Intelligent crop management method and system

Abstract

The invention discloses an intelligent crop management method and system, and belongs to the technical field of crop management, and the method comprises the following steps: S1, collecting crop growth real-time data, processing the crop growth real-time data, and determining crop growth feature data; s2, training a crop growth prediction and evaluation model, performing test optimization on the crop growth prediction and evaluation model, and determining an optimal crop growth prediction and evaluation model; and S3, predicting and evaluating the crop growth characteristic data based on the optimal crop growth prediction and evaluation model. The problems that in the prior art, the crop growth process cannot be monitored in real time, the crop growth condition cannot be mastered, and the crop growth process cannot be intelligently managed in time, so that the crop management effect is poor are solved. The crop growth process can be monitored in real time, the crop growth condition can be mastered in time, the crop growth process can be intelligently managed in time, and the crop management effect can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of crop management, and in particular to an intelligent crop management method and system. Background Art

[0002] Crop management is a comprehensive agricultural practice that aims to optimize the crop growth environment, improve crop yield and quality, and protect soil and environmental resources through a series of measures. Traditional crop planting methods often rely on farmers' experience and skills and are easily affected by natural factors. With the advancement of science and technology, people's demand for agricultural production is also constantly upgrading, requiring more efficient, precise and environmentally friendly planting methods.

[0003] The existing methods cannot monitor the crop growth process in real time, cannot grasp the crop growth situation in time, and cannot intelligently manage the crop growth process in time, resulting in poor crop management effects. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent crop management method and system, which can monitor the crop growth process in real time, grasp the crop growth situation in time, and manage the crop growth process in time and intelligently, thereby improving the crop management effect and solving the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An intelligent crop management method comprises the following steps:

[0007] S1: Collect the temperature, humidity, nutrients and light conditions during the crop growth process, determine the real-time data of crop growth, process the real-time data of crop growth, and determine the characteristic data of crop growth;

[0008] S2: According to the needs of intelligent crop management, a crop growth prediction and evaluation model is trained, and the crop growth prediction and evaluation model is tested and optimized to determine the optimal crop growth prediction and evaluation model;

[0009] S3: Predict and evaluate crop growth characteristic data based on the optimal crop growth prediction and evaluation model, determine the crop growth prediction and evaluation results, and formulate an intelligent crop growth management plan to perform intelligent management of crop growth.

[0010] According to another aspect of the present invention, an intelligent crop management system is provided, which is used to implement the above-mentioned intelligent crop management method, comprising:

[0011] Data collection module, used to collect crop growth temperature, humidity, nutrients and light data, and determine the real-time crop growth data based on artificial intelligence;

[0012] A data processing module, used to process the real-time data of crop growth based on artificial intelligence and determine the characteristic data of crop growth based on artificial intelligence;

[0013] Model training module, used to build crop growth prediction and evaluation models based on intelligent crop management needs;

[0014] A test optimization module is used to test and optimize the crop growth prediction and evaluation model to determine the optimal crop growth prediction and evaluation model;

[0015] A prediction and evaluation module is used to predict and evaluate crop growth characteristic data based on artificial intelligence to determine crop growth prediction and evaluation results;

[0016] The intelligent management module is used to formulate intelligent management plans for crop growth and to carry out intelligent management of crop growth.

[0017] Preferably, the data acquisition module includes:

[0018] The temperature collection unit is used to monitor and collect the temperature conditions during the crop growth process in real time and obtain the crop growth temperature data;

[0019] The humidity collection unit is used to monitor and collect the humidity conditions during crop growth in real time and obtain crop growth humidity data;

[0020] Nutrient collection unit, used to monitor and collect the nutrient status of crops in real time during their growth process, and obtain nutrient data for crop growth;

[0021] Light collection unit, used to monitor and collect light conditions during crop growth in real time and obtain crop growth light data;

[0022] Among them, based on crop growth temperature data, humidity data, nutrient data and light data;

[0023] Determine real-time data on crop growth based on artificial intelligence.

[0024] Preferably, the data acquisition module further includes:

[0025] A bandwidth real-time acquisition module, used for real-time acquisition of the communication bandwidth of the current monitoring cycle between the data acquisition module and the data processing module; wherein the time length of the monitoring cycle ranges from 24h to 72h;

[0026] A communication bandwidth floating coefficient acquisition module, used to acquire the communication bandwidth floating coefficient according to the communication bandwidth of the current monitoring period between the data acquisition module and the data processing module at the end of the current monitoring period;

[0027] The communication bandwidth floating coefficient is obtained by the following formula:

[0028]

[0029] Where F represents the communication bandwidth floating coefficient; n represents the number of unit times contained in the current monitoring cycle; B f Indicates the standard deviation of the communication bandwidth change corresponding to the n unit time contained in the current monitoring cycle; B max and B min Indicates the maximum and minimum communication bandwidth corresponding to the n unit time contained in the current monitoring cycle; B e Indicates the preset minimum communication bandwidth value that satisfies communication; B z Indicates the median value of the communication bandwidth corresponding to the n unit time contained in the current monitoring cycle; B s Indicates the communication bandwidth value corresponding to the middle moment of the current monitoring cycle; B s Indicates the communication bandwidth value corresponding to the middle moment of the current monitoring cycle; B p Indicates the average value of the communication bandwidth corresponding to the middle moment of the current monitoring cycle; m indicates the number of unit times between the moment of the middle value of the communication bandwidth corresponding to the n unit times contained in the current monitoring cycle and the middle moment of the current monitoring cycle;

[0030] A comparison module, used for comparing the communication bandwidth floating coefficient with a preset floating coefficient threshold;

[0031] A first acquisition control module, configured to control the temperature acquisition unit, the humidity acquisition unit, the nutrient acquisition unit and the light acquisition unit to perform data acquisition in the next monitoring cycle according to the data acquisition frequency of the current monitoring cycle when the communication bandwidth floating coefficient is lower than the preset floating coefficient threshold;

[0032] The second acquisition control module is used to set the data acquisition frequency of the temperature acquisition unit, the humidity acquisition unit, the nutrient acquisition unit and the light acquisition unit in the next monitoring period when the communication bandwidth floating coefficient is not lower than the preset floating coefficient threshold.

[0033] Preferably, the execution process of the second acquisition control module includes:

[0034] When the communication bandwidth floating coefficient is not lower than the preset floating coefficient threshold, extracting the communication bandwidth floating coefficients of all the monitoring cycles except the current monitoring cycle as the first floating coefficient data;

[0035] Extracting the communication bandwidth floating coefficient of the current monitoring period as the second floating coefficient data;

[0036] Obtaining a data acquisition frequency adjustment coefficient using the first floating coefficient data and the second floating coefficient data;

[0037] The data acquisition frequency adjustment coefficient is obtained by the following formula:

[0038]

[0039] Wherein, f represents the data acquisition frequency adjustment coefficient; k represents the number of the first floating coefficient data; F 01i represents the coefficient value of the i-th first floating coefficient data; F 02 Indicates the coefficient value corresponding to the second floating coefficient data; F y Indicates the preset floating coefficient threshold;

[0040] The data acquisition frequency adjustment coefficient is used to obtain the data acquisition frequency of the next monitoring cycle corresponding to the temperature acquisition unit, the humidity acquisition unit, the nutrient acquisition unit and the light acquisition unit;

[0041] The data collection frequency of the next monitoring cycle corresponding to the temperature collection unit, humidity collection unit, nutrient collection unit and light collection unit is obtained by the following formula:

[0042]

[0043] Among them, W t represents the data collection frequency of the next monitoring cycle corresponding to the temperature collection unit, humidity collection unit, nutrient collection unit and light collection unit; f represents the data collection frequency adjustment coefficient; k represents the number of the first floating coefficient data; F 01i represents the coefficient value of the i-th first floating coefficient data; F y represents the preset floating coefficient threshold; W0 represents the data collection frequency of the current monitoring cycle corresponding to the temperature collection unit, humidity collection unit, nutrient collection unit and light collection unit; W min Indicates the minimum data collection frequency that the temperature collection unit, humidity collection unit, nutrient collection unit, and light collection unit have experienced.

[0044] Preferably, the data processing module includes:

[0045] Data cleaning unit, used to clean real-time crop growth data based on artificial intelligence;

[0046] Get real-time data on crop growth based on artificial intelligence;

[0047] Conduct consistency checks on AI-based real-time crop growth data;

[0048] According to the reasonable value range and mutual relationship of each parameter in the real-time crop growth data based on artificial intelligence, check whether the real-time crop growth data based on artificial intelligence meets the requirements;

[0049] Remove inconsistent data that is beyond the normal range, logically unreasonable or contradictory in the real-time crop growth data based on artificial intelligence;

[0050] Process invalid and missing values ​​in real-time crop growth data based on artificial intelligence;

[0051] Remove invalid and missing data that are of no value to intelligent crop management from real-time crop growth data based on artificial intelligence;

[0052] Identify real-time crop growth data that is valuable for intelligent crop management;

[0053] A feature extraction unit, used for extracting features from the real-time crop growth data after cleaning;

[0054] Obtain real-time crop growth data that is valuable for intelligent crop management;

[0055] Extract features from real-time crop growth data that are valuable for intelligent crop management;

[0056] Extract features that reflect intelligent crop management;

[0057] Determine artificial intelligence-based crop growth characteristic data.

[0058] Preferably, the model training module includes:

[0059] A data collection unit for collecting historical crop growth data;

[0060] Collect historical crop growth data based on the needs of intelligent crop management;

[0061] A model building unit, used to build a crop growth prediction and evaluation model;

[0062] Obtain historical crop growth data;

[0063] Divide the crop growth history data;

[0064] Determine the training data set and the test data set;

[0065] According to the needs of intelligent crop management, select a model framework suitable for intelligent crop management;

[0066] Based on the training data set, the selected model framework suitable for intelligent crop management is trained;

[0067] Determine the crop growth prediction and evaluation model.

[0068] Preferably, the test optimization module includes:

[0069] A test and evaluation unit, used for testing and evaluating the crop growth prediction and evaluation model;

[0070] Obtain crop growth prediction and assessment models;

[0071] Based on the test data set, the crop growth prediction and evaluation model is tested and evaluated;

[0072] Determine the test evaluation results based on the crop growth prediction evaluation model;

[0073] An adjustment and optimization unit, used to adjust and optimize the crop growth prediction and evaluation model;

[0074] Obtain test evaluation results based on crop growth prediction and evaluation models;

[0075] Conduct mining and analysis on the test evaluation results based on the crop growth prediction and evaluation model;

[0076] Determine the parameter adjustment optimization scheme based on the crop growth prediction and evaluation model;

[0077] Adjust and optimize the crop growth prediction and evaluation model according to a parameter adjustment optimization scheme based on the crop growth prediction and evaluation model;

[0078] Determine the optimal crop growth prediction and evaluation model.

[0079] Preferably, the prediction and evaluation module includes:

[0080] A data extraction unit, used for extracting crop growth characteristic data based on artificial intelligence;

[0081] Extract AI-based crop growth characteristic data according to the needs of intelligent crop management;

[0082] A prediction and evaluation unit, used to predict and evaluate crop growth characteristic data based on artificial intelligence;

[0083] Obtain the optimal crop growth prediction and evaluation model;

[0084] Input the extracted AI-based crop growth characteristic data into the optimal crop growth prediction and evaluation model;

[0085] Predict and evaluate crop growth characteristic data based on artificial intelligence based on the optimal crop growth prediction and evaluation model;

[0086] Determine the crop growth forecast assessment results;

[0087] Among them, the crop growth prediction and evaluation results include normal crop growth and abnormal crop growth.

[0088] Preferably, the intelligent management module includes:

[0089] Strategy formulation unit, used to formulate intelligent management plans for crop growth;

[0090] Obtain crop growth forecast assessment results;

[0091] Based on the crop growth prediction and evaluation results, the crop growth characteristic data is mined and analyzed;

[0092] When crop growth is abnormal, formulate intelligent crop growth management plans in time;

[0093] Intelligent management unit for intelligent management of crop growth;

[0094] Obtain intelligent management solutions for crop growth;

[0095] Intelligent management of crop growth based on intelligent crop growth management solutions, including:

[0096] Timely warnings are given for abnormal crop growth conditions, and the warning information is transmitted to crop management personnel in real time. Fertilization and irrigation plans for crop growth are automatically adjusted according to the actual crop growth conditions, and the amount of fertilization and irrigation is accurately controlled to achieve the best growth effect for crops.

[0097] Compared with the prior art, the present invention has the following beneficial effects:

[0098] The present invention determines real-time crop growth data by collecting temperature, humidity, nutrients and light conditions during crop growth, processes the real-time crop growth data, determines crop growth characteristic data, trains a crop growth prediction and evaluation model according to intelligent crop management needs, tests and optimizes the crop growth prediction and evaluation model, determines the optimal crop growth prediction and evaluation model, predicts and evaluates the crop growth characteristic data based on the optimal crop growth prediction and evaluation model, determines the crop growth prediction and evaluation results, formulates an intelligent crop growth management plan, performs intelligent management of crop growth, can monitor the crop growth process in real time, can timely grasp the crop growth situation, can timely perform intelligent management of the crop growth process, and can improve the crop management effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0099] Figure 1 is a flow chart of the intelligent crop management method of the present invention;

[0100] Figure 2 It is a module block diagram of the intelligent crop management system of the present invention. DETAILED DESCRIPTION

[0101] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0102] In order to solve the existing problems of not being able to monitor the crop growth process in real time, not being able to grasp the crop growth situation in time, and not being able to manage the crop growth process in time and intelligently, resulting in poor crop management results, please refer to Figure 1-Figure 2 , this embodiment provides the following technical solutions:

[0103] An intelligent crop management system comprises: a data collection module, a data processing module, a model training module, a test optimization module, a prediction and evaluation module and an intelligent management module.

[0104] It should be noted that through the interactive communication between the data acquisition module, the data processing module, the model training module, the test optimization module, the prediction and evaluation module and the intelligent management module, the crop growth process can be monitored in real time, the crop growth situation can be grasped in time, and the crop growth process can be managed intelligently in time, which can improve the crop management effect.

[0105] Among them, the data acquisition module is used to collect crop growth temperature, humidity, nutrients and light data, and determine the real-time crop growth data based on artificial intelligence;

[0106] In this embodiment, the data acquisition module includes:

[0107] The temperature collection unit is used to monitor and collect the temperature conditions during the crop growth process in real time and obtain the crop growth temperature data;

[0108] The humidity collection unit is used to monitor and collect the humidity conditions during crop growth in real time and obtain crop growth humidity data;

[0109] Nutrient collection unit, used to monitor and collect the nutrient status of crops in real time during their growth process, and obtain nutrient data for crop growth;

[0110] Light collection unit, used to monitor and collect light conditions during crop growth in real time and obtain crop growth light data;

[0111] Among them, based on crop growth temperature data, humidity data, nutrient data and light data;

[0112] Determine real-time data on crop growth based on artificial intelligence.

[0113] Specifically, the data acquisition module further includes:

[0114] A bandwidth real-time acquisition module, used for real-time acquisition of the communication bandwidth of the current monitoring cycle between the data acquisition module and the data processing module; wherein the time length of the monitoring cycle ranges from 24h to 72h;

[0115] A communication bandwidth floating coefficient acquisition module, used to acquire the communication bandwidth floating coefficient according to the communication bandwidth of the current monitoring period between the data acquisition module and the data processing module at the end of the current monitoring period;

[0116] The communication bandwidth floating coefficient is obtained by the following formula:

[0117]

[0118] Where F represents the communication bandwidth floating coefficient; n represents the number of unit times contained in the current monitoring cycle; B f Indicates the standard deviation of the communication bandwidth change corresponding to the n unit time contained in the current monitoring cycle; B max and B min Indicates the maximum and minimum communication bandwidth corresponding to the n unit time contained in the current monitoring cycle; B e Indicates the preset minimum communication bandwidth value that satisfies communication; B z Indicates the median value of the communication bandwidth corresponding to the n unit time contained in the current monitoring cycle; Bs Indicates the communication bandwidth value corresponding to the middle moment of the current monitoring cycle; B s Indicates the communication bandwidth value corresponding to the middle moment of the current monitoring cycle; B p Indicates the average value of the communication bandwidth corresponding to the middle moment of the current monitoring cycle; m indicates the number of unit times between the moment of the middle value of the communication bandwidth corresponding to the n unit times contained in the current monitoring cycle and the middle moment of the current monitoring cycle;

[0119] A comparison module, used for comparing the communication bandwidth floating coefficient with a preset floating coefficient threshold;

[0120] A first acquisition control module, configured to control the temperature acquisition unit, the humidity acquisition unit, the nutrient acquisition unit and the light acquisition unit to perform data acquisition in the next monitoring cycle according to the data acquisition frequency of the current monitoring cycle when the communication bandwidth floating coefficient is lower than the preset floating coefficient threshold;

[0121] The second acquisition control module is used to set the data acquisition frequency of the temperature acquisition unit, the humidity acquisition unit, the nutrient acquisition unit and the light acquisition unit in the next monitoring period when the communication bandwidth floating coefficient is not lower than the preset floating coefficient threshold.

[0122] The technical effect of the above technical solution is: through the bandwidth real-time acquisition module, the communication bandwidth between the data acquisition module and the data processing module can be monitored in real time to ensure that the system can understand the current communication status in a timely manner. This real-time monitoring provides basic data support for subsequent dynamic adjustments. The introduction of the communication bandwidth floating coefficient and its calculation method comprehensively consider multiple aspects of the communication bandwidth (such as standard deviation, maximum value, minimum value, median value, average value and time interval), so that the coefficient can more comprehensively reflect the volatility and stability of the communication bandwidth. By comparing this coefficient with the preset floating coefficient threshold, the system can intelligently determine whether the current communication bandwidth meets the requirements of efficient data transmission.

[0123] When the communication bandwidth floating coefficient is lower than the preset threshold, it indicates that the current communication bandwidth is relatively stable and sufficient to support the current data collection frequency. At this time, the system keeps the original collection frequency unchanged, avoiding unnecessary adjustments and waste of resources. When the communication bandwidth floating coefficient is not lower than the preset threshold, the system will set the data collection frequency for the next monitoring cycle to adapt to possible bandwidth fluctuations and ensure the stability and efficiency of data transmission. This solution allows the data collection frequency to be adjusted dynamically according to the actual communication conditions, enhancing the flexibility and adaptability of the system. In addition, by adjusting the preset floating coefficient threshold and other related parameters, the system can be further optimized to adapt to different application scenarios and requirements, with good scalability. Through real-time monitoring and intelligent adjustment of data collection frequency, this solution helps to reduce data loss or delay caused by communication problems, thereby improving user experience and data quality. At the same time, stable communication bandwidth also helps to improve the reliability and accuracy of data transmission.

[0124] In summary, this technical solution achieves efficient utilization of communication bandwidth and optimal allocation of resources through real-time monitoring and intelligent adjustment of data collection frequency, thereby improving the overall performance of the system and user experience.

[0125] Specifically, the execution process of the second acquisition control module includes:

[0126] When the communication bandwidth floating coefficient is not lower than the preset floating coefficient threshold, extracting the communication bandwidth floating coefficients of all the monitoring cycles except the current monitoring cycle as the first floating coefficient data;

[0127] Extracting the communication bandwidth floating coefficient of the current monitoring period as the second floating coefficient data;

[0128] Obtaining a data acquisition frequency adjustment coefficient using the first floating coefficient data and the second floating coefficient data;

[0129] The data acquisition frequency adjustment coefficient is obtained by the following formula:

[0130]

[0131] Wherein, f represents the data acquisition frequency adjustment coefficient; k represents the number of the first floating coefficient data; F 01i represents the coefficient value of the i-th first floating coefficient data; F 02 Indicates the coefficient value corresponding to the second floating coefficient data; F y Indicates the preset floating coefficient threshold;

[0132] The data acquisition frequency adjustment coefficient is used to obtain the data acquisition frequency of the next monitoring cycle corresponding to the temperature acquisition unit, the humidity acquisition unit, the nutrient acquisition unit and the light acquisition unit;

[0133] The data collection frequency of the next monitoring cycle corresponding to the temperature collection unit, humidity collection unit, nutrient collection unit and light collection unit is obtained by the following formula:

[0134]

[0135] Among them, W t represents the data collection frequency of the next monitoring cycle corresponding to the temperature collection unit, humidity collection unit, nutrient collection unit and light collection unit; f represents the data collection frequency adjustment coefficient; k represents the number of the first floating coefficient data; F 01i represents the coefficient value of the i-th first floating coefficient data; F y represents the preset floating coefficient threshold; W0 represents the data collection frequency of the current monitoring cycle corresponding to the temperature collection unit, humidity collection unit, nutrient collection unit and light collection unit; W min Indicates the minimum data collection frequency that the temperature collection unit, humidity collection unit, nutrient collection unit, and light collection unit have experienced.

[0136] The technical effect of the above technical solution is: the solution not only takes into account the communication bandwidth floating coefficient (second floating coefficient data) of the current monitoring cycle, but also reviews the communication bandwidth floating coefficient (first floating coefficient data) of all previous monitoring cycles, so as to more comprehensively evaluate the historical change trend of the communication bandwidth. This intelligent adjustment method based on historical data enables the system to more accurately predict future communication conditions and make reasonable adjustments to the data acquisition frequency accordingly. By introducing the data acquisition frequency adjustment coefficient (f), the solution realizes dynamic optimization of the data acquisition frequency. When the communication bandwidth fluctuates greatly (that is, the communication bandwidth floating coefficient is not lower than the preset threshold), the system will calculate a suitable adjustment coefficient based on historical data and current data, and adjust the data acquisition frequency of the next monitoring cycle accordingly. This dynamic optimization helps to minimize data transmission delays and waste of bandwidth resources while ensuring data quality.

[0137] When adjusting the data acquisition frequency, the scheme also takes into account the minimum data acquisition frequency (Wmin) that the temperature acquisition unit, humidity acquisition unit, nutrient acquisition unit, and light acquisition unit have experienced. This measure ensures the stability and continuity of data acquisition and avoids data loss or interruption caused by excessive frequency adjustment. By real-time monitoring of the communication bandwidth and dynamically adjusting the data acquisition frequency, the scheme can effectively improve the overall performance of the system. On the one hand, it reduces data transmission delays and errors caused by insufficient communication bandwidth; on the other hand, it also avoids resource waste and increased system burden caused by excessive data acquisition frequency. The scheme enables the system to automatically adjust the data acquisition frequency according to the actual situation of the communication bandwidth, thereby enhancing the system's adaptive ability. This adaptive ability enables the system to better cope with various complex and changing environmental conditions, maintain a stable operating state and high data acquisition efficiency.

[0138] In summary, this technical solution achieves efficient utilization of communication bandwidth and optimal allocation of resources through intelligent adjustment based on historical data and dynamic optimization of data collection frequency, thereby improving the overall performance of the system and user experience.

[0139] Among them, the data processing module is used to process the real-time data of crop growth based on artificial intelligence and determine the characteristic data of crop growth based on artificial intelligence;

[0140] In this embodiment, the data processing module includes:

[0141] Data cleaning unit, used to clean real-time crop growth data based on artificial intelligence;

[0142] Get real-time data on crop growth based on artificial intelligence;

[0143] Conduct consistency checks on AI-based real-time crop growth data;

[0144] According to the reasonable value range and mutual relationship of each parameter in the real-time crop growth data based on artificial intelligence, check whether the real-time crop growth data based on artificial intelligence meets the requirements;

[0145] Remove inconsistent data that is beyond the normal range, logically unreasonable or contradictory in the real-time crop growth data based on artificial intelligence;

[0146] Process invalid and missing values ​​in real-time crop growth data based on artificial intelligence;

[0147] Remove invalid and missing data that are of no value to intelligent crop management from real-time crop growth data based on artificial intelligence;

[0148] Identify real-time crop growth data that is valuable for intelligent crop management;

[0149] A feature extraction unit, used for extracting features from the real-time crop growth data after cleaning;

[0150] Obtain real-time crop growth data that is valuable for intelligent crop management;

[0151] Extract features from real-time crop growth data that are valuable for intelligent crop management;

[0152] Extract features that reflect intelligent crop management;

[0153] Determine artificial intelligence-based crop growth characteristic data.

[0154] Among them, the model training module is used to build a crop growth prediction and evaluation model based on the needs of intelligent crop management;

[0155] In this embodiment, the model training module includes:

[0156] A data collection unit for collecting historical crop growth data;

[0157] Collect historical crop growth data based on the needs of intelligent crop management;

[0158] A model building unit, used to build a crop growth prediction and evaluation model;

[0159] Obtain historical crop growth data;

[0160] Divide the crop growth history data;

[0161] Determine the training data set and the test data set;

[0162] According to the needs of intelligent crop management, select a model framework suitable for intelligent crop management;

[0163] Based on the training data set, the selected model framework suitable for intelligent crop management is trained;

[0164] Determine the crop growth prediction and evaluation model.

[0165] Among them, the test optimization module is used to test and optimize the crop growth prediction and evaluation model to determine the optimal crop growth prediction and evaluation model;

[0166] In this embodiment, the test optimization module includes:

[0167] A test and evaluation unit, used for testing and evaluating the crop growth prediction and evaluation model;

[0168] Obtain crop growth prediction and assessment models;

[0169] Based on the test data set, the crop growth prediction and evaluation model is tested and evaluated;

[0170] Determine the test evaluation results based on the crop growth prediction evaluation model;

[0171] An adjustment and optimization unit, used to adjust and optimize the crop growth prediction and evaluation model;

[0172] Obtain test evaluation results based on crop growth prediction and evaluation models;

[0173] Conduct mining and analysis on the test evaluation results based on the crop growth prediction and evaluation model;

[0174] Determine the parameter adjustment optimization scheme based on the crop growth prediction and evaluation model;

[0175] Adjust and optimize the crop growth prediction and evaluation model according to a parameter adjustment optimization scheme based on the crop growth prediction and evaluation model;

[0176] Determine the optimal crop growth prediction and evaluation model.

[0177] Among them, the prediction and evaluation module is used to predict and evaluate the crop growth characteristic data based on artificial intelligence to determine the crop growth prediction and evaluation results;

[0178] In this embodiment, the prediction and evaluation module includes:

[0179] A data extraction unit, used for extracting crop growth characteristic data based on artificial intelligence;

[0180] Extract AI-based crop growth characteristic data according to the needs of intelligent crop management;

[0181] A prediction and evaluation unit, used to predict and evaluate crop growth characteristic data based on artificial intelligence;

[0182] Obtain the optimal crop growth prediction and evaluation model;

[0183] Input the extracted AI-based crop growth characteristic data into the optimal crop growth prediction and evaluation model;

[0184] Predict and evaluate crop growth characteristic data based on artificial intelligence based on the optimal crop growth prediction and evaluation model;

[0185] Determine the crop growth forecast assessment results;

[0186] Among them, the crop growth prediction and evaluation results include normal crop growth and abnormal crop growth.

[0187] Among them, the intelligent management module is used to formulate intelligent management plans for crop growth and to carry out intelligent management of crop growth.

[0188] In this embodiment, the intelligent management module includes:

[0189] Strategy formulation unit, used to formulate intelligent management plans for crop growth;

[0190] Obtain crop growth forecast assessment results;

[0191] Based on the crop growth prediction and evaluation results, the crop growth characteristic data is mined and analyzed;

[0192] When crop growth is abnormal, formulate intelligent crop growth management plans in time;

[0193] Intelligent management unit for intelligent management of crop growth;

[0194] Obtain intelligent management solutions for crop growth;

[0195] Intelligent management of crop growth based on intelligent crop growth management solutions, including:

[0196] Timely warnings are given for abnormal crop growth conditions, and the warning information is transmitted to crop management personnel in real time. Fertilization and irrigation plans for crop growth are automatically adjusted according to the actual crop growth conditions, and the amount of fertilization and irrigation is accurately controlled to achieve the best growth effect for crops.

[0197] Therefore, based on the optimal crop growth prediction and evaluation model, the crop growth characteristic data is predicted and evaluated, the crop growth prediction and evaluation results are determined, and an intelligent crop growth management plan is formulated to manage crop growth intelligently. The crop growth process can be monitored in real time, the crop growth situation can be grasped in time, and the crop growth process can be managed intelligently in time, which can improve the crop management effect.

[0198] In order to better demonstrate the intelligent crop management process, this embodiment now provides an intelligent crop management method, which is implemented based on the above-mentioned intelligent crop management system and includes the following steps:

[0199] S1: Collect the temperature, humidity, nutrients and light conditions during the crop growth process, determine the real-time data of crop growth, process the real-time data of crop growth, and determine the characteristic data of crop growth;

[0200] S2: According to the needs of intelligent crop management, a crop growth prediction and evaluation model is trained, and the crop growth prediction and evaluation model is tested and optimized to determine the optimal crop growth prediction and evaluation model;

[0201] S3: Predict and evaluate crop growth characteristic data based on the optimal crop growth prediction and evaluation model, determine the crop growth prediction and evaluation results, and formulate an intelligent crop growth management plan to perform intelligent management of crop growth.

[0202] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0203] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent crop management method, characterized in that: The steps include: S1: Collect the temperature, humidity, nutrients and light conditions during the crop growth process, determine the real-time data of crop growth, process the real-time data of crop growth, and determine the characteristic data of crop growth; S2: According to the needs of intelligent crop management, a crop growth prediction and evaluation model is trained, and the crop growth prediction and evaluation model is tested and optimized to determine the optimal crop growth prediction and evaluation model; S3: Predict and evaluate crop growth characteristic data based on the optimal crop growth prediction and evaluation model, determine the crop growth prediction and evaluation results, and formulate an intelligent crop growth management plan to perform intelligent management of crop growth.

2. An intelligent crop management system, used to implement the intelligent crop management method according to claim 1, characterized in that: include: Data collection module, used to collect crop growth temperature, humidity, nutrients and light data, and determine the real-time crop growth data based on artificial intelligence; A data processing module, used to process the real-time data of crop growth based on artificial intelligence and determine the characteristic data of crop growth based on artificial intelligence; Model training module, used to build crop growth prediction and evaluation models based on intelligent crop management needs; A test optimization module is used to test and optimize the crop growth prediction and evaluation model to determine the optimal crop growth prediction and evaluation model; A prediction and evaluation module is used to predict and evaluate crop growth characteristic data based on artificial intelligence to determine crop growth prediction and evaluation results; The intelligent management module is used to formulate intelligent management plans for crop growth and to carry out intelligent management of crop growth.

3. An intelligent crop management system according to claim 2, characterized in that: The data acquisition module comprises: The temperature collection unit is used to monitor and collect the temperature conditions during the crop growth process in real time and obtain the crop growth temperature data; The humidity collection unit is used to monitor and collect the humidity conditions during crop growth in real time and obtain crop growth humidity data; Nutrient collection unit, used to monitor and collect the nutrient status of crops in real time during their growth process, and obtain nutrient data for crop growth; Light collection unit, used to monitor and collect light conditions during crop growth in real time and obtain crop growth light data; Among them, based on crop growth temperature data, humidity data, nutrient data and light data; Determine real-time data on crop growth based on artificial intelligence.

4. The intelligent crop management system according to claim 3, characterized in that: The data acquisition module further includes: A bandwidth real-time acquisition module, used for real-time acquisition of the communication bandwidth of the current monitoring period between the data acquisition module and the data processing module; wherein the time length of the monitoring period ranges from 24h to 72h; A communication bandwidth floating coefficient acquisition module, used to acquire the communication bandwidth floating coefficient according to the communication bandwidth of the current monitoring period between the data acquisition module and the data processing module at the end of the current monitoring period; The communication bandwidth floating coefficient is obtained by the following formula: Where F represents the communication bandwidth floating coefficient; n represents the number of unit times contained in the current monitoring cycle; B f Indicates the standard deviation of the communication bandwidth change corresponding to the n unit time contained in the current monitoring cycle; B max and B min Indicates the maximum and minimum communication bandwidth corresponding to the n unit time contained in the current monitoring cycle; B e Indicates the preset minimum communication bandwidth value that satisfies communication; B z Indicates the median value of the communication bandwidth corresponding to the n unit time contained in the current monitoring cycle; B s Indicates the communication bandwidth value corresponding to the middle moment of the current monitoring cycle; B s Indicates the communication bandwidth value corresponding to the middle moment of the current monitoring cycle; B p Indicates the average value of the communication bandwidth corresponding to the middle moment of the current monitoring cycle; m indicates the number of unit times between the moment of the middle value of the communication bandwidth corresponding to the n unit times contained in the current monitoring cycle and the middle moment of the current monitoring cycle; A comparison module, used for comparing the communication bandwidth floating coefficient with a preset floating coefficient threshold; A first acquisition control module, configured to control the temperature acquisition unit, the humidity acquisition unit, the nutrient acquisition unit and the light acquisition unit to perform data acquisition in the next monitoring cycle according to the data acquisition frequency of the current monitoring cycle when the communication bandwidth floating coefficient is lower than the preset floating coefficient threshold; The second acquisition control module is used to set the data acquisition frequency of the temperature acquisition unit, the humidity acquisition unit, the nutrient acquisition unit and the light acquisition unit in the next monitoring period when the communication bandwidth floating coefficient is not lower than the preset floating coefficient threshold.

5. An intelligent crop management system according to claim 4, characterized in that: The execution process of the second acquisition control module includes: When the communication bandwidth floating coefficient is not lower than the preset floating coefficient threshold, extracting the communication bandwidth floating coefficients of all the monitoring cycles except the current monitoring cycle as the first floating coefficient data; Extracting the communication bandwidth floating coefficient of the current monitoring period as the second floating coefficient data; Obtaining a data acquisition frequency adjustment coefficient using the first floating coefficient data and the second floating coefficient data; The data acquisition frequency adjustment coefficient is obtained by the following formula: Wherein, f represents the data acquisition frequency adjustment coefficient; k represents the number of the first floating coefficient data; F 01i represents the coefficient value of the i-th first floating coefficient data; F 02 Indicates the coefficient value corresponding to the second floating coefficient data; F y Indicates the preset floating coefficient threshold; The data acquisition frequency adjustment coefficient is used to obtain the data acquisition frequency of the next monitoring cycle corresponding to the temperature acquisition unit, the humidity acquisition unit, the nutrient acquisition unit and the light acquisition unit; The data collection frequency of the next monitoring cycle corresponding to the temperature collection unit, humidity collection unit, nutrient collection unit and light collection unit is obtained by the following formula: Among them, W t represents the data collection frequency of the next monitoring cycle corresponding to the temperature collection unit, humidity collection unit, nutrient collection unit and light collection unit; f represents the data collection frequency adjustment coefficient; k represents the number of the first floating coefficient data; F 01i represents the coefficient value of the i-th first floating coefficient data; F y represents the preset floating coefficient threshold; W0 represents the data collection frequency of the current monitoring cycle corresponding to the temperature collection unit, humidity collection unit, nutrient collection unit and light collection unit; W min Indicates the minimum data collection frequency that the temperature collection unit, humidity collection unit, nutrient collection unit, and light collection unit have experienced.

6. The intelligent crop management system according to claim 3, characterized in that: The data processing module comprises: Data cleaning unit, used to clean real-time crop growth data based on artificial intelligence; Get real-time data on crop growth based on artificial intelligence; Conduct consistency checks on AI-based real-time crop growth data; According to the reasonable value range and mutual relationship of each parameter in the real-time crop growth data based on artificial intelligence, check whether the real-time crop growth data based on artificial intelligence meets the requirements; Remove inconsistent data that is beyond the normal range, logically unreasonable or contradictory in the real-time crop growth data based on artificial intelligence; Process invalid and missing values ​​in real-time crop growth data based on artificial intelligence; Remove invalid and missing data that are of no value to intelligent crop management from real-time crop growth data based on artificial intelligence; Identify real-time crop growth data that is valuable for intelligent crop management; A feature extraction unit, used for extracting features from the real-time crop growth data after cleaning; Obtain real-time crop growth data that is valuable for intelligent crop management; Extract features from real-time crop growth data that are valuable for intelligent crop management; Extract features that reflect intelligent crop management; Determine artificial intelligence-based crop growth characteristic data.

7. An intelligent crop management system according to claim 6, characterized in that: The model training module includes: A data collection unit for collecting historical crop growth data; Collect historical crop growth data based on the needs of intelligent crop management; A model building unit, used to build a crop growth prediction and evaluation model; Obtain historical crop growth data; Divide the crop growth history data; Determine the training data set and the test data set; According to the needs of intelligent crop management, select a model framework suitable for intelligent crop management; Based on the training data set, the selected model framework suitable for intelligent crop management is trained; Determine the crop growth prediction and evaluation model.

8. An intelligent crop management system according to claim 7, characterized in that: The test optimization module includes: A test and evaluation unit, used for testing and evaluating the crop growth prediction and evaluation model; Obtain crop growth prediction and assessment models; Based on the test data set, the crop growth prediction and evaluation model is tested and evaluated; Determine the test evaluation results based on the crop growth prediction evaluation model; An adjustment and optimization unit, used to adjust and optimize the crop growth prediction and evaluation model; Obtain test evaluation results based on crop growth prediction and evaluation models; Conduct mining and analysis on the test evaluation results based on the crop growth prediction and evaluation model; Determine the parameter adjustment optimization scheme based on the crop growth prediction and evaluation model; Adjust and optimize the crop growth prediction and evaluation model according to a parameter adjustment optimization scheme based on the crop growth prediction and evaluation model; Determine the optimal crop growth prediction and evaluation model.

9. An intelligent crop management system according to claim 8, characterized in that: The prediction and evaluation module comprises: A data extraction unit, used for extracting crop growth characteristic data based on artificial intelligence; Extract AI-based crop growth characteristic data according to the needs of intelligent crop management; A prediction and evaluation unit, used to predict and evaluate crop growth characteristic data based on artificial intelligence; Obtain the optimal crop growth prediction and evaluation model; Input the extracted AI-based crop growth characteristic data into the optimal crop growth prediction and evaluation model; Predict and evaluate crop growth characteristic data based on artificial intelligence based on the optimal crop growth prediction and evaluation model; Determine the crop growth forecast assessment results; Among them, the crop growth prediction and evaluation results include normal crop growth and abnormal crop growth.

10. An intelligent crop management system according to claim 9, characterized in that: The intelligent management module comprises: Strategy formulation unit, used to formulate intelligent management plans for crop growth; Obtain crop growth forecast assessment results; Based on the crop growth prediction and evaluation results, the crop growth characteristic data is mined and analyzed; When crop growth is abnormal, formulate intelligent crop growth management plans in time; Intelligent management unit for intelligent management of crop growth; Obtain intelligent management solutions for crop growth; Intelligent management of crop growth based on intelligent crop growth management solutions, including: Timely warnings are given for abnormal crop growth conditions, and the warning information is transmitted to crop management personnel in real time. The fertilization and irrigation plans for crop growth are automatically adjusted according to the actual crop growth conditions, and the amount of fertilization and irrigation is accurately controlled to achieve the best growth effect for crops.

Images