Wheat culture method based on big data analysis

Abstract

The invention discloses a wheat cultivation method based on big data analysis, and belongs to the technical field of wheat cultivation.The method comprises the steps that a platform side is established by a platform side, and a user registers and logs in on the platform side; a user determines planted wheat seeds and corresponding planting requirements through the platform end; wheat seeds of all the users are planted, the planting area where wheat is planted is monitored in real time, corresponding monitoring data are obtained, and the monitoring data are dynamically displayed to the corresponding users through the platform end; determining a cultivation scheme of wheat in the corresponding planting area according to the monitoring data and planting requirements; wheat in the planting area is cultured according to the culture scheme; by establishing the platform end, the whole wheat planting process from seed selection to harvesting is visualized and traceable, the trust degree of consumers on wheat products is enhanced, and the transparency of food safety is improved. Consumers can clearly know the source, the planting mode and the quality control condition of wheat eaten by themselves, and therefore the consumers can eat the wheat at ease.

Description

Technical Field

[0001] The invention belongs to the technical field of wheat cultivation, and specifically relates to a wheat cultivation method based on big data analysis. Background Art

[0002] As people's living standards improve, food safety issues are increasingly receiving widespread public attention. Consumers have put forward higher requirements for food quality, safety and health value, especially for crops that are the basis of many food raw materials, such as wheat. Its planting process, quality control and health impact have become the focus of attention. Traditional wheat planting methods often lack transparency, and it is difficult for consumers to understand the entire process of wheat from planting to harvesting, which to a certain extent affects consumers' trust in food safety.

[0003] In order to meet this challenge and satisfy consumers' demand for healthy and safe wheat products, it is particularly important to establish a wheat cultivation method based on big data analysis. Summary of the invention

[0004] In order to solve the problems existing in the above-mentioned scheme, the present invention provides a wheat cultivation method based on big data analysis.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A wheat cultivation method based on big data analysis, the method comprising:

[0007] Step 1: The platform establishes the platform end, and the user registers and logs in on the platform end; the user determines the wheat seeds to be planted and the corresponding planting requirements through the platform end.

[0008] Further, the method for determining wheat seeds includes:

[0009] The platform selects each to-be-selected seed; sets a seed information template, collects information of each to-be-selected seed according to the seed information template, and obtains seed information of each to-be-selected seed; summarizes the seed information and establishes a seed information database;

[0010] A demand unit is provided, wherein the demand unit is used for a user to input a planting demand; the user inputs a planting demand for wheat through the demand unit; and the planting demand of the user is identified;

[0011] A matching model is established based on the seed information database, and the planting requirements are analyzed through the matching model to obtain various sub-matching information. Each seed matching information is displayed to the user, and the user selects the wheat seeds to be planted.

[0012] Furthermore, a display column is provided in the demand unit, and the display column is used for information display, and each recommended information is dynamically displayed in the display column.

[0013] Furthermore, the expression of the matching model is:

[0014]

[0015] In the formula: (ZA, BAi) is the input data, ZA is the planting requirement, BAi is the corresponding seed information in the seed information database, i = 1, 2, ..., n, n is a positive integer; the output data is the matching value PM (ZA, BAi), and the matching value is 1 or 0.

[0016] Step 2: Plant the wheat seeds of each user, and monitor the planting area of ​​wheat in real time to obtain corresponding monitoring data, and dynamically display the monitoring data to the corresponding users through the platform.

[0017] Furthermore, the method for planting wheat seeds of each user includes:

[0018] Acquire a planting area map, wherein the planting area map is composed of various planting areas, and the planting areas are marked with corresponding area information;

[0019] Identify wheat seed information and planting requirements of each user, classify each user according to the wheat seed information and planting requirements, and obtain classification of each user;

[0020] The classification of each user is analyzed according to each planting area in the planting area map, the planting area of ​​each user's wheat seeds is determined, and each wheat seed is planted according to the corresponding planting area.

[0021] Further, the method for analyzing each user classification according to each planting area in the planting area map includes:

[0022] Identify the regional information of each planting area and the wheat seed information classified by each user, and determine the planting areas corresponding to each user classification according to the regional information and the wheat seed information;

[0023] Determine the planting area corresponding to each user in the user classification, perform simulated planting according to each planting area and planting region, and obtain each planting method to be selected;

[0024] Evaluate each candidate planting method and determine the corresponding management value and experience value;

[0025] Calculate the corresponding mode value according to the formula PA = b1 × GZ + b2 × TZ;

[0026] Where: PA is the mode value; b1 and b2 are both proportionality coefficients, and the value ranges are 0 < b1 ≤ 1, 0 < b2 ≤ 1; GZ is the management value; TZ is the experience value;

[0027] Select the candidate planting mode with the highest mode value as the target planting mode, and determine the planting areas of wheat seeds for each user according to the target planting mode.

[0028] Step 3: Determine the cultivation plan for the wheat in the corresponding planting area according to the monitoring data and planting requirements.

[0029] Furthermore, the method for determining the cultivation plan includes:

[0030] Connect to the seed information database, identify various wheat seeds, and mark them as analysis targets; obtain the historical cultivation data of each of the analysis targets, and process the historical cultivation data to obtain target material data;

[0031] Extract features from the target material data to obtain groups of material feature data, analyze each group of material feature data to determine the corresponding quality prediction values for each group of material feature data, and supplement the quality prediction values to the material feature data; establish a wheat growth analysis model based on each group of material feature data;

[0032] Generate a wheat growth information graph in real time. The horizontal axis of the growth information graph is time, and the vertical axis is the growth trend and quality prediction value; the growth stage corresponding to the current time is marked on the horizontal axis; the growth information graph includes a wheat growth trend curve and a quality prediction curve;

[0033] Identify the monitoring data of the planting area in real time, determine the management requirements for wheat cultivation according to the growth information graph and the monitoring data, and determine each management measure according to the management requirements;

[0034] Perform simulation analysis on the monitoring data, growth information graph and each management measure through the wheat growth analysis model to obtain the growth trend and quality prediction values corresponding to each management measure;

[0035] Obtain the planting requirements corresponding to each planting area, analyze each management measure according to the planting requirements, growth trend and quality prediction value to determine the target management measures corresponding to each planting area; generate a cultivation plan according to the target management measures.

[0036] Furthermore, the value range of the quality prediction value is [0, 100].

[0037] Furthermore, the method for analyzing each management measure according to the planting requirements, growth trend and quality prediction value includes:

[0038] According to the planting requirements, the growth trend and quality prediction value corresponding to each management measure are evaluated to obtain each candidate measure;

[0039] According to the comparison formula Compare the two possible measures; determine the target management measures;

[0040] Wherein: PB is the comparison value; β1 and β2 are weight coefficients, both in the range of [0, 1]; TS1 and TS2 are the growth trends of the two candidate measures for comparison; PY1 and PY2 are the quality prediction values ​​of the two candidate measures for comparison.

[0041] Furthermore, the method for evaluating the growth trend and quality prediction value corresponding to each management measure according to the planting requirements is as follows:

[0042] An evaluation and judgment model is established. The expression of the evaluation and judgment model is:

[0043]

[0044] Where: s is the input data, which includes planting requirements, growth trends and quality prediction values; the output data is the evaluation judgment value PG(s);

[0045] The planting requirements, growth trends and quality prediction values ​​are analyzed through the evaluation and judgment model to obtain the corresponding evaluation and judgment values; and the various candidate measures are determined based on the evaluation and judgment values.

[0046] Step 4: Cultivate the wheat in the planting area according to the cultivation plan.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] By establishing a platform, the wheat planting process from seed selection to harvesting can be visualized and traced, which enhances consumers' trust in wheat products and improves the transparency of food safety. Consumers can clearly understand the source, planting method and quality control of the wheat they eat, so they can eat it with confidence. The platform allows users to choose wheat varieties and demand according to personal needs, while displaying the advantages and disadvantages of each wheat variety and production user information to help users make more scientific and reasonable choices. This personalized customization service not only meets the taste preferences and health needs of different consumers, but also promotes the diversification of wheat varieties and market segmentation. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0051] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. 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.

[0052] like Figure 1 As shown, a wheat cultivation method based on big data analysis comprises:

[0053] Step 1: The platform party establishes the platform end, which is managed by the platform party and used for display to each user; that is, each user registers and logs in on the platform end; the user selects wheat seeds through the platform end and determines the corresponding planting requirements.

[0054] Planting requirements are the user's requirements for wheat planting management, and are mainly used to indicate the user's requirements for yield and quality. For example, if only quality is emphasized, it means that the subsequent impact on quality during the wheat planting process needs to be reduced as much as possible, which is mainly reflected in specific management measures such as weeding and pest control, such as pesticide weeding and manual weeding. Planting requirements are set according to user needs and the preset guidance tutorials, and converted into data that the system can recognize and understand.

[0055] In one embodiment, the platform party is an entity with planting conditions, that is, an entity with fields, planting management capabilities, etc.

[0056] In one embodiment, the platform party is an entity with technical capabilities, which conducts leasing management through personnel with fields and planting capabilities.

[0057] In one embodiment, the method for a user to select wheat seeds through the platform includes:

[0058] The platform selects wheat seeds that can be planted and marks them as seeds to be selected; sets seed information templates, such as yield, use, general planting cost, image, taste and other information items that users may be concerned about; collects information on each seed to be selected according to the seed information template to obtain seed information corresponding to each seed to be selected; summarizes various sub-information and establishes a seed information database;

[0059] A demand unit is set up, and the demand unit is used for users to input corresponding planting requirements according to planting needs; users input corresponding planting requirements through the demand unit, such as requirements for taste, yield, cost, etc.; the planting requirements of users are identified; a matching model is established according to the seed information library, and the matching model is used to match and judge various sub-information in the seed information library with the planting requirements, and judge whether the seed information meets the planting requirements; the planting requirements are analyzed through the matching model, and various sub-information that is successfully matched is obtained, marked as seed matching information, and various sub-matching information is displayed to users, and the users select wheat seeds to be planted.

[0060] In one embodiment, a display column is provided in the demand unit, and the display column is used for information display. Various recommended sub-information is dynamically displayed in the display column and marked as recommended information. The recommended information can be determined in a variety of ways such as planting quantity, yield, taste, evaluation, and platform specification.

[0061] In one embodiment, the matching model is established based on the existing technology.

[0062] In one embodiment, the expression of the matching model is In the formula: (ZA, BAi) is the input data, ZA is the planting requirement, BAi is the corresponding seed information in the seed information database, i = 1, 2, ..., n, n is a positive integer; the output data is the matching value PM (ZA, BAi), the matching value is 1 or 0; meeting the matching requirements means that the corresponding seed information meets the planting requirements.

[0063] Step 2: Plant the wheat seeds of each user, and monitor the wheat planting area in real time to obtain the corresponding monitoring data, and dynamically display the monitoring data to the corresponding users through the platform.

[0064] In one embodiment, wheat is monitored using existing technologies, such as climate environment (such as temperature, humidity, light), soil conditions (such as soil pH, nutrient content, moisture content), pests and diseases, etc.

[0065] In one embodiment, the planting of wheat seeds is manually determined by the platform staff.

[0066] In one embodiment, due to the differences in planting amount, requirements, etc. of each user, if the wheat planting area of ​​each user is determined manually, it will take a lot of time and energy, and the efficiency will be reduced. Therefore, in this embodiment, the method of planting wheat seeds of each user includes:

[0067] Obtain a planting area map, which is the information of each land that can be used for wheat planting. The planting area map is composed of various planting areas and is marked with regional information of each planting area, such as area, plantable quantity, and wheat varieties suitable for planting, etc., which are determined based on the actual corresponding equipment, land and other conditions;

[0068] Identify wheat seed information and planting requirements of each user, classify each user according to the wheat seed information and planting requirements, and obtain a classification of each user, that is, classify users with the same wheat seed information and planting requirements into one category;

[0069] The classification of each user is analyzed according to each planting area in the planting area map, the planting area corresponding to each user's wheat seed is determined, and each wheat seed is planted according to the corresponding planting area.

[0070] In one embodiment, the method for analyzing each user classification according to each planting area in the planting area map includes:

[0071] The various wheat seeds that can be planted are determined based on the corresponding regional information of each planting area, and the planting areas are randomly allocated according to the planting amount to obtain the planting areas corresponding to each wheat seed.

[0072] In one implementation, the method for analyzing each user classification according to each planting area in the planting area map includes:

[0073] Identify the regional information of each planting area and the wheat seed information classified by each user, and determine the planting areas corresponding to each user classification according to the regional information and the wheat seed information;

[0074] Identify the planting quantity corresponding to each user in the user classification, convert it into the required planting area, simulate planting according to each planting area and planting area, determine various planting methods, and mark them as candidate planting methods, that is, combine them according to each planting area and planting area, and determine various planting methods that can achieve all wheat planting;

[0075] Evaluate each candidate planting method to determine the corresponding management value and experience value. The management value is evaluated from the management difficulty of the platform side. Since the management difficulty of different users planting in the same planting area varies, ideally, each user corresponds to a planting area. However, in the actual planting process, generally multiple users plant in the same planting area because the planting volume of many users is not high. The experience value is set from the user's experience perspective. The more users using the same planting area, the worse their experience generally becomes. Specifically, the platform side conducts dynamic analysis based on the continuous operation results to form the setting experience of the management value and experience value, and establishes a training set manually. The training set includes input data and output data. The input data is the planting method, and the output data is the management value and experience value. Based on neural networks such as CNN networks or DNN networks, a planting analysis model is established, trained through the established training set, and analyzed through the trained planting analysis model to obtain the corresponding management value and experience value. In other embodiments, the management value and experience value can also be determined through other existing technologies.

[0076] Calculate the corresponding method value according to the formula PA = b1×GZ + b2×TZ;

[0077] In the formula: PA is the method value; b1 and b2 are both proportionality coefficients, and the value range is 0 < b1 ≤ 1, 0 < b2 ≤ 1; GZ is the management value; TZ is the experience value;

[0078] Select the candidate planting method with the highest method value as the target planting method, and determine the planting areas of the wheat seeds of each user according to the target planting method.

[0079] Step 3: Determine the cultivation plan for the wheat in the corresponding planting area according to the monitoring data and planting requirements;

[0080] In one embodiment, the cultivation plan is set based on existing technologies, such as being set manually.

[0081] In one embodiment, the method for determining the cultivation plan includes:

[0082] Connect to the seed information database to determine the various wheat seeds available and mark them as analysis targets; obtain historical cultivation data for each analysis target, such as collecting historical data related to wheat growth from agricultural research institutions, historical planting records, meteorological stations and other channels. These data include but are not limited to genetic information of wheat varieties, meteorological data over the years (such as temperature, humidity, rainfall, light intensity, etc.), soil conditions (soil type, nutrient content, pH value, etc.), quality data (pesticide residues, wheat quality effects, etc.) and key indicators in the wheat growth process (such as plant height, leaf area, number of tillers, yield, etc.). Based on existing big data technology, integrate, clean and pre-process the massive historical cultivation data collected to ensure the accuracy and availability of the data and obtain the target material data;

[0083] Feature extraction is performed on the target material data to obtain feature data of each group of materials. Each group of feature data is divided into two parts: one is the feature variables that have an important impact on wheat growth, such as meteorological parameters, soil conditions, wheat variety characteristics, drug use, fertilization, etc., and the other is growth and development trends, yield potential, quality, etc.;

[0084] Analyze the characteristic data of each group of materials to determine the quality prediction value. The quality prediction value is evaluated based on the management measures implemented during the growth process. The value range of the quality prediction value is [0, 100]. The better the quality, the higher the quality prediction value. The platform specifies wheat of a certain standard as 100, and specifies several quality standards with reference value, and sets corresponding quality prediction values; for example, qualified wheat with no pollution and pure green planting management is 100; that is, the evaluation is carried out according to the recognition standards of the platform;

[0085] Supplement the quality prediction value to the material characteristic data; establish a wheat growth analysis model based on each group of material characteristic data, which is used for subsequent wheat analysis based on monitoring data and simulation requirements;

[0086] Specifically, a wheat growth analysis model can be established based on neural networks, support vector machines, random forests, etc.

[0087] Exemplarily, a wheat growth analysis model is constructed using the selected machine learning algorithm and feature variables. During the model construction process, the algorithm parameters and model structure need to be continuously adjusted to optimize the model's predictive performance. The collected material feature data is divided into a training set, a validation set, and a test set. The training set is used to train the model, the validation set is used to adjust the model parameters and prevent overfitting, and the test set is used to evaluate the model's predictive performance. Model training: The model is trained using the training set data, and the model parameters are adjusted through an iterative optimization algorithm so that the model can better fit the data and predict the growth process and quality of wheat. Model verification: The trained model is verified using the validation set data to check whether the model's predictive performance meets the requirements. If the model is overfitting or underfitting, it is necessary to return to the model construction stage for adjustment. Model testing: The model is finally tested using the test set data to evaluate the model's predictive accuracy and reliability. If the model performs well, it can be applied to actual wheat planting management.

[0088] The wheat growth information graph is generated in real time. The horizontal axis is time, which is counted from the beginning of planting and the growth stage corresponding to the time is marked; the vertical axis is the growth trend and quality prediction value. For example, one scale corresponds to a certain growth trend and quality prediction value. The growth trend is represented by existing measurement indicators, such as predicted yield; the growth information graph has two growth curves, one is the growth trend curve and the other is the quality prediction curve. The quality prediction value is determined by analysis based on the wheat growth analysis model.

[0089] Identify the monitoring data corresponding to the planting area in real time, and determine the management measures in the subsequent stage according to the growth information map and monitoring data, that is, according to the wheat growth status and monitoring data at the current stage, determine the planting needs that need to be completed according to the scientific planting requirements of wheat, such as weeding, fertilization, pest control, irrigation, drainage, etc., and use the existing wheat planting experience to determine the corresponding planting needs and mark them as management needs; then determine the management measures that can achieve the needs according to the management needs, such as manual weeding, mechanical weeding, drug weeding, etc., and match them according to the specific methods that can be taken;

[0090] The wheat growth analysis model is used to simulate and analyze the monitoring data, growth information diagrams and various management measures to obtain the growth trend and quality prediction value corresponding to each management measure;

[0091] Obtain the planting requirements corresponding to each planting area, analyze each management measure according to the planting requirements, growth trends and quality prediction values, determine the target management measures corresponding to the planting area; generate a cultivation plan based on the target management measures.

[0092] Methods for analyzing management measures based on planting requirements, growth trends, and quality predictions include:

[0093] According to the planting requirements, the growth trend and quality prediction value corresponding to each management measure are evaluated to determine whether the planting requirements are met; each management measure that meets the planting requirements is marked as a candidate measure;

[0094] According to the comparison formula Compare the two possible measures; determine the target management measures;

[0095] Where: PB is the comparison value; β1 and β2 are the weight coefficients of growth trend and quality prediction value, both of which have a value range of [0, 1] and can be set according to the required proportion of the two in the planting requirements; TS1 and TS2 are the growth trends of the two candidate measures for comparison; PY1 and PY2 are the quality prediction values ​​of the two candidate measures for comparison;

[0096] Based on the comparative priority relationship between each other, the one with the highest priority will be regarded as the target management measure.

[0097] In one embodiment, the growth trend and quality prediction value corresponding to each management measure are evaluated according to the planting requirements, and the evaluation and judgment can be made based on existing technologies.

[0098] In one embodiment, the method for evaluating the growth trend and quality prediction value corresponding to each management measure according to the planting requirements is:

[0099] Establish an evaluation judgment model. The expression of the evaluation judgment model is Where: s is the input data, which includes planting requirements, growth trends and quality prediction values; the output data is the evaluation judgment value PG(s);

[0100] The planting requirements, growth trends and quality prediction values ​​are analyzed through the evaluation and judgment model to obtain the corresponding evaluation and judgment values; and the various candidate measures are determined based on the evaluation and judgment values.

[0101] Step 4: Cultivate wheat in the corresponding planting area according to the obtained cultivation plan.

[0102] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0103] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A wheat cultivation method based on big data analysis, characterized in that: The method includes: Step 1: The platform party establishes a platform terminal, and users register and log in on the platform terminal; The user determines the wheat seeds to be planted and the corresponding planting requirements through the platform terminal; Step 2: Plant the wheat seeds of each user, and conduct real-time monitoring on the planting areas of the planted wheat to obtain corresponding monitoring data, and dynamically display the monitoring data to the corresponding users through the platform terminal; Step 3: Determine the cultivation plan for the wheat in the corresponding planting area according to the monitoring data and the planting requirements; Step 4: Cultivate the wheat in the planting area according to the cultivation plan.

2. A wheat cultivation method based on big data analysis according to claim 1, characterized in that: The method for determining wheat seeds includes: The platform party selects each candidate seed; sets a seed information template, collects information on each candidate seed according to the seed information template to obtain the seed information of each candidate seed; summarizes the seed information of each and establishes a seed information library; Set a requirement unit, and the requirement unit is used for the user to input planting requirements; the user inputs the planting requirements for wheat through the requirement unit; identify the planting requirements of the user; Establish a matching model according to the seed information library, analyze the planting requirements through the matching model to obtain various seed matching information, display the seed matching information to the user, and the user selects the wheat seeds to be planted.

3. A wheat cultivation method based on big data analysis according to claim 2, characterized in that: A display column is set in the requirement unit, and the display column is used for information display, and various recommended information is dynamically displayed in the display column.

4. The wheat cultivation method based on big data analysis according to claim 2, characterized in that: The expression of the matching model is: In the formula: (ZA, BAi) is the input data, ZA is the planting requirement, BAi is the corresponding seed information in the seed information library, i = 1, 2,..., n, n is a positive integer; the output data is the matching value PM(ZA, BAi), and the matching value is 1 or 0.

5. The wheat cultivation method based on big data analysis according to claim 1, characterized in that: The method for planting the wheat seeds of each user includes: Obtain a planting area map, which is composed of various planting areas, and the corresponding area information is marked on the planting areas; Identify the wheat seed information and planting requirements of each user, classify each user according to the wheat seed information and planting requirements to obtain each user classification; Analyze each user classification according to the various planting areas in the planting area map to determine the planting areas of the wheat seeds of each user, and plant each wheat seed according to the corresponding planting area.

6. A wheat cultivation method based on big data analysis according to claim 5, characterized in that: The method for analyzing each user classification according to the various planting areas in the planting area map includes: Identify the area information of each planting area and the wheat seed information of each user classification, and determine the various planting areas corresponding to each user classification according to the area information and wheat seed information; Determine the planting area corresponding to each user in the user classification, conduct simulated planting according to the various planting areas and planting areas to obtain various candidate planting methods; Evaluate each candidate planting method to determine the corresponding management value and experience value; Calculate the corresponding method value according to the formula PA = b1×GZ + b2×TZ; In the formula: PA is the method value; b1 and b2 are both proportionality coefficients, and the value range is 0 < b1 ≤ 1, 0 < b2 ≤ 1; GZ is the management value; TZ is the experience value; The candidate planting method with the highest selection method value is selected as the target planting method, and the planting area of ​​wheat seeds for each user is determined according to the target planting method.

7. The wheat cultivation method based on big data analysis according to claim 2, characterized in that: The methods for determining the training program include: Connecting to the seed information database, identifying various wheat seeds, and marking them as analysis targets; obtaining historical cultivation data of each of the analysis targets, processing the historical cultivation data, and obtaining target material data; Extracting features from target material data to obtain feature data of each group of materials, analyzing each group of feature data of each group of materials, determining quality prediction values ​​corresponding to each group of feature data of each group of materials, and adding the quality prediction values ​​to the feature data of each group of materials; establishing a wheat growth analysis model according to the feature data of each group of materials; Generating a wheat growth information graph in real time, wherein the horizontal axis of the growth information graph is time, and the vertical axis is growth trend and quality prediction value; the growth stage corresponding to the current time is marked on the horizontal axis; the growth information graph includes a wheat growth trend curve and a quality prediction curve; Identify the monitoring data of the planting area in real time, determine the management requirements for wheat cultivation based on the growth information map and the monitoring data, and determine various management measures based on the management requirements; The wheat growth analysis model is used to simulate and analyze the monitoring data, growth information diagram and various management measures to obtain the growth trend and quality prediction value corresponding to each management measure; Obtain the planting requirements corresponding to each planting area, analyze each management measure according to the planting requirements, growth trends and quality prediction values, determine the target management measures corresponding to each planting area; generate a cultivation plan based on the target management measures.

8. The wheat cultivation method based on big data analysis according to claim 7, characterized in that: The quality prediction value ranges from [0, 100].

9. The wheat cultivation method based on big data analysis according to claim 7, characterized in that: Methods for analyzing management measures based on planting requirements, growth trends, and quality predictions include: According to the planting requirements, the growth trend and quality prediction value corresponding to each management measure are evaluated to obtain each candidate measure; According to the comparison formula Compare the two possible measures; determine the target management measures; Where: PB is the comparison value; β1 and β2 are weight coefficients, both in the range of [0, 1]; TS1 and TS2 are the growth trends of the two candidate measures for comparison; PY1 and PY2 are the quality prediction values ​​of the two candidate measures for comparison.

10. A wheat cultivation method based on big data analysis according to claim 9, characterized in that: The method for evaluating the growth trend and quality prediction value corresponding to each management measure according to the planting requirements is as follows: An evaluation and judgment model is established. The expression of the evaluation and judgment model is: Where: s is the input data, which includes planting requirements, growth trends and quality prediction values; the output data is the evaluation judgment value PG(s); The planting requirements, growth trends and quality prediction values ​​are analyzed through the evaluation and judgment model to obtain the corresponding evaluation and judgment values; and the various candidate measures are determined based on the evaluation and judgment values.

Images