A recommendation method for optimizing a resource of a kind of cultivation

Abstract

The application relates to the field of agricultural planting and breeding technology, and discloses a kind of recommended method of planting and breeding cycle resource optimization, comprising: collecting corn growth image data, and extracting the growth characteristics of each corn;In the characteristic data set, the characteristic data of all corns are extracted, Gaussian kernel density data processing is carried out, and representative data are determined;Each characteristic data is compared with the representative data to establish a first set, a second set and a third set;The representative data are compared with big data to determine the yield of a single plant, and the yield of a single plant is adjusted according to the first set, the second set and the third set to obtain the final yield of a single plant, and the total yield is determined;The total yield is compared with the initial value to determine whether the scale of breeding livestock and poultry is adjusted, and the recommended scale is determined.The application realizes the evaluation of the growth condition of corn, accurate yield prediction, and reasonable breeding scale recommendation based on the same.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of agricultural breeding technology, in particular to a kind of breeding cycle resource optimization recommendation method. BACKGROUND

[0002] Resource recycling and ecological agriculture become the key direction of sustainable development. The resource use mode of traditional agriculture and breeding industry is usually single, without fully considering the synergy and complementary effect between links, leading to resource waste and increasing ecological environmental pressure.

[0003] At present, CN115281032A based on the diversified ecological cycle of feed mulberry breeding method, proposes a kind of feed mulberry breeding livestock and / or cultivating edible fungi, livestock manure and / or edible fungi bran breeding earthworm, earthworm breeding waste planting feed mulberry scheme, according to the above scheme, corn is made into silage feed, silage feed is fed to livestock, livestock manure is bred to earthworm, and earthworm breeding waste is planted with corn. However, in the scheme, the breeding scale of each stage needs to be based on the experience of workers, and the growth process of plants is affected by many environmental factors. Once the evaluation is wrong, the subsequent breeding will be affected. In actual application, the accuracy is low and is not conducive to subsequent scheme.

[0004] Therefore, it is necessary to design a kind of breeding cycle resource optimization recommendation method to solve the problems existing in the prior art. SUMMARY

[0005] In view of this, the present application provides a kind of breeding cycle resource optimization recommendation method, to solve the current problem that the growth dynamic of feed plant cannot be accurately reflected, the prediction precision is low, and the reliability is poor.

[0006] In one aspect, the present application provides a kind of breeding cycle resource optimization recommendation method, comprising:

[0007] Collecting corn growth image data, processing all growth image data, extracting the growth characteristics of each corn, and establishing a feature data set;

[0008] Extracting the representation data of all corns in the feature data set, the representation data including plant height or leaf area, and performing Gaussian kernel density data processing on the representation data to determine representative data;

[0009] Comparing the representation data of each corn with the representative data to establish a first set, a second set and a third set;

[0010] The representative data is compared with big data to determine single plant predicted yield, and the single plant predicted yield is adjusted according to the first set, the second set and the third set to obtain a final single plant predicted yield, and a total yield is determined according to the final single plant predicted yield;

[0011] The total yield is compared with an initial value, and according to the comparison result, it is judged whether to adjust the scale of the breeding livestock and poultry, and a recommended scale is determined.

[0012] Further, when determining the representative data, the characteristic data is processed by Gaussian kernel density data processing, including:

[0013] All the same characteristic data of corn is integrated to form a first analysis data set, and the data in the first analysis data set is estimated by kernel density to determine the data with the highest probability as the representative data.

[0014] Further, when the data in the first analysis data set is estimated by kernel density, the Gaussian kernel density function is:

[0015]

[0016] Wherein, n is the number of data samples in the first analysis data set, h represents the smoothing bandwidth, s i represents the i-th data point in the first analysis data set, and x represents any variable in the overall data.

[0017] Further, the smoothing bandwidth is calculated by the following formula:

[0018]

[0019] Wherein, h represents the smoothing bandwidth, sigma represents the standard deviation of the data in the first analysis data set, beta1 represents the data skewness, beta2 represents the data kurtosis, n represents the number of data samples in the first analysis data set, and k represents the adjustment coefficient.

[0020] Wherein, the data skewness is calculated by the following formula:

[0021]

[0022] The data kurtosis is calculated by the following formula:

[0023]

[0024] Wherein, n represents the number of data samples in the first analysis data set, s i represents the i-th data point in the first analysis data set, represents the mean of the data in the first analysis data set, and sigma represents the standard deviation of the data in the first analysis data set.

[0025] Further, when establishing the first set, the second set and the third set by comparing each of the characterization data of the corns with the representative data respectively, it includes:

[0026] putting the corns with the characterization data equal to the representative data into the first set;

[0027] putting the corns with the characterization data greater than the representative data into the second set;

[0028] putting the corns with the characterization data less than the representative data into the third set.

[0029] Further, when adjusting the individual yield prediction to obtain the final individual yield prediction according to the first set, the second set and the third set, it includes:

[0030]

[0031] wherein Cz represents the final individual yield prediction, m is the number of the characterization data in the second set, Cp is the pth characterization data in the second set, C0 is the individual yield prediction, n is the number of the characterization data in the third set, Cq is the qth characterization data in the third set.

[0032] Further, when judging whether to adjust the scale of the breeding livestock and poultry according to the comparison result, it includes:

[0033] when the difference between the yield sum and the initial value is less than or equal to a% of the initial value, it is determined that the scale of the breeding livestock and poultry is not adjusted, and the initial scale is taken as the recommended scale;

[0034] when the difference between the yield sum and the initial value is greater than a% of the initial value, it is determined that the scale of the breeding livestock and poultry is adjusted, and the recommended scale is determined.

[0035] Further, when it is determined that the scale of the breeding livestock is adjusted, it includes:

[0036] obtaining a yield difference value according to the yield sum and the initial value, determining an adjustment coefficient according to the yield difference value, and adjusting the scale of the breeding livestock and poultry according to the adjustment coefficient, wherein the adjustment coefficient is in a positive correlation with the yield difference value.

[0037] Compared with the prior art, the present application has the beneficial effect that by processing the corn growth image data, a feature data set is established to determine representative data, and accurate growth characterization is provided for each corn. The growth condition of the corn is dynamically monitored, the yield of each corn is predicted through comparison with big data, and the accuracy of the prediction is further improved through comparison and adjustment of multiple data sets. Through comparison with the initial yield value, it is determined in a timely manner whether the scale of livestock and poultry breeding needs to be adjusted, precise resource allocation and optimization are realized, the synergistic effect of breeding and agricultural planting is improved, and resource waste is reduced.

[0038] In another aspect, the present application also provides a kind of breeding and raising cycle resource optimization recommendation system for applying the above-mentioned breeding and raising cycle resource optimization recommendation method, comprising:

[0039] The acquisition unit is configured to acquire corn growth image data, process all growth image data, extract the growth characteristics of each corn, and establish a feature data set;

[0040] The processing unit is configured to extract the characterization data of all corns in the feature data set, wherein the characterization data includes plant height or leaf area, and to perform Gaussian kernel density data processing on the characterization data to determine representative data;

[0041] The processing unit is further configured to compare the characterization data of each corn with the representative data to establish a first set, a second set and a third set;

[0042] The processing unit is further configured to compare the representative data with big data to determine the predicted yield of each corn, and to adjust the predicted yield of each corn according to the first set, the second set and the third set to obtain the final predicted yield of each corn, and to determine the total yield according to the final predicted yield of each corn;

[0043] The judging unit is configured to compare the total yield with an initial value, and to determine whether the scale of livestock and poultry breeding needs to be adjusted according to the comparison result, and to determine the recommended scale.

[0044] It can be understood that the above-mentioned breeding and raising cycle resource optimization recommendation system and method have the same beneficial effects, which will not be described here. BRIEF DESCRIPTION OF DRAWINGS

[0045] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are for purposes of illustration only and are not considered a limitation of the present application. Moreover, like reference numerals are used to designate like parts throughout the specification and drawings. In the drawings:

[0046] Figure 1A flowchart of a recommendation method for optimizing resource circulation provided by an embodiment of the present application is shown in the figure.

[0047] Figure 2 A functional block diagram of a recommendation system for optimizing resource circulation provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0048] Exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be accurately conveyed to those skilled in the art. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0049] In some embodiments of the present application, referring to Figure 1 The recommendation method for optimizing resource circulation includes the following steps:

[0050] S100: Collect corn growth image data, process all growth image data, extract the growth characteristics of each corn, and establish a feature data set;

[0051] S200: Extract the representation data of all corns in the feature data set, the representation data including plant height or leaf area, and perform Gaussian kernel density data processing on the representation data to determine the representative data;

[0052] S300: Compare the representation data of each corn with the representative data to establish a first set, a second set, and a third set;

[0053] S400: Compare the representative data with big data to determine the single plant predicted yield, adjust the single plant predicted yield according to the first set, the second set, and the third set to obtain the final single plant predicted yield, and determine the total yield according to the final single plant predicted yield;

[0054] S500: Compare the total yield with the initial value, determine whether to adjust the scale of the breeding livestock and poultry according to the comparison result, and determine the recommended scale.

[0055] Specifically, in S100, the growth images of corn are periodically obtained through image acquisition technology (such as high-definition sensors). Information about the growth height, leaf area, plant morphology, etc. of corn is provided. Computer vision and image processing techniques (such as image segmentation, edge detection, etc.) are used to extract the growth characteristics of corn from the images, such as leaf area, plant height, etc. A feature data set containing multiple corns is established. In S200, the representative data is used to measure the growth status of each corn. Through Gaussian kernel density processing, the extracted representative data is smoothed to eliminate noise and irregular fluctuations in the data, thereby more accurately reflecting the overall growth trend of corn. The data after Gaussian kernel density processing can more effectively capture the main mode of data distribution. In S300, the growth status of each corn is classified by comparing with the representative data. In S400, the representative data is compared with the historical data big data set, and the known growth and yield relationship in the historical data is used to determine the individual predicted yield of each corn, and the total yield is obtained by combining the planting scale. In S500, the total yield is compared with the initially set target yield. Analyze and recommend adjusting the scale of livestock and poultry breeding. For example, if the growth of corn is not as expected, the scale of livestock and poultry breeding needs to be reduced.

[0056] It can be understood that through efficient data collection, image analysis and Gaussian kernel density processing, the growth of corn is monitored, and accurate yield prediction is achieved by combining big data analysis. The accuracy and reliability of the prediction are improved. By comparing the various data sets, the prediction results can be self-corrected. Potential resource imbalance problems are discovered in a timely manner, and automatic recommendations are made to adjust the scale of livestock and poultry breeding. The resource utilization efficiency is improved.

[0057] In some embodiments of the present application, when the representative data is determined by Gaussian kernel density data processing of the representative data, the method comprises:

[0058] All the same representative data of corn are integrated to form a first analysis data set, and the data in the first analysis data set is kernel density estimated to determine the data with the highest probability as the representative data.

[0059] In some embodiments of the present application, when the data in the first analysis data set is kernel density estimated, the Gaussian kernel density function is:

[0060]

[0061] Where n is the number of data samples in the first analysis data set, h represents the smoothing bandwidth, s i represents the i-th data point in the first analysis data set, and x represents any variable in the overall data.

[0062] In some embodiments of the present application, the smoothing bandwidth is calculated by the following formula:

[0063]

[0064] wherein, h represents a smoothing bandwidth, σ represents a standard deviation of data in the first analysis data set, β1 represents a data skewness, β2 represents a data kurtosis, n represents a number of data samples in the first analysis data set, and k represents an adjustment coefficient;

[0065] wherein, the data skewness is obtained by the following formula:

[0066]

[0067] the data kurtosis is obtained by the following formula:

[0068]

[0069] wherein, n represents a number of data samples in the first analysis data set, and s i represents an i-th data point in the first analysis data set, represents a mean value of data in the first analysis data set, and σ represents a standard deviation of data in the first analysis data set.

[0070] It can be understood that the kernel density estimation can deeply mine the inherent law of data without relying on explicit assumptions, and provide more accurate and robust analysis results. By calculating the skewness and kurtosis of the data, the adjustment of the smoothing bandwidth is more adaptive to the distribution characteristics of the data, which improves the accuracy and stability of the overall prediction model. The accurate extraction of the representative data helps to further adjust the breeding scale and optimize resource allocation.

[0071] In some embodiments of the present application, when the characteristic data of each corn is compared with the representative data to establish the first set, the second set and the third set, respectively, the comparison includes:

[0072] the corn corresponding to the characteristic data equal to the representative data is classified into the first set;

[0073] the corn corresponding to the characteristic data greater than the representative data is classified into the second set;

[0074] the corn corresponding to the characteristic data less than the representative data is classified into the third set.

[0075] In some embodiments of the present application, when the single plant predicted yield is adjusted according to the first set, the second set and the third set to obtain the final single plant predicted yield, the adjustment includes:

[0076]

[0077] Wherein, Cz represents the final single plant predicted yield, m is the number of characteristic data in the second set, Cp is the pth characteristic data in the second set, C0 is the single plant predicted yield, n is the number of characteristic data in the third set, Cq is the qth characteristic data in the third set.

[0078] It can be understood that the comparison of the characteristic data of corn and the representative data, the construction of the data set and the fine adjustment of the single plant predicted yield according to the set ensure that the yield prediction is more in line with the actual growth conditions, improves the prediction accuracy and avoids the accumulation of errors caused by a single standard.

[0079] In some embodiments of the present application, when it is determined whether to adjust the scale of the livestock and poultry according to the comparison result, it includes: when the difference between the yield sum and the initial value is less than or equal to a% of the initial value, it is determined that the scale of the livestock and poultry is not adjusted, and the initial scale is taken as the recommended scale; when the difference between the yield sum and the initial value is greater than a% of the initial value, it is determined that the scale of the livestock and poultry is adjusted, and the recommended scale is determined.

[0080] In some embodiments of the present application, when it is determined that the scale of the livestock and poultry is adjusted, it includes: obtaining a yield difference according to the yield sum and the initial value, the yield difference being the difference between the yield sum and the initial value, determining an adjustment coefficient according to the yield difference, and adjusting the scale of the livestock and poultry according to the adjustment coefficient, the adjustment coefficient being in a positive correlation with the yield difference.

[0081] It can be understood that by setting a reasonable tolerance threshold, frequent adjustment caused by small fluctuations is avoided, and the stability and efficiency of the operation are ensured. The adjustment process flexibly responds to the actual resource utilization. It can more accurately adapt to different environmental changes and resource demand changes.

[0082] In the above embodiments, the growth image data of corn is processed, the characteristic data set is established, the representative data is determined, and accurate growth characteristics are provided for each corn. The growth conditions of corn are dynamically monitored, the single plant yield of each corn is predicted through comparison with big data, and the accuracy of the prediction is further improved through comparison and adjustment of multiple data sets. Through comparison with the initial yield value, it is determined in time whether the scale of livestock and poultry breeding needs to be adjusted, precise resource allocation and optimization are realized, the synergistic effect of breeding and agricultural planting is improved, and resource waste is reduced.

[0083] In another preferred mode based on the above embodiments, referring to Figure 2 The present embodiment provides a kind of breeding and raising cycle resource optimization recommendation system for applying the recommended method of breeding and raising cycle resource optimization described above, including:

[0084] The collecting unit is configured to collect corn growth image data, process all the growth image data, extract growth features of each corn, and establish a feature data set;

[0085] The processing unit is configured to extract representation data of all the corns from the feature data set, the representation data including plant height or leaf area, and perform Gaussian kernel density data processing on the representation data to determine representative data;

[0086] The processing unit is further configured to compare the representation data of each corn with the representative data to establish a first set, a second set and a third set, respectively;

[0087] The processing unit is further configured to compare the representative data with big data to determine single-predicted yield, adjust the single-predicted yield according to the first set, the second set and the third set to obtain final single-predicted yield, and determine yield sum according to the final single-predicted yield;

[0088] The judging unit is configured to compare the yield sum with an initial value, judge whether to adjust the scale of the breeding livestock and poultry according to the comparison result, and determine a recommended scale.

[0089] It can be understood that the above-mentioned recommended system and method for optimizing breeding and cultivation cycle resources have the same beneficial effects, which will not be described here.

[0090] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit it. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that the specific embodiments of the present application can be modified or replaced by the same, without departing from the spirit and scope of the present application. Any modification or equivalent replacement, which does not depart from the spirit and scope of the present application, should be covered within the protection scope of the claims of the present application.

Claims

1. A recommended method for optimizing crop-livestock cycle resources, characterized in that: include: Collect corn growth image data, process all growth image data, extract the growth characteristics of each corn, and establish a feature data set; Extracting characterization data of all corns from the feature data set, the characterization data including plant height or leaf area, performing Gaussian kernel density data processing on the characterization data to determine representative data; Comparing the characteristic data of each corn with the representative data to establish a first set, a second set, and a third set; Comparing the representative data with the big data to determine a predicted yield per plant, adjusting the predicted yield per plant based on the first set, the second set, and the third set to obtain a final predicted yield per plant, and determining a total yield based on the final predicted yield per plant; Comparing the total output with the initial value, judging whether to adjust the scale of livestock and poultry breeding based on the comparison result, and determining the recommended scale; When the predicted yield per plant is adjusted according to the first set, the second set, and the third set to obtain a final predicted yield per plant, the method includes: Among them, Cz represents the final predicted yield of a single plant, m is the number of characterization data in the second set, Cp is the pth characterization data in the second set, C0 is the predicted yield of a single plant, n is the number of characterization data in the third set, and Cq is the qth characterization data in the third set.

2. The recommendation method according to claim 1, characterized in that Performing Gaussian kernel density data processing on the characterization data to determine representative data includes: The same characterization data of all corns are integrated to form a first analysis data set, kernel density estimation is performed on the data in the first analysis data set, and the data with the highest probability is determined to be the representative data.

3. The recommendation method according to claim 2, characterized in that: When performing kernel density estimation on the data in the first analysis dataset, the Gaussian kernel density function is: Where n is the number of data samples in the first analysis data set, h is the smoothing bandwidth, and s is the i Represents the i-th data point in the first analysis data set, and x represents any variable in the overall data.

4. The recommendation method according to claim 3, characterized in that: The smoothing bandwidth is calculated by the following formula: Where h represents the smoothing bandwidth, σ represents the standard deviation of the data in the first analysis data set, β1 represents the data skewness, β2 represents the data kurtosis, n represents the number of data samples in the first analysis data set, and k represents the adjustment coefficient; The data skewness is calculated by the following formula: The data kurtosis is calculated by the following formula: Where n represents the number of data samples in the first analysis data set, s i represents the i-th data point in the first analysis data set, represents the mean of the data in the first analysis data set, and σ represents the standard deviation of the data in the first analysis data set.

5. The recommendation method according to claim 1, characterized in that: When the characteristic data of each corn are compared with the representative data to establish the first set, the second set and the third set, the method includes: Classifying the corn corresponding to the characterization data being equal to the representative data into the first set; The corn corresponding to the characterization data being greater than the representative data is classified into the second set; The corn corresponding to the characterization data being smaller than the representative data is classified into the third set.

Images