An agricultural intelligent production scheduling prediction method, system and device

Abstract

The application relates to an agricultural intelligent production scheduling prediction method, system and device, which comprises the following steps: acquiring monthly crop sample data and monthly environmental information; establishing a production scheduling prediction model according to the monthly crop sample data and the environmental information; acquiring sowing time, quantity and expected yield input by a user as model input data; and inputting the model input data into the production scheduling prediction model to obtain a production scheduling suggestion result. It can be understood that the technical scheme provided by the application can automatically establish a production scheduling prediction model according to crop sample data, and then automatically obtain a production scheduling suggestion result according to the sowing time desired by the user, so that the user can perform production scheduling on the crop according to the production scheduling suggestion result. Therefore, the technical scheme provided by the application can accurately determine the harvesting time of the crop, is more accurate than manual prediction, and avoids waste of the crop.

Description

Technical Field

[0001] This invention relates to the field of agricultural production scheduling technology, specifically to an intelligent agricultural production scheduling prediction method, system, and equipment. Background Technology

[0002] Currently, in agricultural work, planning the sowing time and space of crops and estimating their yield is considered production scheduling. However, current production scheduling is done manually by agricultural technicians. This scheduling is based on their experience, reversing the production time to determine the sowing time, and the planned yield is rationally planned according to the farm's planting area.

[0003] However, crop production schedules and growth cycles vary with the seasons, and agricultural technicians can only make approximate predictions based on experience, not precise forecasts. If crops have a short shelf life, harvesting too early will result in products remaining in warehouses and failing to meet order requirements for freshness; if harvesting is not completed by the order date, it will impact customer orders.

[0004] Therefore, the current method of scheduling crop production based on the experience of agricultural technicians is not very accurate, and the harvest time cannot be guaranteed, which leads to the waste of crops. Summary of the Invention

[0005] In view of this, the purpose of this invention is to provide an intelligent agricultural production forecasting method, system and equipment to solve the problem that the existing technology of relying on the experience of agricultural technicians to schedule crop production has low accuracy and cannot guarantee the harvest time, which leads to the waste of crops.

[0006] According to a first aspect of the present invention, an intelligent agricultural production scheduling and prediction method is provided, comprising:

[0007] Obtain monthly crop sample data and monthly environmental information;

[0008] Based on the monthly crop sample data and environmental information, a production forecasting model is established.

[0009] The user-inputted sowing time, quantity, and expected harvest yield are used as model input data.

[0010] The model input data is input into the production scheduling prediction model to obtain production scheduling suggestions.

[0011] Preferably, after obtaining monthly crop sample data, the process also includes:

[0012] Outlier detection was performed on the crop sample data using the 3σ principle;

[0013] Delete the detected outliers;

[0014] The crop sample data is updated by using Lagrange interpolation to fill the gaps caused by outlier deletion in the crop sample data.

[0015] Preferably, the step of establishing a production forecasting model based on the monthly crop sample data and environmental information includes:

[0016] Based on the monthly crop sample data, a planting cycle prediction model is established;

[0017] Based on the monthly environmental information, a seedling cycle prediction model is established;

[0018] By integrating the planting cycle prediction model with the seedling cycle prediction model, a production scheduling prediction model is obtained.

[0019] Preferably, the step of establishing a planting cycle prediction model based on the monthly crop sample data includes:

[0020] The model coefficients for each month are derived based on the crop sample data for each month.

[0021] Based on the model coefficients for each month, establish a regression model for each month;

[0022] All regression models were integrated to establish a planting cycle prediction model.

[0023] Preferably, the step of obtaining monthly crop sample data further includes:

[0024] Determine whether the results contain production scheduling recommendations from previous years;

[0025] If not, then generate a crop data acquisition plan;

[0026] According to the crop data acquisition scheme, monthly crop sample data are obtained.

[0027] Preferably, inputting the model input data into the production scheduling prediction model to obtain production scheduling suggestions further includes:

[0028] The model input data is input into the production scheduling prediction model to obtain the predicted production cycle;

[0029] Obtain historical actual production cycles;

[0030] Compare the predicted production cycle with the historical actual production cycle to determine whether the difference is within a preset range;

[0031] If so, the predicted production cycle will be used as the production scheduling suggestion result;

[0032] If not, calculate the residual value between the predicted production cycle and the historical actual production cycle, and determine the confidence interval of the residual value;

[0033] Delete data that fall outside the preset confidence interval in the confidence interval of the residual value;

[0034] The model input data is updated based on the confidence intervals of the deleted residuals.

[0035] Preferably, the step of obtaining monthly crop sample data further includes:

[0036] Determine whether the results contain production scheduling recommendations from previous years;

[0037] If so, rolling optimization is performed based on the production scheduling recommendations from previous years to obtain crop sample data containing cumulative data.

[0038] Preferably, the step of deriving the monthly model coefficients based on monthly crop sample data includes:

[0039] Based on the cumulative data in the crop sample data, the model coefficients are recalculated using the Lagrange multiplier method and used as the monthly model coefficients.

[0040] According to a second aspect of the present invention, an intelligent agricultural production scheduling and prediction system is provided, comprising:

[0041] The data acquisition unit is used to acquire monthly crop sample data; it is also used to acquire the sowing time, quantity and expected harvest yield input by the user as model input data.

[0042] The model building unit is used to establish a production forecasting model based on the crop sample data.

[0043] The production scheduling prediction unit is used to input the model input data into the production scheduling prediction model and obtain production scheduling suggestion results.

[0044] According to a third aspect of the present invention, an intelligent agricultural production forecasting device is provided, comprising:

[0045] The main controller and the memory connected to the main controller;

[0046] Memory, which stores program instructions;

[0047] The main controller is used to execute program instructions stored in the memory and perform any of the methods described above.

[0048] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0049] It is understood that the technical solution provided by this invention can automatically establish a production forecasting model based on crop sample data, and then automatically generate production forecasting suggestions based on the user's desired sowing time. This allows the user to schedule the crop production according to the production forecasting suggestions. Therefore, the technical solution provided by this invention can determine the harvesting time of crops more accurately than manual forecasting, thus avoiding crop waste.

[0050] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0051] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0052] Figure 1 This is a schematic diagram illustrating the steps of an intelligent agricultural production scheduling and prediction method according to an exemplary embodiment;

[0053] Figure 2 This is a schematic diagram illustrating a monthly model coefficient calculation according to an exemplary embodiment;

[0054] Figure 3 This is a schematic diagram of operational logic according to an exemplary embodiment;

[0055] Figure 4 This is a schematic block diagram illustrating an intelligent agricultural production forecasting system according to an exemplary embodiment. Detailed Implementation

[0056] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0057] Example 1

[0058] Figure 1 This is a schematic diagram illustrating the steps of an intelligent agricultural production scheduling and forecasting method according to an exemplary embodiment. See also... Figure 1 This paper provides an intelligent agricultural production scheduling and prediction method, including:

[0059] Step S11: Obtain monthly crop sample data and monthly environmental information;

[0060] In practice, the first step is to obtain monthly crop sample data. This data can be collected by agricultural technicians after planting seedlings of sample crops according to specific requirements, along with information such as crop yield, and then input into the system. Alternatively, pre-stored data can be used as crop sample data. The monthly environmental information includes at least light intensity, light duration, and temperature, which allows for the determination of the time required for a particular crop to grow from sowing to maturity as a seedling.

[0061] Step S12: Based on the monthly crop sample data and environmental information, establish a production forecasting model;

[0062] In practice, crop production is characterized by cyclicality and seasonality, and the main factor affecting the production cycle is seasonality. Therefore, a regression model is used to establish a production forecasting model to predict the production and seedling cycle of crops.

[0063] Step S13: Obtain the sowing time, quantity, and expected harvest yield input by the user as model input data;

[0064] Step S14: Input the model input data into the production scheduling prediction model to obtain the production scheduling suggestion result.

[0065] In practice, once the production forecasting model is established, the user's input of sowing time, quantity, and expected harvest yield can be fed into the production forecasting model to obtain production forecasting suggestions. This allows users to make a more accurate judgment on the harvesting time of this type of crop based on the production forecasting suggestions.

[0066] It is understood that the technical solution provided by this invention can automatically establish a production forecasting model based on crop sample data, and then automatically generate production forecasting suggestions based on the user's desired sowing time. This allows the user to schedule the crop production according to the production forecasting suggestions. Therefore, the technical solution provided by this invention can determine the harvesting time of crops more accurately than manual forecasting, thus avoiding crop waste.

[0067] It should be noted that after obtaining monthly crop sample data, the following is also included:

[0068] Outlier detection was performed on the crop sample data using the 3σ principle;

[0069] Delete the detected outliers;

[0070] The crop sample data is updated by using Lagrange interpolation to fill the gaps caused by outlier deletion in the crop sample data.

[0071] In practice, the 3σ principle is used for testing, meaning that the standard deviation of the data should follow a normal distribution. If a random variable X follows a normal distribution with expected value μ and variance σ², denoted as N(μ, σ²), its probability density function is given. The expected value μ of the normal distribution determines its location, and its standard deviation σ determines the amplitude of the distribution. The normal distribution when μ = 0 and σ = 1 is the standard normal distribution. The system calculates the standard deviation σ of the recorded data:

[0072] The error of ±3σ is usually considered the limiting error. For a normally distributed random error, the probability of falling outside ±3σ is only 0.27%, which is very small in a finite number of measurements; hence, the 3σ criterion exists. Therefore, if the absolute value of the residual error of a certain measurement in a set of measurement data is >3σ, then that measurement value is an outlier.

[0073] The outliers identified in the above steps are deleted. For data loss caused by deletion, Lagrange interpolation is used to fill in the missing data.

[0074] Given the coordinates of n points (x1, y1), (x2, y2), (x3, y3), ..., (x... n y n Find an n-1 degree polynomial passing through these points.

[0075] Suppose the (n-1)th degree polynomial is: y = a0 + a1x + a2x 2 +...a n-1 x n-1

[0076] Substituting the n points into the polynomial, we get:

[0077] y1 = a0 + a1x1 + a2x1 2 +...a n-1 x1 n-1

[0078] y2=a0+a1x2+a2x2 2 +...a n-1 x2 n-1

[0079] ...

[0080] y n =a0+a1x n +a2x n 2 +...a n-1 x n n-1

[0081] The Lagrange polynomial can be easily solved as follows:

[0082]

[0083] Finally, outliers are removed and the data is considered valid, and then it is divided into natural months based on the time label.

[0084] It should be noted that the production forecasting model established based on the monthly crop sample data and environmental information includes:

[0085] Based on the monthly crop sample data, a planting cycle prediction model is established;

[0086] Based on the monthly environmental information, a seedling cycle prediction model is established;

[0087] By integrating the planting cycle prediction model with the seedling cycle prediction model, a production scheduling prediction model is obtained.

[0088] In practice, the established production forecasting models include planting cycle forecasting models and seedling cycle forecasting models. The planting cycle forecasting model is established based on crop sample data and is used to predict the stages of crops from transplanting to harvest.

[0089] The seedling cycle prediction model is established based on the monthly environmental information and is used to predict the stages of crops from sowing to transplanting. Since seedling nurseries are generally artificial light nurseries, which are enclosed environments, the main influencing factors are light intensity, light duration, and temperature. Therefore, a multiple regression model is used to establish the seedling cycle prediction model. The final seedling cycle prediction model can be expressed by the following formula:

[0090] Y 育苗 = b0 + b1X1 + b2X2 + ... + b n X n

[0091] Among them, Y 育苗 X represents the seedling period; X represents the influencing factors, where X1 is the monthly effective accumulated temperature during the seedling period; X2 is the monthly cumulative light duration during the seedling period; X3 is the cumulative light intensity during the seedling period, etc.; and b is the coefficient of each influencing factor, which can be adjusted according to the degree of influence of the influencing factor on the seedling.

[0092] Finally, after establishing the planting cycle prediction model and the seedling cycle prediction model, the two models can be integrated to obtain the production scheduling prediction model. When users input the desired sowing date, the seedling cycle prediction model in the production scheduling prediction model will be run first to predict the seedling cycle, and then the planting cycle prediction model in the production scheduling prediction model will be run to predict the planting cycle.

[0093] It should be noted that the establishment of a planting cycle prediction model based on the monthly crop sample data includes:

[0094] The model coefficients for each month are derived based on the crop sample data for each month.

[0095] Based on the model coefficients for each month, establish a regression model for each month;

[0096] All regression models were integrated to establish a planting cycle prediction model.

[0097] In practice, due to the seasonality of crop planting, seasonality needs to be considered when establishing a planting cycle prediction model. This embodiment can derive monthly model coefficients based on monthly crop sample data, and then establish monthly regression models based on these coefficients. Finally, all regression models are integrated to establish a planting cycle prediction model. When establishing the monthly regression model, the formula Y = b0X1 can be used. 2 +b1X1+b2 represents the model, where Y is the growth cycle for that month, X1 is the yield, and b is the model coefficient. The model coefficient can be obtained from monthly crop sample data. (See [link to relevant documentation]). Figure 2 , Figure 2 The data shown is for one month. The crop sample data includes the weight of seedlings planted at different growth stages in that month, which allows us to derive the model coefficients for that month. In specific application scenarios, data for twelve months is required to derive twelve regression models, which are then integrated to finally establish a planting cycle prediction model.

[0098] After establishing the planting cycle prediction model, the target harvest weight can be X (目标) Expected harvest date D (目标) Determine the planting date, or determine the target harvest weight X based on the planting date. (目标) Expected harvest date D (目标) Now, the target harvest weight is X. (目标) Expected harvest date D (目标) Determine the planting date and provide an explanation:

[0099] First, determine the target harvest weight in grams X (目标) Enter the expected harvest date D (目标) The monthly model formula yields the planned harvesting cycle Y for that month. (当月) As shown in the formula below:

[0100] Y (当月) =b0X (目标) 2 +b1X (目标) +b2

[0101] Y1=D(目标) -Month 1st

[0102] Then, compare Y (当月) Size of Y1:

[0103] If Y (当月) <Y1, then the growth cycle is Y (当月)

[0104] Planting date = Expected harvest date D (目标) -Y (当月)

[0105] If Y (当月) Given Y1, find X. (月底克重)

[0106] b0X (月底克重) 2 +b1X (月底克重) =Y [Y(当月)-Y1] -b2

[0107] Then X (月底克重) Substitute into formula Y (上月) =b0X (月底克重) 2 +b1X (月底克重) +b2, calculate Y (上月)

[0108] Therefore, the planting date = the expected harvest date D. (目标) -Y1-Y (上月) .

[0109] Furthermore, if the seedling cycle is predicted using a seedling cycle prediction model, the sowing date can be calculated: sowing date = fixed date - seedling cycle.

[0110] It should be noted that obtaining monthly crop sample data also includes:

[0111] Determine whether the results contain production scheduling recommendations from previous years;

[0112] If not, then generate a crop data acquisition plan;

[0113] According to the crop data acquisition scheme, monthly crop sample data are obtained.

[0114] In practice, if the user is using the technical solution provided in this embodiment for the first time, this embodiment can generate a crop data acquisition scheme, so that the user can plant samples of crops according to the scheme, collect monthly crop sample data and input it, so that this embodiment can obtain monthly crop sample data according to the crop data acquisition scheme.

[0115] Preferably, the crop data acquisition scheme can be as follows: each month, 12 batches of seedlings are planted at 1 day, 5 days, 10 days...55 days after planting, and the weight of the crop is collected every 5 days. The final data for that month is shown in Table 1.

[0116] 1 6 X1 5 10 X2 10 15 X3 … … X… 55 60 X12

[0117] Table 1

[0118] The above operation is repeated once a month from January to December to obtain twelve sets of data corresponding to January to December, which serve as crop sample data. Based on the crop sample data and the monthly environmental information, a production forecasting model can be established.

[0119] It should be noted that inputting the model input data into the production scheduling prediction model to obtain production scheduling suggestions also includes:

[0120] The model input data is input into the production scheduling prediction model to obtain the predicted production cycle;

[0121] Obtain historical actual production cycles;

[0122] Compare the predicted production cycle with the historical actual production cycle to determine whether the difference is within a preset range;

[0123] If so, the predicted production cycle will be used as the production scheduling suggestion result;

[0124] If not, calculate the residual value between the predicted production cycle and the historical actual production cycle, and determine the confidence interval of the residual value;

[0125] Delete data that fall outside the preset confidence interval in the confidence interval of the residual value;

[0126] The model input data is updated based on the confidence intervals of the deleted residuals.

[0127] In practice, the predicted production cycle can also be diagnosed for error. By obtaining the historical actual production cycle input by agricultural technicians and comparing it with the predicted production cycle, the difference between the two can be determined. If the difference is not within the preset range, the model input data can be updated, and the predicted production cycle can be regenerated. The result error diagnosis can then be performed on the regenerated predicted production cycle to finally obtain a predicted production cycle with an error within the preset range, which can be used as a production scheduling suggestion.

[0128] See Figure 3The diagram illustrates a schematic of the operating logic in one embodiment. First, data is imported. Then, outlier handling is performed on the data, and the 3σ principle is used for detection. Feature extraction is then performed. A model is established, and the production cycle is predicted based on the model. Error diagnosis is performed on the prediction results. If the prediction is within a preset range, a production scheduling suggestion is generated. If the prediction is not within the preset range, the result is corrected for error, the input data of the model is updated, and the production cycle is predicted again.

[0129] It should be noted that obtaining monthly crop sample data also includes:

[0130] Determine whether the results contain production scheduling recommendations from previous years;

[0131] If so, rolling optimization is performed based on the production scheduling recommendations from previous years to obtain crop sample data containing cumulative data.

[0132] In practice, if a user uses the technical solution described in this embodiment for more than one year, the solution will store the production scheduling recommendations from previous years in subsequent years. Rolling optimization can then be performed based on these recommendations to obtain crop sample data containing cumulative data. During the first year of operation, this embodiment records the actual planting cycle and yield, leaving corresponding values ​​as data support for rolling optimization.

[0133] In specific application scenarios, this embodiment, during operation outside the first year, can build a model based on the previous year's production data. Data spanning multiple months is calibrated using formulas by substituting the data into the formulas for the current and following months, adjusting parameters b0, b1, and b2. The corrected parameters b0, b1, and b2 are then used as the parameters for the formula in the second year. In the third year, the model is built based on the production data from the previous two years, and data spanning multiple months is calibrated using formulas by substituting the data into the formulas for the current and following months, adjusting parameters b0, b1, and b2. The corrected parameters b0, b1, and b2 are then used as the parameters for the formula in the third year.

[0134] It is understandable that the longer the model is used, the more data is accumulated, and the higher the model accuracy becomes; this is called rolling optimization.

[0135] It should be noted that the model coefficients for each month are derived from monthly crop sample data, including:

[0136] Based on the cumulative data in the crop sample data, the model coefficients are recalculated using the Lagrange multiplier method and used as the monthly model coefficients.

[0137] In practice, model parameters can be calibrated based on data from previous years, and the system's operating logic performs rolling optimization. The system automatically records production data, and after accumulating one year's worth of data, the model parameters are reconstructed based on the accumulated data. The longer the system has been used and the larger the amount of data, the more accurately the model parameters reflect reality, and the more precise the model becomes.

[0138] Let the original model be expressed by the formula: Y = b0X1 2 +b1X1+b2

[0139] b0, b1, and b2 are model parameters, which can be adjusted as follows:

[0140] Using the newly accumulated data, the function coefficients are re-estimated according to the Lagrange multiplier method:

[0141]

[0142]

[0143]

[0144] Where n is the amount of data accumulated by the system, i.e., n sets (x, y).

[0145] Example 2

[0146] Figure 4 This is a schematic block diagram illustrating an intelligent agricultural production scheduling and prediction system according to an exemplary embodiment. See also... Figure 4 A smart agricultural production scheduling and prediction system is provided, comprising:

[0147] The data acquisition unit 101 is used to acquire monthly crop sample data; it is also used to acquire the sowing time, quantity and expected harvest yield input by the user as model input data.

[0148] The model building unit 102 is used to establish a production forecasting model based on the crop sample data;

[0149] The production scheduling prediction unit 103 is used to input the model input data into the production scheduling prediction model and obtain the production scheduling suggestion result.

[0150] It is understood that the technical solution provided by the present invention can automatically establish a production prediction model based on the crop sample data obtained by the data acquisition unit 101 through the model building unit 102. Then, based on the user's desired sowing time, the production prediction unit 103 can automatically generate a production suggestion result, allowing the user to schedule the crop production according to the production suggestion result. Therefore, the technical solution provided by the present invention can determine the harvest time of crops more accurately than manual prediction, thus avoiding crop waste.

[0151] Example 3

[0152] According to a third aspect of the present invention, an intelligent agricultural production forecasting device is provided, comprising:

[0153] The main controller and the memory connected to the main controller;

[0154] Memory, which stores program instructions;

[0155] The main controller is used to execute program instructions stored in the memory and perform any of the methods described above.

[0156] It is understood that the technical solution provided by this invention can automatically establish a production forecasting model based on crop sample data, and then automatically generate production forecasting suggestions based on the user's desired sowing time. This allows the user to schedule the crop production according to the production forecasting suggestions. Therefore, the technical solution provided by this invention can determine the harvesting time of crops more accurately than manual forecasting, thus avoiding crop waste.

[0157] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0158] It should be noted that in the description of this invention, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this invention, unless otherwise stated, "a plurality of" means at least two.

[0159] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0160] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0161] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0162] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0163] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0164] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0165] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. An intelligent agricultural production scheduling and prediction method, characterized in that, include: Obtain monthly crop sample data and monthly environmental information; Based on the monthly crop sample data and environmental information, a production forecasting model is established, including: establishing a planting cycle forecasting model based on the monthly crop sample data; establishing a seedling cycle forecasting model based on the monthly environmental information; and integrating the planting cycle forecasting model and the seedling cycle forecasting model to obtain a production forecasting model. The user-inputted sowing time, quantity, and expected harvest yield are used as model input data. The model input data is input into the production scheduling prediction model to obtain production scheduling suggestions. Based on the monthly crop sample data, a planting cycle prediction model is established, including: obtaining the monthly model coefficients based on the monthly crop sample data; establishing a monthly regression model based on the monthly model coefficients; and integrating all regression models to establish a planting cycle prediction model.

2. The method according to claim 1, characterized in that, After obtaining monthly crop sample data, the process also includes: Outlier detection was performed on the crop sample data using the 3σ principle; Delete the detected outliers; The crop sample data is updated by using Lagrange interpolation to fill the gaps caused by outlier deletion in the crop sample data.

3. The method according to claim 1, characterized in that, The acquisition of monthly crop sample data also includes: Determine whether the results contain production scheduling recommendations from previous years; If not, then generate a crop data acquisition plan; According to the crop data acquisition scheme, monthly crop sample data are obtained.

4. The method according to claim 1, characterized in that, The process of inputting the model input data into the production scheduling prediction model to obtain production scheduling suggestions also includes: The model input data is input into the production scheduling prediction model to obtain the predicted production cycle; Obtain historical actual production cycles; Compare the predicted production cycle with the historical actual production cycle to determine whether the difference is within a preset range; If so, the predicted production cycle will be used as the production scheduling suggestion result; If not, calculate the residual value between the predicted production cycle and the historical actual production cycle, and determine the confidence interval of the residual value; Delete data that fall outside the preset confidence interval in the confidence interval of the residual value; The model input data is updated based on the confidence intervals of the deleted residuals.

5. The method according to claim 1, characterized in that, The acquisition of monthly crop sample data also includes: Determine whether the results contain production scheduling recommendations from previous years; If so, rolling optimization is performed based on the production scheduling recommendations from previous years to obtain crop sample data containing cumulative data.

6. The method according to claim 5, characterized in that, The model coefficients for each month are derived based on monthly crop sample data, including: Based on the cumulative data in the crop sample data, the model coefficients are recalculated using the Lagrange multiplier method and used as the monthly model coefficients.

7. An intelligent agricultural production scheduling and prediction system, characterized in that, include: The data acquisition unit is used to acquire monthly crop sample data; it is also used to acquire the sowing time, quantity and expected harvest yield input by the user as model input data. The model building unit is used to establish a production forecasting model based on the crop sample data, including: establishing a planting cycle forecasting model based on the monthly crop sample data; establishing a seedling cycle forecasting model based on the monthly environmental information; and integrating the planting cycle forecasting model and the seedling cycle forecasting model to obtain the production forecasting model. Based on the monthly crop sample data, a planting cycle prediction model is established, including: obtaining the monthly model coefficients based on the monthly crop sample data; establishing a monthly regression model based on the monthly model coefficients; and integrating all regression models to establish a planting cycle prediction model. The production scheduling prediction unit is used to input the model input data into the production scheduling prediction model and obtain production scheduling suggestion results.

8. An intelligent agricultural production scheduling and prediction device, characterized in that, include: The main controller and the memory connected to the main controller; Memory, which stores program instructions; The main controller is used to execute program instructions stored in the memory to perform the method as described in any one of claims 1 to 6.

Images