A method and system for recommending crop planting

Through the crop planting recommendation method combining the crop's own characteristics and land characteristics, the problem of insufficient precision in the existing technology is solved, and a more scientific and accurate recommendation of planting plans is achieved, which improves the efficiency and effectiveness of crop planting.

CN117056599BActive Publication Date: 2024-11-26BRIC AGRI-INFO GRP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311014357.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-08-12
Publication Date
2024-11-26
Estimated Expiration
2043-08-12

AI Technical Summary

Technical Problem

The existing crop planting recommendation methods based on big data analysis fail to fully consider the crop's own characteristics, resulting in the inaccurate planting plan.

Method used

By obtaining plot identification data, historical planting data, water and fertilizer use data and land characteristics, combined with the GIS system, crop planting recommendation methods are realized based on mobile terminals, planting recommendation sorting and yield prediction, and planting plans are optimized.

Benefits of technology

It improves the scientificity and accuracy of crop planting, helps users to choose suitable crops more reasonably and optimize land utilization and productivity.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117056599B_ABST
    Figure CN117056599B_ABST
Patent Text Reader

Abstract

The embodiments of the present specification provide a method and system for recommending crop planting, which is implemented based on a mobile terminal and includes: acquiring plot identification data and determining a target plot based on user input information; determining location information of the target plot and its corresponding first planting information, the first planting information including first historical planting data and first water and fertilizer usage data of the current user; determining second planting information corresponding to the target plot, the second planting information including second historical grower data and second water and fertilizer usage data of historical users corresponding to the target plot; determining land characteristics of the target plot based on the location information; determining planting recommendation information based on the first planting information, the second planting information and the land characteristics, the planting recommendation information including at least a recommended planting ranking of the crops.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This specification relates to the field of agricultural big data, and in particular to a method and system for recommending crop planting. Background Art

[0002] With the continuous development of modern agricultural technology, more and more modern means are being applied to crop planting, and big data analysis-assisted planting has gradually been widely used. However, current big data analysis is often conducted on environmental factors that affect crop growth, and rarely involves recommendations on crop types.

[0003] Regarding how to recommend suitable crops for planting, CN110134733B proposed a land management system and method based on GIS system and big data analysis. The application focuses on collecting and analyzing land data. The system can recommend crop planting plans that optimize land productivity and utilization based on land data. However, the application only considers land-related data, but does not consider the characteristics of the crops themselves.

[0004] Therefore, it is hoped to propose a crop planting recommendation method that can combine the characteristics of the crops themselves to better make crop planting recommendations. Summary of the invention

[0005] One or more embodiments of the present specification provide a method for recommending crop planting. The method for recommending crop planting is implemented based on a mobile terminal, and includes: obtaining plot identification data, determining a target plot based on user input information; determining the location information of the target plot and its corresponding first planting information, the first planting information including the first historical planting data and the first water and fertilizer use data of the current user; determining the second planting information corresponding to the target plot, the second planting information including the second historical planting data and the second water and fertilizer use data of the historical user corresponding to the target plot; determining the land characteristics of the target plot based on the location information; determining the planting recommendation information based on the first planting information, the second planting information and the land characteristics, the planting recommendation information including at least the recommended planting ranking of the crops.

[0006] One of the embodiments of the present specification provides a crop planting recommendation system, including a data acquisition module, a first determination module, a second determination module, a feature determination module and a recommendation module; wherein the data acquisition module is used to acquire plot identification data and determine a target plot based on input information from a current user; the first determination module is used to determine location information of the target plot and its corresponding first planting information, the first planting information including first historical planting data and first water and fertilizer usage data of the current user; the second determination module is used to determine second planting information corresponding to the target plot, the second planting information including second historical planting data and second water and fertilizer usage data of historical users corresponding to the target plot; the feature determination module is used to determine land characteristics of the target plot based on the location information; the recommendation module is used to determine planting recommendation information based on the first planting information, the second planting information and the land characteristics, the planting recommendation information at least including a recommended planting ranking of crops.

[0007] One or more embodiments of the present specification provide a crop planting recommendation device, including a processor, wherein the processor is used to execute a crop planting recommendation method.

[0008] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a method for recommending crop planting. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0010] Figure 1 is an exemplary module diagram of a crop planting recommendation system according to some embodiments of this specification;

[0011] Figure 2 is an exemplary flow chart of a crop recommendation method according to some embodiments of this specification;

[0012] Figure 3 is a schematic diagram of determining planting recommendation information according to some embodiments of this specification;

[0013] Figure 4 is another schematic diagram of a method for determining recommended planting information according to some embodiments of this specification;

[0014] Figure 5 It is a schematic diagram of determining a recommended combination scheme according to some embodiments of this specification. DETAILED DESCRIPTION

[0015] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0016] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0017] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" are not intended to refer to the singular but may include the plural.

[0018] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0019] Figure 1 is an exemplary module diagram of a crop planting recommendation system according to some embodiments of this specification. Figure 1 As shown, the crop planting recommendation system 100 may include a data acquisition module 110 , a first determination module 120 , a second determination module 130 , a feature determination module 140 and a recommendation module 150 .

[0020] In some embodiments, the data acquisition module 110 is used to acquire land parcel identification data and determine a target land parcel based on current user input information.

[0021] In some embodiments, the first determination module 120 is used to determine the location information of the target plot and its corresponding first planting information, where the first planting information includes the first historical planting data and first water and fertilizer usage data of the current user.

[0022] In some embodiments, the second determination module 130 determines second planting information corresponding to the target plot, where the second planting information includes second historical planting data and second water and fertilizer usage data of a historical user corresponding to the target plot.

[0023] In some embodiments, the feature determination module 140 is used to determine the land features of the target plot based on the location information.

[0024] In some embodiments, the recommendation module 150 is used to determine the planting recommendation information based on the first planting information, the second planting information and the land characteristics, and the planting recommendation information at least includes the recommended planting ranking of the crops.

[0025] In some embodiments, the user input information also includes soil fertility data and water and fertilizer supply capacity. The recommendation module 150 is also used to predict soil fertility change data in the future based on the soil fertility data; predict crop yield prediction data based on the soil fertility change data and water and fertilizer supply capacity; and determine planting recommendation information based on the yield prediction data.

[0026] In some embodiments, the recommendation module 150 is further used to obtain the time characteristics of the target plot, which characterizes the user's expected planting time; based on the time characteristics, the planting recommendation information is determined according to the first planting information, the second planting information and the land characteristics.

[0027] In some embodiments, the planting recommendation information also includes recommended combination schemes, and the recommendation module 150 is also used to determine multiple groups of candidate combination schemes based on the first planting information, the second planting information and the planting recommendation ranking; obtain the matching degree of the candidate combination schemes; in response to the matching degree satisfying a preset condition, determine the candidate combination scheme as a recommended combination scheme.

[0028] For more information about the crop planting recommendation system 100 and the functions of its various modules, please refer to the manual. Figure 3-Figure 4 Related content.

[0029] It should be understood that Figure 1 The illustrated system and its modules may be implemented in various ways.

[0030] It should be noted that the above description of the crop planting recommendation system and its modules is only for convenience of description and does not limit the present specification to the scope of the embodiments. It is understandable that, after understanding the principle of the system, those skilled in the art may arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from the principle. In some embodiments, Figure 1 The acquisition module, the first determination module, the second determination module, the feature determination module and the recommendation module disclosed in the specification can be different modules in a system, or one module can realize the functions of two or more of the above modules. For example, each module can share a storage module, or each module can have its own storage module. Such variations are all within the protection scope of this specification.

[0031] Figure 2 is an exemplary flow chart of a crop planting recommendation method according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps. In some embodiments, the process 200 can be implemented by a processor of the crop planting recommendation system 100.

[0032] Step 210, obtaining land parcel identification data, and determining a target land parcel based on input information from the current user.

[0033] The land parcel identification data is identification information used to distinguish different land parcels. For example, the land parcel identification data may be land parcel codes corresponding to different land parcels, such as land parcel 1, land parcel 2, and the like.

[0034] In some embodiments, the crop planting recommendation system 100 can obtain the user's land division and each plot code for the land to be planted through a mobile terminal, and determine the plot identification data based on the land division and each plot code.

[0035] The user input information refers to the data information input by the user, such as the plot number, etc. The plot number can be used to determine the target plot for crop planting recommendation.

[0036] In some embodiments, the user input information also includes soil fertility data and water and fertilizer supply capacity.

[0037] Soil fertility data refers to the fertility data of the target land, which may include organic matter content and mineral content, etc.

[0038] Water and fertilizer supply capacity refers to the ability to supply water and fertilizer to the target plot, which may include the water supply per unit time and water supply period, the fertilizer supply within a planting cycle, etc.

[0039] In some embodiments, the processor may obtain user input information through a mobile terminal.

[0040] The target plot refers to the plot that needs to be recommended for crop planting.

[0041] In some embodiments, the crop planting recommendation system 100 may determine the target plot based on user input information. For example, if the user input information is plot 1, then plot 1 is the target plot.

[0042] Step 220, determining the location information of the target plot and its corresponding first planting information, where the first planting information includes the first historical planting data and the first water and fertilizer usage data of the current user.

[0043] The location information of the target plot is information that characterizes the location of the target plot, such as longitude and latitude. In some embodiments, the location information of the target plot can be used to determine the land features of the target plot.

[0044] In some embodiments, the land parcel identification data may be associated with the location information of the land parcel. For example, the crop planting recommendation system 100 may determine the location of each land parcel based on the geographic information data corresponding to the land to be planted.

[0045] The geographic information data corresponding to the land to be planted can be obtained based on the GIS system (Geographic Information System). The GIS system can store spatial data and attribute data of the land to be planted, wherein the spatial data can at least include location information, and the attribute data can at least include planting data.

[0046] The first planting information is the historical planting data of the current user on the target plot, for example, the type of crops planted, the amount of water used, the amount of fertilizer used, and the corresponding planting time.

[0047] In some embodiments, the first planting information includes at least first historical planting data and first water and fertilizer usage data. The first historical planting data includes the types of crops and planting time planted by the current user in the target plot, and the first water and fertilizer usage data includes the historical water consumption and historical fertilizer application of crops planted by the current user in the target plot.

[0048] In some embodiments, the first historical planting data and the first water and fertilizer usage data have a corresponding relationship. For example, for the first planting data (S, T), it has the corresponding first water and fertilizer usage data (W, F). Among them, S represents the historical crop type, T represents the historical planting time of crop S, W represents the historical water consumption of planting crop S, and F represents the historical fertilizer application amount of planting crop S.

[0049] In some embodiments, the first planting information includes at least one set of first historical planting data and its corresponding first water and fertilizer usage data.

[0050] In some embodiments, the crop planting recommendation system 100 can retrieve the location information of the target plot and its corresponding first planting information in the GIS system based on the user's input information. The GIS system at least includes the geographic information of the land to be planted and the historical planting data of the current user. The GIS system can determine the geographic information of the land to be planted and the historical planting data of the current user by obtaining the data uploaded by the user.

[0051] Step 230: Determine the second planting information corresponding to the target plot.

[0052] The second planting information is the historical planting data of the historical users on the target plot, for example, the types of crops planted, the amount of water used, the amount of fertilizer used, and the corresponding planting time.

[0053] In some cases, the target plot may have been transferred and contracted many times before the current user started planting on it, and the user who contracted it before the current user is the historical user.

[0054] In some embodiments, the second planting information includes at least the second historical planting data and the second water and fertilizer use data of the historical user corresponding to the target plot. The second historical planting data includes the types of crops and planting time planted by the historical user in the target plot, and the second water and fertilizer use data includes the historical water consumption and the historical fertilizer application of the historical user in planting crops in the target plot.

[0055] In some embodiments, the second historical planting data and the second water and fertilizer usage data have a corresponding relationship, which is similar to the corresponding relationship between the first historical planting data and the first water and fertilizer usage data, and the details can be referred to the relevant description in step 220.

[0056] In some embodiments, the second planting information includes at least one set of second historical planting data and its corresponding second water and fertilizer usage data.

[0057] In some embodiments, the second planting information can be obtained based on the historical planting information of the historical user and / or the GIS system. For example, the processor can determine the second planting information based on the historical input information of the historical user. For another example, the GIS system can also include the historical planting information of the historical user, and the GIS system can determine the historical planting information by acquiring the data uploaded by the historical user. The processor can determine the number of the target plot based on the input information of the current user, and query the historical planting information of the historical user on the target plot in the GIS system based on the number of the target plot.

[0058] In some embodiments of the present specification, by collecting historical user planting information, more planting data with reference value can be obtained, which is conducive to better recommendations for crop planting.

[0059] Step 240, determining the land characteristics of the target plot based on the location information.

[0060] The land characteristics of the target plot may at least include the topography and soil type of the target plot. The topography of the target plot may include mountainous land, water land, terraced fields, etc.; the soil type may include a first soil type and a second soil type, the first soil type includes red soil, black soil, chestnut soil, etc., and the second soil type includes sandy soil, loam, clay, etc.

[0061] In some embodiments, the GIS system may also include land features of the land to be planted, and the processor may search in the GIS system based on the location information of the target plot to obtain the land features of the target plot.

[0062] Step 250, determining planting recommendation information based on the first planting information, the second planting information and the land characteristics.

[0063] The planting recommendation information is a recommended plan for planting crops in the target plot.

[0064] In some embodiments, the planting recommendation information includes at least a recommended planting ranking of the recommended crops.

[0065] The recommended planting ranking refers to the ranking of the recommended values ​​of the crops recommended for planting. The higher the ranking of a crop, the more suitable the target plot is for planting that crop.

[0066] In some embodiments, the processor can determine the recommended crop types by querying the first planting recommendation table based on the first planting information, the second planting information and the land characteristics. The first planting recommendation table can be obtained based on prior experience, and at least includes a first reference feature group consisting of reference to the first planting information, reference to the second planting information and reference to the land characteristics, and a reference crop type and a first reference recommendation value corresponding to the aforementioned first reference feature group. The higher the reference recommendation value, the more suitable it is for planting the crop. The processor can determine the closest target first reference feature group in the first planting recommendation table based on the first planting information, the second planting information and the land characteristics, determine the recommended crop types based on the reference crop types corresponding to the target first reference feature group, and determine the planting recommendation ranking based on the first reference recommendation value.

[0067] In some embodiments, the processor can determine the yield prediction data of different crops based on the user input information, and determine the planting recommendation order based on the constant prediction data. For more details, please refer to Figure 3 and its related description.

[0068] In some embodiments, the processor may also determine the planting recommendation data based on the current user's expected planting time, combined with the first planting information, the second planting information and the land characteristics of the target plot. Figure 4 and its related description.

[0069] In some cases, the target plot may adopt a crop rotation or intercropping method, and plant two or more crops in a planting cycle, or plant two or more crops at the same time in a planting cycle. Therefore, in order to improve the rationality and accuracy of planting recommendations, the crop planting recommendation system can also provide planting matching plans.

[0070] In some embodiments, the processor may determine a candidate combination scheme based on the first planting information, the second planting information, and the planting recommendation ranking, and determine a planting matching scheme based on the candidate combination scheme. Figure 5 and its related description.

[0071] In some embodiments, the processor may send the planting recommendation information to the mobile terminal of the current user, and display the planting recommendation information through the mobile terminal.

[0072] In some embodiments of the present specification, by obtaining the input information of the current user and combining it with the first information of the current user, the second planting information of historical users and the land characteristics of the target plot for analysis, more reasonable and accurate crop planting recommendations can be made, which is conducive to the scientific planning of regional planting.

[0073] Figure 3 Schematic diagram of determining planting recommendation information in some embodiments of this specification. Figure 3 As shown, the planting recommendation information is determined to include at least the following contents.

[0074] In some embodiments, the processor can predict soil fertility change data 320 in the future based on soil fertility data 310; predict crop yield prediction data based on soil fertility change data 320 and water and fertilizer supply capacity 330; and determine planting recommendation information 360 based on the yield prediction data.

[0075] Soil fertility change data refers to the change in soil fertility of the target plot over a period of time.

[0076] In some embodiments, the processor may determine soil fertility change data in the future by querying a soil fertility database based on the land characteristics of the target plot and the climate characteristics of its location. The soil fertility database may be determined based on historical data, including at least reference land characteristics of the reference plot and reference climate characteristics of its location, and soil fertility sequences of the reference plot at multiple consecutive time points.

[0077] In some embodiments, the processor can query the soil fertility database based on the land characteristics of the target plot and the climate characteristics of its location, construct a feature vector based on the aforementioned land characteristics and climate characteristics, construct a reference feature vector based on the aforementioned reference land characteristics and reference climate characteristics, determine the most similar reference plot based on the reference vector that is closest to the feature vector, and determine the soil fertility change data of the target plot in the future based on the soil fertility sequence of the reference plot at multiple consecutive times.

[0078] Yield forecast data refers to the predicted results of the yield of crops planted on the target plot.

[0079] In some embodiments, the processor may determine the yield prediction data for the future time by querying the yield prediction table based on the land characteristics of the target plot and the climate characteristics of its location. The yield prediction table may be determined based on historical data, including at least reference land characteristics of the reference plot and reference climate characteristics of its location, as well as the corresponding reference yield.

[0080] In some embodiments, the processor may query the yield prediction table based on the land characteristics of the target plot and the climate characteristics of its location, determine the most similar reference plot, and determine the yield prediction data of the target plot based on the reference yield of the reference plot. The method of determining the reference plot is similar to that of determining the soil fertility change data, and the details can be found in the relevant description above.

[0081] In some embodiments, the planting recommendation information further includes confidence 361 of the yield prediction data. The confidence represents the reliability of the constant prediction data.

[0082] In some embodiments, the confidence of the yield prediction data may be determined by a confidence prediction model 340 .

[0083] In some embodiments, the confidence prediction model 340 may be a machine learning model. The input of the confidence prediction model 340 may include crop information, rainfall characteristics, water and fertilizer supply capacity 330, soil fertility change data 320, soil characteristics, historical planting information, and preset yield prediction data 350.

[0084] The crop information refers to the type of crop planned to be planted. The crop information may be determined based on the historical planting conditions of the target plot and / or the crop type input by the user.

[0085] The rainfall characteristics refer to the rainfall characteristics during the crop growth cycle. The rainfall characteristics can be determined based on historical rainfall data, for example, by statistically analyzing the historical rainfall conditions in the same period of time and determining the rainfall characteristics based on the historical rainfall conditions.

[0086] For details on water and fertilizer supply capacity and soil fertility change data, please refer to the previous description.

[0087] In some embodiments, the confidence prediction model may include a matching layer and a prediction layer.

[0088] In some embodiments, the matching layer may be an RNN (Recurrent Neural Network). The input of the matching layer may include crop information, rainfall characteristics throughout the growth cycle, water and fertilizer supply capacity in different time periods in the future, and soil fertility change data at multiple time points in the future. Among them, different time periods in the future and multiple time points in the future have a corresponding relationship, for example, multiple time points in the future are included in different time periods in the future.

[0089] The output of the matching layer may include the first water and fertilizer supply and demand matching degree in different time periods in the future. The first water and fertilizer supply and demand matching degree can characterize the matching degree between the water and fertilizer supply capacity of the target plot and the water and fertilizer demand of the crop. The matching degree can be expressed as a percentage, and the higher the matching degree, the more sufficient the water and fertilizer supply. For example, a matching degree of 100% means that the water and fertilizer supply capacity of the target plot just meets the water demand of the crop, 150% means that the supply exceeds the demand, and 50% means that the supply is insufficient to meet the demand.

[0090] In some embodiments, the prediction layer may be a NN (Neural Network) model. The input of the prediction layer may include the first water-fertilizer supply-demand matching degree, soil characteristics, historical planting information, and preset yield prediction data 350.

[0091] The historical planting information may include a chronological order of crop planting sequences at different time periods on the target plot.

[0092] The preset yield prediction data 350 can be based on the land characteristics of the target plot and the climate characteristics of the location thereof, by querying a yield prediction table. For details of the yield prediction table, please refer to the above description.

[0093] The output of the prediction layer may include confidence 361 of the preset production prediction data 350. When the confidence is greater than a confidence threshold, the preset production prediction data 350 may be used as production prediction data 362. The confidence threshold may be determined based on prior experience or actual demand.

[0094] In some embodiments, the processor may train the matching layer and the prediction layer separately to obtain a trained confidence prediction model.

[0095] In some embodiments, the processor may train the initial matching layer based on a plurality of first training samples with first labels to obtain a trained matching layer.

[0096] The first training sample may include at least sample crop information, sample water and fertilizer supply capacity, sample rainfall characteristics, and sample soil fertility change data. The first training sample may be determined based on historical planting data.

[0097] The first label may at least include the degree of matching between the supply and demand of water and fertilizer for the sample. The first label may be determined based on the historical growth of crops. For example, based on historical data, the growth of crops in a certain period of time within a planting cycle is statistically analyzed. If the growth of crops is good during this period, it indicates that the supply of water and fertilizer can meet the needs of crops. In multiple groups of historical planting data where the needs of crops are met, the degree of matching between the supply and demand of water and fertilizer for the sample corresponding to the planting data with the smallest supply of water and fertilizer in history can be marked as 1, and the degree of matching between the supply and demand of water and fertilizer for the sample corresponding to the planting data with a supply of water and fertilizer greater than the aforementioned minimum value can be marked as a value greater than 1, which can be specifically determined based on the minimum water and fertilizer supply when the needs of crops are met; on the contrary, if the supply of water and fertilizer cannot meet the needs of crops, the corresponding degree of matching between the supply and demand of water and fertilizer for the sample is marked as a value less than 1, which can be determined based on the actual situation of crops. For example, if the crops are slightly withered but can basically grow normally, they can be marked as 0.8, and if the crops are dried up over a large area, they can be marked as 0.3, etc., which can be specifically determined based on prior experience.

[0098] In some embodiments, the processor may train the initial prediction layer based on a plurality of second training samples with second labels to obtain a trained prediction layer.

[0099] The second training sample at least includes the sample water-fertilizer supply-demand matching degree, sample soil characteristics, sample historical planting sequence, and sample preset yield data. The second training sample can be determined based on historical planting data. For example, the sample water-fertilizer supply-demand matching degree can be determined based on whether the water and fertilizer supply in the historical planting cycle meets the needs of crops, with satisfaction marked as 1 and non-satisfaction marked as 0; the sample preset yield data can be determined through a yield prediction table based on historical land characteristics and historical climate characteristics in historical data.

[0100] The second training label includes whether the sample preset production data matches the historical actual production. If it matches, it is marked as 1, and if it does not match, it is marked as 0. Among them, matching means that the difference between the sample preset production data and the historical actual production data is less than the difference threshold, and the difference threshold can be set based on actual needs.

[0101] In some cases, historical data may be incomplete. For example, historical planting data may be missing. In this case, the missing parts need to be processed based on preset rules, and the processed historical data can be used for training the prediction layer.

[0102] In some embodiments, the processor may fill in missing data. For example, missing data may be filled in as 0. In some embodiments, the second label is related to the degree of missingness of historical data. For example, when the sample preset production forecast data matches the historical actual production, but the historical data is missing, the label may be a value between (0, 1) according to the degree of data missingness, and the greater the degree of data missingness, the smaller the label value.

[0103] In some cases, the processor can also determine the label of the missing historical data based on the deviation size of the historical statistical data. For example, for the first historical data that lacks historical planting information, the processor can determine the label corresponding to the first historical data based on the first yield discreteness corresponding to the first historical data and the second yield discreteness corresponding to the second historical data. If the first yield discreteness is 25% greater than the second yield discreteness, the label corresponding to the first historical data is 1 / (1+25%)=80%. The larger the discreteness, the smaller the corresponding label and the lower the confidence. Among them, the second historical data is the historical data without data missing.

[0104] In some embodiments, the processor may also determine the missing historical data in the current plot based on the historical information of the reference plot whose similarity to the current plot meets the preset conditions. For example, assuming that there is a reference plot in the historical statistical data whose similarity to the current plot meets the preset conditions, and the historical data of the reference plot is complete, the second label may be determined based on the historical actual yield of a crop corresponding to the reference plot and the preset yield prediction value of the crop in the current plot. For example, if the aforementioned preset yield prediction value matches the aforementioned historical actual yield, it is marked as 1, and if they do not match, it is marked as 0.

[0105] In some embodiments, the confidence of the confidence prediction model output is affected by the degree of data missingness. The higher the degree of data missingness, the lower the confidence.

[0106] In some embodiments of the present specification, soil fertility may fluctuate greatly with time, planting conditions, rainfall conditions, and artificial watering and fertilization conditions. By reasonably predicting changes in soil fertility, reliable data support can be provided for subsequent predictions of actual crop yield data, making the model output results more in line with actual conditions, thereby better meeting user needs.

[0107] In some embodiments, the planting recommendation information 360 may include yield prediction data 362 and confidence 361, as well as a recommended planting ranking of crops 363. The processor may determine the recommended planting ranking based on the yield prediction data and its confidence. For example, the processor ranks the recommended crops based on the yield prediction data and confidence. The higher the yield, the higher the confidence, and the higher the ranking of the crop.

[0108] In some embodiments, the planting recommendation information 360 also includes an estimated planting cost, which can be determined based on yield prediction data and soil fertility change data.

[0109] The estimated planting cost refers to the estimated cost of the target plot from crop planting to output.

[0110] In the process of crop planting, if you want to achieve ideal yields, you must at least meet the water and fertilizer needs of the crops. Therefore, the estimated planting cost can be determined based on the water and fertilizer supply conditions.

[0111] In some embodiments, the estimated planting cost can be determined by a preset algorithm based on the water and fertilizer supply cost and the first water and fertilizer supply and demand matching degree.

[0112] In some embodiments, the preset algorithm may include formula (1):

[0113]

[0114] Among them, C is the estimated planting cost; C1 is the estimated water and fertilizer supply cost; k is the first water and fertilizer supply and demand matching degree; P is the confidence level; C2 is other costs.

[0115] The estimated water and fertilizer supply cost C1 refers to the supply cost when planting according to the maximum water and fertilizer supply capacity, which can be determined based on the water and fertilizer supply capacity input by the user. The stronger the water and fertilizer supply capacity, the greater the estimated water and fertilizer supply cost; other costs C2 can be determined based on labor costs, electricity costs, seed prices, etc. in the crop planting process; the confidence P can be obtained based on the prediction layer of the confidence prediction model; the first water and fertilizer supply and demand matching degree k can be obtained based on the matching layer of the confidence prediction model.

[0116] When k=1, it indicates that the existing water and fertilizer supply capacity can meet the needs of crops, and users do not need to pay additional water and fertilizer supply costs; when k<1, it indicates that the existing water and fertilizer supply capacity cannot meet the needs of crops, and users need to pay additional water and fertilizer supply costs to achieve ideal yields; when k>1, it indicates that there is redundancy in the water and fertilizer supply capacity, and the actual water and fertilizer supply cost is less than the estimated water and fertilizer supply cost.

[0117] In some embodiments, the processor may rank the recommended crops based on the estimated planting cost. For example, the lower the estimated planting cost, the higher the ranking.

[0118] In some embodiments, the processor may determine the recommended planting order of the recommended crops based on the yield prediction data and its confidence, the estimated planting cost, and the user's needs. For example, if the user expects to choose a high-yield plan, the processor may prioritize the order based on the yield prediction data and its confidence. The higher the yield prediction data and the higher the confidence, the higher the corresponding crop is ranked. For crops with the same yield prediction data and confidence, they may be further ranked based on the estimated planting cost. The lower the estimated planting cost, the higher the ranking.

[0119] Some embodiments of the present specification calculate the estimated planting cost and make crop planting recommendations based on the estimated planting cost, which helps users choose suitable crops according to their own needs and can better meet user needs.

[0120] In some embodiments of the present specification, soil fertility data is used to predict soil fertility change data and yield prediction data step by step, and planting recommendation information is determined and a planting recommendation ranking is given in combination with the estimated planting cost, so that users can intuitively see the results of planting various crops, further optimizing the user's choice of crops.

[0121] Figure 4 FIG. 1 is another schematic diagram of a method for determining planting recommendation information according to some embodiments of this specification. Figure 4 As shown, the process of determining planting recommendation information may also include the following contents.

[0122] In some embodiments, the processor may also obtain a time feature 410 of the target plot, and determine the planting recommendation information 360 based on the time feature 410 , the first planting information 420 , the second planting information 430 , and the land feature 440 .

[0123] The time feature refers to the time related to crop planting. In some embodiments, the time feature 410 includes at least the current time and the user's desired planting time.

[0124] In some embodiments, the time feature 410 may be determined by system preset or user input.

[0125] The expected planting time refers to the time when the user plans to plant crops. For example, the expected planting time may be one month later.

[0126] In some embodiments, the processor may determine the recommended crop type by querying the second planting recommendation table. The planting recommendation table may be obtained based on prior experience, and at least includes a second reference feature group consisting of reference first planting information, reference second planting information, reference land features, and reference time features, and a second reference crop type and a second reference recommendation value corresponding to the second reference feature group.

[0127] The processor can determine the closest target second reference feature group in the second planting recommendation table based on the first planting information 420, the second planting information 430, the land characteristics 440 and the time characteristics 410, determine the recommended crop types based on the reference crop types corresponding to the target second reference feature group, determine the recommended planting order of the crops based on the second reference recommendation value 470 corresponding to the target second reference feature group, and further determine the planting recommendation information 360.

[0128] In some embodiments, the time feature 410 can also be used to determine the confidence level corresponding to the estimated yield prediction data of the crop. For example, the time feature is used as the input of the prediction layer of the aforementioned confidence prediction model, and the confidence level of the estimated yield prediction data is re-output. If the updated confidence level is less than the aforementioned confidence threshold, it indicates that the crop is not suitable for planting under the time feature.

[0129] The planting of some crops is affected by time. If they are planted at an inappropriate time, the yield of the crops will be affected. By using time features as the input of the prediction layer, it is possible to more accurately determine whether the crops are suitable for planting at the time expected by the user, which is conducive to better crop planting recommendations and thus meet user needs.

[0130] In some embodiments, the processor may also determine a category recommendation degree 480 corresponding to the category consultation information in response to user input information including category consultation information 450, based on the first planting information and the second planting information, as well as the time characteristics.

[0131] Category consulting information is consulting information about crop categories. Category consulting information 450 may include at least the type of crop that the user wants to plant, and the category consulting information may also include the time when the user wants to plant the crop. For example, the category consulting information may be "Is August suitable for planting carrots?".

[0132] In some embodiments, the category advisory information may be determined by a processor by obtaining user input.

[0133] Category recommendation degree 480 refers to the degree of recommendation for the corresponding crop category in the category consultation information. Category recommendation degree 480 can be expressed as a percentage. The larger the percentage, the more recommended it is to plant the crop of this category.

[0134] In some embodiments, the processor may determine the category recommendation based on the yield prediction data. In some embodiments, the processor may obtain the yield prediction data of the crop corresponding to the category consultation information based on the time feature, and determine the category recommendation 480 based on the relationship between the yield prediction data of the crop and the average value of the historical statistical data. For example, the processor may use the percentage of the yield prediction data in the average value of the historical yield data as the category recommendation 480 of the planting category. For a detailed description of determining the yield prediction data of the crop, see Figure 3 The historical statistical data may include the historical yield data of this type of crop, which can be obtained based on the user input data.

[0135] In some embodiments, if the category recommendation degree 480 is greater than the recommendation degree threshold, the category of crops is recommended to the user; if the category recommendation degree 480 is less than the recommendation degree threshold, it is not recommended. The recommendation threshold can be determined based on prior experience and / or actual needs. For example, if the yield forecast data of a certain crop accounts for 70% of the average value of historical yield data, the category recommendation degree 480 is 70%, and if the recommendation degree threshold is 60%, it is recommended that the user plant the category of crops.

[0136] In some embodiments, the category recommendation degree 480 is also related to the water and fertilizer supply capacity 460. The processor can determine the category recommendation degree 480 based on the water and fertilizer demand degree of the category of crops and the water and fertilizer supply capacity of the land in the planting area. For example, if the water and fertilizer demand degree of the crop matches the water and fertilizer supply capacity of the land in the planting area, the category recommendation degree 480 is high, and if the difference is large, the category recommendation degree 480 is low. The water and fertilizer demand degree of the crop can be obtained based on the first planting information 420 and the second planting information 430. For example, the water and fertilizer demand degree of the crop can be determined based on the average value of the water and fertilizer usage data of the crop in the first planting information and the second planting information. The water and fertilizer supply capacity of the land in the planting area can be determined based on the average value of the historical water and fertilizer supply capacity input by the user in the historical planting data.

[0137] Some embodiments of this specification also take into account the impact of the water and fertilizer supply capacity of the land on crop yields, and provide reasonable feedback to the consulting information input by the user to better help the user judge the consulting content.

[0138] Different crops have different suitable planting time periods in different plots. If crops are not planted in suitable time periods, their yields may be affected. Some embodiments of this specification consider the influence of time characteristics when determining crop planting recommendation information, and can more accurately determine crop planting recommendation results, thereby better meeting user needs.

[0139] Figure 5 FIG. 1 is a schematic diagram of determining a recommended combination scheme according to some embodiments of this specification. Figure 5 As shown, determining the recommended combination plan includes at least the following contents.

[0140] In some embodiments, the planting recommendation information may further include a recommended combination scheme. The processor may determine multiple groups of candidate combination schemes 510 based on the first planting information 420, the second planting information 430, and the planting recommendation ranking 363; obtain the matching degree 520 of the candidate combination schemes; and determine the candidate combination scheme as a recommended combination scheme 530 in response to the matching degree satisfying a preset condition.

[0141] The candidate combination scheme refers to a combination scheme for planting different crops. In some embodiments, the candidate combination scheme 510 may include at least a planting time, a planting area, and two or more recommended crops.

[0142] In some embodiments, the processor may determine candidate combination schemes in a variety of ways based on the first planting information 420, the second planting information 430, and the planting recommendation ranking 363. For example, the processor may determine multiple groups of reference combination schemes based on the historical combination schemes existing in the first planting information and / or the second planting information, and determine the reference combination schemes that only contain the recommended crop types as candidate combination schemes according to the recommended crop types involved in the planting recommendation ranking. For another example, the processor may randomly generate multiple candidate combination schemes based on the recommended crop types designed in the planting recommendation ranking, and each candidate combination scheme contains no less than two recommended crop types.

[0143] The recommended combination scheme refers to the scheme among the candidate combination schemes whose matching degree meets the preset conditions.

[0144] In some embodiments, the processor may use at least one set of candidate combination schemes whose matching degree 520 satisfies a preset condition as a recommended combination scheme. The preset condition may include a matching degree threshold. For example, the preset condition may be that the matching degree is higher than 80%. The preset condition may be set based on prior experience and / or actual needs.

[0145] The matching degree refers to the degree of adaptation between the candidate combination scheme and the actual planting conditions. The actual planting conditions refer to the environmental conditions that actually affect the planting of crops, such as the planting time, planting area, etc. In some embodiments, the processor can determine the planting time based on the expected planting time input by the user, and determine the planting area corresponding to the target plot based on the plot number input by the user.

[0146] In some embodiments, the processor may determine the degree of matching based on the historical production data corresponding to the candidate combination scheme in the historical statistical data and the preset ideal production. For example, when the historical production data is higher than the preset ideal production, the degree of matching is high. The greater the amount by which the historical production data exceeds the preset ideal production, the higher the degree of matching. The preset ideal production may be determined based on prior experience and / or actual user needs.

[0147] In some embodiments, the matching degree 520 includes at least a crop matching degree 520 - 1 and a second water and fertilizer supply and demand matching degree 520 - 2 .

[0148] Crop matching refers to the suitability of crops to be planted on the target plot at the same time. Crop matching can be expressed as a number from 0 to 10, with the larger the number, the higher the suitability.

[0149] In some embodiments, the crop matching degree 520-1 can be determined based on the yield prediction data and the preset ideal yield. For example, when the yield prediction data is higher than the preset ideal yield, the crop matching degree is high. The greater the difference between the yield prediction data and the preset ideal yield, the higher the crop matching degree. The yield prediction data can be determined based on the yield prediction table and the confidence prediction model. For more details, see Figure 3 and its related description.

[0150] In some embodiments, the crop matching degree 520-1 can be calculated based on the yield prediction data and the preset ideal yield. For example, the processor can calculate the second yield difference between the yield prediction data and the preset ideal yield, and determine the crop matching degree based on the ratio of the second yield difference to the preset ideal yield.

[0151] The second water-fertilizer supply-demand matching degree 520 - 2 refers to the matching degree between the water-fertilizer demand and the water-fertilizer supply capacity of the candidate crops in the candidate combination scheme.

[0152] In some embodiments, the processor may determine the second water-fertilizer supply-demand matching degree based on a matching degree prediction model.

[0153] In some embodiments, the matching prediction model may have the same structure as the matching layer of the confidence prediction model. For example, the matching prediction model may be a RNN (Recurrent Neural Network, recurrent neural network model).

[0154] The input of the matching prediction model can include the crop information and planting sequence in the candidate combination scheme, the water and fertilizer supply capacity in different time periods, the rainfall characteristics in the growth cycle, and the soil fertility change data at multiple time points in the future. Among them, the crop information refers to the crop type information in the candidate combination scheme, and the planting sequence refers to the planting order of different crops in the candidate combination scheme, for example, planting crop A and crop B at the same time, planting crop A first and then planting crop B, etc. The determination method of the water and fertilizer supply capacity in different time periods, the rainfall characteristics in the growth cycle, and the soil fertility change data at multiple time points in the future is similar to that of the confidence prediction model, which can be seen in Figure 3 The output of the matching degree prediction model may include the second water and fertilizer supply and demand matching degree.

[0155] In some embodiments, the matching prediction model can be obtained based on multiple third training samples with third labels. The third training sample can include sample crop information in the sample combination scheme, sample planting order, sample water and fertilizer supply, sample rainfall characteristics, and sample soil fertility change data. The third label can include the matching degree of water and fertilizer supply and demand of the second sample. The determination of the third training sample and the third label is similar to the determination of the first training sample and the first label, which can be seen in Figure 3Related description in .

[0156] In some embodiments, the processor may determine as a recommended combination scheme a candidate combination method whose crop matching degree is greater than a first threshold and whose second water and fertilizer supply and demand matching degree is greater than a second threshold. The first threshold and the second threshold may be determined based on prior experience and / or actual needs of the user.

[0157] Under different planting sequences, the degree of matching between water and fertilizer supply and demand may be different. In some embodiments of the present specification, by considering the influence of the planting sequence of crops, the matching degree of water and fertilizer supply and demand of the target plot can be determined more reasonably and accurately. While considering the suitability of crops for planting, the recommended combination scheme suitable for planting can be reasonably determined, thereby providing users with more reliable planting recommendation information.

[0158] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0159] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0160] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0161] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0162] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0163] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0164] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A recommended method for planting crops, It is characterized in that The method is implemented based on a mobile terminal and includes: Acquire land parcel identification data, and determine a target land parcel based on input information from a current user, wherein the input information also includes soil fertility data and water and fertilizer supply capacity; Determine the location information of the target plot and the first planting information corresponding thereto, wherein the first planting information includes the first historical planting data and the first water and fertilizer usage data of the current user; Determine second planting information corresponding to the target plot, where the second planting information includes second historical planting data and second water and fertilizer usage data of a historical user corresponding to the target plot; Based on the location information, determining land characteristics of the target plot; Determine planting recommendation information based on the first planting information, the second planting information and the land characteristics, wherein the planting recommendation information at least includes a recommended planting order of crops; Based on the soil fertility data, predict soil fertility change data in the future; Predicting the yield prediction data of the crop based on the soil fertility change data and the water and fertilizer supply capacity; The planting recommendation information also includes the yield prediction data and the confidence of the yield prediction data, wherein the confidence is determined by a confidence prediction model, and the confidence prediction model is a machine learning model; The confidence prediction model includes a matching layer and a prediction layer, the matching layer is a recurrent neural network model, and the prediction layer is a neural network model; the matching layer and the prediction layer are trained separately to obtain a confidence prediction model; The input of the matching layer includes crop information, rainfall characteristics, the water and fertilizer supply capacity and the soil fertility change data, and the output of the matching layer includes a first water and fertilizer supply and demand matching degree; the crop information is the type of crop planned to be planted, and the rainfall characteristics are the rainfall characteristics within the growth period of the crop; The input of the prediction layer includes the first water-fertilizer supply-demand matching degree, the land characteristics, historical planting information, and preset yield prediction data, and the output of the prediction layer includes the confidence level of the preset yield prediction data; In response to the confidence of the preset production forecast data being greater than a confidence threshold, using the preset production forecast data as the production forecast data; The planting recommendation information also includes an estimated planting cost, and the estimated planting cost is determined based on the yield prediction data and the soil fertility change data; Based on the estimated planting costs, the recommended planting order of the crops is determined.

2. The crop planting recommendation method according to claim 1, It is characterized in that The determining of the planting recommendation information based on the first planting information, the second planting information and the land characteristics further includes: Acquire a time feature of the target plot, where the time feature represents an expected planting time of the user; Based on the time feature, the planting recommendation information is determined according to the first planting information, the second planting information and the land feature.

3. The crop planting recommendation method according to claim 1, It is characterized in that The planting recommendation information also includes a recommended combination scheme, and the method further includes: Determine multiple groups of candidate combination solutions based on the first planting information, the second planting information and the planting recommendation ranking; Obtaining the matching degree of the candidate combination scheme; In response to the matching degree satisfying a preset condition, the candidate combination scheme is determined to be a recommended combination scheme.

4. A crop planting recommendation system, It is characterized in that It includes a data acquisition module, a first determination module, a second determination module, a feature determination module and a recommendation module; wherein, The data acquisition module is used to acquire land parcel identification data and determine the target land parcel based on input information from the current user, wherein the input information also includes soil fertility data and water and fertilizer supply capacity; The first determination module is used to determine the location information of the target plot and the first planting information corresponding thereto, wherein the first planting information includes the first historical planting data and the first water and fertilizer usage data of the current user; The second determination module is used to determine second planting information corresponding to the target plot, where the second planting information includes second historical planting data and second water and fertilizer usage data of a historical user corresponding to the target plot; The feature determination module is used to determine the land features of the target land based on the location information; The recommendation module is used to determine planting recommendation information based on the first planting information, the second planting information and the land characteristics, and the planting recommendation information at least includes a recommended planting order of crops; Based on the soil fertility data, predict soil fertility change data in the future; Predicting the yield prediction data of the crop based on the soil fertility change data and the water and fertilizer supply capacity; The planting recommendation information also includes the yield prediction data and the confidence of the yield prediction data, wherein the confidence is determined by a confidence prediction model, and the confidence prediction model is a machine learning model; The confidence prediction model includes a matching layer and a prediction layer, the matching layer is a recurrent neural network model, and the prediction layer is a neural network model; the matching layer and the prediction layer are trained separately to obtain a confidence prediction model; The input of the matching layer includes crop information, rainfall characteristics, the water and fertilizer supply capacity and the soil fertility change data, and the output of the matching layer includes a first water and fertilizer supply and demand matching degree; the crop information is the type of crop planned to be planted, and the rainfall characteristics are the rainfall characteristics within the growth period of the crop; The input of the prediction layer includes the first water-fertilizer supply-demand matching degree, the land characteristics, historical planting information, and preset yield prediction data, and the output of the prediction layer includes the confidence level of the preset yield prediction data; In response to the confidence of the preset production forecast data being greater than a confidence threshold, using the preset production forecast data as the production forecast data; The planting recommendation information also includes an estimated planting cost, and the estimated planting cost is determined based on the yield prediction data and the soil fertility change data; Based on the estimated planting costs, the recommended planting order of the crops is determined.

5. The crop planting recommendation system according to claim 4, It is characterized in that The recommendation module is further used to: Acquire a time feature of the target plot, where the time feature represents an expected planting time of the user; Based on the time feature, the planting recommendation information is determined according to the first planting information, the second planting information and the land feature.

6. The crop planting recommendation system according to claim 4, It is characterized in that The planting recommendation information also includes a recommended combination plan, and the recommendation module is further used to: Determine multiple groups of candidate combination solutions based on the first planting information, the second planting information and the planting recommendation ranking; Obtaining the matching degree of the candidate combination scheme; In response to the matching degree satisfying a preset condition, the candidate combination scheme is determined to be a recommended combination scheme.

7. A crop planting recommendation device, comprising a processor, wherein the processor is used to execute the crop planting recommendation method according to any one of claims 1 to 3.

8. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the crop planting recommendation method as described in any one of claims 1 to 3.