A method, device, and medium for monitoring crop growth processes

Abstract

This application discloses a method, device, and medium for monitoring crop growth processes. The method involves collecting information about the crop's growth environment using pre-set sensor components; periodically photographing the crop using a drone equipped with a hyperspectral imager to obtain images of pests and diseases; inputting the acquired growth environment information into a pre-set crop environment information detection model group to obtain predicted crop growth information; determining a corresponding reference growth image set based on the shooting coordinates of the pest and disease images; determining the percentage of damaged leaves based on the reference growth image set; determining the corresponding crop growth parameter adjustment information based on a pre-set crop growth database, predicted growth information, and the percentage of damaged leaves; and uploading the predicted growth information, the percentage of damaged leaves, and the growth parameter adjustment information to a blockchain to store and record the crop's growth process data.

Description

Technical Field

[0001] This application relates to the field of agricultural testing technology, and in particular to a method, equipment and medium for monitoring the growth process of crops. Background Technology

[0002] Traditional crop cultivation is greatly affected by climate and weather factors, and agricultural operations mostly rely on the personal experience of growers, making it impossible to form standardized planting methods, and yields are often not guaranteed.

[0003] In crop cultivation, farmers' lack of professional knowledge and inability to conduct proper planting management easily leads to the occurrence of agricultural pests and diseases. After pests and diseases occur, the inability to find the correct solutions in a timely manner causes the cross-infection and spread of multiple diseases, increasing control costs. In addition to pests and diseases, environmental parameters causing abnormal crop growth include humidity, temperature, and light levels. Analyzing the causes of these abnormalities usually requires significant time and labor costs, and the long response time severely impacts crop yield. Summary of the Invention

[0004] This application provides a method, device, and medium for monitoring the growth process of crops, which is used to solve the following technical problem: In existing crop cultivation, the response time for manual analysis of environmental and pest information is long, which affects the yield of crops.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] This application provides a method for monitoring crop growth. The method includes: collecting crop growth environment information using pre-set sensor components; wherein the growth environment information includes at least one of temperature, soil moisture, sunlight exposure, and fertilizer application; periodically photographing the crop using a drone equipped with a hyperspectral imager to obtain images of crop diseases and pests; inputting the acquired growth environment information into a pre-set crop environment information detection model group to obtain predicted crop growth information; determining a corresponding reference growth image set based on the shooting coordinates of the disease and pest images, and determining the percentage of damaged leaves based on the disease and pest images and the reference growth image set; determining crop growth parameter adjustment information based on a pre-set crop growth database, predicted growth information, and the percentage of damaged leaves, and adjusting the corresponding agricultural infrastructure based on the growth parameter adjustment information; and uploading the predicted growth information, the percentage of damaged leaves, and the growth parameter adjustment information to a blockchain to store and record the crop growth process data.

[0007] This application embodiment utilizes IoT sensing devices, combined with modern agricultural infrastructure such as water and fertilizer facilities and spraying facilities, to collect farmland monitoring data. The collected crop environmental data is then input into a pre-set crop environmental information detection model group. This eliminates the need for manual analysis of crop growth information, improving the efficiency of crop environmental analysis and avoiding the problem of excessive analysis time affecting crop yield. Furthermore, based on the obtained percentage of damaged leaves, corresponding growth parameter adjustment information for the crop is determined. This achieves standardized planting, and the crop growth data is recorded throughout the entire process using the accuracy and immutability of blockchain technology, avoiding repetitive agricultural operations, thus improving data security and work efficiency, and ensuring healthy crop growth.

[0008] In one implementation of this application, a corresponding reference growth image set is determined based on the shooting coordinates corresponding to the pest and disease image. The proportion of damaged leaves corresponding to the crop is then determined based on the pest and disease image and the reference growth image set. Specifically, this includes: determining the latitude and longitude information marked on the pest and disease image to determine a reference growth image set with the same latitude and longitude information; wherein the images in the reference growth image set are all images of pest-affected crops; comparing the pest and disease image with the reference growth image set to determine the set of damaged locations in the pest and disease image; wherein the set of damaged locations includes at least the set of damaged locations such as spots, discoloration, wilting, and missing leaves in the damaged leaves; obtaining a binary image corresponding to the pest and disease image based on the pest and disease image and the set of damaged locations; and calculating the proportion of damaged leaves corresponding to the set of damaged locations using the binary image; wherein the proportion of damaged leaves is the percentage of the damaged leaf area in the total leaf area.

[0009] In one implementation of this application, after determining the set of damaged locations in the pest and disease images, the method further includes: comparing the brightness of the pest and disease images corresponding to the determined damaged locations with preset images of non-pest and disease-damaged leaves; determining the damaged locations with the same brightness comparison results as non-pest and disease-damaged locations; wherein, non-pest and disease-damaged locations include at least one or more of soil salinization, plant water shortage, plant nutrient excess, plant nutrient deficiency, excessively high temperature, and excessively low temperature; and removing non-pest and disease-damaged locations from the damaged locations to determine the proportion of damaged leaves corresponding to the crop based on the remaining damaged location information.

[0010] In one implementation of this application, the acquired growth environment information is input into a pre-set crop environment information detection model group to obtain predicted crop growth information. Specifically, this includes: inputting the current growth cycle of the crop and the growth environment information into the pre-set crop environment information detection model group; wherein, the pre-set crop environment information detection model group includes at least one of the following: a crop growth and development and yield and quality formation simulation model, a soil-crop production system water and nutrient dynamic balance simulation model, and a winter crop production prediction model; and obtaining the corresponding predicted crop growth information through the pre-set crop environment information detection model group; wherein, the predicted growth information includes at least one of the following: predicted crop quality information, predicted water and nutrient dynamic balance information, and predicted yield information.

[0011] In one implementation of this application, the growth parameter adjustment information corresponding to the crop is determined based on a preset crop growth database, predicted growth information, and the proportion of damaged leaves. Specifically, this includes: querying reference growth information in the preset crop growth database based on the current growth cycle of the crop; comparing the reference growth information with the predicted growth information to determine the difference in growth parameters corresponding to the current growth cycle; inputting pest and disease images into a pest and disease type recognition neural network model to obtain images labeled with pest and disease types; inputting the images labeled with pest and disease types and the proportion of damaged leaves into a preset pest and disease level estimation model to obtain the pest and disease level of the crop; and obtaining the growth parameter adjustment information corresponding to the crop based on the difference in growth parameters corresponding to multiple consecutive cycles of the crop and the pest and disease levels corresponding to multiple consecutive cycles of the crop.

[0012] In one implementation of this application, the agricultural infrastructure corresponding to the crop is adjusted based on growth parameter adjustment information. Specifically, this includes: when the difference in growth parameters corresponding to multiple consecutive cycles of the crop is increasing, determining the agricultural infrastructure that needs adjustment based on the difference in growth parameters; determining the adjustment parameters of the agricultural infrastructure that needs adjustment based on the predicted growth information and the preset infrastructure adjustment information table for the current cycle; adjusting the adjustment parameters a second time based on the increasing trend of the difference in growth parameters, and adjusting the agricultural infrastructure based on the adjusted parameters after the second adjustment; and adjusting the pest and disease control device corresponding to the crop based on the degree of increase in the pest and disease level when the pest and disease severity levels corresponding to multiple cycles of the crop are increasing.

[0013] In one implementation of this application, when the pest and disease severity levels of crops are increasing across multiple cycles, the pest and disease control device corresponding to the crops is adjusted based on the degree of increase in pest and disease severity levels. Specifically, this includes: obtaining the percentage of damaged leaves corresponding to each of the multiple crop cycles when the pest and disease severity levels are increasing; calculating the ratio of two adjacent percentages of damaged leaves based on chronological order to obtain the leaf damage increment; determining the pesticide ratio information for the current cycle based on a pre-set pest and disease control data table and the leaf damage increment, and adjusting the pest and disease control device based on the pesticide ratio information for the current cycle; wherein the pre-set pest and disease control data table includes multiple reference leaf damage increment information, and also includes pesticide ratio information corresponding to each of the multiple reference leaf damage increment information.

[0014] In one implementation of this application, predicted growth information, the proportion of damaged leaves, and growth parameter adjustment information are uploaded to the blockchain to store and record the growth process data of the crop. Specifically, this includes: obtaining the identification information of the current crop and the corresponding historical cultivation data; generating new cultivation data based on the historical cultivation data and the current actual cultivation data; performing hash calculation on the new cultivation data, and creating the current block with the identification information, the new cultivation data, and the hash value as the source data and storing it in the blockchain.

[0015] This application provides a crop growth process monitoring device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: collect crop growth environment information through preset sensor components; wherein the growth environment information includes at least one of temperature information, soil moisture information, sunlight exposure information, and fertilizer application information; take timed photos of the crop using a drone equipped with a hyperspectral imager to obtain images of crop diseases and pests; and process the acquired growth environment information. The system inputs a pre-set crop environmental information detection model group to obtain predicted crop growth information; based on the shooting coordinates corresponding to the pest and disease images, a corresponding reference growth image set is determined; based on the pest and disease images and the reference growth image set, the proportion of damaged leaves corresponding to the crop is determined; based on the pre-set crop growth database, predicted growth information, and the proportion of damaged leaves, the corresponding crop growth parameter adjustment information is determined, so as to adjust the corresponding agricultural infrastructure based on the growth parameter adjustment information; the predicted growth information, the proportion of damaged leaves, and the growth parameter adjustment information are uploaded to the blockchain to store and record the corresponding crop growth process data.

[0016] This application provides a non-volatile computer storage medium storing computer-executable instructions. These instructions are configured to: collect crop growth environment information via a pre-set sensor assembly; wherein the growth environment information includes at least one of temperature, soil moisture, sunlight exposure, and fertilizer application; periodically photograph the crop using a drone equipped with a hyperspectral imager to obtain images of crop diseases and pests; input the acquired growth environment information into a pre-set crop environment information detection model group to obtain predicted crop growth information; determine a corresponding reference growth image set based on the shooting coordinates of the disease and pest images, and determine the percentage of damaged leaves based on the disease and pest images and the reference growth image set; determine crop growth parameter adjustment information based on a pre-set crop growth database, predicted growth information, and the percentage of damaged leaves, and adjust the corresponding agricultural infrastructure based on the growth parameter adjustment information; and upload the predicted growth information, the percentage of damaged leaves, and the growth parameter adjustment information to a blockchain to store and record the crop's growth process data.

[0017] The above-mentioned technical solutions adopted in this application embodiment can achieve the following beneficial effects: This application embodiment, by deploying IoT sensing devices and combining them with modern agricultural infrastructure such as water and fertilizer facilities and spraying facilities, collects farmland monitoring data and inputs the collected crop environmental data into a pre-set crop environmental information detection model group. This eliminates the need for manual analysis of crop growth information, improving the efficiency of crop environmental analysis and avoiding the problem of excessive analysis time affecting crop yield. Secondly, based on the obtained percentage of damaged leaves, the corresponding growth parameter adjustment information for the crop is determined. This achieves standardized planting, and the crop growth data is recorded throughout the process based on the accuracy and immutability of blockchain technology, avoiding repetitive agricultural operations, thereby improving data security and work efficiency, and ensuring healthy crop growth. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0019] Figure 1 A flowchart of a method for monitoring crop growth process provided in this application embodiment;

[0020] Figure 2This is a schematic diagram of the structure of a crop growth monitoring device provided in an embodiment of this application. Detailed Implementation

[0021] This application provides a method, equipment, and medium for monitoring the growth process of crops.

[0022] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0023] Traditional crop cultivation is greatly affected by climate and weather factors, and agricultural operations mostly rely on the personal experience of growers, making it impossible to form standardized planting methods, and yields are often not guaranteed.

[0024] In crop cultivation, farmers' lack of professional knowledge and inability to conduct proper planting management easily leads to the occurrence of agricultural pests and diseases. After these pests and diseases occur, the inability to find timely and correct solutions causes cross-infection and spread of multiple diseases, increasing control costs and posing significant challenges to pollution-free production. Furthermore, in addition to pests and diseases, environmental parameters causing abnormal crop growth include humidity, temperature, and light levels. Analyzing the causes of these abnormalities typically requires substantial time and labor costs, and the slow response time severely impacts crop yields.

[0025] To address the aforementioned issues, this application provides a method, device, and medium for monitoring crop growth. By deploying IoT sensing devices and integrating them with modern agricultural infrastructure such as water and fertilizer facilities and spraying facilities, farmland monitoring data is collected, and the collected crop environmental data is input into a pre-set crop environmental information detection model group. This eliminates the need for manual analysis of crop growth information, improving the efficiency of crop environmental analysis and avoiding the problem of excessive analysis time affecting crop yield. Furthermore, based on the obtained percentage of damaged leaves, corresponding growth parameter adjustment information for the crop is determined. This enables standardized planting, and the crop growth data is recorded throughout the process using the accuracy and immutability of blockchain technology, avoiding repetitive agricultural operations, thereby improving data security and work efficiency, and ensuring healthy crop growth.

[0026] The technical solutions proposed in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0027] Figure 1This is a flowchart illustrating a method for monitoring crop growth processes, provided as an embodiment of this application. Figure 1 As shown, the method for monitoring crop growth includes the following steps:

[0028] S101. Collect information on the growth environment of crops through a pre-set sensor assembly; wherein the growth environment information includes at least one of the following: temperature information, soil moisture information, sunlight exposure information, and fertilizer application information.

[0029] In one embodiment of this application, a pre-set sensor assembly is installed to collect information about the crop's growth environment. This pre-set sensor assembly includes at least a temperature sensor, a humidity sensor, and a light sensor. Through this sensor assembly, environmental information such as the current crop's temperature, soil moisture, sunlight exposure, and fertilizer application rate is collected.

[0030] Furthermore, by collecting environmental information corresponding to crops, this information can be analyzed, and agricultural infrastructure can be adjusted in a timely manner when crop environmental information fails to meet standards. For example, if soil moisture does not meet requirements, crop irrigation facilities can be automatically adjusted to increase or decrease irrigation volume until soil moisture meets the requirements.

[0031] S102. Use a drone equipped with a hyperspectral imager to take photos of crops at regular intervals to obtain images of the corresponding diseases and pests of the crops.

[0032] In one embodiment of this application, crops are photographed periodically by a drone equipped with a hyperspectral imager to capture hyperspectral images of the crops, and the drone is also equipped with a positioning device.

[0033] Furthermore, during the photography process, the latitude and longitude of the shooting location can be obtained, thereby determining the latitude and longitude corresponding to each image of pests and diseases. By taking multiple photos of crops at the same latitude and longitude, the crops corresponding to that latitude and longitude can be analyzed at different times to determine the changes in pests and diseases affecting the crops.

[0034] S103. Input the obtained growth environment information into the preset crop environment information detection model group to obtain the predicted growth information of crops.

[0035] In one embodiment of this application, the current growth cycle of the crop and its growing environment information are input into a pre-set crop environmental information detection model group. This pre-set crop environmental information detection model group includes at least one of the following: a crop growth and development and yield / quality formation simulation model; a soil-crop production system water and nutrient dynamic balance simulation model; and a winter crop production prediction model. Through the pre-set crop environmental information detection model group, predicted crop growth information is obtained, which includes at least one of the following: predicted crop quality information; predicted water and nutrient dynamic balance information; and predicted yield information.

[0036] Specifically, this application embodiment pre-sets a pre-configured crop environmental information detection model group. This model group includes at least one of the following: a crop growth and development and yield / quality formation simulation model, a soil-crop production system water and nutrient dynamic balance simulation model, and a winter crop production prediction model. The crop growth and development and yield / quality formation simulation model is used to predict the yield and quality of the crop after inputting the current crop environmental information. The soil-crop production system water and nutrient dynamic balance simulation model is used to predict the dynamic balance of water and nutrient information corresponding to the crop after inputting the current crop environmental information. The winter crop production prediction model is used to predict the yield of the winter crop after inputting the current crop environmental information, assuming the current crop is a winter crop.

[0037] S104. Based on the shooting coordinates corresponding to the disease and pest images, determine the corresponding reference growth image set, and determine the proportion of damaged leaves of the crop based on the disease and pest images and the reference growth image set.

[0038] In one embodiment of this application, the latitude and longitude information marked on the pest and disease image is determined to identify a reference growth image set with the same latitude and longitude information. The images in the reference growth image set are all images of crops affected by pests and diseases. The pest and disease image is compared with the reference growth image set to determine the set of damaged locations in the pest and disease image. This set of damaged locations includes at least the locations of spots, discoloration, wilting, and missing leaves on damaged leaves. Based on the pest and disease image and the set of damaged locations, a binary image corresponding to the pest and disease image is obtained. Using the binary image, the percentage of damaged leaves corresponding to the set of damaged locations is calculated; the percentage of damaged leaves is the proportion of the damaged leaf area to the total leaf area.

[0039] Specifically, since the drone is equipped with a positioning device, it can acquire the latitude and longitude information of the shooting location, thereby obtaining the latitude and longitude information corresponding to each pest and disease image. This embodiment also includes an image dataset containing multiple image sets with different latitude and longitude locations. A reference growth image set with the same latitude and longitude information as the current image dataset is identified within this dataset. The reference growth image set is determined by latitude and longitude to ensure that the crops in the reference growth image set compared with the current pest and disease image are the same. Furthermore, all images in this reference growth image set are images of pest-infested crops. By comparing these images with images of pest-infested crops, the damaged locations in the current pest and disease image can be determined.

[0040] Furthermore, after identifying the damaged locations in the current pest and disease image, the brightness of the pest and disease image corresponding to the identified damaged location is compared with a preset image of non-pest and disease-damaged leaves. Damaged locations with the same brightness comparison result are identified as non-pest and disease-damaged locations. Non-pest and disease-damaged locations include at least one or more of the following: soil salinization, plant water shortage, plant nutrient excess, plant nutrient deficiency, excessively high temperature, and excessively low temperature. Non-pest and disease-damaged locations are then removed from the damaged locations to determine the percentage of damaged leaves corresponding to the crop based on the remaining damaged location information.

[0041] Furthermore, by obtaining the set of remaining damaged locations after removal, a binary image corresponding to the pest and disease image can be obtained. From this binary image, the total area of ​​the remaining damaged locations and the area of ​​the leaves in the pest and disease image can be obtained. By calculating the ratio of the total area of ​​the damaged locations to the total area of ​​the page, the percentage of damaged leaves can be obtained. This percentage of damaged leaves indicates the current pest and disease status of the crop.

[0042] S105. Based on the preset crop growth database, predicted growth information and the proportion of damaged leaves, determine the corresponding crop growth parameter adjustment information, and adjust the corresponding agricultural infrastructure based on the growth parameter adjustment information.

[0043] In one embodiment of this application, reference growth information is retrieved from a preset crop growth database based on the current growth cycle of the crop. The reference growth information is compared with predicted growth information to determine the difference in growth parameters corresponding to the current growth cycle. Pest and disease images are input into a pest and disease type recognition neural network model to obtain images labeled with pest and disease types. The ratio of the labeled pest and disease types to damaged leaves is input into a preset pest and disease level estimation model to obtain the pest and disease level of the crop. Based on the differences in growth parameters corresponding to multiple consecutive growth cycles of the crop, and the pest and disease levels corresponding to multiple consecutive growth cycles of the crop, the corresponding growth parameter adjustment information for the crop is obtained.

[0044] Specifically, this application embodiment pre-sets a crop growth database, which includes multiple reference growth information, representing information corresponding to different crops at different growth stages. The predicted growth information corresponding to the current crop at the current stage is compared with the corresponding reference growth information to determine the difference in growth parameters between the two.

[0045] Furthermore, the current pest and disease image is input into a pre-set pest and disease type recognition neural network model to determine the type of pest and disease. Next, the image labeled with the pest and disease type and the calculated ratio of damaged leaves are input into a pre-set pest and disease level estimation model to obtain the pest and disease level of the crop.

[0046] Furthermore, the crop is monitored for multiple consecutive growth cycles. The differences in growth parameters and the severity of pests and diseases corresponding to each growth cycle are obtained. Based on the information corresponding to each of the multiple consecutive growth cycles, the growth parameter adjustment information of the crop is obtained.

[0047] In one embodiment of this application, when the differences in growth parameters corresponding to multiple consecutive crop cycles are increasing, the agricultural infrastructure requiring adjustment is determined based on these differences. Based on the predicted growth information for the current cycle and a pre-set infrastructure adjustment information table, the adjustment parameters for the agricultural infrastructure requiring adjustment are determined. Based on the increasing trend of the growth parameter differences, the adjustment parameters are adjusted a second time, and the agricultural infrastructure is then adjusted based on these adjusted parameters. When the severity of pests and diseases is increasing across multiple crop cycles, the pest and disease control device corresponding to the crop is adjusted based on the degree of increase in the pest and disease severity.

[0048] Specifically, when the differences in growth parameters corresponding to multiple consecutive crop cycles are increasing, it is determined which parameters need adjustment, and then, based on these adjusted parameters, which agricultural infrastructure needs adjustment. Secondly, the predicted growth information for the current cycle is compared with a pre-set infrastructure adjustment information table to determine the values ​​of agricultural infrastructure that need adjustment. The pre-set infrastructure adjustment information table includes predicted growth information for multiple growth cycles, as well as infrastructure adjustment parameter values ​​for each of the predicted growth information pairs.

[0049] Furthermore, after identifying the infrastructure that needs adjustment and the parameters that need adjustment for each infrastructure, the parameters of the infrastructure can be increased based on the rising difference in the current growth parameters. For example, if the conclusion is that the crop yield is low and the amount of fertilizer needs to be increased, and the amount of fertilizer needed to be increased is gradually increasing, then the fertilization facilities can be adjusted to increase the amount of fertilizer a second time based on the current corresponding fertilization parameters, thereby making up for the difference in fertilization amount.

[0050] Furthermore, when the severity of pests and diseases increases across multiple crop cycles, the percentage of damaged leaves corresponding to each cycle is obtained. Based on chronological order, the ratio of the percentages of damaged leaves between adjacent cycles is calculated to determine the incremental damage. Using a pre-set pest and disease control data table and the incremental damage, the pesticide application ratio for the current cycle is determined. This ratio is then used to adjust the pest and disease control device. The pre-set pest and disease control data table includes various reference leaf damage increments and corresponding pesticide application ratios. For example, as the incremental damage gradually increases, the pesticide concentration can be increased to eliminate pests.

[0051] S106. Upload the predicted growth information, the percentage of damaged leaves, and the growth parameter adjustment information to the blockchain to store and record the corresponding growth process data of the crop.

[0052] In one embodiment of this application, the identification information of the current crop and the corresponding historical cultivation data are obtained. New cultivation data is generated based on the historical cultivation data and the current actual cultivation data. A hash calculation is performed on the new cultivation data, and the identification information, the new cultivation data, and the hash value are used to create the current block and store it in the blockchain.

[0053] Specifically, the agricultural operation process and crop growth data in this application embodiment are recorded throughout the entire process using the accuracy and immutability of blockchain technology, avoiding repetitive agricultural operations, thereby improving data security and work efficiency, and ensuring the healthy growth of crops. Each crop is assigned a unique identifier. New cultivation data is generated based on the existing historical data and current data of the current crop. The new cultivation data is hashed, and the calculated data, identifier information, and new cultivation data are uploaded to the blockchain for storage.

[0054] Figure 2 This is a schematic diagram of the structure of a crop growth monitoring device provided in an embodiment of this application. Figure 2 As shown, the crop growth monitoring equipment includes:

[0055] At least one processor; and,

[0056] A memory communicatively connected to the at least one processor; wherein,

[0057] The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to:

[0058] Information about the crop's growth environment is collected using pre-installed sensor components; the growth environment information includes at least one of the following: temperature, soil moisture, sunlight exposure, and fertilizer application rate.

[0059] The crops are photographed at regular intervals by a drone equipped with a hyperspectral imager to obtain images of the diseases and pests affecting the crops.

[0060] The acquired growth environment information is input into a pre-set crop environment information detection model group to obtain the predicted growth information of the crop.

[0061] Based on the shooting coordinates corresponding to the pest and disease images, a corresponding reference growth image set is determined, and based on the pest and disease images and the reference growth image set, the percentage of damaged leaves corresponding to the crop is determined.

[0062] Based on a preset crop growth database, the predicted growth information, and the percentage of damaged leaves, the growth parameter adjustment information corresponding to the crop is determined, so as to adjust the agricultural infrastructure corresponding to the crop based on the growth parameter adjustment information.

[0063] The predicted growth information, the percentage of damaged leaves, and the growth parameter adjustment information are uploaded to the blockchain to store and record the growth process data corresponding to the crop.

[0064] This application embodiment also provides a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows:

[0065] Information about the crop's growth environment is collected using pre-installed sensor components; the growth environment information includes at least one of the following: temperature, soil moisture, sunlight exposure, and fertilizer application rate.

[0066] The crops are photographed at regular intervals by a drone equipped with a hyperspectral imager to obtain images of the diseases and pests affecting the crops.

[0067] The acquired growth environment information is input into a pre-set crop environment information detection model group to obtain the predicted growth information of the crop.

[0068] Based on the shooting coordinates corresponding to the pest and disease images, a corresponding reference growth image set is determined, and based on the pest and disease images and the reference growth image set, the percentage of damaged leaves corresponding to the crop is determined.

[0069] Based on a preset crop growth database, the predicted growth information, and the percentage of damaged leaves, the growth parameter adjustment information corresponding to the crop is determined, so as to adjust the agricultural infrastructure corresponding to the crop based on the growth parameter adjustment information.

[0070] The predicted growth information, the percentage of damaged leaves, and the growth parameter adjustment information are uploaded to the blockchain to store and record the growth process data corresponding to the crop.

[0071] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0072] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0073] The above description is merely an embodiment of this application and is not intended to limit this application. For those skilled in the art, various modifications and variations can be made to the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the embodiments of this application should be included within the scope of the claims of this application.

Claims

1. A method of monitoring the growth of a crop, characterized by, The method includes: Information about the crop's growth environment is collected using pre-installed sensor components; the growth environment information includes at least one of the following: temperature, soil moisture, sunlight exposure, and fertilizer application rate. The crops are photographed at regular intervals by a drone equipped with a hyperspectral imager to obtain images of the diseases and pests affecting the crops. The acquired growth environment information is input into a pre-set crop environment information detection model group to obtain the predicted growth information of the crop. Based on the shooting coordinates corresponding to the pest and disease images, a corresponding reference growth image set is determined, and based on the pest and disease images and the reference growth image set, the percentage of damaged leaves corresponding to the crop is determined. Based on a preset crop growth database, the predicted growth information, and the percentage of damaged leaves, the growth parameter adjustment information corresponding to the crop is determined, so as to adjust the agricultural infrastructure corresponding to the crop based on the growth parameter adjustment information. The predicted growth information, the percentage of damaged leaves, and the growth parameter adjustment information are uploaded to the blockchain to store and record the growth process data corresponding to the crop. The step of determining the corresponding growth parameter adjustment information for the crop based on a preset crop growth database, the predicted growth information, and the proportion of damaged leaves specifically includes: Based on the current growth cycle of the crop, reference growth information is retrieved from a preset crop growth database; The reference growth information is compared with the predicted growth information to determine the difference in growth parameters corresponding to the current growth cycle. The images of pests and diseases are input into the neural network model for identifying pest and disease types to obtain images labeled with pest and disease types. The ratio of the image labeled with the type of pest and disease to the damaged leaf is input into a preset pest and disease level estimation model to obtain the pest and disease level of the crop. Based on the differences in growth parameters corresponding to multiple consecutive cycles of the crop, and the pest and disease levels corresponding to multiple consecutive cycles of the crop, the growth parameter adjustment information corresponding to the crop is obtained.

2. The method for monitoring crop growth process according to claim 1, characterized in that, The process of determining a corresponding reference growth image set based on the shooting coordinates of the pest and disease images, and determining the percentage of damaged leaves of the crop based on the pest and disease images and the reference growth image set, specifically includes: The latitude and longitude information marked on the images of pests and diseases is determined, and a reference growth image set with the same latitude and longitude information is determined; wherein, the images in the reference growth image set are all images of crops affected by pests and diseases; The pest and disease images are compared with the reference growth image set to determine the set of damaged locations in the pest and disease images; wherein, the set of damaged locations includes at least the set of damaged locations such as spots, discoloration, wilting, and missing leaves in the damaged leaves; Based on the pest and disease images and the set of damaged locations, a binary image corresponding to the pest and disease images is obtained; Using the binary image, the percentage of damaged leaves corresponding to the set of damaged locations is calculated; wherein, the percentage of damaged leaves is the proportion of the area of ​​the damaged leaf in the total area of ​​the leaf.

3. The method for monitoring crop growth process according to claim 2, characterized in that, After determining the set of damaged locations in the pest and disease image, the method further includes: The brightness of the images of pests and diseases corresponding to the identified damaged locations is compared with that of preset images of leaves damaged without pests and diseases. Damaged locations with the same brightness comparison results are identified as non-pest and disease-related damaged locations; wherein, the non-pest and disease-related damaged locations include at least one or more of the following: soil salinization, plant water shortage, plant nutrient excess, plant nutrient deficiency, excessively high temperature, and excessively low temperature. The non-pest / disease-damaged locations are removed from the damaged locations to determine the percentage of damaged leaves corresponding to the crop based on the remaining damaged location information.

4. The method for monitoring crop growth process according to claim 1, characterized in that, The step of inputting the acquired growth environment information into a pre-set crop environment information detection model group to obtain the predicted growth information of the crop specifically includes: The current growth cycle of the crop and the growth environment information are input into the pre-set crop environment information detection model group; wherein the pre-set crop environment information detection model group includes at least one of the following: crop growth and development and yield and quality formation simulation model, soil-crop production system water and nutrient dynamic balance simulation model, and winter crop production prediction model; The predicted growth information of the crop is obtained through the pre-set crop environmental information detection model group; wherein the predicted growth information includes at least one of the following: predicted quality information, predicted water and nutrient dynamic balance information, and predicted yield information of the crop.

5. The method for monitoring crop growth process according to claim 1, characterized in that, The adjustment of agricultural infrastructure corresponding to the crop based on the growth parameter adjustment information specifically includes: When the difference in growth parameters corresponding to multiple consecutive cycles of the crop is in an upward trend, the agricultural infrastructure that needs to be adjusted is determined based on the difference in growth parameters. Based on the predicted growth information and the pre-set infrastructure adjustment information table corresponding to the current cycle, the adjustment parameters of the agricultural infrastructure that needs to be adjusted are determined. Based on the rising trend of the difference in the growth parameters, the adjustment parameters are adjusted a second time, so as to adjust the agricultural infrastructure based on the adjusted parameters after the second adjustment. When the pest and disease severity levels of the crop are increasing in multiple cycles, the pest and disease control device corresponding to the crop is adjusted based on the degree of increase in the pest and disease severity levels.

6. The method for monitoring crop growth process according to claim 1, characterized in that, When the severity of pests and diseases on the crop increases across multiple crop cycles, the pest and disease control device corresponding to the crop is adjusted based on the degree of increase in the severity of the pest and disease severity. Specifically, this includes: When the severity of pests and diseases in the crop is increasing at multiple stages, the percentage of damaged leaves corresponding to each of the multiple stages of the crop is obtained. Based on the chronological order, the ratio of the percentage of damage to two adjacent damaged leaves is calculated to obtain the incremental damage to the leaves; Based on the pre-set pest and disease control data table and the leaf damage increment, the pest and disease control drug ratio information corresponding to the current cycle is determined, and the pest and disease control device is adjusted based on the pest and disease control drug ratio information corresponding to the current cycle; wherein, the pre-set pest and disease control data table includes multiple reference leaf damage increment information, and also includes pest and disease control drug ratio information corresponding to each of the multiple reference leaf damage increment information.

7. The method for monitoring crop growth process according to claim 1, characterized in that, The step of uploading the predicted growth information, the percentage of damaged leaves, and the growth parameter adjustment information to the blockchain to store and record the growth process data corresponding to the crop specifically includes: Obtain the current crop's identification information and corresponding historical breeding data; New breeding data is generated based on the historical breeding data and the current actual breeding data; The new breeding data is hashed, and the identification information, the new breeding data, and the hash value are used to create the current block and store it in the blockchain.

8. A crop growth monitoring device, comprising: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: Information about the crop's growth environment is collected using pre-installed sensor components; the growth environment information includes at least one of the following: temperature, soil moisture, sunlight exposure, and fertilizer application rate. The crops are photographed at regular intervals by a drone equipped with a hyperspectral imager to obtain images of the diseases and pests affecting the crops. The acquired growth environment information is input into a pre-set crop environment information detection model group to obtain the predicted growth information of the crop. Based on the shooting coordinates corresponding to the pest and disease images, a corresponding reference growth image set is determined, and based on the pest and disease images and the reference growth image set, the percentage of damaged leaves corresponding to the crop is determined. Based on a preset crop growth database, the predicted growth information, and the percentage of damaged leaves, the growth parameter adjustment information corresponding to the crop is determined, so as to adjust the agricultural infrastructure corresponding to the crop based on the growth parameter adjustment information. The predicted growth information, the percentage of damaged leaves, and the growth parameter adjustment information are uploaded to the blockchain to store and record the growth process data corresponding to the crop. The step of determining the corresponding growth parameter adjustment information for the crop based on a preset crop growth database, the predicted growth information, and the proportion of damaged leaves specifically includes: Based on the current growth cycle of the crop, reference growth information is retrieved from a preset crop growth database; The reference growth information is compared with the predicted growth information to determine the difference in growth parameters corresponding to the current growth cycle. The images of pests and diseases are input into the neural network model for identifying pest and disease types to obtain images labeled with pest and disease types. The ratio of the image labeled with the type of pest and disease to the damaged leaf is input into a preset pest and disease level estimation model to obtain the pest and disease level of the crop. Based on the differences in growth parameters corresponding to multiple consecutive cycles of the crop, and the pest and disease levels corresponding to multiple consecutive cycles of the crop, the growth parameter adjustment information corresponding to the crop is obtained.

9. A non-volatile computer storage medium storing computer-executable instructions, wherein the computer... Executable instructions are set as follows: Information about the crop's growth environment is collected through pre-installed sensor components; among which... The growth environment information includes at least one of the following: temperature information, soil moisture information, sunlight exposure information, and fertilizer application information; The crops are photographed at regular intervals by a drone equipped with a hyperspectral imager to obtain images of the diseases and pests affecting the crops. The acquired growth environment information is input into a pre-set crop environment information detection model group to obtain the predicted growth information of the crop. Based on the shooting coordinates corresponding to the pest and disease images, a corresponding reference growth image set is determined, and based on the pest and disease images and the reference growth image set, the percentage of damaged leaves corresponding to the crop is determined. Based on a preset crop growth database, the predicted growth information, and the percentage of damaged leaves, the growth parameter adjustment information corresponding to the crop is determined, so as to adjust the agricultural infrastructure corresponding to the crop based on the growth parameter adjustment information. The predicted growth information, the percentage of damaged leaves, and the growth parameter adjustment information are uploaded to the blockchain to store and record the growth process data corresponding to the crop. The step of determining the corresponding growth parameter adjustment information for the crop based on a preset crop growth database, the predicted growth information, and the proportion of damaged leaves specifically includes: Based on the current growth cycle of the crop, reference growth information is retrieved from a preset crop growth database; The reference growth information is compared with the predicted growth information to determine the difference in growth parameters corresponding to the current growth cycle. The images of pests and diseases are input into the neural network model for identifying pest and disease types to obtain images labeled with pest and disease types. The ratio of the image labeled with the type of pest and disease to the damaged leaf is input into a preset pest and disease level estimation model to obtain the pest and disease level of the crop. Based on the differences in growth parameters corresponding to multiple consecutive cycles of the crop, and the pest and disease levels corresponding to multiple consecutive cycles of the crop, the growth parameter adjustment information corresponding to the crop is obtained.

Images