Planting recommendation method, device, terminal equipment and storage medium for citrus varieties

Abstract

The application is suitable for the technical field of planting, and provides a citrus variety planting recommendation method and device, a terminal device and a storage medium. The citrus variety planting recommendation method specifically comprises the following steps: acquiring planting data, determining output results of a plurality of models according to the planting information and the plurality of models, the plurality of models including a planting adaptability model, a citrus growth model, a price prediction model and a production environment related prediction analysis model, and fusing the output results of the plurality of models to obtain a recommendation result of planting recommendation for the plurality of varieties. The embodiments of the application can improve the reliability of the planting recommendation result of the citrus variety.

Description

Technical Field

[0001] This application belongs to the field of planting technology, and in particular relates to a recommended method, apparatus, terminal equipment and storage medium for planting a citrus variety. Background Technology

[0002] Citrus varieties are directly related to their selling price, but the harvest yield and price of a variety are affected by various factors such as season, market availability, and supply and demand. Traditionally, farmers often select citrus varieties based on experience, a method that is largely unreliable. Therefore, some related technologies have proposed planting recommendation methods that analyze the suitability of citrus varieties based on factors such as soil and rainfall, and then recommend citrus varieties. However, these methods do not consider the growth cycle of each citrus variety, nor do they take into account price factors. Therefore, the recommendations are often unsatisfactory and have low reliability. Summary of the Invention

[0003] This application provides a method, apparatus, terminal equipment, and storage medium for recommending the planting of citrus varieties, which can solve the problem of insufficient reliability of current citrus variety planting recommendation results.

[0004] The first aspect of this application provides a method for recommending the planting of citrus varieties, comprising: acquiring planting data, wherein the planting information includes the planting location for citrus planting, and production environment information related to harvest period and price; determining the output results of the multiple models based on the planting information and multiple models, wherein the multiple models include a planting adaptability model, a citrus growth model, a price prediction model, and a production environment-related predictive analysis model, wherein the output result of the planting adaptability model is the planting suitability of multiple citrus varieties, the output result of the citrus growth model is the harvest period and yield of the multiple citrus varieties, the output result of the price prediction model is the predicted price of the multiple citrus varieties, and the output result of the production environment-related predictive analysis model is the optimal harvest time and required agricultural operations for the multiple citrus varieties; and fusing the output results of the multiple models to obtain a recommendation result for recommending the planting of the multiple varieties.

[0005] A second aspect of this application provides a citrus variety planting recommendation device, comprising: an acquisition unit for acquiring planting data, the planting information including the planting location of the citrus planted, and production environment information related to the harvest period and price; a determination unit for determining the output results of the multiple models based on the planting information and multiple models, the multiple models including a planting adaptability model, a citrus growth model, a price prediction model, and a production environment-related predictive analysis model, wherein the output result of the planting adaptability model is the planting suitability of multiple citrus varieties, the output result of the citrus growth model is the harvest period and yield of the multiple citrus varieties, the output result of the price prediction model is the predicted price of the multiple citrus varieties, and the output result of the production environment-related predictive analysis model is the optimal harvest time and required agricultural operations for the multiple citrus varieties; and a fusion unit for fusing the output results of the multiple models to obtain a recommendation result for planting the multiple varieties.

[0006] A third aspect of this application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method for recommending the cultivation of citrus varieties.

[0007] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method for recommending the planting of citrus varieties.

[0008] The fifth aspect of this application provides a computer program product that, when run on a terminal device, causes the terminal device to execute the planting recommendation method for citrus varieties described in any of the first aspects above.

[0009] In the embodiments of this application, planting data is acquired, and based on planting information and multiple models, the output results of multiple models are determined. The output results of multiple models are then fused to obtain planting recommendations for multiple varieties. These multiple models include a planting adaptability model, a citrus growth model, a price prediction model, and a production environment-related predictive analysis model. The planting adaptability model outputs the suitability of planting multiple citrus varieties; the citrus growth model outputs the harvest period and yield of multiple citrus varieties; the price prediction model outputs the predicted price of multiple citrus varieties; and the production environment-related predictive analysis model outputs the optimal harvest time and required agricultural operations for multiple citrus varieties. Therefore, by combining planting suitability, harvest period, yield, price, optimal harvest time, and required agricultural operations, planting recommendations for citrus varieties can be made to farmers, resulting in more reliable recommendations. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a schematic diagram illustrating the implementation process of a method for recommending the planting of citrus varieties provided in an embodiment of this application;

[0012] Figure 2 This is a schematic diagram of the structure of a citrus variety planting recommendation device provided in an embodiment of this application;

[0013] Figure 3 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application. Detailed Implementation

[0014] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are protected by this application.

[0015] To illustrate the technical solution of this application, specific embodiments are described below.

[0016] Figure 1This illustration shows a flowchart of a method for recommending citrus varieties according to an embodiment of this application. This method can be applied to terminal devices and is suitable for situations where the reliability of planting recommendation results needs to be improved. The aforementioned terminal devices can refer to smart devices such as mobile phones, computers, and tablets, and this application does not impose any limitations on this.

[0017] Specifically, the recommended planting method for the above-mentioned citrus varieties may include the following steps S101 to S103.

[0018] Step S101: Obtain planting data.

[0019] The planting information can include the location of the citrus trees, production environment information related to the harvest period and price, etc. The terminal device can obtain planting data input by farmers through touch screen operation, manual input, etc., or it can determine the above planting information based on the location information of the terminal device.

[0020] Step S102: Based on the planting information and multiple models, determine the output results of multiple models.

[0021] In embodiments of this application, the multiple models may include a planting adaptability model, a citrus growth model, a price prediction model, and a production environment-related predictive analysis model. Specifically, the terminal device can acquire historical planting data and train multiple models based on this historical planting data. For example, the aforementioned historical planting data may be planting data of various high-quality citrus varieties cultivated over the past 5-10 years.

[0022] The planting adaptability model can be used to analyze planting suitability, and its output can show the planting suitability of multiple citrus varieties. Based on planting data, the terminal equipment can identify key ecological factors, including but not limited to sunlight, average annual temperature, precipitation, altitude, soil pH, soil organic matter, and soil conditions at the planting location. These key ecological factors are then input into the planting adaptability model to obtain the planting suitability of multiple citrus varieties.

[0023] Specifically, the terminal equipment can acquire historical planting data from high-quality fruit-growing areas that have been cultivated for 5-10 years, identify key ecological factors affecting fruit tree growth and development, fruit quality, and yield, and conduct a multi-factor comprehensive weighted evaluation of these key factors. A scoring model is used to assign values ​​and make judgments, and the ecological suitability of different tree species in the planning area is ranked according to the scores. The discontinuities of the ranking criteria are used as indicators, and the key factors are input into the model for training to obtain an ecological adaptability assessment decision model. This model is then used to assess whether the decision-making planting area is suitable for introducing and planting the fruit tree.

[0024] Citrus growth models can be used to predict the growth period of various citrus varieties. The model output can provide the harvest date and yield for multiple citrus varieties. Terminal equipment can determine the growth indicators for each citrus variety from multiple varieties based on planting information. These growth indicators may include, but are not limited to, the growth period, canopy width, chlorophyll content, flowering quantity, and fruit yield for each variety. By inputting the growth indicators of each citrus variety into the corresponding citrus growth model, the harvest date and yield for that variety can be obtained.

[0025] Specifically, terminal devices can acquire various growth indicators and, combined with environmental factors of the planting location, such as soil fertility, pest and disease occurrence, and environmental climate factors, select key growth indicators. By comparing and analyzing raw datasets or transformed datasets of different citrus varieties during their growth stages, citrus growth models for different citrus varieties are established. Transformation methods can include normalization, standardized logarithmic transformation, sigmoid transformation, and Box-Cox transformation. Data analysis methods include correlation analysis, multiple regression analysis, principal component analysis, exponential smoothing, and the Downhill-Simplex algorithm. Models at different growth stages are correlated using an interval assignment method, which involves comparing them with environmental growth factors of the same period and assigning different scores based on the matching degree of growth elements. These scores are then multiplied by the weight of each factor in the entire model to calculate a matrix and establish citrus growth models for different citrus varieties. The citrus growth model can predict and correct the citrus growth status at the planting location in real time, thereby accurately predicting and determining the harvest period and yield.

[0026] Price prediction models can be used to estimate the price of citrus fruits, and their output can be the predicted price for multiple varieties of citrus. Terminal equipment can determine the price factor for each of the multiple varieties of citrus based on planting information, and input the price factor of each variety into the corresponding price prediction model to obtain the predicted price for that variety of citrus.

[0027] Specifically, the terminal device can obtain the prices and related factors of various varieties over the past 5-10 years. Key factors are selected through correlation analysis, principal component analysis, regression analysis, etc., and their weights are calculated. Price prediction models for different varieties of citrus are established through various methods such as exponential smoothing, ensemble learning, optimized BP neural network, and KNN algorithm, thereby enabling the determination and real-time prediction of price trends for different varieties of citrus.

[0028] Production environment-related predictive analysis models can be used to analyze the production environment of citrus. The model outputs the optimal harvest time and required agricultural operations for multiple citrus varieties. Terminal equipment can determine price fluctuation factors and harvest period factors for each variety based on planting information. These factors are then input into the production environment-related predictive analysis model to obtain the optimal harvest time and required agricultural operations for multiple citrus varieties.

[0029] Specifically, the terminal equipment can acquire 5-10 years of environmental factor data related to citrus planting and prices. Key factors are selected through correlation analysis, principal component analysis, and regression analysis, and their weights are calculated. A price prediction model for different citrus varieties is established using ensemble learning, optimized BP neural networks, KNN, LSTM algorithms, and other methods. This constructs an environmental analysis and prediction model to predict and analyze factors affecting citrus harvesting and price fluctuations, thereby calculating the optimal harvest time and determining whether corresponding agricultural operations are needed to adjust the harvest period to ensure maximum profit for users. Preferably, the price prediction model can also output the required storage measures. The agricultural operation suggestions refer to recommendations given throughout the entire citrus growth period (new shoot budding, budding and flowering, fruit development, and fruit ripening), based on historical experience and suitable values ​​for citrus soil nutrients, citrus leaf nutrient content, suitable temperature and humidity, disaster standards, and citrus pest and disease control standards. For example, if the soil nutrient content is below the appropriate level, fertilization is recommended; if the nutrient element content in the citrus leaves is below the appropriate level, fertilization is recommended; if pests and diseases reach the control standards, pest and disease control measures are recommended to reduce the damage to the fruit and the resulting quality decline. By analyzing and predicting the optimal harvest time and taking storage measures, farmers can avoid low prices and choose to sell when prices are high, achieving a bumper harvest.

[0030] Step S103: The output results of multiple models are fused to obtain the recommendation results for planting multiple varieties.

[0031] Specifically, the terminal device can obtain the weights of the output results of each model in multiple models, perform weighted processing on the output results of each model in multiple models using the corresponding weights, and concatenate the weighted results to obtain the recommendation result.

[0032] To improve the fusion effect, a dynamic parameter mechanism can be used to examine user evaluations of the recommendation results and their consistency with the system's predictions, generating a weighted model. Dynamically adjusting the weights significantly improves the effect. Then, a cross-fusion algorithm is used to interweave results from different recommendation models into the overall recommendation list, ensuring diversity. This interleaved display is suitable for recommendation scenarios that can simultaneously display multiple results, meeting farmers' needs for selecting recommendations. Finally, the waterfall fusion method can be used to chain the four models together, with each prediction algorithm acting as a filter, ultimately resulting in a small but high-quality set of results.

[0033] In some implementations, to verify the reliability of the model and whether the data reported by farmers matches the predictions, each prediction algorithm is tested again to obtain prediction results from different algorithms. The terminal device can train a second-layer prediction algorithm to perform a second prediction on the predicted results and generate the final recommendation result. Specifically, the terminal device can use the output results of the above multiple models to train with three different algorithms to obtain three different prediction results, then perform data processing and training data to obtain the optimal training model, obtain the evaluation model (merged model), and finally output the user's needs.

[0034] In the embodiments of this application, planting data is acquired, and based on planting information and multiple models, the output results of multiple models are determined. The output results of multiple models are then fused to obtain planting recommendations for multiple varieties. These multiple models include a planting adaptability model, a citrus growth model, a price prediction model, and a production environment-related predictive analysis model. The planting adaptability model outputs the suitability of planting multiple citrus varieties; the citrus growth model outputs the harvest period and yield of multiple citrus varieties; the price prediction model outputs the predicted price of multiple citrus varieties; and the production environment-related predictive analysis model outputs the optimal harvest time and required agricultural operations for multiple citrus varieties. Therefore, by combining planting suitability, harvest period, yield, price, optimal harvest time, and required agricultural operations, planting recommendations for citrus varieties can be made to farmers, resulting in more reliable recommendations.

[0035] Based on the implementation method of this application, farmers can select the best citrus varieties, changing the current situation where citrus growers blindly follow trends when choosing varieties. Simultaneously, based on the growth characteristics and planting techniques of different citrus varieties, the application allows for multi-dimensional prediction and evaluation of planting costs, ease of cultivation, yield, and planting risks, providing citrus growers with planting technology guidance and risk assessment reports in advance, offering reliable analytical data support. Furthermore, by incorporating production environment information, the application allows for real-time correction of citrus growth status, thereby obtaining the harvest period and optimal harvest time. In addition, by using historical and current citrus sales prices, the application can predict short-term citrus prices and fluctuations, maximizing farmers' profits from citrus cultivation. Therefore, by comprehensively analyzing planting, benefits, yield, price, and varieties from pre-production, production, and post-production stages, the application provides farmers with more reliable recommendations.

[0036] It should be noted that, for the sake of simplicity, the aforementioned method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders.

[0037] like Figure 2 The diagram shown is a schematic diagram of a citrus variety planting recommendation device 200 provided in an embodiment of this application. The citrus variety planting recommendation device 200 is configured on a terminal device.

[0038] Specifically, the citrus variety planting recommendation device 200 may include:

[0039] The acquisition unit 201 is used to acquire planting data, including the planting location of citrus planting and production environment information related to harvest period and price;

[0040] The determining unit 202 is used to determine the output results of the multiple models based on the planting information and multiple models. The multiple models include a planting adaptability model, a citrus growth model, a price prediction model, and a production environment-related predictive analysis model. The output result of the planting adaptability model is the planting suitability of multiple citrus varieties. The output result of the citrus growth model is the harvest period and yield of the multiple citrus varieties. The output result of the price prediction model is the predicted price of the multiple citrus varieties. The output result of the production environment-related predictive analysis model is the optimal harvesting time and required agricultural operations for the multiple citrus varieties.

[0041] The fusion unit 203 is used to fuse the output results of the multiple models to obtain a recommendation result for planting the multiple varieties.

[0042] In some embodiments of this application, the fusion unit 203 can be specifically used to: obtain the weight of the output result of each model in the plurality of models; perform weighted processing on the output result of each model in the plurality of models using the corresponding weights, and concatenate the weighted results to obtain the recommendation result.

[0043] In some embodiments of this application, the aforementioned determining unit 202 may be specifically used to: determine key ecological factors based on the planting data, the key ecological factors including the light intensity, average annual temperature, precipitation, altitude, soil pH, soil organic matter, and soil of the planting location; input the key ecological factors into the planting adaptability model to obtain the planting suitability of the multiple citrus varieties.

[0044] In some embodiments of this application, the determining unit 202 can be specifically used to: determine the growth indicators of each of the plurality of varieties of citrus based on the planting information, wherein the growth indicators include the growth period, canopy width, chlorophyll content, flowering amount, and fruit yield of each of the plurality of varieties of citrus; input the growth indicators of each of the plurality of varieties of citrus into the citrus growth model of the corresponding variety to obtain the harvest period and yield of the corresponding variety of citrus.

[0045] In some embodiments of this application, the determining unit 202 may be specifically used to: determine the price factor of each of the plurality of varieties of citrus based on the planting information; input the price factor of each of the plurality of varieties of citrus into the price prediction model of the corresponding variety to obtain the predicted price of the corresponding variety of citrus.

[0046] In some embodiments of this application, the determining unit 202 can be specifically used to: determine the price fluctuation factor and harvest period factor for each of the plurality of varieties based on the planting information; input the price fluctuation factor and the harvest period factor into the production environment-related prediction and analysis model to obtain the optimal harvesting time and required agricultural operations for the plurality of citrus varieties.

[0047] In some embodiments of this application, the above-mentioned citrus variety planting recommendation device 200 may further include a training unit for: acquiring historical planting data; and training the plurality of models based on the historical planting data.

[0048] It should be noted that, for the sake of convenience and brevity, the specific working process of the above-mentioned citrus variety planting recommendation device 200 can be found by referring to... Figure 1 The corresponding process of the method will not be described in detail here.

[0049] like Figure 3The diagram shown is a schematic of a terminal device provided in an embodiment of this application. The terminal device 3 may include: a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the processor 30, such as a citrus variety planting recommendation program. When the processor 30 executes the computer program 32, it implements the steps in the above-described embodiments of the citrus variety planting recommendation methods, for example... Figure 1 Steps S101 to S103 are shown. Alternatively, when the processor 30 executes the computer program 32, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 2 The acquisition unit 201, determination unit 202, and fusion unit 203 are shown.

[0050] The computer program can be divided into one or more modules / units, which are stored in the memory 31 and executed by the processor 30 to complete this application. The one or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0051] For example, the computer program can be divided into: an acquisition unit, a determination unit, and a fusion unit.

[0052] The specific functions of each unit are as follows: The acquisition unit acquires planting data, including the planting location of citrus trees and production environment information related to harvest time and price; the determination unit determines the output results of multiple models based on the planting information and multiple models, including a planting adaptability model, a citrus growth model, a price prediction model, and a production environment-related predictive analysis model. The planting adaptability model outputs the suitability of planting multiple citrus varieties; the citrus growth model outputs the harvest time and yield of the multiple citrus varieties; the price prediction model outputs the predicted price of the multiple citrus varieties; and the production environment-related predictive analysis model outputs the optimal harvest time and required agricultural operations for the multiple citrus varieties; the fusion unit fuses the output results of the multiple models to obtain a recommendation result for planting the multiple varieties.

[0053] The terminal device may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will understand that... Figure 3 This is merely an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown, or combine certain components, or different components. For example, the terminal device may also include input / output devices, network access devices, buses, etc.

[0054] The processor 30 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0055] The memory 31 can be an internal storage unit of the terminal device, such as a hard drive or memory. The memory 31 can also be an external storage device of the terminal device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 31 can include both internal and external storage units. The memory 31 is used to store the computer program and other programs and data required by the terminal device. The memory 31 can also be used to temporarily store data that has been output or will be output.

[0056] It should be noted that, for the sake of convenience and brevity, the structure of the terminal device described above can also be referred to the specific description of the structure in the method embodiment, which will not be repeated here.

[0057] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0058] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0059] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for various specific applications, but such implementations should not be considered beyond the scope of this application.

[0060] In the embodiments provided in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0061] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0062] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0063] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0064] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for recommending planting of a citrus variety, characterized by, include: Obtain planting data, including planting location for citrus cultivation, and production environment information related to harvest time and price; Based on the planting information and multiple models, the output results of the multiple models are determined. The multiple models include a planting adaptability model, a citrus growth model, a price prediction model, and a production environment-related predictive analysis model. Each model is trained based on historical planting data. The output result of the planting adaptability model is the planting suitability of multiple citrus varieties. The output result of the citrus growth model is the harvest period and yield of the multiple citrus varieties. The output result of the price prediction model is the predicted price of the multiple citrus varieties. The output result of the production environment-related predictive analysis model is the optimal harvesting time and required agricultural operations for the multiple citrus varieties. Obtain the weight of the output result of each of the multiple models; The output of each of the multiple models is weighted according to its corresponding weight, and the weighted results are concatenated to obtain the recommendation result. The step of determining the output results of the multiple models based on the planting information includes: determining key ecological factors based on the planting data, wherein the key ecological factors include the light intensity, average annual temperature, precipitation, altitude, soil pH, soil organic matter, and soil conditions of the planting location; and inputting the key ecological factors into the planting adaptability model to obtain the planting suitability of the multiple citrus varieties. The step of determining the output results of the multiple models based on the planting information includes: determining the growth indicators of each citrus variety among the multiple varieties based on the planting information, wherein the growth indicators include the growth period, canopy width, chlorophyll content, flowering amount, and fruit yield of each citrus variety among the multiple varieties; and inputting the growth indicators of each citrus variety among the multiple varieties into the citrus growth model of the corresponding variety to obtain the harvest period and yield of the corresponding citrus variety. The step of determining the output results of the multiple models based on the planting information includes: determining the price factor of each citrus variety among the multiple varieties based on the planting information; inputting the price factor of each citrus variety among the multiple varieties into the price prediction model of the corresponding variety to obtain the predicted price of the corresponding citrus variety. The step of determining the output results of the multiple models based on the planting information includes: determining the price fluctuation factor and harvest period factor for each of the multiple varieties based on the planting information; inputting the price fluctuation factor and the harvest period factor into the production environment-related predictive analysis model to obtain the optimal harvesting time and required agricultural operations for the multiple varieties of citrus.

2. The citrus variety planting recommendation method according to claim 1, characterized by, Before determining the output results of the multiple models based on the planting information and the multiple models, the process includes: Obtain historical planting data; The multiple models were trained based on the historical planting data.

3. A citrus variety planting recommendation device characterized by comprising: include: The acquisition unit is used to acquire planting data, including planting location for citrus cultivation and production environment information related to harvest time and price. The determining unit is used to determine the output results of the multiple models based on the planting information and multiple models. The multiple models include a planting adaptability model, a citrus growth model, a price prediction model, and a production environment-related predictive analysis model. Each model is trained based on historical planting data. The output result of the planting adaptability model is the planting suitability of multiple citrus varieties. The output result of the citrus growth model is the harvest period and yield of the multiple citrus varieties. The output result of the price prediction model is the predicted price of the multiple citrus varieties. The output result of the production environment-related predictive analysis model is the optimal harvesting time and required agricultural operations for the multiple citrus varieties. The fusion unit is used to obtain the weights of the output results of each model in the plurality of models; the output results of each model in the plurality of models are weighted according to their corresponding weights, and the weighted results are concatenated to obtain the recommendation result; The determining unit is specifically used to: determine key ecological factors based on the planting data, the key ecological factors including the light intensity, average annual temperature, precipitation, altitude, soil pH, soil organic matter, and soil conditions of the planting location; and input the key ecological factors into the planting adaptability model to obtain the planting suitability of the multiple citrus varieties. Furthermore, based on the planting information, the growth indicators of each citrus variety among the multiple varieties are determined, including the growth period, canopy width, chlorophyll content, flowering amount, and fruit yield of each citrus variety among the multiple varieties; the growth indicators of each citrus variety among the multiple varieties are input into the citrus growth model of the corresponding variety to obtain the harvest period and yield of the corresponding citrus variety. Furthermore, based on the planting information, the price factor of each of the multiple varieties of citrus is determined; the price factor of each of the multiple varieties of citrus is input into the price prediction model of the corresponding variety to obtain the predicted price of the corresponding variety of citrus. Furthermore, based on the planting information, the price fluctuation factor and harvest period factor for each of the multiple varieties are determined; the price fluctuation factor and the harvest period factor are input into the production environment-related predictive analysis model to obtain the optimal harvesting time and required agricultural operations for the multiple varieties of citrus.

4. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the planting recommendation method for citrus varieties as described in claim 1 or 2.

5. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 4. When the computer program is executed by the processor, it implements the steps of the planting recommendation method for citrus varieties as described in claim 1 or 2.

Images