Smart agriculture supervision method and system based on Internet of Things

Abstract

The invention relates to a smart agriculture supervision method and system based on the Internet of Things, and relates to the field of smart agriculture, and the method comprises the steps: obtaining real-time data generated in the growth process of crops in an agricultural greenhouse, taking the real-time data as growth data, and uploading the growth data to a database in a cloud platform, bidirectional communication with a client in a cloud platform is realized through a subscription table in a subscription or release form, growth data in the subscription table is acquired to establish a decision model, the predicted growth condition of the current festival environment of crops is judged according to the decision model, and target plants in different areas in the agricultural greenhouse are determined; and obtaining the real growth condition of each target plant, determining the health degree of the target plant based on the real growth condition, and if an abnormal target plant exists, adjusting the operation parameters of each device related to the area where the abnormal target plant is located based on the predicted growth condition and the real growth condition of the target plant. The application has the effect of improving the operation accuracy of each device in the greenhouse.

Description

Technical Field

[0001] The present application relates to the field of smart agriculture, and in particular to a smart agriculture supervision method and system based on the Internet of Things. Background Art

[0002] With the development of agricultural planting technology and people's pursuit of more and more abundant food, the use of agricultural greenhouse technology to plant off-season crops and other cash crops is becoming more and more popular. However, the use of greenhouses to plant crops has high requirements for factors such as soil, air, and light in the greenhouse. When the growth factors required by crops change, the crops will grow slowly or even wither. At present, the prevention of abnormal growth of crops is mainly through manual inspections and paying attention to changes in factors such as soil and air to water, increase light, etc., which leads to inaccurate operation of equipment such as irrigation equipment and heating equipment in the greenhouse, thereby reducing the growth quality of crops. Summary of the invention

[0003] In order to improve the operating accuracy of each device in the greenhouse, the present application provides a smart agriculture supervision method and system based on the Internet of Things.

[0004] In the first aspect, the present application provides a smart agriculture supervision method based on the Internet of Things, which adopts the following technical solutions:

[0005] A smart agriculture supervision method based on the Internet of Things, comprising:

[0006] Acquire real-time data generated by crops in agricultural greenhouses during their growth process, including soil pH value, soil element content value, soil moisture value, soil oxygen value, greenhouse ambient temperature value, greenhouse light value, total carbon dioxide value, greenhouse ambient noise value, and atmospheric environment value;

[0007] Uploading the real-time data as growth data to a database in the cloud platform, and implementing two-way communication with a client in the cloud platform through a subscription table in the form of subscription or publication;

[0008] Acquire the growth data in the subscription table to establish a decision model, and determine the predicted growth status of the crop in the current seasonal environment according to the decision model;

[0009] Determine target plants in different areas of the agricultural greenhouse, and obtain the real growth status of each target plant at different heights, including leaf length, leaf width, outline, color, and trunk diameter;

[0010] Determine the health of each target plant based on the actual growth condition;

[0011] If there is an abnormal target plant whose health is less than a preset health, the operating parameters of each device related to the area where the abnormal target plant is located are adjusted based on the predicted growth status and the actual growth status of the target plant.

[0012] By adopting the above technical solution, real-time data is obtained to facilitate subsequent analysis. The real-time data is uploaded to the cloud platform in the form of subscription or publication to facilitate more efficient communication between the cloud platform and the client. The database in the cloud platform is constructed in the form of different seasons of the year, so as to obtain a predicted growth condition that is more in line with the current time, and the actual growth condition of the target plants in each area at different growth heights is obtained. The health degree is determined according to the actual growth condition, and the abnormal target plants are judged according to the health degree. The operating parameters of each device related to the area where the abnormal target plants are located are adjusted according to the predicted growth condition and the actual growth condition of the target plants, so as to make the regulation and control operation of the equipment in the greenhouse more precise.

[0013] In another possible implementation, determining the health of each target plant based on the actual growth condition includes:

[0014] Determine the ratio of leaf length to leaf width at each height, and determine the growth score at each height based on the ratio and the trunk diameter;

[0015] Determining a first similarity between the blade profile and a preset standard profile of the blade at each height, and a second similarity between the blade color and a preset standard color of the blade at each height;

[0016] determining a nutritional score at each height based on the first similarity and the second similarity;

[0017] Determine a growth score at each height based on the growth score and the nutrition score;

[0018] An overall growth score of each target plant is determined based on the growth score at each height, wherein the overall growth score represents the health of each target plant.

[0019] In another possible implementation, determining the overall growth score of each target plant based on the growth score at each height includes:

[0020] determining the difference between the growth score at each height and the corresponding benchmark score;

[0021] Determine a first height at which the difference is a negative number and a second height at which the difference is a non-negative number;

[0022] determining a baseline growth score based on the weight at each second height and the number at the second height;

[0023] Determine the scores at all first heights based on the weights at each first height and the difference;

[0024] Determine the variance of the difference values ​​at all first heights, and determine the growth scores at all first heights based on the variance, the scores, and the respective corresponding coefficients;

[0025] The overall growth score is determined based on the baseline growth score and the growth scores at all the first heights.

[0026] In another possible implementation, the real-time data generated by crops in the agricultural greenhouse during their growth process is obtained, including:

[0027] Collecting real-time data of crops from a sensor network, which consists of crop data collection equipment in a greenhouse connected to a Beidou radio frequency transceiver chip and several sensors. Each sensor node collects real-time data of crops under different parameters by connecting to a coordinator;

[0028] Get the real-time data of several groups of crops within the current preset time, calculate the real-time data within the preset time m hours and divide them into n 1 , n 2 , n 3 …n m The average Subtract the average value from each real-time data As the residual value f of the growth data i ;

[0029] According to the residual value f i Calculate the standard deviation s within the preset time m and calculate

[0030] According to the Grubbs criterion g(n,a), n is the number of nodes where sensors collect real-time data, and a is the preset significance level of real-time data. and the size of g(n,a);

[0031] like If it is less than g(n, a), it means that there are outliers. The collected outliers are eliminated, and finally the real-time data that are not eliminated are retained as the growth data within the preset time.

[0032] In another possible implementation, the acquisition of growth data in the subscription table to establish a decision model, and judging the predicted growth status of the crop in the current seasonal environment according to the decision model, includes:

[0033] Collecting growth data in each subscription table as a model sample, extracting available features in the model sample for training, and obtaining a training sample for building a decision model;

[0034] Setting constraints on model parameters in the decision model, and using the parameter variable difference range of the constraint conditions as the first threshold range;

[0035] Setting an objective function of the optimal environment growth parameters of crops in the decision model, and using the numerical range of the objective function as the second threshold range;

[0036] It is determined whether the growth data is within the first threshold range and also within the second threshold range.

[0037] In another possible implementation, adjusting the operating parameters of each device related to the area where the abnormal target plant is located based on the predicted growth condition and the actual growth condition of the target plant includes:

[0038] Perform fuzzy control on the growth data of the model parameters in the decision model, input the growth data into the fuzzy controller, predict the predicted growth status of the crops in the future time according to the fuzzy rules, and output the predicted growth status;

[0039] Determining abnormal factors based on the predicted growth conditions and the actual growth conditions of the abnormal target plants, and determining related equipment for the abnormal factors;

[0040] The predicted growth status is obtained and the control interval threshold of the crop growth parameter is calculated, and the operating parameters of the relevant equipment in the area where the abnormal target plant is located are controlled according to the control interval threshold.

[0041] In another possible implementation, the method further includes:

[0042] After regularly acquiring abnormal data in the model building module and parameter adjustment module, early warning signals are set respectively, and transmitted to the client users through the cloud platform for early warning prompts;

[0043] Set exception rules and determine whether the abnormal data is real growth data, perform noise reduction on the abnormal data, and issue a warning message in the cloud platform if it still matches the exception rules after processing;

[0044] After receiving the warning information, the cloud platform locates the crop area where the warning information is located according to the Beidou radio frequency transceiver chip in the sensor network, and uploads the geographic location to the cloud platform server. After receiving it, the cloud platform generates a message queue with the abnormal data of the crops and the geographic location and pushes it to the client user.

[0045] In the second aspect, the present application provides a smart agricultural supervision system based on the Internet of Things, which adopts the following technical solutions:

[0046] A smart agricultural supervision system based on the Internet of Things, comprising:

[0047] The first acquisition module is used to acquire real-time data generated by crops in the agricultural greenhouse during their growth process, wherein the real-time data includes soil pH value, soil element content value, soil moisture value, soil oxygen value, greenhouse ambient temperature value, greenhouse light value, total carbon dioxide value, greenhouse ambient noise value and atmospheric environment value;

[0048] A data transmission module, used to upload the real-time data as growth data to a database in the cloud platform, and to achieve two-way communication with a client in the cloud platform through a subscription table in the form of subscription or publication;

[0049] A model building module is used to obtain the growth data in the subscription table to establish a decision model, and to determine the predicted growth status of the crop in the current seasonal environment according to the decision model;

[0050] The second acquisition module is used to determine the target plants in different areas of the agricultural greenhouse, and obtain the real growth status of each target plant at different heights, including leaf length, leaf width, leaf outline, leaf color and trunk diameter;

[0051] A health determination module, used to determine the health of each target plant based on the actual growth condition;

[0052] The adjustment module is used to adjust the operating parameters of various devices related to the area where the abnormal target plant is located based on the predicted growth status and the actual growth status of the target plant when there is an abnormal target plant whose health is less than a preset health.

[0053] By adopting the above technical solution, the first acquisition module acquires real-time data to facilitate subsequent analysis, the data transmission module uploads the real-time data to the cloud platform in the form of subscription or publication to facilitate more efficient communication between the cloud platform and the client, the model construction module constructs the database in the cloud platform in the form of different seasons of the year, so as to obtain a predicted growth condition that is more in line with the current time, the second acquisition module acquires the actual growth condition of the target plants in each area at different growth heights, the health determination module determines the health according to the actual growth condition, and judges the abnormal target plants according to the health, and the adjustment module adjusts the operating parameters of each device related to the area where the abnormal target plants are located according to the predicted growth condition and the actual growth condition of the target plants, so as to make the control operation of the equipment in the greenhouse more precise.

[0054] In another possible implementation, when determining the health of each target plant based on the actual growth condition, the health determination module is specifically configured to:

[0055] Determine the ratio of leaf length to leaf width at each height, and determine the growth score at each height based on the ratio and the trunk diameter;

[0056] Determining a first similarity between the blade profile and a preset standard profile of the blade at each height, and a second similarity between the blade color and a preset standard color of the blade at each height;

[0057] determining a nutritional score at each height based on the first similarity and the second similarity;

[0058] Determine a growth score at each height based on the growth score and the nutrition score;

[0059] An overall growth score of each target plant is determined based on the growth score at each height, wherein the overall growth score represents the health of each target plant.

[0060] In another possible implementation, when determining the overall growth score of each target plant based on the growth score at each height, the health determination module is specifically configured to:

[0061] determining the difference between the growth score at each height and the corresponding benchmark score;

[0062] Determine a first height at which the difference is a negative number and a second height at which the difference is a non-negative number;

[0063] determining a baseline growth score based on the weight at each second height and the number at the second height;

[0064] Determine the scores at all first heights based on the weights at each first height and the difference;

[0065] Determine the variance of the difference values ​​at all first heights, and determine the growth scores at all first heights based on the variance, the scores, and the respective corresponding coefficients;

[0066] The overall growth score is determined based on the baseline growth score and the growth scores at all the first heights.

[0067] In another possible implementation, when acquiring the real-time data generated by crops in the agricultural greenhouse during their growth, the first acquisition module is specifically used to:

[0068] Collecting real-time data of crops from a sensor network, which consists of crop data collection equipment in a greenhouse connected to a Beidou radio frequency transceiver chip and several sensors. Each sensor node collects real-time data of crops under different parameters by connecting to a coordinator;

[0069] Get the real-time data of several groups of crops within the current preset time, calculate the real-time data within the preset time m hours and divide them into n 1 , n 2, n 3 …n m The average Subtract the average value from each real-time data As the residual value f of the growth data i ;

[0070] According to the residual value f i Calculate the standard deviation s within the preset time m and calculate

[0071] According to the Grubbs criterion g(n,a), n is the number of nodes where sensors collect real-time data, and a is the preset significance level of real-time data. and the size of g(n,a);

[0072] like If it is less than g(n, a), it means that there are outliers. The collected outliers are eliminated, and finally the real-time data that are not eliminated are retained as the growth data within the preset time.

[0073] In another possible implementation, the model building module establishes a decision model after acquiring the growth data in the subscription table, and determines the predicted growth status of the crop in the current seasonal environment according to the decision model, specifically for:

[0074] Collecting growth data in each subscription table as a model sample, extracting available features in the model sample for training, and obtaining a training sample for building a decision model;

[0075] Setting constraints on model parameters in the decision model, and using the parameter variable difference range of the constraint conditions as the first threshold range;

[0076] Setting an objective function of the optimal environment growth parameters of crops in the decision model, and using the numerical range of the objective function as the second threshold range;

[0077] It is determined whether the growth data is within the first threshold range and also within the second threshold range.

[0078] In another possible implementation, when the adjustment module adjusts the operating parameters of each device related to the area where the abnormal target plant is located based on the predicted growth condition and the actual growth condition of the target plant, the adjustment module includes:

[0079] Perform fuzzy control on the growth data of the model parameters in the decision model, input the growth data into the fuzzy controller, predict the predicted growth status of the crops in the future time according to the fuzzy rules, and output the predicted growth status;

[0080] Determining abnormal factors based on the predicted growth conditions and the actual growth conditions of the abnormal target plants, and determining related equipment for the abnormal factors;

[0081] The predicted growth status is obtained and the control interval threshold of the crop growth parameter is calculated, and the operating parameters of the relevant equipment in the area where the abnormal target plant is located are controlled according to the control interval threshold.

[0082] In another possible implementation, the system further includes:

[0083] After regularly acquiring abnormal data in the model building module and parameter adjustment module, early warning signals are set respectively, and transmitted to the client users through the cloud platform for early warning prompts;

[0084] Set exception rules and determine whether the abnormal data is real growth data, perform noise reduction on the abnormal data, and issue a warning message in the cloud platform if it still matches the exception rules after processing;

[0085] After receiving the warning information, the cloud platform locates the crop area where the warning information is located according to the Beidou radio frequency transceiver chip in the sensor network, and uploads the geographic location to the cloud platform server. After receiving it, the cloud platform generates a message queue with the abnormal data of the crops and the geographic location and pushes it to the client user.

[0086] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0087] An electronic device, comprising:

[0088] at least one processor;

[0089] Memory;

[0090] At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and at least one is configured to: execute a smart agriculture supervision method based on the Internet of Things as shown in any possible implementation of the first aspect.

[0091] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0092] A computer-readable storage medium, when the computer program is executed in a computer, enables the computer to execute a smart agriculture supervision method based on the Internet of Things as described in any one of the first aspects.

[0093] In summary, the present application includes at least one of the following beneficial technical effects:

[0094] Real-time data is obtained to facilitate subsequent analysis. Real-time data is uploaded to the cloud platform in the form of subscription or publication to facilitate more efficient communication between the cloud platform and the client. The database in the cloud platform is constructed in the form of different seasons of the year to obtain a predicted growth condition that is more in line with the current time. The actual growth conditions of the target plants in each area at different growth heights are obtained, and the health status is determined based on the actual growth conditions. Abnormal target plants are judged based on the health status, and the operating parameters of various equipment related to the area where the abnormal target plants are located are adjusted according to the predicted growth conditions and the actual growth conditions of the target plants, thereby making the regulation and control of the equipment in the greenhouse more precise. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] Figure 1 It is a flow chart of a smart agriculture supervision method based on the Internet of Things in an embodiment of the present application.

[0096] Figure 2 It is a structural diagram of a smart agriculture supervision system based on the Internet of Things in an embodiment of the present application.

[0097] Figure 3 It is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0098] The present application is further described in detail below in conjunction with the accompanying drawings.

[0099] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0100] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0101] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0102] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0103] The embodiment of the present application provides a smart agriculture supervision method based on the Internet of Things, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and the embodiment of the present application does not limit this. Figure 1 As shown, the method includes step S101, step S102, step S103, step S104, step S105 and step S106, wherein:

[0104] S101, obtaining real-time data generated during the growth of crops in an agricultural greenhouse.

[0105] Among them, real-time data include soil pH value, soil element content value, soil moisture value, soil oxygen value, greenhouse ambient temperature value, greenhouse light value, total carbon dioxide value, greenhouse ambient noise value and atmospheric environment value.

[0106] For the embodiment of the present application, since the agricultural greenhouse has a certain floor space, the staff can divide the planting area in the agricultural greenhouse into multiple areas, and each area is provided with a sensor for collecting the above real-time data, such as a soil pH sensor, a soil element content sensor, a soil moisture sensor, a temperature sensor, a light sensor, etc. The electronic device is connected to the above sensors through wires or wirelessly to obtain real-time data.

[0107] S102, uploading the real-time data as growth data to the database in the cloud platform, and realizing two-way communication with the client in the cloud platform through a subscription table in the form of subscription or publication.

[0108] For the embodiment of the present application, the growth data is obtained, and the growth data is transmitted to the server of the cloud platform by establishing a communication connection between the input terminal node of the cloud platform and the sensor network, and dynamic monitoring is implemented. The data connection pool of the cloud platform is configured to connect to the database through the data pool, and the configuration content includes the connection number size of the connection pool, the database index, and the database connection information. The database contains 24 sub-libraries named after festivals in a year, and the sub-libraries are sorted according to the order of the festivals, and the time period between the previous festival date and the next festival date in the current date is used as the current growth cycle of the crop, and the crop parameter attributes contained in each sub-library are the same. After receiving the growth data of the input terminal node, the server in the cloud platform classifies the festival cycle to which the growth data belongs according to the current date, and stores it in the corresponding sub-library. If the current date happens to be on the festival day, the real-time data is stored in the sub-library of the growth cycle between the current festival and the next festival.

[0109] The cloud platform transmits crop growth data bidirectionally in a subscription or publishing mode. In this mode, the client is divided into two roles: subscriber and publisher. After the user enters the cloud platform, it is determined whether the user is a subscriber or a publisher. If there is no identity information, it is determined that the current user is logging in for the first time and no identity information has been established. The user who logs in to the cloud platform for the first time is registered. The registration content includes selecting the user's role identity, filling in the user name and password, and authenticating the identity through the mobile phone number. After the registration is completed, return to the login page to log in again. After the login is completed, the connection between the client and the cloud platform server is established to determine whether the current connection is successful. If not, the server needs to reset the connection parameters. If the connection is successful, the user can directly enter the cloud platform.

[0110] The publisher client is used to receive the growth data in the cloud platform server and summarize the message queue and publish it to the subscription table of the cloud platform. After publishing the growth data, the subscriber client inputs the message to the cloud platform server. After receiving the message, the server triggers the matching mechanism between the input message and the subscription table, intercepts the keyword information in the message, and forms the message subject through the keyword information. The message subject is retrieved through the retrieval routing table. The message subject consists of several characters. It is determined whether there is an address range for the message subject. If so, the subscription table in the cloud platform is retrieved according to the message subject. If the subscription table where the message subject is located is retrieved, the growth data in the subscription table is transmitted to the subscriber in the client, realizing two-way communication between the cloud platform and the client.

[0111] S103, acquiring the growth data in the subscription table to establish a decision model, and determining the predicted growth status of the crop in the current seasonal environment according to the decision model.

[0112] The season may be the spring equinox, the summer solstice, etc., or the dog days, the coldest days, etc. The electronic device determines the decision model according to the season and the growth data and makes the growth status prediction of the current season more accurate.

[0113] Step S103 specifically includes step S1031 (not shown in the figure), step S1032 (not shown in the figure), step S1033 (not shown in the figure) and step S1034 (not shown in the figure), wherein:

[0114] S1031, collecting growth data in each subscription table as model samples, extracting available features in the model samples for training, and obtaining training samples for building a decision model.

[0115] S1032, setting constraints on model parameters in the decision model, and using the parameter variable difference range of the constraints as the first threshold range.

[0116] S1033, setting the objective function of the optimal environment growth parameters of the crops in the decision model, and taking the numerical range of the objective function as the second threshold range.

[0117] S1034, determining whether the growth data is within the first threshold range and at the same time within the second threshold range.

[0118] For the embodiment of the present application, after the cloud platform collects the growth data of crops, the growth data is learned and simulated. A decision model for growth data is constructed, a subscription table in the cloud platform is obtained, and a set of growth data of different seasons in a year and the actual growth conditions of plants (such as leaf length, leaf width, leaf outline, leaf width, leaf color, and trunk diameter, etc.) in the subscription table are collected as model samples, and the available features in the model samples are extracted. Taking the carbon dioxide concentration in the greenhouse as an example, the minimum concentration, the maximum concentration, the average concentration, and the corresponding actual growth conditions in the model samples are extracted. The available features are trained using a deep learning algorithm, and the training samples finally obtained are used to construct a decision model. The model parameters of the decision model are set, and the attributes of the model parameters are consistent with the attributes of crops in the cloud platform database. The constraints of the model parameters are set to prevent the variables in the model parameters from exceeding the threshold range within the constraints, and this threshold range is used as the first threshold range. The constraint condition is to calculate the difference in growth data under different seasons in previous years based on the historical data of crop growth. The difference between the parameter value in the decision model and the parameter value under the optimal environment of the crop in the database is obtained as the objective function, and the numerical range of the objective function is set as the second threshold range. When the server of the cloud platform obtains the crop growth data, it determines whether the growth data is within the first threshold range. If so, it means that the crop is in a normal growth state. If not, it means that the crop growth is abnormal, and this data is saved as abnormal data. The electronic device subsequently determines the abnormal factors and the equipment to solve the abnormal factors based on the normal growth status of the plants in the current season output by the decision model, that is, the predicted growth status and the actual growth status.

[0119] In addition, it is further determined whether the objective function of the difference calculation of the crop growth data in normal growth is within the second threshold range. If so, it means that the crops are in the optimal growth state. The results obtained by the decision model are sent to the publisher client through the cloud platform. The publisher client updates the subscription table and sends it to the subscriber client in a push mode, so that the user can intuitively see the growth status of the crops in the current greenhouse. The decision model continuously trains the model samples according to the optimal growth state in each time period to accurately calculate the growth data of crops in the greenhouse.

[0120] S104, determining target plants in different areas of the agricultural greenhouse, and obtaining the actual growth status of each target plant at different heights.

[0121] Among them, the actual growth conditions include leaf length, leaf width, leaf outline, leaf color and trunk diameter.

[0122] For the embodiment of the present application, the target plant can be a plant in the middle of each area, or a plant randomly determined in each area. After determining the target plant, the electronic device can control the drone to fly to each target plant, and collect images of the target plant through the camera device configured on the drone, so that the electronic device can determine the leaf length, leaf width, outline, leaf color and trunk diameter of the target plant at different heights through the image.

[0123] Specifically, the electronic device determines the outline of the leaf at each height by edge detection, and then determines the number of pixels along the direction of the main vein, and uses the number of pixels to represent the leaf length, and then determines the number of pixels in the direction perpendicular to the main vein, and uses the largest number of pixels to represent the leaf width. Similarly, the trunk diameter is represented by the number of pixels in the horizontal direction of the trunk outline.

[0124] S105, determining the health of each target plant based on the actual growth condition.

[0125] For the embodiment of the present application, after the electronic device determines the actual growth condition, the above-mentioned leaf length, leaf width, etc. all characterize the growth condition of the target plant at each height in different aspects. Therefore, the electronic device can determine the health of each target plant based on the acquired actual growth condition.

[0126] S106: If there is an abnormal target plant whose health is less than a preset health, the operating parameters of each device related to the area where the abnormal target plant is located are adjusted based on the predicted growth status and the actual growth status of the target plant.

[0127] For the embodiment of the present application, the preset health degree is used as the dividing point of whether the growth of the target plant is healthy or not. The electronic device compares the determined health degree with the preset health degree, thereby determining the abnormal target plant whose health degree is less than the preset health degree. After determining the abnormal target plant, the electronic device can determine the factors that need to be improved for the abnormal target plant based on the predicted growth condition and the actual growth condition, thereby determining the equipment related to the factors that need to be improved, and finally the electronic device can adjust the operating parameters of the related equipment.

[0128] In a possible implementation of the embodiment of the present application, the health of each target plant is determined based on the actual growth status in step S105, which specifically includes steps S1051, S1052, S1053, S1054 and S1055, wherein:

[0129] S1051, determining the ratio of leaf length to leaf width at each height, and determining the growth score at each height based on the ratio and the trunk diameter.

[0130] For the embodiment of the present application, the electronic device calculates the ratio of leaf length to leaf width at each height, and the ratio characterizes the fullness of the leaves at each height, and then combines the trunk diameter to determine the growth score at each height. Specifically, the electronic device can calculate the product or ratio of the ratio and the trunk diameter to obtain a score, and use the score to characterize the growth score at each height. Or the electronic device sets different coefficients for the ratio and trunk diameter at each height, and then the electronic device performs weighted calculation on the ratio and trunk diameter and the corresponding coefficients to obtain the growth score at each height.

[0131] S1052, determining a first similarity between the blade profile and a preset standard profile of the blade at each height, and a second similarity between the blade color and a preset standard color of the blade at each height.

[0132] For the embodiment of the present application, the contour is compared with the preset standard contour to determine whether there is dryness, growth deformity, etc., that is, whether there is a lack of nutrients. The leaf color is compared with the preset standard color to determine whether the leaf is lacking nutrients. The electronic device calculates the first similarity between the leaf contour at each height and the corresponding preset standard contour by calculating the cosine distance. The electronic device can calculate the second similarity between the leaf color at each height and the corresponding preset standard color by using the color difference calculation formula, weighted Euclidean distance, HVS color space, and LAB color space. The higher the first similarity, the more standard the leaf growth, the less lack of nutrients, and vice versa. The higher the second similarity, the healthier the leaf color, the less lack of nutrients, and vice versa.

[0133] S1053: Determine a nutrition score at each height based on the first similarity and the second similarity.

[0134] For the embodiment of the present application, leaf contour and leaf color are both key factors affecting leaf nutrition. The staff can set different weights for the first similarity and the second similarity in advance, and then perform weighted calculation on the first similarity, the second similarity and their corresponding weights to obtain a nutritional score.

[0135] S1054, determining a growth score at each height based on the growth score and the nutrition score.

[0136] For the embodiment of the present application, the electronic device can determine the growth score at each height after determining the growth score and the nutrition score at each height. Specifically, the electronic device can directly sum the growth score and the nutrition score to obtain the growth score, or set weights for the growth score and the nutrition score and perform weighted calculation to obtain the growth score.

[0137] S1055, determining the overall growth score of each target plant based on the growth score at each height.

[0138] Among them, the overall growth score represents the health of each target plant.

[0139] For the embodiment of the present application, after the electronic device determines the growth score at each height, it determines the overall growth score of the target plant based on the growth scores at all heights. By analyzing the growth conditions of the target plant at different heights, the growth score at each height is determined. Finally, the growth scores at different heights are combined to more accurately determine the overall growth score that characterizes the growth of the target plant.

[0140] In a possible implementation of the embodiment of the present application, in step S1055, the overall growth score of each target plant is determined based on the growth score at each height, specifically including step Sa (not shown in the figure), step Sb (not shown in the figure), step Sc (not shown in the figure), step Sd (not shown in the figure), step Se (not shown in the figure) and step Sf (not shown in the figure), wherein:

[0141] Sa, determine the difference between the growth score at each height and the corresponding benchmark score.

[0142] For the embodiment of the present application, the growth conditions at different heights correspond to different benchmark scores. The benchmark score indicates that the plant growth condition at the corresponding height is good, and a score lower than the benchmark score indicates that the growth of the plant at the corresponding height is unqualified. Therefore, the electronic device subtracts the growth score at each height from the corresponding benchmark score to obtain a difference. The difference indicates the difference between the growth condition at each height and the good growth condition.

[0143] Sb, determine the first height where the difference is a negative number and the second height where the difference is a non-negative number.

[0144] For the embodiment of the present application, after the electronic device determines the difference, if the difference is a negative number, it means that the growth score is less than the benchmark score, and the growth condition does not meet the standard of good growth condition, and if the difference is a non-negative number, it means that the growth score reaches the benchmark score, and the growth condition reaches the standard of good growth condition. Therefore, the electronic device determines the first height and the second height according to the positive or negative of the difference.

[0145] Sc, a benchmark growth score is determined based on the weight at each second height and the number at the second height.

[0146] For the embodiment of the present application, the importance of the growth conditions at different heights is different, so different weights are set for the growth conditions at different heights. The more the number at the second height, the better the overall growth condition of the target plant, and the higher the corresponding benchmark growth score. The electronic device can calculate the average weight or total weight of all the weights at the second height. The larger the average weight or the larger the total weight, the more the number, the better the growth condition of the target plant at a high-importance position. The staff can set a coefficient for the average weight or the total weight, and set a coefficient for the number. Then the electronic device performs a weighted calculation based on the average weight or the total weight, the number at the second height, and the corresponding coefficients to obtain a score, and determines the preset score interval where the score is located from multiple preset score intervals. Each preset score interval corresponds to a benchmark growth score, thereby determining the benchmark growth score. Or the electronic device directly determines the score as the benchmark growth score.

[0147] Sd, determines the scores at all first heights based on the weight at each first height and the difference.

[0148] For the embodiment of the present application, the electronic device determines the weight at each first height and the product of the difference to obtain a score for each first height, and then sums the scores at all first heights to obtain a score.

[0149] Se, determine the variance of the difference values ​​at all first heights, and determine the growth scores at all first heights based on the variance, the scores, and the respective corresponding coefficients.

[0150] For the embodiment of the present application, the electronic device determines the variance of the difference at all first heights according to the variance calculation formula. The smaller the variance, the less similar the growth quality at the first height where the growth condition is poor, that is, the growth condition is uneven. The larger the variance, the more similar the growth quality at the first height where the growth condition is poor. When the operating parameters of each device are subsequently adjusted, the growth condition at each height can be uniformly corrected to a level with good growth condition. Therefore, the variance can standardize the degree of proximity of the target plant to the area with poor growth condition as a whole, and the size of the score represents the gap between the growth quality at all first heights and the good growth condition. In summary, the variance and the score are both key factors affecting the height where the growth condition of the target plant is poor, and the degree of influence is different. Therefore, different coefficients are set for the variance and the score, and the electronic device performs weighted calculation on the variance, the score and the corresponding coefficients to obtain the growth score at all first heights.

[0151] Sf, determines an overall growth score based on the baseline growth score and the growth scores at all first heights.

[0152] For the embodiment of the present application, after the electronic device determines the baseline growth score and the growth scores at all first heights, the difference between the baseline growth score and the growth scores at all first heights can be determined to obtain the overall growth score of the target plant. The baseline score is determined by the weight and number of the second heights with good growth conditions, and then the variance and the score of the difference are determined according to the growth conditions at all first heights, thereby obtaining the growth scores at all first heights, and the overall growth score of the target plant can be accurately obtained by subtracting the two.

[0153] In a possible implementation of the embodiment of the present application, in step S101, real-time data generated by crops in the agricultural greenhouse during their growth is obtained, which specifically includes step S1011 (not shown in the figure), step S1012 (not shown in the figure), step S1013 (not shown in the figure), step S1014 (not shown in the figure) and step S1015 (not shown in the figure), wherein:

[0154] S1011, collect real-time data of crops from sensor networks.

[0155] Among them, the sensor network is composed of crop data collection equipment in the greenhouse connected to the Beidou RF transceiver chip and several sensors. Each sensor node collects real-time data under different parameters of crops through the connection coordinator.

[0156] For the embodiments of the present application, since the growth of crops will be affected by soil parameters, and at the same time, the air temperature and humidity in the greenhouse will also be affected by transpiration and metabolism, it is necessary to achieve accurate supervision of crops by acquiring such data. A sensor network consisting of a data acquisition device connected to a Beidou radio frequency transceiver chip and a sensor is constructed on the ground of the agricultural greenhouse. The data acquisition device includes a parameter scanner and a weather station, which respectively collects data on the parameters of the crop soil environment and other internal environments of the greenhouse. The data collected by the sensor network include: soil pH value, soil element content value, soil moisture value, soil oxygen value, greenhouse ambient temperature value, greenhouse light value, total carbon dioxide value, greenhouse ambient noise value, and atmospheric environment value, etc.

[0157] S1012, obtaining real-time data of several groups of crops within the current preset time, calculating the real-time data within the preset time m hours into n groups 1 , n 2 , n 3 …n m The average Subtract the average value from each real-time data As the residual value f of the growth data i .

[0158] S1013, according to the residual value fi Calculate the standard deviation s within the preset time m and calculate

[0159] S1014, according to the Grubbs criterion g(n,a), n is the number of nodes where the sensor collects real-time data, a is the preset significance level of the real-time data, compare and the size of g(n,a).

[0160] S1015, if If it is less than g(n, a), it means that there are outliers. The collected outliers are eliminated, and finally the real-time data that are not eliminated are retained as the growth data within the preset time.

[0161] Specifically, several groups of crop growth data are obtained within the current preset time. Taking soil moisture value as an example, the soil moisture values ​​within the preset time m hours are calculated into n groups. 1 , n 2 , n 3 …n m The average Subtract the average value from each soil moisture value As the residual value f of the soil moisture value data i , according to the residual value f i Calculate the standard deviation s within the preset time m and calculate According to the Grubbs criterion g(n,a), n is the number of nodes where the sensor collects soil moisture values, and a is the preset significance level for calculating soil moisture values. and the size of g(n,a), if If it is less than g(n, a), it means that there are outliers. The collected outliers are eliminated, and finally the uneliminated data are retained as the real-time data of soil moisture value within the preset time.

[0162] In a possible implementation of the embodiment of the present application, in step S106, the operating parameters of each device related to the area where the abnormal target plant is located are adjusted based on the predicted growth status and the actual growth status of the target plant, specifically including step S1061 (not shown in the figure), step S1062 (not shown in the figure) and step S1063 (not shown in the figure), wherein:

[0163] S1061, fuzzy control is performed on the growth data of the model parameters in the decision model, the growth data is input into the fuzzy controller, the predicted growth status of the crops in the future is predicted according to the fuzzy rules, and the predicted growth status is output.

[0164] S1062, determining abnormal factors based on the predicted growth conditions and the actual growth conditions of the abnormal target plants, and determining related equipment of the abnormal factors;

[0165] S1063, obtaining the predicted growth status and calculating the control interval threshold of the crop growth parameter, and controlling the operating parameters of the relevant equipment in the area where the abnormal target plant is located according to the control interval threshold.

[0166] For the embodiment of the present application, the electronic device can also input the growth data into the decision model, and the decision model outputs the leaf data and trunk diameter and other data of the target plant under the standard of good growth condition at the current time, that is, the predicted growth condition, such as leaf length, leaf width, leaf outline, leaf color, etc. The electronic device compares the obtained data of the leaf length, leaf width, etc. of the target plant with the leaf length, leaf width, etc. in the predicted growth condition, so as to determine the data with too large a difference. If the leaf color is too different from the leaf color in the predicted growth condition, it may be due to insufficient nutrients, and the electronic device determines the required amount of nutrients according to the specific difference, and then controls the fertilization equipment to fertilize the area where the target plant is located.

[0167] Or, by obtaining the growth data of crops in the decision model, the growth parameters of crops can be adjusted according to the growth of crops, and the growth status of crops within a preset time can be predicted. Since the measurement methods and accuracy of various parameters in the greenhouse environment are different, a fuzzy algorithm is needed to predict the growth of crops.

[0168] A fuzzy controller for fuzzy calculation is constructed. Taking soil moisture as an example, the soil moisture deviation value and error change rate are calculated, and the fuzzy rules for the change of soil moisture value during the growth of crops in the greenhouse are set. The fuzzy rules are set by professional agricultural technicians in the cloud platform, and the growth conditions of crops in different time periods under different seasons are preset, and the variables of the fuzzy rules can be changed by the client users. The calculated deviation value and error change rate are used as the input parameters of the fuzzy controller, and the estimated time is input at the same time. According to the fuzzy rules, the fuzzy operation is processed to calculate the output soil moisture value within the estimated time.

[0169] According to the current season information, the control interval threshold of the soil moisture value within the expected time is set, and the interval threshold is input into the irrigation machine water volume controller to finally control the water volume of the crop irrigation machine in the greenhouse. The actual soil moisture value measured after the expected time is reached is used as a feedback parameter and re-entered when the control interval threshold is calculated next time. The changed soil moisture value data is visualized and displayed in the cloud platform, so that users can intuitively see the parameter adjustment change process.

[0170] In other embodiments, the electronic device may also obtain weather data for a preset future time period, determine the diseases to be prevented and the associated growth data of the diseases based on the weather data and the season, determine the probability of occurrence of the diseases based on the weather data and the associated growth data, and modify the operating parameters based on the probability. For example, if a drought is about to occur, the electronic device controls the irrigation equipment to replenish the surplus during watering, thereby achieving the effect of preventing drought. For another example, if a frost disaster is about to occur, the electronic device controls the heating equipment to extend the heating time, thereby achieving the effect of preventing frost.

[0171] In a possible implementation manner of the embodiment of the present application, the method further includes step S107, step S108 (not shown in the figure) and step S109 (not shown in the figure), wherein:

[0172] S107, after regularly acquiring abnormal data in the model building module and the parameter adjustment module, warning signals are set respectively, and transmitted to the client user through the cloud platform for warning prompts.

[0173] S108, setting exception rules and determining whether the abnormal data is real growth data, performing noise reduction processing on the abnormal data, and issuing a warning message in the cloud platform if the abnormal data still matches the exception rules after processing.

[0174] S109, after receiving the warning information, the cloud platform locates the crop area where the warning information is located according to the Beidou radio frequency transceiver chip in the sensor network, and uploads the geographic location to the cloud platform server. After receiving it, the cloud platform generates a message queue with the abnormal data of the crops and the geographic location and pushes it to the client user.

[0175] For the embodiment of the present application, the sensor network will display the uploaded real-time data visually on the cloud platform, and based on the abnormal data analyzed by the decision model and parameter adjustment module, the cloud platform client will be warned. Due to the continuous changes in the crop environment in the greenhouse, there may be random triggering of warning errors within a certain period of time. In order to prevent data misjudgment, the monitored abnormal data is subjected to noise reduction processing. First, after receiving the abnormal data, it is first determined whether the abnormal data belongs to the real crop growth data or environmental noise as the abnormal matching rule. If it belongs to environmental noise, it does not match, and noise reduction processing is performed. After the processing is completed, it continues to determine whether the abnormal data matches the abnormal rule. If so, a warning message is issued.

[0176] When the warning information is received, the Beidou RF transceiver chip used to collect data is obtained according to the sensor network. The Beidou RF transceiver chip also records the geographic location of the abnormal data crop, which is convenient for the client to check. The abnormal monitoring unit has built-in speech templates for specific types of abnormal data scenarios, and the warning of abnormal data is divided into email warning, SMS warning and cloud platform push. When the abnormal monitoring unit is called, the cloud platform will send emails, SMS and cloud platform messages to the client user for warning according to the built-in speech template. The client user finds the corresponding crop and changes the parameters according to the warning information.

[0177] The above embodiment introduces a smart agriculture supervision method based on the Internet of Things from the perspective of method flow. The following embodiment introduces a smart agriculture supervision system based on the Internet of Things from the perspective of virtual modules or virtual units. For details, please see the following embodiments.

[0178] The present application embodiment provides a smart agricultural supervision system 20 based on the Internet of Things, such as Figure 2 As shown, the smart agriculture supervision system 20 based on the Internet of Things may specifically include:

[0179] The first acquisition module 201 is used to acquire real-time data generated by crops in the agricultural greenhouse during their growth process, the real-time data including soil pH value, soil element content value, soil moisture value, soil oxygen value, greenhouse ambient temperature value, greenhouse light value, total carbon dioxide value, greenhouse ambient noise value and atmospheric environment value;

[0180] The data transmission module 202 is used to upload the real-time data as growth data to the database in the cloud platform, and realize two-way communication with the client in the cloud platform through the subscription table in the form of subscription or publication;

[0181] The model building module 203 is used to obtain the growth data in the subscription table to establish a decision model, and determine the predicted growth status of the crop in the current seasonal environment according to the decision model;

[0182] The second acquisition module 204 is used to determine the target plants in different areas of the agricultural greenhouse, and obtain the real growth status of each target plant at different heights, including the leaf length, leaf width, leaf outline, leaf color and trunk diameter of the real growth status;

[0183] A health determination module 205, for determining the health of each target plant based on the actual growth condition;

[0184] The adjustment module 206 is used to adjust the operating parameters of each device related to the area where the abnormal target plant is located based on the predicted growth status and the actual growth status of the target plant when there is an abnormal target plant whose health level is less than a preset health level.

[0185] The embodiment of the present application discloses a smart agriculture supervision system 20 based on the Internet of Things, wherein a first acquisition module 201 acquires real-time data to facilitate subsequent analysis, a data transmission module 202 uploads real-time data to a cloud platform in the form of subscription or publication to facilitate more efficient communication between the cloud platform and the client, a model construction module 203 constructs a database in the cloud platform in the form of different seasons of the year, so as to obtain a predicted growth condition that is more in line with the current time, a second acquisition module 204 acquires the actual growth condition of target plants in each area at different growth heights, a health determination module 205 determines the health according to the actual growth condition, and judges abnormal target plants according to the health, and an adjustment module 206 adjusts the operating parameters of various equipment related to the area where the abnormal target plants are located according to the predicted growth condition and the actual growth condition of the target plants, so as to make the control operation of the equipment in the greenhouse more precise.

[0186] In a possible implementation of the embodiment of the present application, when the health determination module 205 determines the health of each target plant based on the actual growth condition, it is specifically used to:

[0187] Determine the ratio of leaf length to leaf width at each height, and determine the growth score at each height based on the ratio and the trunk diameter;

[0188] Determining a first similarity between the blade profile and a preset standard profile of the blade at each height, and a second similarity between the blade color and a preset standard color of the blade at each height;

[0189] determining a nutritional score at each height based on the first similarity and the second similarity;

[0190] Determine a growth score at each height based on the growth score and the nutrition score;

[0191] An overall growth score of each target plant is determined based on the growth score at each height, and the overall growth score represents the health of each target plant.

[0192] In a possible implementation of the embodiment of the present application, when the health determination module 205 determines the overall growth score of each target plant based on the growth score at each height, it is specifically configured to:

[0193] determining the difference between the growth score at each height and the corresponding benchmark score;

[0194] Determine a first height at which the difference is a negative number and a second height at which the difference is a non-negative number;

[0195] determining a baseline growth score based on the weight at each second height and the number at the second height;

[0196] Determine the scores at all first heights based on the weights at each first height and the difference;

[0197] Determine the variance of the difference values ​​at all first heights, and determine the growth scores at all first heights based on the variance, the scores, and the respective corresponding coefficients;

[0198] An overall growth score is determined based on the baseline growth score and the growth scores at all first heights.

[0199] In a possible implementation of the embodiment of the present application, when the first acquisition module 201 acquires the real-time data generated by the crops in the agricultural greenhouse during the growth process, it is specifically used to:

[0200] Collect real-time data of crops from the sensor network. The sensor network consists of crop data collection equipment in the greenhouse connected to the Beidou radio frequency transceiver chip and several sensors. Each sensor node collects real-time data of different crop parameters by connecting to the coordinator.

[0201] Get the real-time data of several groups of crops within the current preset time, calculate the real-time data within the preset time m hours and divide them into n 1 , n 2 , n 3 …n m The average Subtract the average value from each real-time data As the residual value f of the growth data i ;

[0202] According to the residual value f i Calculate the standard deviation s within the preset time m and calculate

[0203] According to the Grubbs criterion g(n,a), n is the number of nodes where sensors collect real-time data, and a is the preset significance level of real-time data. and the size of g(n,a);

[0204] like If it is less than g(n, a), it means that there are outliers. The collected outliers are eliminated, and finally the real-time data that are not eliminated are retained as the growth data within the preset time.

[0205] In a possible implementation of the embodiment of the present application, the model building module 203 establishes a decision model after acquiring the growth data in the subscription table, and determines the predicted growth status of the crop in the current seasonal environment according to the decision model, specifically for:

[0206] Collect the growth data in each subscription table as model samples, extract the available features in the model samples for training, and obtain training samples for building decision models;

[0207] Setting constraints on model parameters in the decision model, and using the parameter variable difference range of the constraints as the first threshold range;

[0208] Setting the objective function of the optimal environmental growth parameters of the crops in the decision model, and using the numerical range of the objective function as the second threshold range;

[0209] It is determined whether the growth data is within the first threshold range and also within the second threshold range.

[0210] In a possible implementation of the embodiment of the present application, when the adjustment module 206 adjusts the operating parameters of each device related to the area where the abnormal target plant is located based on the predicted growth status and the actual growth status of the target plant, it includes:

[0211] Perform fuzzy control on the growth data of the model parameters in the decision model, input the growth data into the fuzzy controller, predict the predicted growth status of the crops in the future time according to the fuzzy rules, and output the predicted growth status;

[0212] Determine abnormal factors based on the predicted growth conditions and the actual growth conditions of the abnormal target plants, and determine related equipment for the abnormal factors;

[0213] The predicted growth status is obtained and the control interval threshold of the crop growth parameters is calculated, and the operating parameters of the relevant equipment in the area where the abnormal target plants are located are controlled according to the control interval threshold.

[0214] In a possible implementation of the embodiment of the present application, the system 20 further includes:

[0215] After regularly acquiring abnormal data in the model building module and parameter adjustment module, early warning signals are set respectively, and transmitted to the client users through the cloud platform for early warning prompts;

[0216] Set exception rules and determine whether the abnormal data is real growth data, perform noise reduction on the abnormal data, and issue a warning message in the cloud platform if it still matches the exception rules after processing;

[0217] After receiving the warning information, the cloud platform locates the crop area where the warning information is located according to the Beidou radio frequency transceiver chip in the sensor network, and uploads the geographic location to the cloud platform server. After receiving it, the cloud platform generates a message queue with the abnormal data of the crops and the geographic location and pushes it to the client user.

[0218] Technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the IoT-based smart agricultural supervision system 20 described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0219] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3 The electronic device 30 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 30 does not constitute a limitation on the embodiments of the present application.

[0220] Processor 301 may be a CPU (Central Processing Unit), a general purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0221] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0222] The memory 303 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0223] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0224] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0225] The embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment. Compared with the related art, in the embodiment of the present application, real-time data is obtained to facilitate subsequent analysis, and the real-time data is uploaded to the cloud platform in the form of subscription or publication to facilitate more efficient communication between the cloud platform and the client, and the database in the cloud platform is constructed in the form of different seasons in a year, so as to obtain a predicted growth condition that is more in line with the current time, obtain the actual growth condition of the target plant at different growth heights in each area, and determine the health degree according to the actual growth condition, judge the abnormal target plant according to the health degree, and adjust the operating parameters of each device related to the area where the abnormal target plant is located according to the predicted growth condition and the actual growth condition of the target plant, so as to make the control operation of the equipment in the greenhouse more accurate.

[0226] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0227] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A smart agriculture supervision method based on the Internet of Things, characterized in that: include: Acquire real-time data generated by crops in agricultural greenhouses during their growth process, including soil pH value, soil element content value, soil moisture value, soil oxygen value, greenhouse ambient temperature value, greenhouse light value, total carbon dioxide value, greenhouse ambient noise value, and atmospheric environment value; Uploading the real-time data as growth data to a database in the cloud platform, and implementing two-way communication with a client in the cloud platform through a subscription table in the form of subscription or publication; Acquire the growth data in the subscription table to establish a decision model, and determine the predicted growth status of the crop in the current seasonal environment according to the decision model; Determine target plants in different areas of the agricultural greenhouse, and obtain the real growth status of each target plant at different heights, including leaf length, leaf width, leaf outline, leaf color, and trunk diameter; Determine the health of each target plant based on the actual growth condition; If there is an abnormal target plant whose health is less than a preset health, the operating parameters of each device related to the area where the abnormal target plant is located are adjusted based on the predicted growth status and the actual growth status of the target plant.

2. A smart agriculture supervision method based on the Internet of Things according to claim 1, characterized in that: Determining the health of each target plant based on the actual growth condition includes: Determine the ratio of leaf length to leaf width at each height, and determine the growth score at each height based on the ratio and the trunk diameter; Determining a first similarity between the blade profile and a preset standard profile of the blade at each height, and a second similarity between the blade color and a preset standard color of the blade at each height; determining a nutritional score at each height based on the first similarity and the second similarity; Determine a growth score at each height based on the growth score and the nutritional score; An overall growth score of each target plant is determined based on the growth score at each height, wherein the overall growth score represents the health of each target plant.

3. According to the method of intelligent agriculture supervision based on the Internet of Things as claimed in claim 2, it is characterized in that: Determining the overall growth score of each target plant based on the growth score at each height includes: determining the difference between the growth score at each height and the corresponding benchmark score; Determine a first height at which the difference is a negative number and a second height at which the difference is a non-negative number; determining a baseline growth score based on the weight at each second height and the number at the second height; Determine the scores at all first heights based on the weights at each first height and the difference; Determine the variance of the difference values ​​at all first heights, and determine the growth scores at all first heights based on the variance, the scores, and the respective corresponding coefficients; The overall growth score is determined based on the baseline growth score and the growth scores at all the first heights.

4. According to the method of intelligent agriculture supervision based on the Internet of Things in claim 1, it is characterized in that: The real-time data generated by crops in the agricultural greenhouse during their growth process is obtained, including: Collecting real-time data of crops from a sensor network, which consists of crop data collection equipment in a greenhouse connected to a Beidou radio frequency transceiver chip and several sensors. Each sensor node collects real-time data of crops under different parameters by connecting to a coordinator; Get the real-time data of several groups of crops within the current preset time, calculate the real-time data within the preset time m hours and divide them into n1, n2, n3...n m The average Subtract the average value from each real-time data As the residual value f of the growth data i ; According to the residual value f i Calculate the standard deviation s within the preset time m and calculate According to the Grubbs criterion g(n,a), n is the number of nodes where sensors collect real-time data, and a is the preset significance level of real-time data. and the size of g(n,a); like If it is less than g(n, a), it means that there are outliers. The collected outliers are eliminated, and finally the real-time data that are not eliminated are retained as the growth data within the preset time.

5. According to claim 1, a smart agriculture supervision method based on the Internet of Things is characterized in that: The step of acquiring the growth data in the subscription table to establish a decision model, and determining the predicted growth status of the crop in the current seasonal environment according to the decision model, includes: Collecting growth data in each subscription table as a model sample, extracting available features in the model sample for training, and obtaining a training sample for building a decision model; Setting constraints on model parameters in the decision model, and using the parameter variable difference range of the constraint conditions as the first threshold range; Setting an objective function of the optimal environmental growth parameters of crops in the decision model, and using the numerical range of the objective function as a second threshold range; It is determined whether the growth data is within the first threshold range and also within the second threshold range.

6. According to the method of intelligent agriculture supervision based on the Internet of Things in claim 1, it is characterized in that: The adjusting the operating parameters of each device related to the area where the abnormal target plant is located based on the predicted growth condition and the actual growth condition of the target plant includes: Perform fuzzy control on the growth data of the model parameters in the decision model, input the growth data into the fuzzy controller, predict the predicted growth status of the crops in the future time according to the fuzzy rules, and output the predicted growth status; Determining abnormal factors based on the predicted growth conditions and the actual growth conditions of the abnormal target plants, and determining related equipment for the abnormal factors; The predicted growth status is obtained and the control interval threshold of the crop growth parameter is calculated, and the operating parameters of the relevant equipment in the area where the abnormal target plant is located are controlled according to the control interval threshold.

7. The method for monitoring smart agriculture based on the Internet of Things according to claim 1, characterized in that: The method further comprises: After regularly acquiring abnormal data in the model building module and parameter adjustment module, early warning signals are set respectively, and transmitted to the client users through the cloud platform for early warning prompts; Set exception rules and determine whether the abnormal data is real growth data, perform noise reduction on the abnormal data, and issue a warning message in the cloud platform if it still matches the exception rules after processing; After receiving the warning information, the cloud platform locates the crop area where the warning information is located according to the Beidou radio frequency transceiver chip in the sensor network, and uploads the geographic location to the cloud platform server. After receiving it, the cloud platform generates a message queue with the abnormal data of the crops and the geographic location and pushes it to the client user.

8. A smart agricultural supervision system based on the Internet of Things, characterized in that: include: The first acquisition module is used to acquire real-time data generated by crops in the agricultural greenhouse during their growth process, wherein the real-time data includes soil pH value, soil element content value, soil moisture value, soil oxygen value, greenhouse ambient temperature value, greenhouse light value, total carbon dioxide value, greenhouse ambient noise value and atmospheric environment value; A data transmission module, used to upload the real-time data as growth data to a database in the cloud platform, and to achieve two-way communication with a client in the cloud platform through a subscription table in the form of subscription or publication; A model building module is used to obtain the growth data in the subscription table to establish a decision model, and to determine the predicted growth status of the crop in the current seasonal environment according to the decision model; The second acquisition module is used to determine the target plants in different areas of the agricultural greenhouse, and obtain the real growth status of each target plant at different heights, including leaf length, leaf width, leaf outline, leaf color and trunk diameter; A health determination module, used to determine the health of each target plant based on the actual growth condition; The adjustment module is used to adjust the operating parameters of various devices related to the area where the abnormal target plant is located based on the predicted growth status and the actual growth status of the target plant when there is an abnormal target plant whose health is less than a preset health.

9. An electronic device, characterized in that: It includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and configured to be executed by the at least one processor, and the at least one application is used to execute a smart agriculture supervision method based on the Internet of Things according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the smart agriculture supervision method based on the Internet of Things as described in any one of claims 1 to 7.

Images