CN114757326B

CN114757326B - Method and system for determining fertilization formula of farm crops based on artificial intelligence

Info

Publication number: CN114757326B
Application number: CN202210396682.7A
Authority: CN
Inventors: 孙彤; 黄桂恒
Original assignee: Brake Agricultural Big Data Technology Group Co ltd
Current assignee: Brake Agricultural Big Data Technology Group Co ltd
Priority date: 2021-06-22
Filing date: 2021-06-22
Publication date: 2023-04-07
Anticipated expiration: 2041-06-22
Also published as: CN113435566B; CN113435566A; CN114757326A

Abstract

The embodiment of the specification discloses a method and a system for determining a fertilization formula of farm crops based on artificial intelligence. The method comprises the following steps: acquiring multiple groups of quality parameters and crop environment information corresponding to multiple organs of crops; determining a plurality of effect scores corresponding to the candidate fertilization formulas through an evaluation model based on fertilizer element values corresponding to the candidate fertilization formulas, the plurality of groups of quality parameters corresponding to the organs and the crop environment information, wherein the effect scores comprise at least one of leaf growth scores, fruit growth scores and soil quality scores, and the evaluation model is a machine learning model; and taking the candidate fertilization formula corresponding to the effect score meeting the preset condition in the plurality of effect scores as the target fertilization formula of the crop.

Description

Method and system for determining fertilization formula of farm crops based on artificial intelligence

Description of the cases

The application is a divisional application which is provided by Chinese application with the application date of 2021, 06 and 22 months and the application number of 2021106944242, and the invention name of the method, the system, the device and the storage medium for fertilizing farm crops.

Technical Field

The specification relates to the technical field of agricultural production and planting, in particular to a method and a system for determining a fertilization formula of farm crops based on artificial intelligence.

Background

Various fertilizers are widely used in agricultural production, for some crops such as tomatoes, the growth states of stems, leaves, flowers and fruits of the crops are different and mutually influenced, the stems, leaves, flowers and fruits in different growth states respectively have corresponding growth requirements, different growth requirements influence the fertilization schemes of the crops, such as the control of the proportion of various fertilizer elements, if the fertilization schemes are not suitable, the growth requirements of the crops cannot be met, and the problems that the crop is lack of fertilizer due to less fertilizer application or the plant burns roots due to more fertilizer application and the like can occur.

Therefore, a method for fertilizing farm crops is needed, which can timely determine a proper fertilizing formula to fertilize the crops by monitoring the growth conditions of the crops, and improve the effectiveness of fertilization and the quality of the crops.

Disclosure of Invention

One of the embodiments of the present specification provides a method for determining a fertilization recipe for a farm crop based on artificial intelligence. The method comprises the following steps: acquiring multiple sets of quality parameters and crop environment information corresponding to multiple organs of crops; determining a plurality of effect scores corresponding to the candidate fertilization formulas through an evaluation model based on fertilizer element values corresponding to the candidate fertilization formulas, the plurality of groups of quality parameters corresponding to the organs and the crop environment information, wherein the effect scores comprise at least one of leaf growth scores, fruit growth scores and soil quality scores, and the evaluation model is a machine learning model; and taking the candidate fertilization formula corresponding to the effect score meeting the preset condition in the plurality of effect scores as the target fertilization formula of the crop.

One embodiment of the specification provides a system for determining a fertilization formula of a farm crop based on artificial intelligence. The method comprises the following steps: the acquisition module is used for acquiring multiple sets of quality parameters and crop environment information corresponding to multiple organs of crops; the determination module is used for determining a plurality of effect scores corresponding to a plurality of candidate fertilization formulas through an evaluation model based on fertilizer element values corresponding to the candidate fertilization formulas, the plurality of groups of quality parameters corresponding to the organs and the crop environment information, wherein the effect scores comprise at least one of leaf growth scores, fruit growth scores and soil quality scores, and the evaluation model is a machine learning model; and the candidate fertilization formula corresponding to the effect score meeting the preset condition in the plurality of effect scores is used as the target fertilization formula of the crop.

One of the embodiments of the present specification provides an apparatus for determining a fertilization formula of a farm crop based on artificial intelligence. The device comprises: at least one storage medium and at least one processor, the at least one storage medium configured to store computer instructions; the at least one processor is configured to execute the computer instructions to implement a method of fertilizing farm crops.

Some embodiments of the present description relate to a computer readable storage medium storing computer instructions that, when executed by a processor, implement a method of fertilizing farm crops.

Drawings

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. Wherein:

fig. 1 is a diagram of an exemplary application scenario for a farm crop fertilization system according to some embodiments of the present description;

FIG. 2 is an exemplary flow diagram of a method for fertilizing farm crops according to some embodiments of the present description;

FIG. 3 is an exemplary flow chart for determining a crop fertilization recipe, according to some embodiments of the present description;

fig. 4 is an exemplary flow chart illustrating the determination of a next time period target fertilization recipe according to some embodiments of the present description;

FIG. 5 is an exemplary diagram illustrating the acquisition of sets of quality parameters and crop environmental information corresponding to various organs of a crop according to some embodiments of the present description;

fig. 6 is a block diagram of a farm crop fertilization system according to some embodiments of the present description.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings 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.

Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of the present specification. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, 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 diagram of an exemplary application scenario for a farm crop fertilization system according to some embodiments of the present disclosure. In some embodiments, as shown in fig. 1, an application scenario 100 of a farm crop fertilization system may include a processing device 110, a network 120, a farm crop 130, and a storage device 140.

The farm crop 130 may be any kind of crop. In some embodiments, the farm crop 130 may include tomatoes 130-1, radishes 130-2, bovines 130-3, and the like, or any combination thereof.

Processing device 110 may process data and/or information obtained from storage device 140. For example, the processing device 110 may retrieve sets of quality parameters and crop environment information from the storage device 140 and train a predictive model and an evaluation model based on sample sets of quality parameters and sample crop environment information. In some embodiments, the processing device 110 may process information and/or data related to the farm crop 130 to perform one or more functions described herein.

In some embodiments, the processing device 110 may be a single server or a server farm. The server farm can be centralized or distributed (e.g., processing device 110 can be a distributed system). In some embodiments, the processing device 110 may be local or remote. For example, processing device 110 accesses information and/or data stored in storage device 140 via network 120. As another example, processing device 110 may be directly connected to storage device 140 to access stored information and/or data. In some embodiments, the processing device 110 may be implemented by a cloud platform. By way of example only, the cloud platform may include private clouds, public clouds, hybrid clouds, community clouds, distributed clouds, between clouds, multiple clouds, the like, or any combination thereof.

In some embodiments, processing device 110 may include one or more processing devices 110 (e.g., single-core or multi-core processors). By way of example only, the processing device 110 may include one or more hardware processors, such as a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an application specific instruction set processor (ASIP), an image processor (GPU), a physical arithmetic unit (PPU), a Digital Signal Processor (DSP), a field-programmable gate array (FPGA), a Programmable Logic Device (PLD), a controller, a micro-controller unit, a Reduced Instruction Set Computer (RISC), a microprocessor, or the like, or any combination thereof.

Storage device 140 may store data and/or instructions. In some embodiments, storage device 140 may store data/information obtained from components of processing device 110, and the like. In some embodiments, storage device 140 may store data and/or instructions for execution or use by processing device 110 to perform the example methods described in this specification.

In some embodiments, storage device 140 may include mass storage, removable memory, random Access Memory (RAM), read Only Memory (ROM), the like, or any combination thereof. Exemplary mass storage may include magnetic disks, optical disks, solid state disks, and the like. Exemplary removable memory may include flash drives, floppy disks, optical disks, memory cards, compact disks, magnetic tape, and the like. Exemplary random access memories may include Dynamic RAM (DRAM), double-data-rate synchronous dynamic RAM (DDR SDRAM), static RAM (SRAM), thyristor RAM (T-RAM), zero-capacitance RAM (Z-RAM), and the like. Exemplary read-only memories can include Mask ROM (MROM), programmable ROM (PROM), erasable programmable ROM (PEROM), electrically Erasable Programmable ROM (EEPROM), compact disk ROM (CD-ROM), digital versatile disk ROM, and the like. In some embodiments, storage device 140 may be implemented by a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-tiered cloud, and the like, or any combination thereof.

In some embodiments, a storage device 140 may be connected to the network 120 to communicate with one or more components in the scenario 100. One or more components in the scenario 100 may access data or instructions stored in the storage device 140 through the network 120. In some embodiments, the storage device 140 may be directly connected or in communication with one or more components in the scenario 100. In some embodiments, the storage device 140 may be part of the processing device 110.

Network 120 may be used to facilitate the exchange of information and/or data. In some embodiments, one or more components in the scenario 100 may send and/or receive information and/or data to/from other components in the scenario 100 via the network 120. For example, processing device 110 may retrieve data from storage device 140 via network 120. In some embodiments, the network 120 may be any form or combination of wired or wireless network. Merely by way of example, network 120 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an intranet, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), a bluetooth network, a zigbee network, a Near Field Communication (NFC) network, a global system for mobile communications (GSM) network, a Code Division Multiple Access (CDMA) network, a Time Division Multiple Access (TDMA) network, a General Packet Radio Service (GPRS) network, an enhanced data rates for GSM evolution (EDGE) network, a Wideband Code Division Multiple Access (WCDMA) network, a High Speed Downlink Packet Access (HSDPA) network, a Long Term Evolution (LTE) network, a User Datagram Protocol (UDP) network, a transmission control protocol/internet protocol (TCP/IP) network, a Short Message Service (SMS) network, a Wireless Application Protocol (WAP) network, an Ultra Wideband (UWB) network, mobile communications (1G, 2G, 3G, 4G, 5G) network, wi-Fi, li-NB, ioT (NB-narrowband), and the like, or any combination thereof.

In some embodiments, network 120 may include one or more network access points. For example, network 120 may include wired or wireless network access points (e.g., base stations and/or internet switching points 120-1, 120-2, \ 8230;) through which one or more components of scenario 100 may connect to network 120 to exchange data and/or information.

It should be noted that the above description of the fertilizing system for farm crops is for convenience of description only and should not be taken as limiting the scope of the present description to the examples. It will be appreciated by those skilled in the art that, given the teachings of the present system, any combination of components or sub-system may be configured to connect to other components without departing from such teachings.

Fig. 2 is an exemplary flow diagram of a method for fertilizing farm crops according to some embodiments of the present disclosure. In some embodiments, the flow 200 may include the following steps.

Step 210, obtaining multiple sets of quality parameters and crop environmental information corresponding to multiple organs of the crop. In some embodiments, step 210 may be performed by the obtaining module 610.

The crop 130 refers to various plants cultivated in agriculture, for example, oil crops (such as soybean, peanut, sesame, etc.), vegetable crops (such as tomato 130-1, radish 130-2, cabbage 130-3, etc.), flowers (rose, lily, etc.), grasses (such as qia grass, fescue, zoysia japonica, etc.), trees (such as pine, cypress, locust tree, etc.), etc.

Plant organs refer to plant structures composed of various tissues with certain functions. In some embodiments, the various organs of crop 130 may include vegetative organs (e.g., roots, stems, leaves) and reproductive organs (e.g., flowers, fruits, seeds), among others.

In this specification, the crop 130 is the tomato 130-1, and the various organs are the stem, leaf, flower and fruit.

The quality parameters may include relevant data indicative of growth, quality, etc. of various organs of the crop 130. In some embodiments, the quality parameters may include quality parameters of various organs of the crop 130, for example, quality parameters of at least one of a stem, a leaf, a flower, or a fruit may be included. In some embodiments, the quality parameter may include various parameters of various organs of the crop 130, for example, at least one of a diameter parameter of a stem of the crop 130, a leaf size parameter, a number of leaves parameter, a flower size parameter, a number of flowers parameter, a fruit size parameter, a fruit number parameter, and the like.

The environmental information may include data regarding the growing environment in which the crop 130 is located. In some embodiments, the environmental information may include weather-related data, such as temperature, humidity, wind speed, and the like. In some embodiments, the environmental information may include soil-related data, such as soil type (e.g., brick red soil, yellow brown soil, gray brown soil, etc.), soil texture (e.g., type and combination of different mineral particles in the soil), soil layer thickness, elemental content of the soil (e.g., potassium content, nitrogen content, etc.), and the like. In some embodiments, the environmental information may include geomorphic related data, such as terrain type (e.g., plain, plateau, mountain, hilly, etc.), geomorphic features (e.g., loess geomorphology, karst geomorphology, river geomorphology, etc.), and the like.

In some embodiments, data related to the crop 130, weather-related data, soil-related data, geomorphic-related data, and the like may be collected by the monitoring device 530, the drone 540, and the like, and the quality parameters and the crop environmental information may be directly or indirectly obtained based on the collected data (e.g., image recognition of the obtained image, analysis processing of the data, and the like). The monitoring device 530 may refer to a device having a monitoring function, such as a monitoring camera, an infrared detector, a soil content detecting device, and the like. For more details on data acquisition and quality parameter acquisition and crop environmental information, reference may be made to fig. 5 and its related description, which are not repeated herein.

And step 220, obtaining multiple groups of fertilizer requirement characteristics corresponding to the multiple organs through a characteristic extraction unit based on the multiple groups of quality parameters. In some embodiments, step 220 may be performed by feature module 620.

The fertilizer is a substance for providing one or more nutrient elements necessary for plants, improving soil properties and improving soil fertility level, and is one of the material bases of agricultural production. The fertilizer mainly comprises ammonium phosphate fertilizers, macroelement water-soluble fertilizers, secondary element fertilizers, biological fertilizers, organic fertilizers, multi-dimensional field energy concentrated organic fertilizers and the like. The nutrient elements included or provided by the fertilizer may include: trace elements such as nitrogen, phosphorus, potassium, boron, calcium, etc., and growth hormone-promoting, growth hormone-inhibiting, etc.

The fertilizer requirement profile refers to the requirement of the organs of the crop 130 for different fertilizers or nutrients during growth, for example, 100mg nitrogen and 10ml hormones are required for leaf growth of the crop 130. In some embodiments, the sets of fertilizer requirement characteristics for the various organs of crop 130 may be different, for example, 100mg nitrogen for leaf growth of crop 130, 50mg nitrogen for fruit set of crop 130, 3ml growth hormone inhibitor and 60mg nitrogen for fruit set enlargement of crop 130. In some embodiments, the sets of fertilizer requirement characteristics corresponding to the various organs of the crop 130 may also be the same, for example, the stem and fruit of the crop 130 may each require 50mg of nitrogen.

In some embodiments, the feature extraction unit may be a neural network for feature extraction. For example, the feature extraction unit may be a Convolutional Neural Network (CNN), which is a deep learning model or a multi-layer perceptron similar to an artificial Neural network. For another example, the feature extraction unit may be a Recurrent Neural Network (RNN), such as: LSTM (Long-Short Term Memory), GRU (Gate Recurrent Unit), etc. The recurrent neural network is a recurrent neural network which takes sequence data as input, recurses in the evolution direction of the sequence and all nodes are connected in a chain manner.

In some embodiments, the input of the feature extraction unit is multiple sets of quality parameters corresponding to multiple organs of the crop 130, and the output of the feature extraction unit is multiple sets of fertilizer requirement features corresponding to multiple organs, wherein a set of fertilizer requirement features may correspond to fertilizer or nutrient requirements of an organ. In some embodiments, a set of fertilizer demand characteristics may include demand for trace elements such as nitrogen, phosphorus, potassium, boron, calcium, and the like, and demand for growth hormone promoting, growth hormone inhibiting, and the like.

In some embodiments, the feature extraction unit may be obtained by training. Specifically, the training samples in the training process may include multiple sets of quality parameter samples, and based on the multiple sets of quality parameter samples, the quality parameter samples, and the labels corresponding to the samples (e.g., fertilizer requirement characteristics corresponding to the samples), the initial neural network is trained through at least one iteration process to obtain the characteristic extraction unit. In some embodiments, the model parameters may be iteratively updated by training through various methods based on the training samples. For example, the training may be based on a gradient descent method.

The characteristic extraction unit extracts a plurality of groups of fertilizer requirement characteristics from a plurality of groups of quality parameters, so that different fertilizer requirements of a plurality of different organs of the crop 130 can be reflected, and more complete crop characteristic information can be obtained.

And step 230, obtaining the fused fertilizer demand characteristics through a characteristic fusion unit based on the multiple groups of fertilizer demand characteristics. In some embodiments, step 230 may be performed by feature fusion module 630.

In some embodiments, the feature fusion unit may be a neural network unit for fusing sets of fertilizer demand features. For example, the feature fusion unit may be a Deep Neural Network (DNN). For another example, the feature fusion unit can be a two-layer convolutional neural network unit, and the structure can better fuse multiple groups of fertilizer requirement features, so that under-fitting caused by a single-layer neural network unit and over-fitting caused by multiple layers of neural network units are avoided.

In some embodiments, the input to the feature fusion unit is a plurality of sets of fertilizer requirement features corresponding to various organs of the crop 130, and the output is a fused set of fertilizer requirement features.

The fused fertilizer demand characteristics refer to fertilizer demand characteristics obtained by fusing a plurality of groups of fertilizer demand characteristics. In some embodiments, the respective fertilizer requirement characteristics of the stem, leaf, flower and fruit of the crop 130 may be superimposed by the characteristic fusion unit to obtain the fused fertilizer requirement characteristics, for example, the fertilizer requirement of the stem of tomato is 100mg nitrogen and 10ml hormone, the fertilizer requirement of the leaf thereof is 50mg nitrogen and 5ml hormone, and the fertilizer requirement of the stem and leaf may be superimposed to obtain 100mg +50mg =150mg nitrogen and 10ml +5ml =15ml hormone, so the fused fertilizer requirement characteristics are 150mg nitrogen and 15ml hormone. In some embodiments, the fused fertilizer requirement profile may be further obtained by weighting the fertilizer requirement profile of each of the stem, leaf, flower, fruit of the crop 130 by the profile fusion unit, for example, the fertilizer requirement of the stem of tomato is 100mg nitrogen, the weight proportion is 60%, the fertilizer requirement of the leaf thereof is 50mg nitrogen, the weight proportion is 40%, by weighting the fertilizer requirements of the stem and leaf, 100mg x 60 g +50mg x 40% =80mg nitrogen may be obtained, and thus, the fused fertilizer requirement profile is 80mg nitrogen. It is understood that the fused fertilizer requirement characteristics can also be obtained by subtracting the growth hormone promoting hormone and the growth hormone inhibiting hormone in a certain proportion, and the embodiment is not limited. Compared with the single fertilizer demand characteristic, the fused fertilizer demand characteristic can reflect the fertilizer demands of multiple groups of organs more accurately and perfectly.

And 240, determining a fertilization formula of the crop through a prediction model based on the fused fertilizer demand characteristics and the crop environment information. In some embodiments, step 240 may be performed by determining module 640.

The fertilization formula refers to a fertilizer element proportioning scheme determined according to the fertilizer requirements of the crops 130. In some embodiments, the fertilization formula can include, but is not limited to, at least one of the type of fertilizer used for fertilization, content values of each element of the fertilizer, content ratios of each element of the fertilizer, and the like. For example, the fertilization recipe may be to fertilize tomatoes with 100mg nitrogen, 200ml phosphorus, and 200ml potassium. For another example, the fertilization formula may be a 1:2:2, nitrogen, phosphorus and potassium. In some embodiments, the fertilizer formulation may include a range of fertilizer element contents, such as a nitrogen content of 100mg to 150mg.

In some embodiments, the predictive model may refer to a model for predicting a fertilization recipe for the crop 130. In some embodiments, the prediction model may be a machine learning model such as a binary model, a logistic regression model, or a neural network, which is not limited in this specification.

In some embodiments, the input to the predictive model is the fused fertilizer demand profile and crop environmental information, and the output of the predictive model is the fertilization recipe for the crop 130.

In some embodiments, the predictive model may be derived by training an initial predictive model. Specifically, the training samples in the training process may include a plurality of fertilizer demand characteristic samples and crop environment information samples, and the initial prediction model is trained through at least one iteration process based on the plurality of fertilizer demand characteristic samples, the crop environment information samples and the labels (such as corresponding fertilization recipes) corresponding to the samples, so as to determine the prediction model. In some embodiments, the model parameters may be iteratively updated by training through various methods based on the training samples. For example, training may be based on a gradient descent method.

In some embodiments, the method may further compriseThe multiple groups of quality parameters corresponding to multiple organs of the crop 130 are input into the feature extraction unit to obtain multiple groups of fertilizer demand features corresponding to the multiple organs, the fused fertilizer demand features are obtained through the feature fusion unit based on the multiple groups of fertilizer demand features, and the fused fertilizer demand features and the crop environment information are input into the prediction model to obtain the fertilization formula of the crop 130. For example, 4 sets of quality parameters were obtained for the stems, leaves, flowers, fruits of tomato: the group of quality parameters corresponding to the stem comprises that the average diameter parameter of the stem of a single plant is 5mm, the group of quality parameters corresponding to the leaves comprises that the average quantity parameter of the leaves of the single plant is 7 leaves, the leaf area index of the leaves is 2.3, the group of quality parameters corresponding to the flowers comprises that the average quantity parameter of the flowers of the single plant is 4, the group of quality parameters corresponding to the fruits comprises that the average quantity of the fruits of the single plant is 3, and the fruit area index of the fruits is 2 (wherein, the leaf area index is the ratio of the average leaf surface area to the unit area, and the fruit area index is the ratio of the average fruit volume to the unit volume), the 4 groups of quality parameters of the stem, the leaves, the flowers and the fruits are input into the characteristic extraction unit, and 4 groups of fertilizer demand characteristics corresponding to the stem, the leaves, the flowers and the fruits are obtained: the fertilizer requirement characteristics of stems are 100mg nitrogen and 10ml growth hormone promotion, the fertilizer requirement characteristics of leaves are 50mg nitrogen and 5ml growth hormone promotion, the fertilizer requirement characteristics of flowers are 150mg nitrogen and 20ml growth hormone promotion, the fertilizer requirement characteristics of fruits are 50mg nitrogen and 10ml growth hormone inhibition, the fused fertilizer requirement characteristics are 300mg nitrogen and 25ml growth hormone inhibition are obtained through a characteristic fusion unit based on the multiple groups of fertilizer requirement characteristics, the fused fertilizer requirement characteristics are 300mg nitrogen and 25ml growth hormone inhibition, and crop environment information (the temperature is 25 degrees, the humidity is 40 percent, the soil thickness is 5m, and the soil nitrogen content is 20mg/cm ² The soil potassium content is 22mg/cm ² ) Inputting a prediction model to obtain a tomato fertilization formula as follows: the fertilizer content comprises 370-420 mg of nitrogen and 25-35 ml of growth hormone inhibitor.

Based on the fused fertilizer demand characteristics and crop environment information, determining the fertilization formula of the crop 130 through the prediction model can comprehensively consider the fertilizer demand characteristics of different organs of the crop 130 and various surrounding environmental factors, so that the predicted fertilization formula of the crop 130 is more accurate, various different requirements (such as leaf growth, rhizome growth, fruit swelling and the like) for the growth of the crop 130 are met, and the optimal effect of promoting the growth of the crop 130 is achieved.

It should be noted that the above description related to the flow 200 is only for illustration and description, and does not limit the application scope of the present specification. Various modifications and alterations to flow 200 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. 3 is an exemplary flow chart illustrating the determination of a crop fertilization recipe according to some embodiments of the present description. In some embodiments, the flow 300 may include the following steps.

And 310, determining multiple combination modes of multiple fertilizer elements based on at least part of the multiple groups of quality parameters and the value ranges of the multiple fertilizer elements in the fertilization formula, wherein the multiple combination modes correspond to multiple candidate fertilization formulas. In some embodiments, step 310 may be performed by determining module 640.

In some embodiments, multiple combinations of values of multiple fertilizer elements may be determined based on at least some of the sets of quality parameters and the ranges of values of the multiple fertilizer elements in the fertilization recipe. If the value range of nitrogen is 40 mg-60 mg, the value range of phosphorus is 40 mg-60 mg, the value range of potassium is 40 mg-60 mg, and the value range of growth hormone inhibition is 3 ml-6 ml, the combination mode of the values of various fertilizer elements can be determined to be 45mg of nitrogen, 50mg of phosphorus, 53mg of potassium and 5ml of growth hormone inhibition, such as 48mg of nitrogen, 52mg of phosphorus, 58mg of potassium and 4ml of growth hormone inhibition.

In some embodiments, multiple combinations of values of multiple fertilizer elements may be determined based on preset conditions, such as the value relationships of the elements. For example, the phosphorus value = phosphorus minimum + (phosphorus max-phosphorus minimum) nitrogen value ratio/crop leaf area index, the potassium value = potassium minimum + (potassium max-potassium minimum) nitrogen value ratio/fruit area index, and the like.

The candidate fertilization formula refers to a fertilization formula as a fertilization candidate. In some embodiments, the plurality of combinations correspond to a plurality of candidate fertilization formulas, i.e., each combination is a candidate fertilization formula.

And step 320, determining a plurality of effect scores of the plurality of candidate fertilization formulas through an evaluation model based on the fertilizer element values of the plurality of combination modes, the plurality of groups of quality parameters corresponding to the plurality of organs and the crop environment information. In some embodiments, step 320 may be performed by determining module 640.

In some embodiments, the evaluation model may refer to a model for evaluating a plurality of effectiveness scores for a plurality of candidate fertilization formulas. In some embodiments, the evaluation model may be an evaluation type machine learning model such as a linear weighting model (lrp), an Analytic Hierarchy Process (AHP), and the like, which is not limited in this specification.

In some embodiments, values of fertilizer elements in multiple combination modes, multiple sets of quality parameters corresponding to multiple organs, and crop environment information may be input into the evaluation model, and multiple effect scores of multiple candidate fertilization formulas may be output.

In some embodiments, the effect score may be used to represent the effect of a candidate fertilization recipe upon fertilization of multiple organs of crop 130. Specifically, the effect score may include, but is not limited to, at least one of a leaf growth score, a fruit growth score, a soil goodness score, etc. of the crop 130. In some embodiments, the effect score may be expressed as an integer between 0 and 10, with 0 representing the least effective fertilization and 10 representing the best fertilization, and with a leaf growth score of 1, indicating that the candidate fertilization formulation is not effective for leaf fertilization of crop 130. In some embodiments, the effect score may be good, general, or poor, and if the leaf growth score is good, the candidate fertilization formula is indicated to be good for leaf fertilization of the crop 130. In some embodiments, the effect score may be a composite score of a plurality of effect scores, such as a leaf vigor score, a fruit vigor score, a soil goodness score, and the like, for all crops 130. For example, when the effect score is expressed as a number, the composite score may be an average score of a plurality of effect scores, for example, if the leaf growth score is 3, the fruit growth score is 5, and the soil quality score is 8, the composite score may also be (3 +5+ 7)/3 =5, and the composite score may also be a weighted average score of the plurality of effect scores, and may also be calculated based on a weight ratio, which is not limited in this embodiment. For another example, when the effect scores are expressed as words, the composite score may be determined based on the proportion of each score, such as when the effect score is the most effective number, the composite score is effective.

In some embodiments, the evaluation model may be derived by training an initial evaluation model. Specifically, the training samples in the training process may include sample fertilizer element values of multiple combination modes, multiple sets of sample quality parameters and sample crop environment information corresponding to multiple sample organs, and the initial evaluation model is trained through at least one iteration process based on the sample fertilizer element values of the multiple combination modes, the multiple sets of sample quality parameters and sample crop environment information corresponding to the multiple sample organs, and labels (such as corresponding effect scores) corresponding to the training samples to determine the evaluation model.

And 330, taking the candidate fertilization formula corresponding to the effect score meeting the preset condition in the effect scores as the target fertilization formula of the crop. In some embodiments, step 330 may be performed by determining module 640.

In some embodiments, the target fertilization recipe may refer to a fertilization recipe selected from the candidate fertilization recipes that provides the best fertilization effect. In some embodiments, the preset condition may be that the composite score of the plurality of effect scores is highest or ranked as TopN, i.e., the sum of the plurality of effect scores is highest or ranked as TopN. In some embodiments, the preset condition may be that the number of the plurality of effectiveness scores scored as being very effective is the greatest or the number is ranked TopN.

In some embodiments, the candidate fertilization recipe corresponding to the effect score satisfying the preset condition from among the plurality of effect scores may be used as the target fertilization recipe for the crop 130. For example, if the candidate fertilization recipe corresponding to the effect score satisfying the preset condition among the plurality of effect scores is 300mg nitrogen and 35ml hormone, 300mg nitrogen and 35ml hormone are used as the target fertilization recipe of the crop 130.

The evaluation model is used for evaluating the effects of the fertilizer element values in various combination modes, multiple groups of quality parameters corresponding to various organs and crop environment information, and the parameters of the fertilizer and the organs of the crop 130 and the comprehensive information of the crop environment can be more accurately and comprehensively considered, so that the accuracy of selecting the target fertilization formula is improved.

It should be noted that the above description related to the flow 300 is only for illustration and description, and does not limit the application scope of the present specification. Various modifications and changes to flow 300 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. 4 is an exemplary flow chart illustrating the determination of a next time period target fertilization recipe in accordance with some embodiments of the present description. In some embodiments, the flow 400 may include the following steps.

And 410, acquiring staged multiple groups of quality parameters and staged environmental information of at least one time stage through a monitoring device in a period of time for fertilizing the crops by adopting the target fertilization formula. In some embodiments, step 410 may be performed by determining module 640.

In some embodiments, a period of time has a length of time, such as 24 hours, 2 days, and the like. During the period of time that the crop 130 is fertilized with the target fertilization recipe, the fertilizer can exert a fertilizing effect on the crop 130, and the growth state of the crop 130 can be changed, i.e., the quality parameter can also be changed. In some embodiments, the period of time during which the crop 130 is fertilized with the target fertilization recipe can include a plurality of time periods, each of which can correspond to a single fertilization, e.g., after a first fertilization, a first time period corresponding to the first fertilization can be followed by a second fertilization of the crop 130, followed by a second time period corresponding to the second fertilization, the second time period can be followed by a third fertilization of the crop 130, followed by a third time period corresponding to the third fertilization.

In some embodiments, the time period has a length of time, such as 3 hours, 1 day, and the like. In some embodiments, where there are multiple time periods, the time lengths of the multiple time periods may be the same, e.g., 3 hours. In some embodiments, where there are multiple time periods, the time periods may be different in length, such as 24 hours for the first time period and 48 hours for the second time period.

In some embodiments, the periodic sets of quality parameters and periodic environmental information refer to sets of quality parameters and environmental information obtained during a specified time period (e.g., a first time period, a second time period, etc.). In some embodiments, the periodic sets of quality parameters and periodic environmental information may be sets of quality parameters and environmental information acquired at time points in time phases such as a middle time point and an end time point of a specified time phase. The method for obtaining multiple sets of quality parameters and environmental information may refer to step 210 and fig. 5 and the related description thereof, which are not described herein again.

And step 420, determining a staged effect score of the target fertilization formula through the evaluation model based on the fertilizer element values of the target fertilization formula, the staged multiple sets of quality parameters and the staged environmental information. In some embodiments, step 420 may be performed by determining module 640.

In some embodiments, a staged effect score refers to a score of the effect of fertilization corresponding to a target fertilization recipe employed for a time period.

In some embodiments, the values of fertilizer elements of the target fertilization formula adopted for a given time period (e.g., the first time period currently targeted), the periodic sets of quality parameters and the periodic environmental information for the time period may be input into an evaluation model, and the evaluation model outputs a periodic effectiveness score for the target fertilization formula. For determining the effectiveness score by the evaluation model, see step 320, which is not described in detail herein.

Step 430, determining the target fertilization formula for the next time period based on the staged effect score of the target fertilization formula for the current period. In some embodiments, step 430 may be performed by determining module 640.

In some embodiments, where the crop 130 is fertilized with the target fertilization recipe for multiple time-phased fertilization, the multiple time-phased fertilization recipes may differ. In some embodiments, the target fertilization recipe for a next time period (e.g., a second time period) may be determined based on the staged effect score of the target fertilization recipe for the current time period (e.g., a first time period). For example, if the effect score of the first time stage does not exceed the expected value, and the fertilization effect is considered to be poor, a plurality of effect scores of a plurality of candidate fertilization formulas can be output through the evaluation model according to the staged sets of quality parameters and staged environmental information corresponding to the first time stage after the first fertilization and the values of the fertilizer elements in the plurality of combination modes, and the target fertilization formula of the second time stage is determined again based on the plurality of obtained effect scores.

In some embodiments, the density of sample points for at least one area at a next time period (e.g., a second time period) or at a next time point data collection may be adjusted based on the staged effect score of the target fertilization recipe for the current time period (e.g., the first time period) or the current time point. In some embodiments, the sampling trajectory of the at least one area at the next time period (e.g., the second time period) or at the next time point data acquisition may also be adjusted based on the staged effect score of the target fertilization recipe for the current time period (e.g., the first time period) or the current time point. For example, when the effect score is low, the sampling density may be increased or decreased to obtain the next time period (e.g., the second time period) or the periodic sets of quality parameters and the periodic environmental information corresponding to the next time point. For another example, when the effect score is low, the acquisition trajectory of the drone 540 for at least one sampling point may be changed, so that an acquisition point not included in the current time phase (e.g., the first time phase) or the acquisition trajectory of the current time point is added to the sampling trajectory of the next time phase or the next time point, so as to obtain a periodic plurality of sets of quality parameters and periodic environmental information corresponding to the next time phase (e.g., the second time phase) or the next time point. In some embodiments, if the stage effect score is low, a key monitoring area (an area where the growth of the crop 130 is not good) may be determined, and the density of sampling points and the sampling trajectory in the key monitoring area may be adjusted according to the foregoing method. The description of at least one area, the sampling points 520, the data acquisition and the drone 540 may refer to fig. 5, which is not repeated again.

In some embodiments, the staged sets of quality parameters and staged environmental information for the next time period (e.g., the second time period) may be used in a targeted fertilization recipe determination process for fertilization (e.g., a third fertilization) after the second time period. In some embodiments, the staged sets of quality parameters and staged environmental information corresponding to the next time point may be used in a target fertilization recipe determination process for fertilization (e.g., second fertilization) after the time period (e.g., first time period) at the time point.

By increasing or decreasing the sampling points 520 based on the staged effect scores, the statistical analysis results of the collected data can be influenced, so that the quality parameters and the environmental information of the crops 130 can be changed in stages, the effect scores of the evaluation model are influenced, and the target fertilization scheme selected from the multiple candidate fertilization schemes can be continuously optimized based on the updated effect scores, so that the fertilization effect of the target fertilization scheme is better.

It should be noted that the above description related to the flow 400 is only for illustration and description, and does not limit the application 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 diagram illustrating the acquisition of sets of quality parameters and crop environmental information corresponding to various organs of a crop according to some embodiments of the present description. In some embodiments, flow 500 may include the following steps.

Step 510, setting at least one sampling point in at least one area of the farm where the crop is located. In some embodiments, step 510 may be performed by determining module 640.

The farm 550 is a farm, a vegetable garden, or the like, for cultivating the crop 130. At least one area may be divided in the farm 550. In some embodiments, the area of at least one region may be the same, such as 5 acres each. In some embodiments, the area of at least one region may be different.

In some embodiments, the shape of at least one region may be the same. In some embodiments, the shape of at least one region may be different.

The at least one sampling point 520 refers to a location where sets of quality parameters and crop environmental information corresponding to various organs of the crop 130 are collected in at least one area of the farm 550 where the crop 130 is located.

In some embodiments, the spacing of the at least one sampling point 520 may be the same, e.g., 5 meters before and after each at least one sampling point 520, and for example, 3 meters in rows and 4 meters in columns. In some embodiments, the spacing of at least one sampling point 520 may be different.

And step 520, obtaining at least one group of corresponding crop data and at least one group of corresponding environmental data at the at least one sampling point through the monitoring device. In some embodiments, step 520 may be performed by determining module 640.

In some embodiments, the monitoring device 530 may be positioned in the at least one area of the at least one sampling point 520. In some embodiments, the placement density of the monitoring devices 530 may be determined based on quality parameters of the crop 130. In some embodiments, if the leaf area index of the crop 130 is small, the placement density of the monitoring devices 530 is large; if the fruit area index of the crop 130 is small, the placement density of the monitoring device 530 is large. In some embodiments, the placement density determination formula for the monitoring device 530 may be, for example:

packing density = [1+ (1/leaf area index) × 0.5+ (1/fruit area index) × 0.5] × m (1)

Where m is the empirical density value for the conventional monitoring device 530.

In some embodiments, the monitoring device 530 may be launched into at least one area by a drone 540.

In some embodiments, at least one set of crop data and at least one set of environmental data may be obtained at least one sampling point 520 via a monitoring device 530. Specifically, each monitoring device 530 corresponds to one ID/ID, a two-dimensional code, a barcode or an NFC tag corresponding to the ID/ID is provided on each monitoring device 530, a positioning device is provided in each monitoring device 530 to position the position of the sampling point 520, a crop image and environmental data corresponding to the sampling point 520 can be obtained by scanning (e.g., scanning by the unmanned aerial vehicle 540) the two-dimensional code, barcode or NFC tag of the monitoring device 530, and then image recognition is performed on the crop image to obtain quality parameters of a part of the crop 130, such as a leaf area index (leaf area index is a ratio of an average leaf surface area to a unit area) of the crop 130, a fruit area index (fruit area index is a ratio of an average fruit volume to a unit volume) and the like of the crop 130, and part of the crop environmental data.

Step 530, acquiring the at least one group of crop data and the at least one group of environmental data by an unmanned aerial vehicle, and performing statistical analysis on the at least one group of crop data and the at least one group of environmental data to obtain the multiple groups of quality parameters and the crop environmental information corresponding to the multiple organs. In some embodiments, step 530 may be performed by determining module 640.

Drone 540 refers to an unmanned aircraft that is operated with a radio remote control device and self-contained program control, or is operated autonomously, either completely or intermittently, by an onboard computer.

In some embodiments, the multiple sets of crop data and the multiple sets of environmental data of the multiple sampling points 520 in the multiple regions obtained by the monitoring device 530 may be collected by the unmanned aerial vehicle 540, and the multiple sets of crop data and the multiple sets of environmental data of the multiple sampling points 520 in the multiple regions may be statistically analyzed to obtain multiple sets of quality parameters and crop environmental information corresponding to multiple organs. In some embodiments, the multiple sets of crop data and the multiple sets of environmental data corresponding to the multiple sampling points 520 may be statistically analyzed based on the weights corresponding to the sampling points 520 to obtain overall crop data and overall environmental data reflecting the overall situation of at least one area, and the weights may be related to the density of the sampling points in the area where the sampling points 520 are located, that is, the higher the density of the sampling points is, the greater the weights are; the lower the density of the sampling points, the smaller the weight; and obtaining multiple sets of quality parameters and crop environment information corresponding to multiple organs based on the overall crop data and the overall environment data.

By performing statistical analysis on the collected data based on the weights of the sampling points 520, more accurate sets of quality parameters and crop environmental information corresponding to various organs of the crop 130 can be obtained, so that the subsequent determination of the target implementation formula is more accurate.

It should be noted that the above description related to the flow 500 is only for illustration and description, and does not limit the applicable scope of the present specification. Various modifications and changes to flow 500 may occur to those skilled in the art, given the benefit of this description. However, such modifications and variations are still within the scope of the present specification.

Fig. 6 is a block diagram of a farm crop fertilization system according to some embodiments of the present description. As shown in fig. 6, the system 600 may include an obtaining module 610, a feature module 620, a feature fusion module 630, and a determination module 640.

In some embodiments, the obtaining module 610 is configured to obtain multiple sets of quality parameters and crop environmental information corresponding to multiple organs of the crop 130.

In some embodiments, the acquisition module 610 is further configured to set at least one sampling point 520 in at least one area of the farm 550 where the crop 130 is located; obtaining at least one set of crop data and at least one set of environmental data corresponding to the at least one sampling point 520 via a monitoring device 530; the at least one group of crop data and the at least one group of environmental data obtained by the monitoring device 530 are collected by the unmanned aerial vehicle 540, and statistical analysis is performed on the at least one group of crop data and the at least one group of environmental data to obtain the multiple groups of quality parameters and the crop environmental information corresponding to the multiple organs.

In some embodiments, the obtaining module 610 is further configured to perform statistical analysis on the at least one set of crop data and the at least one set of environmental data to obtain overall crop data and overall environmental data reflecting an overall condition of the at least one area based on a weight corresponding to the sampling point 520, where the weight is related to a density of the sampling point in an area where the sampling point 520 is located; and obtaining the multiple groups of quality parameters and the crop environment information corresponding to the multiple organs based on the whole crop data and the whole environment data.

In some embodiments, the characteristic module 620 is configured to obtain, through the characteristic extraction unit, a plurality of sets of fertilizer requirement characteristics corresponding to the plurality of organs based on the plurality of sets of quality parameters.

In some embodiments, the feature fusion module 630 is configured to obtain the fused fertilizer demand features through the feature fusion unit based on the plurality of fertilizer demand features.

In some embodiments, the determining module 640 is configured to determine the fertilization recipe for the crop 130 through a predictive model based on the fused fertilizer demand characteristics and the crop environmental information.

In some embodiments, the determining module 640 is further configured to determine a plurality of combinations of the plurality of fertilizer elements based on at least some of the plurality of sets of quality parameters and the value ranges of the plurality of fertilizer elements in the fertilization recipe, the plurality of combinations corresponding to a plurality of candidate fertilization recipes; determining a plurality of effect scores of the plurality of candidate fertilization formulas through an evaluation model based on the values of the fertilizer elements in the plurality of combination modes, the plurality of sets of quality parameters corresponding to the plurality of organs and the crop environment information; and taking the candidate fertilization formula corresponding to the effect score meeting the preset condition in the plurality of effect scores as the target fertilization formula of the crop 130.

In some embodiments, the determining module 640 is further configured to obtain, via the monitoring device 530, a periodic set of quality parameters and a periodic environmental information for at least one time period during a period of time in which the crop 130 is fertilized with the target fertilization recipe; determining a staged effect score of the target fertilization formula through the evaluation model based on fertilizer element values of the target fertilization formula, the staged multiple sets of quality parameters and the staged environmental information; determining the target fertilization recipe for a next time period based on the staged effect score of the target fertilization recipe for a current time period.

In some embodiments, the determining module 640 is further configured to adjust the density of sample points in at least one area of the farm 550 where the crop 130 is located and/or adjust the sampling trajectory in the at least one area.

It should be appreciated that the processing device 110 and its modules illustrated in FIG. 6 may be implemented in a variety of ways. For example, in some embodiments, a processing device 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 then be stored in a memory and executed by a suitable instruction execution system (e.g., a microprocessor or specially designed hardware). Those skilled in the art will appreciate that the processing devices and modules thereof described above may be implemented via computer-executable instructions. The system and its modules of the present specification may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, or the like, but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).

It should be noted that the above description of the system 600 and its modules is merely for convenience of description and should not be construed as limiting the present disclosure to 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. For example, the data acquiring module 610, the feature module 620, the feature fusing module 630 and the determining module 640 in fig. 5 may be different modules in one device, or one module may implement the functions of two or more modules described above. For another example, each module in the system 600 may share one storage module, and each module may have its own storage unit. As another example, the acquisition module 610 may be a separate component rather than belonging to a module within the system 600. Such variations are within the scope of the present disclosure.

The embodiment of the specification also provides a farm crop fertilizing device, which comprises at least one processor and at least one memory; the at least one memory is for storing computer instructions; the at least one processor is configured to execute at least some of the computer instructions to implement a method for fertilizing farm crops.

The beneficial effects that may be brought by the embodiments of the present description include, but are not limited to: (1) Based on the fused fertilizer demand characteristics and crop environment information, the fertilizer demand characteristics of different organs of crops and various surrounding environmental factors can be comprehensively considered, so that the predicted fertilizer application formula of the crops is more accurate, various different demands for crop growth are met, and the optimal effect of promoting the crop growth is achieved; (2) The evaluation model is used for evaluating the effects of the fertilizer element values in various combination modes, multiple groups of quality parameters corresponding to various organs and crop environment information, so that the parameters of the fertilizer and various organs of crops and the comprehensive information of the crop environment can be more accurately and comprehensively considered, and the accuracy of selecting a target fertilization formula is improved; (3) The statistical analysis result of the acquired data can be influenced by increasing or decreasing sampling points based on the stage effect score, so that the quality parameters and the environmental information of the crops can be changed in stages, the effect score of the evaluation model is influenced, and a target fertilization scheme selected from multiple candidate fertilization schemes can be continuously optimized based on the updated effect score, so that the fertilization effect of the target fertilization scheme is better; (4) By carrying out statistical analysis on the acquired data based on the weight of the sampling point, more accurate multiple groups of quality parameters and crop environment information corresponding to multiple organs of the crop can be obtained, so that the subsequent target determination implementation formula is more accurate.

It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.

The foregoing describes the present specification and/or some other examples. Various modifications may be made in the present disclosure in light of the above teachings. The subject matter disclosed herein is capable of being implemented in various forms and examples, and of being applied to a wide variety of applications. All applications, modifications and variations that may be claimed in the following claims are within the scope of the present description.

Also, the description uses specific words to describe embodiments of the specification. 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" or "another embodiment" in various places throughout this specification are not necessarily to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.

Those skilled in the art will appreciate that various modifications and improvements may be made to the disclosure herein. For example, the different system components described above are implemented by hardware devices, but may also be implemented by software solutions only. For example: the system is installed on an existing server. Further, the location information disclosed herein may be provided via a firmware, firmware/software combination, firmware/hardware combination, or hardware/firmware/software combination.

All or a portion of the software may sometimes communicate over a network, such as the internet or other communication network. Such communication enables loading of software from one computer device or processor to another. For example: from a management server or host computer of the radiation therapy system to a hardware platform of a computer environment, or other computer environment implementing the system, or similar functionality associated with providing information needed to determine wheelchair target structural parameters. Thus, another medium capable of transferring software elements may also be used as a physical connection between local devices, such as optical, electrical, electromagnetic waves, etc., propagating through cables, optical cables, or the air. The physical medium used for the carrier wave, such as an electric, wireless or optical cable or the like, may also be considered as the medium carrying the software. As used herein, unless limited to a tangible "storage" medium, other terms referring to a computer or machine "readable medium" refer to media that participate in the execution of any instructions by a processor.

Computer program code required for the operation of various portions of this specification may be written in any one or more programming languages, including an object oriented programming language such as Java, scala, smalltalk, eiffel, JADE, emerald, C + +, C #, VB.NET, python, and the like, a conventional programming language such as C, visual Basic, fortran 2003, perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, ruby, and Groovy, or other programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any form of network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or connected to an external computer (for example, through the Internet), or in a cloud computing environment, or used as a service, such as software as a service (SaaS).

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 foregoing 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.

Numbers describing attributes, quantities, etc. are used in some embodiments, it being understood that such numbers 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 set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by a particular embodiment. 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, articles, and the like, cited in this specification, the entire contents of each patent, patent application publication, and other material, is specifically incorporated herein by reference. Except where the application history document is inconsistent or contrary to the present specification, and except where the application history document is inconsistent or contrary to the present specification, the application history document is not inconsistent or contrary to the present specification, but is to be read in the broadest scope of the present claims (either currently or hereafter added to 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 the embodiments explicitly described and depicted herein.

Claims

1. A method for determining a fertilization recipe for a farm crop based on artificial intelligence, the method comprising:

acquiring multiple groups of quality parameters and crop environment information corresponding to multiple organs of crops;

determining a plurality of effect scores corresponding to the candidate fertilization formulas through an evaluation model based on fertilizer element values corresponding to the candidate fertilization formulas, the plurality of groups of quality parameters corresponding to the organs and the crop environment information, wherein the effect scores comprise at least one of leaf growth scores, fruit growth scores and soil quality scores, and the evaluation model is a machine learning model;

taking a candidate fertilization formula corresponding to an effect score meeting a preset condition in the plurality of effect scores as a target fertilization formula of the crop; wherein the content of the first and second substances,

the acquiring of the multiple sets of quality parameters and crop environmental information corresponding to the multiple organs of the crop comprises:

collecting multiple groups of crop images and multiple groups of environmental data of multiple sampling points in multiple areas of a farm through a monitoring device; each monitoring device corresponds to one ID/identity, a two-dimensional code, a bar code or an NFC label corresponding to the ID/identity is arranged on each monitoring device, and a positioning device is arranged in each monitoring device to position the position of at least one sampling point;

on the basis of weights corresponding to the plurality of sampling points respectively, performing statistical analysis on the plurality of sets of crop images and the plurality of sets of environmental data corresponding to the plurality of sampling points to obtain integral crop images and integral environmental data reflecting the integral conditions of a plurality of areas, wherein the weight corresponding to any one of the plurality of sampling points is positively correlated with the density of the sampling points of the plurality of sampling points;

performing image recognition on the whole crop image, and determining multiple groups of quality parameters corresponding to multiple organs of the crop;

and carrying out image recognition on the overall environment data to determine the crop environment information.

2. The method of claim 1, wherein values of fertilizer elements corresponding to the plurality of candidate fertilization formulas are determined based on at least some of the plurality of sets of quality parameters and ranges of values of the plurality of fertilizer elements in the fertilization formula.

3. The method of claim 1, wherein the method further comprises:

in a period of time when the target fertilization formula is adopted to fertilize the crops, acquiring staged multiple groups of quality parameters and staged environmental information of at least 1 time stage through a monitoring device;

determining a staged effect score of the target fertilization formula through the evaluation model based on fertilizer element values of the target fertilization formula, the staged multiple sets of quality parameters and the staged environmental information;

determining the target fertilization recipe for a next time period based on the staged effect score of the target fertilization recipe for a current time period.

4. The method of claim 3, wherein the determining the target fertilization recipe for a next time period based on the staged effect score for the target fertilization recipe for a current time period comprises:

adjusting the density of sampling points of at least one area of the farm where the crop is located and/or adjusting the sampling trajectory of the at least one area.

5. A system for determining a fertilization recipe for a farm crop based on artificial intelligence, the system comprising:

the acquisition module is used for acquiring multiple sets of quality parameters and crop environment information corresponding to multiple organs of crops;

the determination module is used for determining a plurality of effect scores corresponding to a plurality of candidate fertilization formulas through an evaluation model based on fertilizer element values corresponding to the candidate fertilization formulas, the plurality of groups of quality parameters corresponding to the organs and the crop environment information, wherein the effect scores comprise at least one of leaf growth scores, fruit growth scores and soil quality scores, and the evaluation model is a machine learning model; and the candidate fertilization formula corresponding to the effect score meeting the preset condition in the plurality of effect scores is used as the target fertilization formula of the crop; wherein the content of the first and second substances,

the acquisition module is further configured to:

collecting multiple groups of crop images and multiple groups of environmental data of multiple sampling points in multiple areas of a farm through a monitoring device; each monitoring device corresponds to one ID/identity, a two-dimensional code, a bar code or an NFC label corresponding to the ID/identity is arranged on each monitoring device, and a positioning device is arranged in each monitoring device to position the position of the at least one sampling point;

on the basis of weights corresponding to the plurality of sampling points respectively, carrying out statistical analysis on the plurality of groups of crop images and the plurality of groups of environmental data corresponding to the plurality of sampling points to obtain integral crop images and integral environmental data reflecting the integral conditions of a plurality of areas, wherein the weight corresponding to any one of the plurality of sampling points is positively correlated with the density of the sampling points;

6. The system of claim 5, wherein the determination module is further to:

and determining the values of the fertilizer elements corresponding to the candidate fertilization formulas respectively based on at least part of the quality parameters and the value ranges of the multiple fertilizer elements in the fertilization formulas.

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

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

9. An apparatus for determining a fertilization recipe for a farm crop based on artificial intelligence, comprising at least one storage medium and at least one processor, the at least one storage medium configured to store computer instructions; the at least one processor is configured to execute the computer instructions to implement the method of any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that the storage medium stores computer instructions which, when executed by a processor, implement the method according to any one of claims 1 to 4.