A production area-oriented planting decision service system and method

Abstract

The application relates to a production area-oriented planting decision service system and method, which comprises the following: a crop development model based on effective accumulated temperature; sensors deployed based on the planting varieties, cultivation methods and geographical division of a production area; real-time and historical meteorological data are introduced to monitor the growth and development of crops, and automatic intelligent identification is performed on development nodes to accurately grasp the phenological period nodes of crops; a production environment and water and fertilizer index database; production parameters are controlled and recommended through a general data interface; a cloud service system and an APP; the APP comprises a crop index library, production area environment data, meteorological grid data, a crop-accumulated temperature-development basic model, feature recognition, meteorological data service, process pushing service and equipment control service. The application has the advantages that the definition of the phenological period is more intelligent and accurate, planting plans, planting process definitions and equipment intelligent control from planting to harvesting of crops are realized, the service range is wide and personalized, and the cost is low.

Description

[0001] The application is a divisional application of the patent application entitled "Planting Decision Service System and Method for Production Area", the original application date is March 13, 2020, and the application number is 202010172862.8. TECHNICAL FIELD

[0002] The application belongs to the technical field of agricultural technology services, and particularly relates to a planting decision service system and method for a production area. BACKGROUND

[0003] In China, economic planting is mainly carried out by small and medium-sized growers, and the production areas are concentrated. A production area is usually composed of one or several counties with similar climate and soil conditions, and a large number of similar economic crops are planted in the production area, and the planting methods of the economic crops are diversified (open field, greenhouse, sunlight greenhouse, etc.). A large number of growers in the production area manage their own land in a scattered manner and all face similar problems. In recent years, with the rapid development of information network technology, the production area is generally covered by a network, and the field is connected to power. Therefore, individual advanced farmers have begun to install and deploy production tools such as temperature and humidity control and automatic water-saving equipment to promote quality production and labor-saving work. However, in actual use, ordinary farmers cannot accurately adjust the operation of water and fertilizer, temperature and humidity control equipment according to the growth stage and growth of crops, but only rely on experience to operate, which greatly limits the use of equipment, and even the equipment does not work.

[0004] Due to the large area of the production area, in order to effectively help the growers, the most reasonable way is to monitor the growth of crops through an intelligent and information system, and give production suggestions for different plots. At the same time, from the perspective of a single farmer or a single garden, it is not economical and difficult to develop such an information system, and the common characteristics of the production area provide a basis and feasibility for the development and construction of such a system.

[0005] Therefore, how to construct a service system that can cover the production area and make intelligent decisions to generate production decision information and help growers to produce in quality and save labor is one of the problems to be solved in the industry.

[0006] In the patent with the application number 201710154721.1, a planting technology service system and method for small and medium-sized growers are described, and the service system includes a server end and a user end. The server end includes a user interaction module, a planting plan module, a weather data module, a user data module, and a data interface; the user end includes a user interaction module, a planting data pushing module, a communication module, and a user data module. The system defines the growth nodes of crops, including the development nodes of the budding, flowering, fruiting, leaf falling, and dormancy periods, forms a planting plan of the crops, and pushes text and pictures for daily farming operations, irrigation and fertilization, disease and pest control, weather warning, and other planting processes.

[0007] Since the growth nodes of crops are important basis for production measures adjustment, they are not fixed and may have certain differences according to climate conditions of years or environments, so the patent has the following defects: (1) no basic index model of crop growth and development is established; (2) no effective growth node acquisition means is established, and only self-judgment of users is relied on; (3) the method described does not effectively combine field sensor data, and no quantitative index data and interface of water and fertilizer and temperature and humidity control in each stage of the planting plan are given; (4) only weather forecast is introduced in weather data, and no real-time and historical monitoring data related to crop growth and development are introduced; (5) the planting process pushing link described is arranged and deployed in the client (APP), which means that users need to obtain all process information and data from the client to make decisions and push, which will reduce the reliability and accuracy of the system.

[0008] Therefore, the patent improves related aspects on the basis of the patent 201710154721.1, and forms a unique system and method. SUMMARY

[0009] The purpose of the present application is to solve the above problems, and provide a planting decision service system and method for production areas, which is more intelligent and accurate in defining phenological stages, realizes planting plan, planting process definition and intelligent control of equipment for crops from planting to harvesting, has wide service range, individualization and low cost.

[0010] To achieve the above purpose, the present application provides the following technical solutions:

[0011] A planting decision service system for production areas, comprising:

[0012] A crop development model: based on effective accumulated temperature, used for growth and development node monitoring; the module sets typical markers for each stage on different crop growth and development morphologies, establishes a linear relationship between growth and development indexes and effective accumulated temperature and growth checkpoints, and optimizes model parameters and phenological stage indexes through machine learning;

[0013] Based on the cultivation varieties, cultivation methods and geographical division of production areas, sensors are deployed: and meteorological grid point data of a meteorological information sharing platform are accessed; wherein the sensors are sparsely arranged in production areas without field monitoring equipment;

[0014] Grid point meteorological data obtained based on the latitude and longitude of the plot is fused and calculated with sensor data, crop growth and development is monitored, and development nodes are automatically and intelligently identified, and confirmation of growth stages based on video or image uploaded by users is supported;

[0015] Production environment and water and fertilizer index database: control and recommend the production parameters through the general data interface;

[0016] Disease and pest prediction and early warning module model: based on the model relationship between temperature and humidity in environmental data and main crop diseases, generate disease and pest occurrence trend and implement early warning;

[0017] Device control service: used for automatically controlling the air release machine and the roller machine equipment according to the environmental temperature and humidity, controlling the light supplementing lamp equipment according to the crop growth, and controlling the water and fertilizer all-in-one machine according to the water and fertilizer plan of the crop plot;

[0018] Cloud service system and APP: the cloud includes crop index library, production area environmental data, meteorological grid data, crop-accumulative temperature-development basic model, feature recognition, meteorological data service, process pushing service and device control service; the server side calculates and pushes the planting plan, planting process and device control parameters, and the APP side calls the calculation results for display;

[0019] The crop-accumulative temperature-development basic model is mainly used for growth and development node monitoring, and the growth and development of crops is expressed by the formula:

[0020]

[0021] In the growth and development formula of the crop, DSI(s, k) represents the development index of the s stage on the k day, ATDi represents the effective accumulative temperature of the s stage on the i day, and ACTem s-1 is the accumulative effective accumulative temperature of the s stage.

[0022] A working method of a planting decision service system for a production area, comprising the following steps:

[0023] S1: Establish a basic crop-accumulative temperature-development model to quantitatively process the monitoring of crop growth and development nodes, and provide a basis for decision-making;

[0024] S2: Collect meteorological grid data through the meteorological information sharing platform interface, calculate the real-time temperature and accumulative temperature of different plots in combination with the latitude and longitude position of the plot, conduct meteorological disaster warning for low-temperature freezing and heat damage, and predict the growth and development of crops according to the model;

[0025] S3: Build a crop index library on the server side, provide different planting process pushing services and device control services for crops according to different stages of crop growth and development and weather data;

[0026] S4: Build a data service system, use sensor data to realize accurate agricultural service in the whole world: according to the geographical position, fuse and calculate the collected real-time data and meteorological grid data, and make data guidance products for different plots and different cultivation modes;

[0027] S5: predicting the development trend of diseases and pests by constructing the relationship between the environmental data and the index model of the main diseases of crops;

[0028] S6: constructing a crop growth node monitoring system to perfect the crop index library, and controlling the equipment on the basis of fusing the meteorological grid data and the sensor data to provide decision-making services;

[0029] S7: calculating and pushing the planting plan, the planting process and the equipment control parameters on the server side, and calling the calculation results on the APP side to display;

[0030] The working process of the crop-accumulated temperature-development model is as follows:

[0031] 1) accumulated temperature calculation;

[0032] 2) accumulated temperature model prediction of phenological stage;

[0033] 3) confirmation of phenological stage: if no error is found, the next step is entered, otherwise the model is optimized and returned to step 2);

[0034] 4) adjustment of process parameters;

[0035] The method for confirming the phenological stage in step 3) is that the video or image uploaded by the user is used as the confirmation basis for the crop entering the next growth stage.

[0036] Preferably, in S1, the typical signs of each stage are defined on the morphology of different crop growth and development, the linear relationship between the growth and development index, the accumulated temperature and the growth checkpoint is established, and the model is optimized through machine learning.

[0037] Preferably, in S4, when constructing the data service system, in the production area without field monitoring equipment, the method of sparsely arranging sensors is adopted to enhance the system capacity.

[0038] Preferably, in S6, the specific method for controlling the equipment is that the air exhaust fan and the roller shutter machine equipment are automatically controlled according to the environmental temperature and humidity, the light supplement lamp equipment is automatically controlled according to the crop growth, and the water and fertilizer integrated machine equipment is controlled according to the water and fertilizer plan of the crop plot.

[0039] Preferably, the decision-making services in S6 include planting process pushing, greenhouse ventilation and temperature control, water and fertilizer plan pushing, disease and pest warning and weather disaster warning.

[0040] Compared with the prior art, the present application has the following beneficial effects:

[0041] The planting decision service system of the application is a service system with learning and decision-making capabilities. Compared with a planting technology service system and method for small and medium-sized planters, the phenological phase definition is more intelligent and accurate, and on this basis, the planting plan, planting process definition and equipment intelligent control of crops from planting to harvesting are realized. In addition, the application is not a single-point service system that cannot be popularized, but a system that can cover large areas of county-level production areas, and can provide personalized services for different crop varieties, thereby effectively reducing the cost of popularization.

[0042] The production area planting decision system and method described in the application can build an accurate production service system for a large number of planters in a production area, avoid the waste of repeated construction of a production area service system, and overcome the difficulty of a single main body (farmer, garden area) in constructing an information system. After being put into use, it can not only serve production and help improve production quality in the production area, but also provide technical support for the commercial operation and equipment popularization of the digital system in the production area. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only for more clearly illustrating the technical solutions in the embodiments of the application or the prior art, and other drawings can also be obtained by those skilled in the art without creative labor.

[0044] Figure 1 The cloud service system of the application is shown in the schematic diagram.

[0045] Figure 2 The workflow diagram of the crop-accumulative temperature-development model of the application is shown.

[0046] Figure 3 The planting process pushing service and equipment control service flowchart of the application is shown.

[0047] Figure 4 The data service system flowchart of the application is shown.

[0048] Figure 5 The decision service system composition schematic diagram of the application is shown. DETAILED DESCRIPTION

[0049] In order to enable those skilled in the art to better understand the technical solutions of the application and implement them, the application will be further described below in conjunction with specific embodiments. However, the embodiments are only used to illustrate the application, not to limit the application.

[0050] As Figure 1The shown one is a production area-oriented planting decision service system, 1) the system first establishes a crop development model based on effective accumulated temperature; 2) secondly, based on the production area, the cultivation variety, the cultivation method, the geographical division, the sensor is deployed, the real-time and historical meteorological data are introduced to monitor the growth and development of crops, and the development nodes are automatically and intelligently identified, so as to master the accurate phenological period nodes of crops; 3) again, the production environment, water and fertilizer index database is established according to different stages, and the production parameters are controlled and recommended through a general data interface; 4) finally, the cloud service system and the APP and the control system are improved to optimize the system. The schematic diagram of the cloud service system is as shown in Figure 1 .

[0051] 1、Crop-accumulated temperature-development model

[0052] The growth and development of crops are related to temperature, humidity, water and fertilizer, light and other factors, but the physiological development is mainly related to temperature, and the management methods are quite different in different physiological periods. The model here is mainly used for growth and development node (phenological period) monitoring, so a basic crop-accumulated temperature-development model is established to quantitatively process the monitoring of crop growth and development nodes and provide a basis for decision-making. Since the annual soil temperature and air temperature in the same region have a linear correlation, suitable effective accumulated temperature (accumulated temperature greater than the growth and development threshold) is selected for different crops to represent the growth and development of crops, and machine learning (regression algorithm) is used to continuously optimize the accuracy of the model. Among them, the growth and development of crops is represented as:

[0053]

[0054] DSI(s,k) represents the development index of the s stage on the k day, ATDi represents the effective accumulated temperature of the s stage on the i day, and ACTem s-1 is the cumulative effective accumulated temperature of the previous s stage. On this basis, typical markers (such as germination, leaf expansion, initial flowering, fruiting, etc.) of each stage are defined on the basis of the morphology of different crop growth and development, a linear relationship between growth and development index and accumulated temperature and growth checkpoint is established, and machine learning (clustering analysis algorithm) is used to optimize the model index. The process is as shown in Figure 2 .

[0055] Embodiment:

[0056] Take open-field apples as an example, assuming that the effective accumulated temperature index from the germination stage to the initial flowering stage is 1000, and the service object is the apple grower in Luochuan. Through the calculation of historical temperature data in the early stage, it is known that the time for the No. 1 plot to enter the initial flowering stage is March 28. In reality, the actual initial flowering stage confirmed by the APP user or the camera recognition is March 29, and through the learning and comparison of the temperature data of the plot this year, the accumulated temperature index of the phenological stage can be optimized through weight optimization. Similarly, if there are 10,000 plots confirmed by users or sensors, the phenological stage index can be optimized through clustering analysis and other methods, and it can approach the true situation infinitely.

[0057] Feature recognition defines the typical characteristics of a crop entering the next stage, and confirms the accurate date of the crop entering the next growth stage through image recognition (user upload or video shooting).

[0058] 2. In view of the actual situation that the geographical location of the production area is close and the crops cultivated are close, first, the 5x5km 2 resolution meteorological grid data is collected through the meteorological information sharing platform interface, and combined with the latitude and longitude position of the plot, the real-time temperature and accumulated temperature of different plots are calculated, the meteorological disaster warning of low temperature frost damage and heat damage is carried out, and the growth and development of crops is predicted according to the model. At the same time, deploy sparse sensors (video, temperature) or access existing sensors to monitor the development of crops.

[0059] 3. Build a crop index library on the server side, provide different planting process push services and equipment control services for crops in different stages of growth and development and weather data, and the specific process is as shown in Figure 3 .

[0060] 4. Existing production areas often deploy a certain number of field sensors, which generally include temperature and humidity, precipitation, light, CO 2 concentration, soil pH value, etc., but due to weak algorithm and model support, they cannot provide direct services to planting, and their data cannot be used to process service products for the production area. In fact, the production area of economic planting is generally dominated by vegetables and fruit trees, among which the cultivation methods can be divided into open-field cultivation, greenhouse (arched shed) cultivation and sunlight greenhouse cultivation. Based on the grasp of the geographical position (three-dimensional coordinates) of the plot and the type of crop, a data service system can be constructed, and existing sensor data can be used to realize accurate agricultural services in the whole area, that is, according to the geographical location, the real-time data collected and the meteorological grid data are fused and calculated to produce data guidance products for different plots and different cultivation modes. In the production area without field monitoring equipment, sparse sensors can be used to enhance the system's ability. The specific process is as shown in Figure 4 .

[0061] The specific way of fusion calculation is:

[0062] 1) First, meteorological grid data (temperature) is used to help growers make accurate crop planning and to provide crop production plans for open-field crops, including phenological forecasts and agricultural guidance for each phenological stage.

[0063] 2) Provide early warnings at different stages for growers with different cultivation methods and varieties in the production area through meteorological data, such as low temperature freezing damage, high temperature, waterlogging, etc.

[0064] 3) Since the gridded meteorological data for the fields is calculated using interpolation based on the latitude and longitude of the fields from meteorological station data, there are errors. It can be used for large-scale phenological calculations and agricultural technology updates. However, it is insufficient for water and fertilizer control and environmental control in facility-based production.

[0065] 4) Supplementing the lack of meteorological data by deploying sensors in the fields, mainly for water and fertilizer control of open-field crops and implementing environmental control of production crops;

[0066] 5) By comprehensively utilizing meteorological and monitoring data, we provide production areas with accurate planting data services at different levels, covering planting plans, agricultural techniques, pest and disease management, early warning information, water and fertilizer control, and environmental control. These data can complement and correct each other, reducing data errors.

[0067] 5. Based on the disease and pest technology library of patent 201710154721.1, this patent constructs a disease and pest prediction model by building a model relationship between environmental data (temperature, humidity) and major crop diseases, which can provide early warning of crop disease trends in the plot. Combined with the water and fertilizer model library of patent 201710154721.1, it generates water and fertilizer plans for the plot based on meteorological grid data and sensor data.

[0068] 6. Based on patent 201710154721.1, this patent constructs a crop indicator database by building a crop growth node monitoring system. Integrating meteorological grid data and sensor data, it automatically controls ventilation fans and rolling shutters based on environmental temperature and humidity, automatically controls supplemental lighting based on crop growth, and controls integrated water and fertilizer machines based on the crop plot's water and fertilizer plan. Therefore, the system not only provides planting process recommendations to growers but also equipment control services for production equipment, collectively constituting a production decision-making service for the production area. The aforementioned equipment is all prior art, and the decision-making service system can support services such as... Figure 5 As shown.

[0069] 7. On the basis of the patent 201710154721.1, the patent optimizes the calculation structure, pushes the planting plan, planting technology and equipment control parameters on the server side, and the APP side only needs to call the calculation result for display, which can play the advantages of the framework and computing power of the server side, reduce the pressure of the client side, and improve the reliability of the system.

[0070] The application is a service system with learning and decision-making ability, compared with a planting technology service system and method for small and medium-sized planters, the phenological period definition is more intelligent and accurate, and on this basis, the planting plan, planting technology definition and equipment intelligent control of crops from planting to harvesting are realized. In addition, it is not a single-point service system that cannot be promoted, but a system that can cover large areas of county-level production areas, which can provide personalized services for different crop varieties, thereby effectively reducing the promotion cost.

[0071] The production area planting decision system and method described in the patent can construct an accurate production service system for a large number of planters in the production area, can avoid the waste of repeated construction of the production area service system, and overcome the difficulty of single subject (farmer, park) cannot construct information system. After its use, it can not only serve the production and help the production area to improve the production quality, but also provide technical support for the commercial operation of the production area digital system and the equipment promotion.

[0072] The patent 201710154721.1 not described in detail in the application is disclosed, and the specific content of the patent application can be referred to, and will not be repeated in the application.

[0073] The contents not described in detail in the application are prior art.

[0074] The above only describes the preferred embodiments of the application, and does not limit the application, any modification, equivalent replacement, improvement, etc. within the spirit and principle of the application should be included in the protection scope of the application.

Claims

1. A planting decision-making service system for production areas, characterized in that, include: Crop development model: Based on effective accumulated temperature, it is used to monitor growth and development nodes; the module sets typical markers for each stage in different crop growth and development morphologies, establishes a linear relationship between growth and development indicators and effective accumulated temperature and growth checkpoints, and optimizes model parameters and phenological indicators through machine learning. Sensors are deployed based on the cultivated varieties, cultivation methods, and geographical divisions of the production area, and connected to meteorological grid data from the meteorological information sharing platform. In production areas without field monitoring equipment, sensors are sparsely deployed. The system integrates gridded meteorological data obtained by interpolating the latitude and longitude of plots with sensor data to monitor crop growth and development, automatically and intelligently identify development nodes, and supports confirmation of growth stages based on user-uploaded videos or images. Production environment and water and fertilizer index database: Production parameters can be controlled and recommended through a common data interface; Pest and disease prediction and early warning module model: Based on the model relationship between temperature and humidity in environmental data and major crop diseases, it generates pest and disease occurrence trends and implements early warning; Equipment control services: Used to automatically control ventilation fans and curtain machines based on ambient temperature and humidity, control supplemental lighting based on crop growth, and control integrated water and fertilizer machines based on the water and fertilizer plan of the crop plot; Cloud service system and APP: The cloud includes crop index database, production area environmental data, meteorological grid data, crop-accumulated temperature-development basic model, feature recognition, meteorological data service, process push service and equipment control service; The server calculates and pushes planting plans, planting processes, and equipment control parameters, while the APP displays the calculation results. The crop-accumulated temperature-development basic model is mainly used for monitoring growth and development nodes. The growth and development of crops can be expressed by the following formula: In the crop growth and development formula, DSI(s,k) represents the development index on day k of stage s, ATDi represents the effective accumulated temperature on day i of stage s, and ACTem s-1 is the cumulative effective accumulated temperature of the previous s stages.

2. A working method for a planting decision-making service system oriented towards production areas, characterized in that, Includes the following steps: S1: Establish a basic crop-accumulated temperature-development model to quantify the monitoring of crop growth and development nodes, and provide a basis for decision-making; S2: Collect meteorological grid data through the meteorological information sharing platform interface, combine it with the latitude and longitude of the plot, calculate the real-time temperature and accumulated temperature of different plots, provide meteorological disaster warnings for low temperature freezing damage and heat damage, and predict the growth and development of crops based on the model. S3: Build a crop index database on the server side, and provide different planting technology push services and equipment control services for crops based on different stages of crop growth and development and weather data; S4: Build a data service system and use sensor data to achieve accurate agricultural services across the entire region: Based on geographical location, integrate the collected real-time data with meteorological grid data to calculate and produce data guidance products for different fields and different cultivation modes. S5: Predict the development trend of pests and diseases by constructing an indicator model relationship between environmental data and major crop diseases; S6: Construct a crop growth node monitoring system to improve the crop index database, and control equipment and provide decision-making services based on the integration of meteorological grid data and sensor data; S7: The server calculates and pushes planting plans, planting processes, and equipment control parameters, and the APP displays the calculation results. The workflow of the crop-accumulated temperature-development model is as follows: 1) Accumulated temperature calculation; 2) Accumulated temperature model predicts phenological periods; 3) Confirm phenological period: If confirmed, proceed to the next step; otherwise, regress the optimization model and return to step 2). 4) Adjust process parameters; The method for confirming the phenological stage in step 3) is to use videos or images uploaded by users as the basis for confirming that the crop has entered the next growth stage.

3. The working method of a planting decision-making service system for production areas according to claim 1, characterized in that, In S1, typical markers for each stage are defined in the morphology of different crop growth and development, a linear relationship is established between growth and development indicators, accumulated temperature, and growth checkpoints, and the model is optimized through machine learning.

4. The working method of a planting decision-making service system for production areas according to claim 1, characterized in that, In S4, when constructing the data service system, in production areas without field monitoring equipment, a method of sparsely deploying sensors is adopted to enhance the system's capabilities.

5. The working method of a planting decision-making service system for production areas according to claim 1, characterized in that, In S6, the specific method for controlling the equipment is as follows: automatically controlling the ventilation fan and the curtain rolling machine according to the ambient temperature and humidity, automatically controlling the supplemental lighting according to the crop growth, and controlling the integrated water and fertilizer machine according to the water and fertilizer plan of the crop plot.

6. The working method of a planting decision-making service system for production areas according to claim 1, characterized in that, The decision services in S6 include: planting process push, greenhouse ventilation and temperature control, water and fertilizer plan push, pest and disease early warning, and weather disaster early warning.

Images