizer adjustment plan of the agricultural product can be determined in other ways. For example, candidate water and fertilizer information of which the size of the agricultural product at maturity is larger than a threshold value is determined, and the candidate water and fertilizer information with the least amount of water and fertilizer in the part of the candidate water and fertilizer information is determined as a water and fertilizer adjustment plan of the agricultural product.

The composition of each nutrient in the base body for cultivating the agricultural products is adjusted by determining the liquid fertilizer adjustment plan of the agricultural products, so that the base body is more favorable for the growth of the agricultural products, the most suitable growth environment is provided for the agricultural products, the growth of the agricultural products is promoted to the maximum extent, the yield of the agricultural products can be effectively improved, and the quality of the agricultural products is enhanced.

The embodiment of this specification still provides an wisdom agriculture optimizing apparatus, the device includes: the infrared acquisition equipment is used for acquiring the near infrared spectrum of the agricultural product and determining the maturity information of the agricultural product; the light transmission acquisition equipment is used for acquiring the light transmission coefficient of the leaves of the agricultural products and determining the nutrition information of the leaves of the agricultural products; the substrate detection equipment is used for detecting a substrate for cultivating the agricultural product and determining substrate detection information; a memory for storing program code; and the processor is used for executing the program codes to realize the intelligent agriculture optimization method.

The embodiment of the present specification further provides a computer-readable storage medium, where the storage medium stores computer instructions, and when the computer reads the computer instructions in the storage medium, the computer executes the foregoing intelligent agriculture optimization method.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present specification.

Also, the description uses specific words to describe embodiments of the description. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.

Additionally, the order in which the elements and sequences of the process are recited in the specification, the use of alphanumeric characters, or other designations, is not intended to limit the order in which the processes and methods of the specification occur, unless otherwise specified in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose 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 that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the present specification, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to imply that more features than are expressly recited in a claim. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the number allows a variation of ± 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.

For each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this specification, the entire contents of each are hereby incorporated by reference into this specification. Except where the application history document does not conform to or conflict with the contents of the present specification, it is to be understood that the application history document, as used herein in the present specification or appended claims, is intended to define the broadest scope of the present specification (whether presently or later in the specification) rather than the broadest scope of the present specification. It is to be understood that the descriptions, definitions and/or uses of terms in the accompanying materials of this specification shall control if they are inconsistent or contrary to the descriptions and/or uses of terms in this specification.

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

Claims

1. An intelligent agricultural optimization method, comprising:

acquiring a near infrared spectrum of an agricultural product based on infrared acquisition equipment in a movable acquisition device, and determining maturity information of the agricultural product;

determining the nutrition information of the leaves of the agricultural products based on the light transmittance of the leaves of the agricultural products acquired by the light transmittance acquisition equipment in the movable acquisition device;

detecting a substrate for cultivating the agricultural product based on a substrate detection device in the mobile acquisition device, and determining substrate detection information; and

and determining a water and fertilizer adjustment plan based on the maturity information, the leaf nutrition information and the matrix detection information.

2. The method of claim 1, further comprising:

acquiring positioning information of the movable acquisition device;

determining a route for the movable collection device to travel from a current location to the agricultural product based on a preset map and the positioning information;

controlling the mobile gathering device to travel to an area associated with the agricultural produce based on the route; and

and controlling the infrared acquisition equipment, the light transmission acquisition equipment or the matrix detection equipment to acquire in the related area so as to acquire the near infrared spectrum, the light transmission coefficient or the matrix detection information.

3. The method of claim 2, wherein the movable acquisition device further comprises a body device, the body device being detachably connected to the infrared acquisition device, the transmission acquisition device, and the substrate detection device,

the controlling the infrared collection device, the light transmission collection device or the substrate detection device to collect in the relevant area to obtain the near infrared spectrum, the light transmission coefficient or the substrate detection information includes:

controlling the infrared acquisition equipment, the light transmission acquisition equipment or the matrix detection equipment to be separated from the main body equipment;

and controlling the separated infrared acquisition equipment, the separated light transmission acquisition equipment or the separated matrix detection equipment to acquire in the related area.

4. The method of claim 1, wherein determining a water and fertilizer adjustment plan based on the maturity information, the leaf nutrition information, and the matrix detection information comprises:

acquiring a plurality of candidate water and fertilizer information;

processing the maturity information of a plurality of time points, the leaf nutrition information of the plurality of time points, the matrix detection information of the plurality of time points and the plurality of candidate water and fertilizer information based on a water and fertilizer demand prediction model, and determining corresponding growth prediction information of the agricultural product under different candidate water and fertilizer information;

and determining a water and fertilizer adjustment plan of the agricultural product based on the growth prediction information.

5. An intelligent agricultural optimization system, the system comprising:

the infrared acquisition module is used for acquiring the near infrared spectrum of the agricultural product based on infrared acquisition equipment in the movable acquisition device and determining the maturity information of the agricultural product;

the light transmission acquisition module is used for acquiring the light transmission coefficient of the blade of the agricultural product based on light transmission acquisition equipment in the movable acquisition device and determining the blade nutrition information of the agricultural product;

the base body detection module is used for detecting a base body for cultivating the agricultural product based on a base body detection device in the movable acquisition device and determining base body detection information;

and the water and fertilizer adjustment plan determining module is used for determining a water and fertilizer adjustment plan based on the maturity information, the leaf nutrition information and the matrix detection information.

6. The system of claim 5, further comprising:

the positioning information acquisition module is used for acquiring the positioning information of the movable acquisition device;

the route determining module is used for determining a route of the movable acquisition device from the current position to the agricultural product based on a preset map and the positioning information;

a first control module for controlling the mobile gathering device to travel to an area associated with the agricultural product based on the route;

and the second control module is used for controlling the infrared acquisition equipment, the light transmission acquisition equipment or the matrix detection equipment to acquire in the related area so as to acquire the near infrared spectrum, the light transmission coefficient or the matrix detection information.

7. The system of claim 6, wherein the movable collection device further comprises a main body device, the main body device is detachably connected to the infrared collection device, the light transmission collection device and the substrate detection device, and the second control module is further configured to:

8. The system of claim 1, wherein the water and fertilizer adjustment plan determination module is further configured to:

acquiring a plurality of candidate water and fertilizer information;

9. An intelligent agricultural optimization device, the device comprising:

the infrared acquisition equipment is used for acquiring a near infrared spectrum of the agricultural product and determining maturity information of the agricultural product;

the light transmission acquisition equipment is used for acquiring the light transmission coefficient of the leaves of the agricultural products and determining the nutrition information of the leaves of the agricultural products;

the substrate detection equipment is used for detecting a substrate for cultivating the agricultural product and determining substrate detection information;

a memory for storing program code;

a processor for executing the program code to implement the method of any of claims 1-4.

10. A computer-readable storage medium storing computer instructions, wherein when the computer instructions in the storage medium are read by a computer, the computer performs the method of any one of claims 1-4.