Comprehensive informatization management platform for agricultural company

Abstract

The invention discloses an agricultural company comprehensive informatization management platform, which relates to the technical field of comprehensive management and comprises a seed information acquisition module, a farmer information acquisition module, a relationship matching module, a seed recovery module, a seed screening module, a seed detection module and a farmer evaluation module. The seed information acquisition module is used for setting seed labels according to different varieties and models of seeds, acquiring seed information of various varieties and models, and associating the seed information with the corresponding seed labels; according to the comprehensive informatization management platform for the agricultural company, by arranging the seed information acquisition module, the farmer information acquisition module, the relationship matching module, the seed recovery module and the like, the recovered seeds of each farmer can be detected and evaluated, and the influence of the planting mode of each farmer on the quality of the propagated seeds is judged; therefore, cooperation schemes can be independently customized for the farmer households according to the seed quality of different farmer households, and the quality of the recycled seeds can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of integrated management, and specifically relates to a comprehensive information management platform for an agricultural company. Background Art

[0002] The prior art with publication number CN114677033A discloses an intelligent monitoring and analysis management system for the full-cycle process of laboratory cultivation data. This intelligent monitoring and analysis management system for the full-cycle process of laboratory cultivation data includes: a cultivation sample screening module, an experimental group information setting module, a monitoring stage division module, a growth information collection module, a cloud processing center, a database, and an information sending center; by monitoring and analyzing the growth information collected during the seed germination monitoring stage, morphological formation monitoring stage, flowering and pollination monitoring stage, and fruiting monitoring stage of each cultivation sample in the biological laboratory, it effectively solves the problems that the content of the existing biological cultivation process monitoring is single and the reliability of the monitoring results cannot be improved, realizes the analysis of the cultivation influence of a single environmental factor on the cultivated organism, and also greatly improves the scientificity and reference value of the monitoring and analysis results of the biological cultivation process.

[0003] The quality of the recycled crop seeds is not only related to the genes of the crops from which the seeds are reproduced, that is, not only related to the genes and quality of the seeds of the previous generation of the planted crops, but also has a certain relationship with the planting conditions and planting methods of the crops. Therefore, if you want to improve the quality of the recycled seeds, you also need to study the quality of the seeds recycled from different growers, analyze the quality of various seeds grown by each grower, so as to better cooperate and recover more seeds of higher quality. Summary of the Invention

[0004] The purpose of the present invention is to provide a comprehensive information management platform for an agricultural company to solve the above deficiencies in the prior art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: A comprehensive information management platform for an agricultural company, including a seed information acquisition module, a grower information acquisition module, a relationship matching module, a seed recycling module, a seed screening module, a seed detection module, and a grower evaluation module;

[0006] The seed information acquisition module is used to set seed tags according to different variety models of seeds, acquire seed information of various variety models, and associate the seed information with the corresponding seed tags, where the seed information may include seed source, origin, quantity, quality, sales destination, sales date, and relevant responsible personnel, etc.;

[0007] The grower information acquisition module is used to set corresponding grower tags according to different growers, obtain grower information, and associate the grower information with the corresponding grower tags. Among them, the grower information may include grower types, such as individual businesses, enterprises, etc., grower addresses, contact information, sales contracts, seed purchase records, etc.;

[0008] The relationship matching module is used to obtain the variety models of seeds purchased by various growers and associate the growers with the variety models of seeds purchased by the growers;

[0009] The seed recycling module is used to recycle the seeds grown by various growers to obtain recycled seeds, and obtain recycled seed information. The recycled seed information includes the variety models of the recycled seeds, and associate the recycled seed information with the corresponding growers. Among them, the variety models of the recycled seeds can be initially determined by the variety models of the previous generation of seeds corresponding to the recycled seeds.

[0010] The seed screening module is used to preliminarily screen the recycled seeds using a sieve to separate impurities therein to obtain preliminarily screened seeds. The impurities include dust, stones, weeds, etc., and then based on machine vision, identify the plump preliminarily screened seeds from the preliminarily screened seeds, calculate the proportion of the plump preliminarily screened seeds in the preliminarily screened seeds to obtain the plumpness rate, and save the plumpness rate into the corresponding recycled seed information;

[0011] The seed detection module is used to sample the preliminarily screened seeds to obtain sample seeds, perform germination rate detection and gene purity detection on the sample seeds, and save the detection results into the corresponding recycled seed information;

[0012] The grower evaluation module is used to evaluate and classify the corresponding growers based on the plumpness rate and the results detected by the seed detection module, that is, the plumpness rate, germination rate and high-quality gene purity of the recycled seeds, to obtain grower ratings, and save the grower ratings into the corresponding grower information. Among them, when evaluating and classifying growers, custom rules can be used.

[0013] Further, the seed screening module based on machine vision identifies the plump preliminarily screened seeds from the preliminarily screened seeds, calculates the proportion of the plump preliminarily screened seeds in the preliminarily screened seeds to obtain the plumpness rate, including the following steps:

[0014] Lay the preliminarily screened seeds flat on the conveyor belt;

[0015] Select a suitable industrial camera to take pictures of the preliminarily screened seeds on the conveyor belt to obtain preliminarily screened seed images, where the suitable industrial camera is such that the number of clearly displayed preliminarily screened seeds in the images taken per second is greater than the set frame number threshold;

[0016] Perform seed marking on the pre-screened seeds in the set number of pre-screened seed images, and perform underfilled marking on the underfilled pre-screened seeds to obtain a sample set;

[0017] Train a machine learning model based on the sample set to obtain an underfilled seed recognition model, which is used to output seed marking and underfilled marking according to the input pre-screened seed image; where when training the machine learning model, there is no restriction on the specific machine learning model, and edge detection algorithms, k-nearest neighbor algorithms, support vector machines, random forests, etc. can be used; during training, the sample set is randomly divided into a training set and a validation set according to a certain ratio (such as 6:4, 7:3, 5:5, etc.); use the training set to train the selected machine learning model. When training, use the pre-screened seed image as the input and the seed marking and underfilled marking as the output, so as to obtain the numerical values of the parameters of the first machine learning model; then substitute the obtained parameter values into the machine learning model, and then use the validation set to verify the accuracy of the output of the machine learning model to determine whether it meets the set accuracy standard. If not, adjust the parameters, the selected machine learning model or the loss function, and retrain. If so, determine the numerical values of the parameters of the machine learning model.

[0018] Obtain the number of underfilled markings and the number of seed markings, and calculate the fullness rate based on the output number of underfilled markings and seed markings. The fullness rate can be calculated by the following formula:

[0019]

[0020] Furthermore, the seed detection module is also used to divide the sample seeds into first sample seeds and second sample seeds.

[0021] Furthermore, the seed detection module performs a germination rate detection on the sample seeds, including the following steps:

[0022] Divide the first sample seeds into multiple groups evenly to obtain multiple first sample seed groups;

[0023] Test the germination rate of each first sample seed group in an independent environment respectively;

[0024] Calculate the average germination rate of each first sample seed group, and output the average germination rate as the germination rate. The quality of the corresponding recycled seeds can be judged based on the germination rate of the sample seeds;

[0025] Save the germination rate into the corresponding recycled seed information.

[0026] Furthermore, the seed detection module performs a germination rate detection on the sample seeds, including the following steps:

[0027] Obtain the number of second sample seeds;

[0028] Perform genetic testing on the second sample of seeds;

[0029] Mark the high-quality genes of the second sample of seeds and obtain the number of seeds with high-quality genes. The high-quality genes can be determined by planting the second sample of seeds and observing their growth characteristics to determine the genotype and phenotype of the plants, and setting the genotype with excellent phenotype as the high-quality genes;

[0030] Calculate the percentage of the number of seeds with high-quality genes in the number of the second sample of seeds to obtain the high-quality gene purity, so as to conveniently obtain the quality of the corresponding recycled seeds based on the high-quality gene purity;

[0031] Save the high-quality gene purity into the corresponding recycled seed information.

[0032] Furthermore, the management platform further includes an employee management module, which is used to set corresponding employee tags according to different employees and associate the employee information with the corresponding employee tags.

[0033] Furthermore, the employee management module is also used to send employees to negotiate and sign a transaction contract with the growers, obtain the contract value between the employees and the growers, and associate and bind the employees with the growers who have successfully signed the transaction contract. Based on the plumpness rate, germination rate, high-quality gene purity of each batch of recycled seeds of the growers and the grower rating, score the employees associated with the growers. Among them, the employees can negotiate the content of the transaction contract with the growers according to the plumpness rate, germination rate, high-quality gene purity of each variety model in the grower information and the grower rating. The contract value can be manually evaluated according to industry experience and the enterprise's system; the employees can be scored manually according to the self-defined scoring rules stipulated by the enterprise.

[0034] Compared with the prior art, an integrated information management platform for an agricultural company provided by the present invention can detect and evaluate the seeds of various growers through setting a seed information acquisition module, a grower information acquisition module, a relationship matching module, a seed recycling module, a seed screening module, a seed detection module and a grower evaluation module, and judge the influence of the planting methods of various growers on the quality of the reproduced seeds, so as to conveniently customize a cooperation plan for each grower according to the seed quality of different growers to promote the improvement of the quality of the recycled seeds. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings.

[0036] Figure 1 Schematic diagram of the system module provided by the embodiment of the present invention;

[0037] Figure 2 Diagram of the fullness rate calculation steps provided by the embodiment of the present invention;

[0038] Figure 3 Diagram of the germination rate calculation steps provided by the embodiment of the present invention;

[0039] Figure 4 Diagram of the high-quality gene purity calculation steps provided by the embodiment of the present invention. Detailed implementation manners

[0040] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0041] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality of" means two or more unless otherwise specifically defined. In addition, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the internal communication of two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0042] In the following, the exemplary embodiments will be described more fully with reference to the accompanying drawings, but the exemplary embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of this disclosure to those skilled in the art.

[0043] Without conflict, the embodiments of the present disclosure and the features in the embodiments may be combined with each other.

[0044] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0045] The embodiments described herein may be described with reference to plan views and / or cross-sectional views by means of the ideal schematic diagrams of the present disclosure. Therefore, the example illustrations may be modified according to manufacturing techniques and / or tolerances. Accordingly, the embodiments are not limited to the embodiments shown in the drawings, but include modifications of configurations formed based on manufacturing processes. Therefore, the regions illustrated in the drawings have schematic properties, and the shapes of the regions shown in the figures illustrate the specific shapes of the regions of the components, but are not intended to be restrictive.

[0046] Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein.

[0047] Please refer to Figure 1 , an integrated information management platform for an agricultural company, comprising a seed information acquisition module, a grower information acquisition module, a relationship matching module, a seed recycling module, a seed screening module, a seed detection module, and a grower evaluation module;

[0048] The seed information acquisition module is used to set seed tags according to different variety models of seeds, acquire seed information of various variety models, and associate the seed information with the corresponding seed tags, where the seed information may include seed source, origin, quantity, quality, sales destination, sales date, and relevant responsible personnel, etc.;

[0049] The grower information acquisition module is used to set corresponding grower tags according to different growers, acquire grower information of various growers, and associate the grower information with the corresponding grower tags, where the grower information may include grower types, such as individual businesses, enterprises, etc., grower addresses, contact information, sales contracts, seed purchase records, etc.;

[0050] The relationship matching module is used to acquire the variety models of seeds purchased by various growers and associate the growers with the variety models of seeds purchased by the growers;

[0051] The seed recycling module is used to recycle the seeds grown by various growers to obtain recycled seeds, and acquire recycled seed information. The recycled seed information includes the variety models of the recycled seeds, and associates the recycled seed information with the corresponding growers. Among them, the variety models of the recycled seeds can be initially determined by the variety models of the previous generation of seeds corresponding to the recycled seeds.

[0052] The seed screening module is used to preliminarily screen the recycled seeds using a sieve to separate impurities such as dust, stones, weeds, etc. from them, obtaining preliminarily screened seeds. Then, based on machine vision, plump preliminarily screened seeds are identified from the preliminarily screened seeds, the proportion of plump preliminarily screened seeds among the preliminarily screened seeds is calculated to obtain the plumpness rate, and the plumpness rate is saved into the corresponding recycled seed information;

[0053] Please refer to Figure 2 , where identifying plump preliminarily screened seeds from the preliminarily screened seeds based on machine vision and calculating the proportion of plump preliminarily screened seeds among the preliminarily screened seeds to obtain the plumpness rate includes the following steps:

[0054] (1) Spread the preliminarily screened seeds flat on the conveyor belt;

[0055] (2) Select a suitable industrial camera to take pictures of the preliminarily screened seeds on the conveyor belt to obtain images of the preliminarily screened seeds, where the suitable industrial camera is one that can clearly display more than the set frame number threshold of the preliminarily screened seeds in the images taken per second;

[0056] (3) Mark the seeds in a set number of images of the preliminarily screened seeds, and mark the non-plump preliminarily screened seeds as non-plump to obtain a sample set;

[0057] (4) Train a machine learning model based on the sample set to obtain a non-plump seed recognition model. The non-plump seed recognition model is used to output seed marks and non-plump marks according to the input images of the preliminarily screened seeds. When training the machine learning model, there is no restriction on the specific machine learning model, and edge detection algorithms, k-nearest neighbor algorithms, support vector machines, random forests, etc. can be used. During training, the sample set is randomly divided into a training set and a validation set according to a certain ratio (such as 6:4, 7:3, 5:5, etc.). The selected machine learning model is trained using the training set. During training, the images of the preliminarily screened seeds are used as the input, and the seed marks and non-plump marks are used as the output, so as to obtain the numerical values of the parameters of the first machine learning model. Then, the obtained parameter numerical values are substituted into the machine learning model, and the validation set is used to verify the accuracy of the output of the machine learning model to determine whether the set accuracy standard is reached. If not, the parameters, the selected machine learning model, or the loss function are adjusted and training is carried out again. If so, the numerical values of the parameters of the machine learning model are determined.

[0058] (5) Obtain the number of non-plump marks and the number of seed marks, and calculate the plumpness rate based on the output number of non-plump marks and the number of seed marks. The plumpness rate can be calculated by the following formula:

[0059]

[0060] The seed detection module is used to sample the initially screened seeds to obtain sample seeds, detect the germination rate and gene purity of the sample seeds, and save the detection results to the corresponding recycled seed information;

[0061] The grower evaluation module is used to evaluate and classify the corresponding growers based on the plumpness rate and the results detected by the seed detection module, namely, the plumpness rate, germination rate and high-quality gene purity of the recycled seeds, to obtain the grower rating, and save the grower rating to the corresponding grower information. Among them, when evaluating and classifying the growers, custom rules can be used. In one embodiment:

[0062] Set the grower score = 0.6 * germination rate * 100 / 100% + 0.4 * plumpness rate * 100 / 100%;

[0063] Growers with a grower score above 90 are extremely high-quality growers, growers with a grower score of 80 or above and below 90 are high-quality growers, growers with a grower score of 70 or above and below 80 are average growers, and growers with a grower score below 70 are low-quality growers;

[0064] Set special grade for growers with high-quality gene purity of 98% or above and being extremely high-quality growers, first grade for growers with high-quality gene purity of 95% or above and being high-quality growers or above, second grade for growers with high-quality gene purity of 85% or above and below 95% and being high-quality growers or above, third grade for growers with high-quality gene purity of 85% or above and below 95% and being average growers or above, and fourth grade for growers who are not special grade, first grade, second grade, or third grade.

[0065] The seed detection module is also used to divide the sample seeds into the first sample seeds and the second sample seeds.

[0066] Please refer to Figure 3 , the seed detection module detects the germination rate of the sample seeds, including the following steps:

[0067] (1) Divide the first sample seeds into multiple groups evenly to obtain multiple first sample seed groups;

[0068] (2) Test the germination rate of each first sample seed group in an independent environment respectively;

[0069] (3) Calculate the average germination rate of each first sample seed group, and output the average germination rate as the germination rate. The quality of the corresponding recycled seeds can be judged based on the germination rate of the sample seeds;

[0070] (4) Save the germination rate to the corresponding recycled seed information.

[0071] Please refer to Figure 4 , the seed detection module detects the germination rate of the sample seeds, including the following steps:

[0072] (1) Obtain the number of second sample seeds;

[0073] (2) Conduct gene detection on the second sample seeds;

[0074] (3) Mark the high-quality genes of the second sample seeds and obtain the number of seeds with high-quality genes. The high-quality genes can be determined by planting the second sample seeds and observing their growth characteristics to determine the genotype and phenotype of the plants, and setting the genotype with excellent phenotype as the high-quality genes;

[0075] (4) Calculate the percentage of the number of seeds with high-quality genes in the number of second sample seeds to obtain the high-quality gene purity, so as to facilitate obtaining the quality of the corresponding recycled seeds based on the high-quality gene purity;

[0076] (5) Save the high-quality gene purity into the corresponding recycled seed information.

[0077] The management platform also includes an employee management module. The employee management module is used to set corresponding employee tags according to different employees and obtain the association between employee information and the corresponding employee tags.

[0078] The employee management module is also used to send employees to negotiate and sign a transaction contract with the grower, obtain the contract value between the employee and the grower, and associate and bind the employee with the grower who has successfully signed the transaction contract. Based on the plumpness rate, germination rate, high-quality gene purity of each batch of recycled seeds of the grower and the grower rating, score the employees associated with the grower. Among them, the employee can negotiate the content of the transaction contract with the grower according to the plumpness rate, germination rate, high-quality gene purity of each variety model in the grower information and the grower rating. The contract value can be manually evaluated according to industry experience and the enterprise's system; the score for employees can be manually scored according to the self-defined scoring rules stipulated by the enterprise.

[0079] Only some exemplary embodiments of the present invention have been described above by way of illustration. Undoubtedly, for those of ordinary skill in the art, without departing from the spirit and scope of the present invention, the described embodiments can be modified in various different ways. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the protection scope of the claims of the present invention.

Claims

1. A comprehensive information management platform for agricultural companies, characterized by: It includes a seed information acquisition module, a grower information acquisition module, a relationship matching module, a seed recovery module, a seed screening module, a seed detection module and a grower evaluation module; The seed information acquisition module is used to set seed labels according to different seed varieties and models, and obtain seed information of various varieties and models, and associate the seed information with corresponding seed labels; The grower information acquisition module is used to set corresponding grower labels according to different growers, and obtain information of each grower, and associate the grower information with the corresponding grower label; The relationship matching module is used to obtain the variety model of seeds purchased by each grower, and associate the grower with the variety model of seeds purchased by the grower; The seed recovery module is used to recover the seeds planted by each grower, obtain the recovered seeds, and obtain the recovered seed information, the recovered seed information includes the variety model of the recovered seeds, and associate the recovered seed information with the corresponding grower; The seed screening module is used to use a sieve to perform preliminary screening on the recovered seeds, separate impurities therein, obtain primary screened seeds, and then identify primary screened seeds with full morphology from the primary screened seeds based on machine vision, calculate the proportion of primary screened seeds with full morphology to the primary screened seeds, obtain the full rate, and save the full rate to the corresponding recovered seed information; The seed detection module is used to sample the pre-screened seeds to obtain sample seeds, perform germination rate detection and gene purity detection on the sample seeds, and save the detection results to the corresponding recovered seed information; The grower evaluation module is used to evaluate and grade the corresponding growers based on the fullness rate and the results of the seed detection module, obtain the grower rating, and save the grower rating in the corresponding grower information.

2. The comprehensive information management platform for agricultural companies according to claim 1 is characterized by: The seed screening module identifies the primary screened seeds with full morphology from the primary screened seeds based on machine vision, calculates the proportion of the primary screened seeds with full morphology to the primary screened seeds, and obtains the full rate, including the following steps: Spread the pre-screened seeds onto the conveyor belt; Selecting a suitable industrial camera to shoot the pre-screened seeds on the conveyor belt to obtain a pre-screened seed image, wherein the number of pre-screened seeds clearly displayed in the image shot by the suitable industrial camera per second is greater than a set frame number threshold; Marking the primary screened seeds in a set number of primary screened seed images, and marking the incomplete primary screened seeds in the primary screened seeds as incomplete, to obtain a sample set; Training a machine learning model based on the sample set to obtain an incomplete seed recognition model, wherein the incomplete seed recognition model is used to output a seed mark and an incomplete mark according to an input primary screening seed image; The number of insufficiency marks and the number of seed marks are obtained, and the fullness rate is calculated based on the output number of insufficiency marks and the number of seed marks.

3. The comprehensive information management platform for agricultural companies according to claim 1 is characterized by: The seed detection module is further used to divide the sample seeds into first sample seeds and second sample seeds.

4. The comprehensive information management platform for agricultural companies according to claim 2 is characterized by: The seed detection module performs germination rate detection on the sample seeds, including the following steps: Dividing the first sample seeds equally into multiple groups to obtain multiple first sample seed groups; Testing the germination rate of each first sample seed group in an independent environment; Calculating an average germination rate of each first sample seed group, and outputting the average germination rate as a germination rate; The germination rate is saved in the corresponding recovered seed information.

5. The comprehensive information management platform for agricultural companies according to claim 2 is characterized by: The seed detection module performs germination rate detection on the sample seeds, including the following steps: Get the number of second sample seeds; Conduct genetic testing on the second sample of seeds; Marking the high-quality genes of the second sample seeds and obtaining the number of seeds with the high-quality genes; The purity of high-quality genes is obtained by calculating the percentage of the number of seeds with high-quality genes to the number of seeds in the second sample; Save the high-quality genetic purity to the corresponding recovered seed information.

6. The comprehensive information management platform for agricultural companies according to claim 1 is characterized by: The management platform also includes an employee management module, which is used to set corresponding employee tags according to different employees and obtain employee information and associate it with the corresponding employee tags.

7. The comprehensive information management platform for agricultural companies according to claim 6 is characterized by: The employee management module is also used to send employees to negotiate and sign transaction contracts with growers, obtain the contract value between employees and growers, and associate employees with growers who have successfully signed transaction contracts. Based on the fullness rate, germination rate and high-quality gene purity of each batch of recovered seeds from the growers and the grower rating, the employees associated with the growers are scored.

Images