Irrigation area agricultural information service system based on big data

Abstract

The invention discloses an irrigation area agricultural information service system based on big data, and the system comprises an associated peasant household group generation module, a peasant household information monitoring module and an agricultural information service module, and carries out the precise grouping of peasant households through the characteristics of planting scale characteristics, planting crop types, soil characteristics, geographical climate characteristics, etc. The method is advantaged in that subsequent agricultural service guidance information can be conveniently and accurately sent, dynamic information monitoring and sorting are carried out on each associated farmer group, a system is facilitated to rapidly focus on farmers who may urgently need agricultural service guidance information updating, a ripple effect for farmer service is further optimized through generation of a farmer information association sequence, and agricultural service guidance information updating efficiency is improved. The method is convenient for efficiently and preferentially locking the farmers needing to update the agricultural service guidance information, forms an agricultural information service closed loop of'accurate identification-scientific verification-efficient diffusion ', and remarkably improves the service quality and efficiency of agricultural information.

Description

Technical Field

[0001] This invention relates to the field of agricultural information management technology, and more specifically, to an irrigation district agricultural information service system based on big data. Background Technology

[0002] With the rapid development of smart agriculture, the role of irrigation district agricultural information service systems in improving production efficiency and optimizing resource allocation is becoming increasingly prominent. In existing technologies, agricultural information services mainly rely on collecting basic data from farmers (such as planting area and crop type) to provide service delivery, but this approach faces the following key challenges:

[0003] I. Lack of dynamic monitoring mechanism and delayed demand response: The existing system lacks real-time quantitative assessment methods for farmers' service needs, and cannot dynamically identify farmers who urgently need service updates. For example, when farmers have new needs due to climate change, changes in soil moisture, or outbreaks of pests and diseases, the system relies on manual inspections or farmers' proactive feedback, with response times as long as several days or even a week, missing the best service opportunity.

[0004] Second, service plan verification relies on experience, resulting in high trial-and-error costs: Traditional agricultural service plans are mostly based on the experience of agricultural technicians and lack scientific simulation and verification processes. For example, whether an irrigation plan is suitable for a specific soil type or whether fertilizer application leads to nitrogen leaching requires verification through field trials. Each trial-and-error cycle is long and consumes a lot of manpower and resources, which is difficult for small farmers to afford.

[0005] Third, the service dissemination efficiency is low and the resource utilization rate is low: the existing system has not established a quantitative evaluation system for the relationship between farmers, and high-quality service solutions (such as efficient pest and disease control methods) are difficult to quickly spread to related farmers with similar characteristics.

[0006] To address the aforementioned issues, there is an urgent need for an irrigation district agricultural information service system that can integrate multi-dimensional farmer profiles, dynamically assess service needs, combine scientific simulation verification, and achieve efficient service dissemination. This system would solve the core pain points of existing technologies, such as "extensive grouping, delayed response, lack of verification, and inefficient dissemination," and promote the transformation of agricultural information services from "experience-driven" to "data-model dual-driven." Summary of the Invention

[0007] In view of the shortcomings of existing technologies, the purpose of this invention is to provide an irrigation district agricultural information service system based on big data.

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] An irrigation district agricultural information service system based on big data includes a module for generating associated farmer groups, a module for monitoring farmer information, and a module for providing agricultural information services.

[0010] The module for generating associated farmer groups periodically determines the profile feature set of each farmer in the system, and then generates multiple associated farmer groups.

[0011] The farmer information monitoring module generates farmer information monitoring sequences for each associated farmer group and simultaneously builds an agricultural planting reference model for each associated farmer group.

[0012] The agricultural information service module obtains the information service index of the top-ranked farmer in each farmer's information monitoring sequence. Based on the comparison between the information service index and its threshold, it determines whether to generate a corresponding farmer information association sequence to provide agricultural service guidance information.

[0013] Furthermore, the steps for periodically determining the profile feature set of farmers are as follows: select a farmer, periodically obtain various types of profile features of the farmer, integrate the various types of profile features to form the profile feature set of the farmer.

[0014] Further, the steps for generating the farmer information monitoring sequence for the associated farmer group are as follows: Select an associated farmer group, obtain the information service intervention index of each farmer in the associated farmer group, arrange all farmers in the associated farmer group in descending order of information service intervention index, and generate the farmer information monitoring sequence based on the arrangement order.

[0015] Further, the steps for obtaining the farmer's information service intervention index are as follows: Select a farmer, obtain the information service index for the previous i periods, sort all information service indices in chronological order, sum the two adjacent information service indices after sorting to calculate the information service retention index, set the information service retention threshold index, when the information service retention index ≥ the information service retention threshold index, increase the number of consecutive information replacement needs by one, sum the information service indices of all periods and take the average value to calculate the information service average index, and calculate the farmer's information service intervention index based on the number of consecutive information replacement needs and the information service average index.

[0016] Further, the steps for obtaining the farmer's information service index are as follows: Obtain the latest agricultural service guidance information received by the farmer, determine the agricultural planting reference model of the farmer's associated farmer group, first, obtain the initial growth data of the crop in the agricultural planting reference model, control the agricultural planting reference model to run for a duration of Tq, after the run is completed, obtain the final growth data of the crop in the agricultural planting reference model, obtain the information service analysis model corresponding to the crop, match the initial growth data and the final growth data into a start-end growth data comparison group, import the start-end growth data comparison group into the information service analysis model, and the information service analysis model derives the information service index.

[0017] Furthermore, based on the comparison results between the information service index and its threshold, it is determined whether to generate a corresponding farmer information association sequence to provide agricultural service guidance information: when the farmer's information service index is greater than or equal to the information service threshold index, the farmer is marked as a farmer to be served, agricultural service guidance information for the farmer to be served is generated, the agricultural service guidance information is sent to the farmer to be served, and a farmer information association sequence is generated simultaneously. The information service index of the first potential associated farmer in the farmer information association sequence is obtained. When the information service index of the potential associated farmer is greater than or equal to the information service threshold index, the agricultural service guidance information for the farmer to be served is sent to the potential associated farmer, and the information service index of the next potential associated farmer in the farmer information association sequence is obtained. When the information service index of the potential associated farmer is less than the information service threshold index, the information service index of the next potential associated farmer in the farmer information association sequence is obtained.

[0018] When a farmer's information service index is less than the information service threshold index, obtain the information service index of the next farmer in the corresponding farmer information monitoring sequence.

[0019] Further, the steps for generating the farmer information association sequence are as follows: all farmers ranked after the corresponding farmer in the farmer information monitoring sequence are marked as potential associated service farmers, the planting dynamic association index of each potential associated service farmer is obtained, and all potential associated service farmers are arranged in descending order of the planting dynamic association index. Based on the arrangement order, the farmer information association sequence is generated.

[0020] Further, the steps for generating agricultural service guidance information for farmers awaiting service are as follows: determine the agricultural planting reference model of the associated farmer group to which the farmer awaiting service belongs, control the agricultural planting reference model to run autonomously multiple times, and mark the agricultural service guidance information generated corresponding to the autonomous run with the smallest information service index value as the agricultural service guidance information for the farmer awaiting service.

[0021] Furthermore, the planting dynamic correlation index of potential related service farmers is calculated as follows: Select a potential related service farmer and determine whether the potential related service farmer was in the same related farmer group as the farmer to be served in the previous j periods. Whenever the potential related service farmer and the farmer to be served were in the same related farmer group in a period, the planting correlation count is increased by one, and the corresponding period is marked as the planting correlation period. All planting correlation periods are compared pairwise. When the two compared planting correlation periods are adjacent periods, the correlation duration count is increased by one. The planting dynamic correlation index of the potential related service farmer is calculated based on the planting correlation count and the correlation duration count.

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] The system of this invention accurately groups farmers based on characteristics such as planting scale, crop type, soil features, and geographical and climatic features. This facilitates the precise delivery of subsequent agricultural service guidance information. The system dynamically monitors and sorts information for each associated farmer group, allowing it to quickly focus on farmers who may urgently need updated agricultural service guidance information. Combined with finite element model mapping technology, a suitable agricultural planting reference model is constructed for each farmer group. The system simulates the execution of the latest agricultural service guidance information received by farmers according to the information monitoring and sorting, accurately determining whether farmers need to update their agricultural service guidance information. Once a farmer is identified as needing updated agricultural service guidance information, a farmer information association sequence is generated to further optimize the ripple effect of the service to that farmer. This facilitates efficient and priority identification of farmers who need updated agricultural service guidance information, forming a closed loop of "precise identification - scientific verification - efficient dissemination" for agricultural information services, significantly improving the quality and efficiency of agricultural information services. Attached Figure Description

[0024] Figure 1 This is a schematic diagram outlining the principle of an irrigation district agricultural information service system based on big data.

[0025] Figure 2 Flowchart for obtaining the information service index for farmers;

[0026] Figure 3 A flowchart for determining whether to generate a corresponding farmer information association sequence to provide agricultural service guidance information. Detailed Implementation

[0027] Reference Figures 1 to 3 A big data-based agricultural information service system for irrigation districts includes a module for generating associated farmer groups, a module for monitoring farmer information, and a module for providing agricultural information services.

[0028] The module for generating associated farmer groups periodically determines the profile feature set of each farmer in the system, and then generates multiple associated farmer groups.

[0029] The steps for periodically determining the profile feature set of farmers are as follows: Select a farmer, periodically obtain various types of profile features of the farmer (profile features include planting scale features, crop type, soil features, geographical and climatic features, etc. The above profile features are only examples. More features can be added according to the actual needs of the system to depict the farmer's profile. In the specific implementation, no further details are provided, and the extraction methods of each type of profile feature are not explained in detail. All of them are existing technologies). Integrate the various types of profile features to form the profile feature set of the farmer.

[0030] Each associated farmer group contains multiple farmers with similar profile features. The similarity of profile features between farmers is calculated using cosine similarity. Taking farmer A and farmer B as an example, the various types of profile features of farmer A are vectorized and transformed into feature vector A = (a1, a2, ..., a...). n The various profile features of farmer B are vectorized and transformed into feature vector B = (b1, b2, ..., bb2). n Using the similarity formula Calculate the similarity of the portrait features between farmer A and farmer B, and set a portrait feature threshold similarity (set by the system). When the similarity of the portrait features between farmer A and farmer B is greater than or equal to the portrait feature threshold similarity, farmer A and farmer B are grouped into a group of related farmers.

[0031] The farmer information monitoring module generates a farmer information monitoring sequence for each associated farmer group (the farmer information monitoring sequence contains all farmers in an associated farmer group and is arranged in a certain order), and simultaneously builds an agricultural planting reference model for each associated farmer group.

[0032] The steps for generating a farmer information monitoring sequence for a group of related farmers are as follows: Select a group of related farmers, obtain the information service intervention index of each farmer in the group, arrange all farmers in the group in descending order of the information service intervention index, and generate a farmer information monitoring sequence based on the arrangement order.

[0033] The steps for obtaining the farmer's information service intervention index are as follows: Select a farmer, obtain the information service index for the previous i periods (one information service index for each period), sort all information service indices in chronological order, sum the two adjacent information service indices after sorting to obtain the information service retention index, set the information service retention threshold index (set by the system), when the information service retention index ≥ the information service retention threshold index, increase the number of consecutive information replacement requests by one, when the information service retention index < the information service retention threshold index, there is no need to increase the number of consecutive information replacement requests by one, finally, label the number of consecutive information replacement requests as Net(pe), sum the information service indices of all periods and take the average value to obtain the information service average index Fay(da), and calculate the farmer's information service intervention index Psw(vn) by Psw(vn) = [Net(pe) + 1] * Fay(da).

[0034] The steps for building an agricultural planting reference model for a linked farmer group are as follows: First, identify all farmers included in the linked farmer group. Second, collect various types of profile features for each farmer in the linked farmer group, and then generate fused profile features of each type. Third, import these fused profile features into a general finite element software. Finally, map the fused profile features to the physical parameters required for finite element simulation. For example: the soil pH value of the fused profile features is 7.8; the input parameters for the finite element model are soil electrochemical parameters (affecting ion migration); the mapping method is to directly use them as initial conditions; and the planting density of the fused profile features is 25 plants / m². 2 The input parameter for the finite element model is the crop canopy porosity (porosity = 0.65), and the mapping method is based on geometric model calculation (each plant occupies 0.04m). 2 In general finite element software, the scale and key components of the three-dimensional field entity are set. The key components include soil domain, crop canopy, and boundary conditions. Soil domain: Define the soil parameters of each layer (merged hydraulic conductivity, bulk density, and field water holding capacity). Crop canopy: Use a porous medium model to simulate canopy resistance, and the porosity is calculated from the planting density. Boundary conditions: The top is the atmospheric boundary (input the merged meteorological parameters), and the bottom is the groundwater boundary. A multiphysics coupling model is built in general finite element software. The physical fields include soil moisture transport, soil heat transfer, and crop growth model. Finally, through model verification and validation, an agricultural planting reference model for the associated farmer group is built. The agricultural planting reference model can simulate crop growth in the environment.

[0035] The steps for generating a type of fused profile feature are as follows: Select a profile feature of a certain type, and fuse the profile features of that type for all farmers in the associated farmer group to generate a fused profile feature of that type (for the same profile feature of multiple farmers, the individual profile features of all farmers are integrated through existing feature fusion methods to finally generate a comprehensive feature that can represent the commonality of the entire farmer group, which is the fused profile feature); Taking the planting scale feature as an example, the fused feature of the planting scale feature can be calculated by the average planting area calculation method (the associated farmer group contains four farmers with planting areas of [50, 80, 120, 150] mu respectively, and the average value = 100 mu, representing the average size of the group); Taking the type of crop planted as an example, the fused feature of the type of crop planted can be obtained by the mode method (calculating the crop type with the highest frequency, applicable to groups where ≥90% of farmers plant the same crop).

[0036] The agricultural information service module obtains the information service index of the first-ranked farmer in each farmer's information monitoring sequence, sets an information service threshold index (set by the system), and marks the farmer as a farmer awaiting service when the farmer's information service index is greater than or equal to the information service threshold index. It then generates agricultural service guidance information for the farmer awaiting service (agricultural service guidance information includes planting suggestions for crops, such as irrigation plans, fertilization plans, and pest and disease control), and sends this information to the farmer awaiting service (this agricultural service guidance information is the latest agricultural service guidance information received by the farmer awaiting service). Simultaneously, it generates a farmer information association sequence, obtains the information service index of the first-ranked potential associated service farmer in the farmer information association sequence, and sends the agricultural service guidance information to the farmer awaiting service when the information service index of the potential associated service farmer is greater than or equal to the information service threshold index. It continues to obtain the information service index of the next-ranked potential associated service farmer in the farmer information association sequence, and obtains the information service index of the next-ranked potential associated service farmer when the information service index of the potential associated service farmer is less than the information service threshold index.

[0037] When a farmer's information service index is less than the information service threshold index, obtain the information service index of the next farmer in the corresponding farmer information monitoring sequence (i.e., the farmer's information monitoring sequence).

[0038] The steps for generating agricultural service guidance information for farmers awaiting service are as follows: Determine the agricultural planting reference model of the associated farmer group to which the farmer awaiting service belongs, and control the agricultural planting reference model to run autonomously multiple times (each autonomous run generates one piece of agricultural service guidance information; after each autonomous run, ensure that the farmer's information service index is less than the information service threshold index, which means that the agricultural service guidance information can effectively provide farmers with planting suggestions for crop planting). Mark the agricultural service guidance information generated by the autonomous run with the smallest information service index value as the agricultural service guidance information for the farmer awaiting service.

[0039] The steps for obtaining the farmer's information service index are as follows: First, obtain the latest agricultural service guidance information received by the farmer. Then, determine the agricultural planting reference model for the farmer's associated farmer group. Next, obtain the initial crop growth data (including average plant height, average stem length, average number of leaves, and average leaf area) from the agricultural planting reference model. Finally, import the agricultural service guidance information into the agricultural planting reference model. (Before importing, perform information parsing, semantic mapping, and structured output processing on the agricultural service guidance information. For example, for irrigation plans: parse the value "15" and the unit "mm" in "irrigation amount 15mm / time" and convert it into the "volume flux" required by the model (unit: m / s, which needs to be calculated in conjunction with irrigation time, such as "15mm / 6 hours = 6.94 × 10⁻⁶"). -7m / s”), “drip irrigation” → “point source infiltration” boundary condition in the model (small flow rate, long duration), “flood irrigation” → “non-point source infiltration” boundary condition in the model (large flow rate, short duration)), control the agricultural planting reference model to run for Tq time (the agricultural planting reference model simulates planting for Tq time based on agricultural service guidance information). After the operation is completed, obtain the crop’s termination growth data in the agricultural planting reference model, obtain the corresponding information service analysis model for the crop, match the initial growth data and termination growth data into a start-end growth data comparison group, import the start-end growth data comparison group into the information service analysis model, and the information service analysis model derives the information service index.

[0040] Each crop corresponds to an information service analysis model, and each information service analysis model is built based on a deep learning model. Specifically, the process of building the information service analysis model for crop A is disclosed as follows: A deep learning model is built, and multiple sets of start and end growth data comparisons for crop A are collected. Each set of start and end growth data comparisons includes one initial growth data point and one final growth data point for crop A. Using these start and end growth data comparisons as the base data, the built deep learning model is trained. During this process, each set of start and end growth data comparisons for crop A is assigned an information service index. The value range of the information service index is set between 1 and 10, and the magnitude of the information service index has a clear... The greater the numerical value, the weaker the effectiveness of agricultural service guidance information in the comparison of crop growth status before and after (i.e., the lower the change in the termination growth data compared to the initial growth data in the comparison group of start and end growth data is). Then, the comparison groups of start and end growth data of multiple crops A are divided into training set, validation set and test set according to a specific ratio of 70%:15%:15%. First, the deep learning model is repeatedly trained using the training set. During the training process, the performance of the model during the training stage is verified in a timely manner using the validation set. The parameters of the model are adjusted in a timely manner according to the validation results, and the structure of the model is optimized so that it develops in a more accurate and stable direction. Finally, the information service analysis model of crop A is completed.

[0041] The steps for generating the farmer information association sequence are as follows: all farmers ranked after the corresponding farmer in the farmer information monitoring sequence are marked as potential associated service farmers. The planting dynamic association index of each potential associated service farmer is obtained. All potential associated service farmers are arranged in descending order of planting dynamic association index. Based on the arrangement order, the farmer information association sequence is generated.

[0042] The planting dynamic correlation index of potential associated service farmers: Select a potential associated service farmer and determine whether the potential associated service farmer was in the same associated farmer group as the farmer to be served in the previous j periods. Whenever the potential associated service farmer and the farmer to be served were in the same associated farmer group in a period, the planting correlation count is increased by one, and the corresponding period is marked as the planting correlation period. All planting correlation periods are compared pairwise. When the two compared planting correlation periods are adjacent periods, the correlation duration count is increased by one. Finally, the planting correlation count is marked as Ehu(be), and the correlation duration count is marked as Sxg(yd). The planting dynamic correlation index Swui of the potential associated service farmer is calculated by Swui = Ehu(be) × ka1 + Sxg(yd) × ka2, where ka1 is the first correlation coefficient, ka2 is the second correlation coefficient, ka1 has a value of 0.81, and ka2 has a value of 0.89.

[0043] The system of this invention accurately groups farmers based on characteristics such as planting scale, crop type, soil features, and geographical and climatic features. This facilitates the precise delivery of subsequent agricultural service guidance information. The system dynamically monitors and sorts information for each associated farmer group, allowing it to quickly focus on farmers who may urgently need updated agricultural service guidance information. Combined with finite element model mapping technology, a suitable agricultural planting reference model is constructed for each farmer group. The system simulates the execution of the latest agricultural service guidance information received by farmers according to the information monitoring and sorting, accurately determining whether farmers need to update their agricultural service guidance information. Once a farmer is identified as needing updated agricultural service guidance information, a farmer information association sequence is generated to further optimize the ripple effect of the service to that farmer. This facilitates efficient and priority identification of farmers who need updated agricultural service guidance information, forming a closed loop of "precise identification - scientific verification - efficient dissemination" for agricultural information services, significantly improving the quality and efficiency of agricultural information services.

[0044] The above formulas are all dimensionless calculations, and the preset parameters in the formulas should be set by those skilled in the art according to the actual situation.

[0045] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0046] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0047] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0048] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0049] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0050] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0051] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A big data-based agricultural information service system for irrigation districts, characterized in that, This includes a module for generating associated farmer groups, a module for monitoring farmer information, and a module for providing agricultural information services. The module for generating associated farmer groups periodically determines the profile feature set of each farmer in the system, and then generates multiple associated farmer groups. The farmer information monitoring module generates farmer information monitoring sequences for each associated farmer group and simultaneously builds an agricultural planting reference model for each associated farmer group. The agricultural information service module obtains the information service index of the top-ranked farmer in each farmer's information monitoring sequence. Based on the comparison between the information service index and its threshold, it determines whether to generate a corresponding farmer information association sequence to provide agricultural service guidance information.

2. The irrigation district agricultural information service system based on agricultural big data according to claim 1, characterized in that, The steps for periodically determining the profile feature set of farmers are as follows: Select a farmer, periodically obtain various types of profile features of the farmer, integrate the various types of profile features to form the profile feature set of the farmer.

3. The irrigation district agricultural information service system based on agricultural big data according to claim 1, characterized in that, The steps for generating a farmer information monitoring sequence for a group of related farmers are as follows: Select a group of related farmers, obtain the information service intervention index of each farmer in the group, arrange all farmers in the group in descending order of the information service intervention index, and generate a farmer information monitoring sequence based on the arrangement order.

4. The irrigation district agricultural information service system based on agricultural big data according to claim 3, characterized in that, The steps for obtaining the farmer's information service intervention index are as follows: Select a farmer, obtain the information service index for the previous i periods, sort all information service indices in chronological order, sum the two adjacent information service indices after sorting to obtain the information service retention index, set the information service retention threshold index, when the information service retention index is greater than or equal to the information service retention threshold index, increase the number of consecutive information replacement needs by one, sum the information service indices of all periods and take the average value to obtain the information service average index, and calculate the farmer's information service intervention index based on the number of consecutive information replacement needs and the information service average index.

5. The irrigation district agricultural information service system based on agricultural big data according to claim 1, characterized in that, The steps for obtaining the information service index for farmers are as follows: Obtain the latest agricultural service guidance information received by the farmer; determine the agricultural planting reference model of the farmer's associated farmer group; first, obtain the initial growth data of the crop in the agricultural planting reference model; control the agricultural planting reference model to run for a duration of Tq; after the run, obtain the final growth data of the crop in the agricultural planting reference model; obtain the information service analysis model corresponding to the crop; match the initial growth data and the final growth data into a start-end growth data comparison group; import the start-end growth data comparison group into the information service analysis model; and derive the information service index from the information service analysis model.

6. The irrigation district agricultural information service system based on agricultural big data according to claim 1, characterized in that, Based on the comparison between the information service index and its threshold, it is determined whether to generate a corresponding farmer information association sequence to provide agricultural service guidance information: when the farmer's information service index is greater than or equal to the information service threshold index, the farmer is marked as a farmer to be served, agricultural service guidance information for the farmer to be served is generated and sent to the farmer to be served, and a farmer information association sequence is generated simultaneously. The information service index of the first potential associated farmer in the farmer information association sequence is obtained. When the information service index of the potential associated farmer is greater than or equal to the information service threshold index, the agricultural service guidance information for the farmer to be served is sent to the potential associated farmer, and the information service index of the next potential associated farmer in the farmer information association sequence is obtained. When the information service index of the potential associated farmer is less than the information service threshold index, the information service index of the next potential associated farmer in the farmer information association sequence is obtained. When a farmer's information service index is less than the information service threshold index, obtain the information service index of the next farmer in the corresponding farmer information monitoring sequence.

7. The irrigation district agricultural information service system based on agricultural big data according to claim 6, characterized in that, The steps for generating the farmer information association sequence are as follows: all farmers ranked after the corresponding farmer in the farmer information monitoring sequence are marked as potential associated service farmers. The planting dynamic association index of each potential associated service farmer is obtained. All potential associated service farmers are arranged in descending order of planting dynamic association index. Based on the arrangement order, the farmer information association sequence is generated.

8. The irrigation district agricultural information service system based on agricultural big data according to claim 6, characterized in that, The steps for generating agricultural service guidance information for farmers awaiting service are as follows: Determine the agricultural planting reference model of the associated farmer group to which the farmer awaiting service belongs, control the agricultural planting reference model to run autonomously multiple times, and mark the agricultural service guidance information generated corresponding to the autonomous run with the smallest information service index value as the agricultural service guidance information for the farmer awaiting service.

9. The irrigation district agricultural information service system based on agricultural big data according to claim 7, characterized in that, Planting dynamic association index of potential associated service farmers: Select a potential associated service farmer and determine whether the potential associated service farmer was in the same associated farmer group as the farmer to be served in the previous j periods. Whenever the potential associated service farmer and the farmer to be served were in the same associated farmer group in a period, the planting association count is increased by one, and the corresponding period is marked as the planting association period. All planting association periods are compared pairwise. When the two compared planting association periods are adjacent periods, the association duration count is increased by one. The planting dynamic association index of the potential associated service farmer is calculated based on the planting association count and the association duration count.

Images