Grass and livestock balance patrol supervision method and system

Abstract

The invention relates to the technical field of grassland livestock management, in particular to a grass and livestock balance patrol supervision method and system, and the method comprises the steps: obtaining historical grassland livestock data of a current supervision grassland in a historical patrol supervision time period; updating an original grass and livestock balance model according to the historical grassland livestock data, and generating an enhanced grass and livestock balance model; acquiring real-time livestock patrol data of the current supervised grassland; and according to the real-time livestock patrolling data and the enhanced livestock balance model, generating a livestock balance livestock suggestion. According to the method, key parameters in the model are more accurately estimated and updated according to historical data matched with the current supervised grassland, so that high-efficiency and high-precision supervision and management of grass and livestock balance are realized.

Description

Technical Field

[0001] The present application relates to the technical field of grassland livestock management, and particularly to a method and system for grass-livestock balance patrol supervision. Background Art

[0002] Grass-livestock balance refers to the balance relationship between the growth of herbaceous plants in the grassland and livestock grazing in the grassland ecosystem. In order to maintain the health of the grassland ecosystem, the supervision and patrol of grass-livestock balance are crucial.

[0003] In the prior art, regarding the method of grass-livestock balance, for example, the Chinese invention patent with the publication number CN113011235A discloses a multi-source remote sensing grassland grass-livestock balance evaluation method based on a CPU-GPU heterogeneous platform on June 22, 2021, including the following steps: obtaining remote sensing data and performing preprocessing; extracting grassland classification according to the preprocessed remote sensing data; obtaining the measured data of the grass yield sample points of each classified grassland; establishing a grass yield random forest estimation model using a CART decision tree according to the remote sensing data of grassland classification extraction and the measured data of the grass yield sample points of each classified grassland; taking different decision trees as tasks for parallel computing, distributing them on the CPU and GPU for parallel training, and finally synthesizing all the decision trees into a final random forest; performing CPU-GPU parallel estimation through the grass yield random forest estimation model according to the remote sensing data of grassland classification extraction and outputting the estimated total grass yield result.

[0004] Although the technical solution in the above patent document can evaluate the grass-livestock balance using the grass-livestock balance index and the grassland carrying capacity pressure index according to the estimated total grass yield result, however, it still has problems. Specifically, similar to other methods in the prior art, it adopts a relatively broad model, such as the grass yield random forest estimation model, which is prone to the problem that due to the single and broad model, it does not match the specific grassland area, and thus easily leads to inaccurate supervision of grass-livestock balance. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide a grass-livestock balance patrol supervision method and system that can solve the problem that due to the single and broad model, it does not match the specific grassland area, and thus easily leads to inaccurate supervision of grass-livestock balance. By estimating and updating the key parameters in the model more precisely according to the historical data matching the currently supervised grassland, the high-efficiency and high-precision supervision and management of grass-livestock balance can be realized.

[0006] The technical solution of the present invention is as follows:

[0007] A grass-livestock balance patrol supervision method, the method includes:

[0008] Obtain the historical grassland livestock data of the current supervised grassland within the historical patrol and supervision time period;

[0009] Update the original grassland-livestock balance model according to the historical grassland livestock data, and generate an enhanced grassland-livestock balance model, wherein the original grassland-livestock balance model is preset;

[0010] Obtain the real-time livestock patrol data of the current supervised grassland;

[0011] Generate grassland-livestock balance livestock suggestions according to the real-time livestock patrol data and the enhanced grassland-livestock balance model, wherein the grassland-livestock balance livestock suggestions are used to assist grassland-livestock balance supervisors in adjusting livestock.

[0012] Optionally, updating the original grassland-livestock balance model according to the historical grassland livestock data and generating an enhanced grassland-livestock balance model includes:

[0013] Generate a grassland growth factor according to the historical grassland livestock data;

[0014] Generate a grassland health quality factor according to the historical grassland livestock data;

[0015] Update the original grassland-livestock balance model according to the grassland growth factor and the grassland health quality factor, and generate an enhanced grassland-livestock balance model.

[0016] Optionally, generating a grassland growth factor according to the historical grassland livestock data includes:

[0017] Extract grassland growth environment data according to the historical grassland livestock data in accordance with the sampling time period;

[0018] Normalize the grassland growth environment data and generate standard grassland growth environment data;

[0019] Extract and generate grassland plant quantity according to the standard grassland growth environment data at preset data collection points;

[0020] Calculate the plant growth rate of the grassland plant quantity corresponding to adjacent two data collection points respectively;

[0021] Calculate the mean value of each plant growth rate and set the mean value as the grassland growth factor.

[0022] Optionally, the adjacent two data collection points are the first time point and the second time point respectively, the grassland plant quantity corresponding to the first time point is the first plant quantity, and the grassland plant quantity corresponding to the second time point is the second plant quantity;

[0023] Based on the following formula, calculate the plant growth rate of the grassland plant quantity corresponding to adjacent two data collection points:

[0024]

[0025] Among them, rs is the plant growth rate, Uaf is the second plant quantity, Ube is the first plant quantity, Taf is the second time point, and Tbe is the first time point.

[0026] Optionally, generating a grassland health quality factor according to the historical grassland livestock data includes:

[0027] Extracting the original grassland basic data according to the historical grassland livestock data in sampling time periods. The number of the sampling time periods is multiple, one sampling time period corresponds to one piece of the original grassland basic data, and one piece of the original grassland data includes multiple grassland original parameters;

[0028] Performing normalization processing on the grassland original parameters corresponding to each piece of the original grassland data and respectively generating standard grassland parameters;

[0029] Obtaining the grassland health impact weights corresponding to each of the standard grassland parameters;

[0030] Obtaining the grassland attenuation coefficient of the current supervised grassland;

[0031] Generating a grassland health coefficient according to the grassland attenuation coefficient, the standard grassland parameters corresponding to each piece of the original grassland data, and the grassland health impact weights, where one piece of the original grassland basic data corresponds to one grassland health coefficient;

[0032] Generating a grassland health quality factor according to each of the grassland health coefficients.

[0033] Optionally, generating a grassland health coefficient based on the following formula:

[0034]

[0035] Among them, Qt is the grassland health coefficient, λ is the grassland attenuation coefficient, Qpr is the original health coefficient, M is the number of standard grassland parameters, αi is the grassland health impact weight corresponding to the i-th standard grassland parameter, p is the identifier of the standard grassland parameter, Zp(t) is the parameter value of the standard grassland parameter p at the time point t in the sampling time period, κi is the exponential coefficient of the i-th standard grassland parameter, m is the number of impact parameters related to the i-th standard grassland parameter, Zpj(t) is the parameter value of the j-th standard grassland parameter that interacts with the standard grassland parameter p at the time point t in the sampling time period, and νij is the impact index coefficient between the i-th standard grassland parameter and the j-th standard grassland parameter.

[0036] Optionally, obtaining the grassland attenuation coefficient of the current supervised grassland includes:

[0037] Obtain the recovery half-life of the current supervised grassland;

[0038] Based on the recovery half-life, generate a grassland decay coefficient according to the following formula:

[0039] λ = e -ln(2) / Tah ;

[0040] where λ is the grassland decay coefficient, e is the base of the natural logarithm, and Tah is the recovery half-life.

[0041] In this embodiment, the recovery half-life of the current supervised grassland refers to the time required for the current supervised grassland to recover to half of its initial state, and is used to represent the ecological recovery ability of the current supervised grassland. The recovery half-life is set by measuring in advance before livestock grazing in the current supervised grassland or by measuring in a grassland similar to the current supervised grassland. Then, the impact of time on grassland health is represented by generating a grassland decay coefficient.

[0042] Optionally, the enhanced grass-livestock balance model is as follows:

[0043]

[0044] where G(x) is the biomass of the current supervised grassland, x is time, Rrs is the grassland growth factor, K is the carrying capacity of the current supervised grassland, c is the grassland consumption coefficient, ΔQ is the grassland health quality factor, and N(x) is the number of livestock in the current supervised grassland.

[0045] Optionally, the method further includes obtaining the carrying capacity of the current supervised grassland:

[0046] Extract grassland environmental data according to the historical grassland livestock data, where the grassland environmental data includes a temperature information set, a precipitation information set, and a sunshine duration information set;

[0047] Generate a temperature average value according to the temperature information set;

[0048] Generate a precipitation average value according to the precipitation information set;

[0049] Generate a sunshine duration average value according to the sunshine duration information set;

[0050] Based on the temperature average value, precipitation average value, and sunshine duration average value, generate the carrying capacity of the current supervised grassland according to the following formula:

[0051]

[0052] Wherein, K is the carrying capacity of the currently supervised grassland, Pot is the theoretical maximum biomass, ΔTavr is the average temperature, Tmin is the standard minimum growth temperature, Tmax is the standard maximum growth temperature, ΔRavr is the average precipitation, Rot is the optimal precipitation, ΔSavr is the average sunshine duration, Sot is the optimal sunshine duration, and Cres is the unit biological resource.

[0053] Optionally, a grass-livestock balance patrol and supervision system is also provided. The system includes:

[0054] A historical livestock data acquisition module for acquiring historical grassland livestock data of the currently supervised grassland during the historical patrol and supervision time period;

[0055] An enhanced balance model generation module for updating the original grass-livestock balance model according to the historical grassland livestock data and generating an enhanced grass-livestock balance model, wherein the original grass-livestock balance model is preset;

[0056] A real-time livestock data acquisition module for acquiring real-time livestock patrol data of the currently supervised grassland;

[0057] A grass-livestock balance suggestion generation module for generating grass-livestock balance livestock suggestions according to the real-time livestock patrol data and the enhanced grass-livestock balance model, wherein the grass-livestock balance livestock suggestions are used to assist grass-livestock balance supervisors in adjusting livestock.

[0058] Optionally, the enhanced balance model generation module is further configured to: generate a grassland growth factor according to the historical grassland livestock data; generate a grassland health quality factor according to the historical grassland livestock data; update the original grass-livestock balance model according to the grassland growth factor and the grassland health quality factor, and generate an enhanced grass-livestock balance model.

[0059] Optionally, the enhanced balance model generation module is further configured to: extract grassland growth environment data according to the historical grassland livestock data in accordance with the sampling time period; perform normalization processing on the grassland growth environment data and generate standard grassland growth environment data; extract and generate grassland plant quantity according to the standard grassland growth environment data at preset data collection points; calculate the plant growth rate of the grassland plant quantity corresponding to two adjacent data collection points respectively; calculate the average value of each plant growth rate and set the average value as the grassland growth factor.

[0060] Optionally, two adjacent data collection points are a first time point and a second time point respectively, the grassland plant quantity corresponding to the first time point is the first plant quantity, and the grassland plant quantity corresponding to the second time point is the second plant quantity; the enhanced balance model generation module is further configured to: calculate the plant growth rate of the grassland plant quantity corresponding to two adjacent data collection points based on the following formula:

[0061]

[0062] Wherein, rs is the plant growth rate, Uaf is the second plant quantity, Ube is the first plant quantity, Taf is the second time point, and Tbe is the first time point.

[0063] Optionally, the enhanced balance model generation module is further configured to: extract original grassland basic data according to the historical grassland livestock data in sampling time periods, wherein the number of sampling time periods is multiple, one sampling time period corresponds to one piece of original grassland basic data, and one piece of original grassland data includes multiple grassland original parameters; perform normalization processing on the grassland original parameters corresponding to each piece of original grassland data and generate standard grassland parameters respectively; obtain the grassland health impact weights corresponding to each standard grassland parameter; obtain the grassland decay coefficient of the current supervised grassland; generate a grassland health coefficient according to the grassland decay coefficient, the standard grassland parameters corresponding to each piece of original grassland data, and the grassland health impact weights, wherein one piece of original grassland basic data corresponds to one grassland health coefficient; generate a grassland health quality factor according to each grassland health coefficient.

[0064] Optionally, the enhanced balance model generation module is further configured to: generate a grassland health coefficient based on the following formula:

[0065]

[0066] Wherein, Qt is the grassland health coefficient, λ is the grassland decay coefficient, Qpr is the original health coefficient, M is the number of standard grassland parameters, αi is the grassland health impact weight corresponding to the i-th standard grassland parameter, p is the identifier of the standard grassland parameter, Zp(t) is the parameter value of the standard grassland parameter p at the time point t in the sampling time period, κi is the exponential coefficient of the i-th standard grassland parameter, m is the number of impact parameters related to the i-th standard grassland parameter, Zpj(t) is the parameter value of the j-th standard grassland parameter that interacts with the standard grassland parameter p at the time point t in the sampling time period, and νij is the impact index coefficient between the i-th standard grassland parameter and the j-th standard grassland parameter.

[0067] Optionally, the enhanced balance model generation module is further configured to: obtain the recovery half-life of the current supervised grassland; generate a grassland decay coefficient based on the following formula according to the recovery half-life:

[0068] λ = e -ln(2) / Tah ;

[0069] Wherein, λ is the grassland decay coefficient, e is the base of the natural logarithm, and Tah is the recovery half-life.

[0070] Optionally, the enhanced balance model generation module is further configured to update the model, and the model is as follows:

[0071]

[0072] Wherein, G(x) is the biomass of the currently supervised grassland, x is time, Rrs is the grassland growth factor, which is, K is the carrying capacity of the currently supervised grassland, c is the grassland consumption coefficient, ΔQ is the grassland health quality factor, and N(x) is the livestock quantity of the currently supervised grassland.

[0073] Optionally, the enhanced balance model generation module is further configured to: extract grassland environment data according to the historical grassland livestock data, wherein the grassland environment data includes a temperature information set, a precipitation information set, and a sunshine duration information set; generate a temperature average value according to the temperature information set; generate a precipitation average value according to the precipitation information set; generate a sunshine duration average value according to the sunshine duration information set; and generate the carrying capacity of the currently supervised grassland based on the following formula according to the temperature average value, the precipitation average value, and the sunshine duration average value:

[0074]

[0075] Wherein, K is the carrying capacity of the currently supervised grassland, Pot is the theoretical maximum biomass, ΔTavr is the temperature average value, Tmin is the standard minimum growth temperature, Tmax is the standard maximum growth temperature, ΔRavr is the precipitation average value, Rot is the optimal precipitation, ΔSavr is the sunshine duration average value, Sot is the optimal sunshine duration, and Cres is the unit biological resource.

[0076] Optionally, a computer device is further provided, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned grass-livestock balance patrol supervision method are implemented.

[0077] Optionally, a computer-readable storage medium is further provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned grass-livestock balance patrol supervision method are implemented.

[0078] The technical effects achieved by the present invention are as follows:

[0079] The above-mentioned grass-livestock balance patrol and supervision method and system obtain the historical grassland livestock data of the current supervised grassland during the historical patrol and supervision time period; update the original grass-livestock balance model according to the historical grassland livestock data, and generate an enhanced grass-livestock balance model; obtain the real-time livestock patrol data of the current supervised grassland; generate grass-livestock balance livestock suggestions according to the real-time livestock patrol data and the enhanced grass-livestock balance model, wherein the grass-livestock balance livestock suggestions are used to assist grass-livestock balance supervisors in adjusting livestock. In this application, in order to effectively and reliably supervise the grass-livestock balance of grasslands and overcome the problems in the prior art that the models are single and broad and do not match specific grassland areas, resulting in inaccurate grass-livestock balance supervision, an original grass-livestock balance model is obtained in advance in this application. In order to make the original grass-livestock balance model adapt to the current supervised grassland, it is necessary to monitor the current supervised grassland, that is, obtain the historical livestock data of the current supervised grassland, specifically, obtain the historical grassland livestock data of the current supervised grassland during the historical patrol and supervision time period. Then, update the original grass-livestock balance model according to the historical grassland livestock data, and generate an enhanced grass-livestock balance model. Through the generated enhanced grass-livestock balance model, the model matches the grassland that needs to be supervised currently. That is, by introducing historical livestock and grassland data, the accuracy, stability and adaptability of the enhanced grass-livestock balance model are improved to achieve better prediction of the current grass-livestock balance of the grassland, and then more efficient real-time adjustment. Furthermore, obtain the real-time livestock patrol data of the current supervised grassland; then generate grass-livestock balance livestock suggestions according to the real-time livestock patrol data and the enhanced grass-livestock balance model, and assist grass-livestock balance supervisors in adjusting livestock through the grass-livestock balance livestock suggestions. Therefore, this application more accurately estimates the key parameters in the model and updates them by targeting the historical data matching the current supervised grassland, so as to achieve high-efficiency and high-precision supervision and management of the grass-livestock balance. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] Figure 1 It is a schematic flowchart of the grass-livestock balance patrol and supervision method in an embodiment;

[0081] Figure 2 It is a structural block diagram of the grass-livestock balance patrol and supervision system in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0082] In order to make the purpose, technical solutions and advantages of this application clearer, the following further describes this application in detail with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application, and are not used to limit this application.

[0083] In one embodiment, as Figure 1As shown, a method for grassland-livestock balance patrol supervision is provided, and the method includes:

[0084] Step S100: Obtain the historical grassland-livestock data of the current supervised grassland during the historical patrol supervision time period;

[0085] Step S200: Update the original grassland-livestock balance model according to the historical grassland-livestock data, and generate an enhanced grassland-livestock balance model, wherein the original grassland-livestock balance model is preset;

[0086] Step S300: Obtain the real-time livestock patrol data of the current supervised grassland;

[0087] Step S400: Generate grassland-livestock balance livestock suggestions according to the real-time livestock patrol data and the enhanced grassland-livestock balance model, wherein the grassland-livestock balance livestock suggestions are used to assist grassland-livestock balance supervisors in adjusting livestock.

[0088] In this embodiment, in order to effectively and reliably supervise the grassland-livestock balance of the grassland and overcome the problems in the prior art that the model is single and broad and does not match the specific grassland area, resulting in inaccurate grassland-livestock balance supervision, in this application, the original grassland-livestock balance model is obtained in advance. In order to make the original grassland-livestock balance model adapt to the current supervised grassland, it is necessary to monitor the current supervised grassland, that is, obtain the historical livestock data of the current supervised grassland, specifically, obtain the historical grassland-livestock data of the current supervised grassland during the historical patrol supervision time period. Then, update the original grassland-livestock balance model according to the historical grassland-livestock data, and generate an enhanced grassland-livestock balance model. Through the generated enhanced grassland-livestock balance model, the model is a model that matches the grassland that needs to be supervised currently. That is, by introducing historical livestock and grassland data, the accuracy, stability and adaptability of the enhanced grassland-livestock balance model are improved to achieve better prediction of the current grassland-livestock balance situation, and then more efficient real-time adjustment is carried out. Furthermore, obtain the real-time livestock patrol data of the current supervised grassland; then generate grassland-livestock balance livestock suggestions according to the real-time livestock patrol data and the enhanced grassland-livestock balance model, and assist grassland-livestock balance supervisors in adjusting livestock through the grassland-livestock balance livestock suggestions. Therefore, this application more accurately estimates the key parameters in the model and updates them by targeting the historical data matching the current supervised grassland, so as to achieve high-efficiency and high-precision grassland-livestock balance supervision and management.

[0089] In one embodiment, step S200: Update the original grassland-livestock balance model according to the historical grassland-livestock data, and generate an enhanced grassland-livestock balance model, includes:

[0090] Step S210: Generate a grassland growth factor according to the historical grassland-livestock data;

[0091] Step S220: Generate a grassland health quality factor based on the historical grassland livestock data;

[0092] Step S230: Update the original grass-livestock balance model according to the grassland growth factor and the grassland health quality factor, and generate an enhanced grass-livestock balance model.

[0093] In this embodiment, the grassland growth factor represents the magnitude of the growth and recovery ability of the currently supervised grassland during the historical patrol and supervision time period. The grassland health quality factor represents the grassland quality of the currently supervised grassland during the historical patrol and supervision time period. Therefore, by first generating a grassland growth factor according to the historical grassland livestock data, then generating a grassland health quality factor according to the historical grassland livestock data, and finally, comprehensively updating the original grass-livestock balance model with the grassland growth factor and the grassland health quality factor, and generating an enhanced grass-livestock balance model, subsequent accurate judgment and supervision of grass-livestock balance are realized through the enhanced grass-livestock balance model.

[0094] In one embodiment, in step S210, generating a grassland growth factor according to the historical grassland livestock data includes:

[0095] Step S211: Extract grassland growth environment data according to the historical grassland livestock data in accordance with the sampling time period;

[0096] Step S212: Perform normalization processing on the grassland growth environment data, and generate standard grassland growth environment data;

[0097] Step S213: Extract and generate the grassland plant quantity according to the standard grassland growth environment data at preset data collection points;

[0098] Step S214: Calculate the plant growth rate of the grassland plant quantity corresponding to two adjacent data collection points respectively;

[0099] Step S215: Calculate the average value of each plant growth rate, and set the average value as the grassland growth factor.

[0100] In this embodiment, by obtaining the sampling time period, the data is processed in sub-time periods to achieve refined data analysis. Specifically, the grassland growth environment data is extracted from the historical grassland livestock data according to the sampling time period, and then the dimension is unified. The Z-Score normalization method is used to normalize the grassland growth environment data and generate the standard grassland growth environment data. Then, according to the standard grassland growth environment data, the grassland plant quantity is extracted and generated according to the preset data collection points. The plant growth rate of the grassland plant quantity corresponding to two adjacent data collection points is calculated respectively. Finally, the average value of each plant growth rate is calculated, and the average value is set as the grassland growth factor, so as to first calculate the growth rate of each time period in a refined manner, then calculate the average value of the growth rates, and finally calculate the grassland growth factor that overall reflects the growth situation of the grassland.

[0101] In one embodiment, two adjacent data collection points are the first time point and the second time point respectively. The grassland plant quantity corresponding to the first time point is the first plant quantity, and the grassland plant quantity corresponding to the second time point is the second plant quantity.

[0102] Based on the following formula, the plant growth rate of the grassland plant quantity corresponding to two adjacent data collection points is calculated:

[0103]

[0104] Wherein, rs is the plant growth rate, Uaf is the second plant quantity, Ube is the first plant quantity, Taf is the second time point, and Tbe is the first time point.

[0105] In this embodiment, more refined calculations can also be performed through interpolation. In fact, the time interval between the first time point and the second time point is already very small. Therefore, the growth rate obtained by the interpolation method is similar to the growth rate calculated by the above formula. Therefore, in actual calculation, it is selected and set by those skilled in the art themselves.

[0106] In one embodiment, in step S220, generating the grassland health quality factor according to the historical grassland livestock data includes:

[0107] Step S221: Extract the original grassland basic data from the historical grassland livestock data according to the sampling time period. Wherein, the number of sampling time periods is multiple, one sampling time period corresponds to one original grassland basic data, and one original grassland data includes multiple grassland original parameters;

[0108] Step S222: Normalize the grassland original parameters corresponding to each original grassland data and generate standard grassland parameters respectively;

[0109] Step S223: Obtain the grassland health impact weights corresponding to each of the standard grassland parameters;

[0110] Step S224: Obtain the grassland attenuation coefficient of the currently supervised grassland;

[0111] Step S225: Generate a grassland health coefficient based on the grassland attenuation coefficient, the standard grassland parameters corresponding to each of the original grassland data, and the grassland health impact weights, where one of the original grassland basic data corresponds to one grassland health coefficient;

[0112] Step S226: Generate a grassland health quality factor based on each of the grassland health coefficients.

[0113] In this embodiment, the sampling time period is preset. By presetting the sampling time period, data extraction can be performed through the preset sampling time, thereby realizing the segmented processing of data. Specifically, the original grassland basic data is extracted according to the historical grassland livestock data in accordance with the sampling time period. The number of sampling time periods is multiple, one sampling time period corresponds to one original grassland basic data, and one original grassland data includes multiple grassland original parameters. Then, the grassland original parameters corresponding to each of the original grassland data are normalized using the Z-Score normalization method and standard grassland parameters are generated respectively to ensure the unity of the data dimension. Next, the grassland health impact weights corresponding to each of the standard grassland parameters are obtained. The grassland health impact weights are preset and represent the impact of each standard grassland parameter on the grassland quality. Then, the grassland attenuation coefficient of the currently supervised grassland is obtained. The grassland attenuation coefficient represents the impact of time on the grassland quality. Then, based on the grassland attenuation coefficient, the standard grassland parameters corresponding to each of the original grassland data, and the grassland health impact weights, a grassland health coefficient is generated, where one of the original grassland basic data corresponds to one grassland health coefficient. Finally, a grassland health quality factor is generated based on each of the grassland health coefficients. Specifically, the mean value of each of the grassland health coefficients is calculated and the mean value is set as the grassland health quality factor.

[0114] For example, taking the original grassland parameters corresponding to the original grassland data as the original soil humidity, original terrain slope, original vegetation cover, original precipitation, and original temperature. After obtaining the original soil humidity, original terrain slope, original vegetation cover, original precipitation, and original temperature, normalization processing is performed, that is, standardization processing is performed on the original soil humidity, original terrain slope, original vegetation cover, original precipitation, and original temperature to generate the standard soil humidity, standard terrain slope, standard vegetation cover, standard precipitation, and standard temperature. Then, obtain the grassland health impact weights corresponding to the standard soil humidity, standard terrain slope, standard vegetation cover, standard precipitation, and standard temperature, and then obtain the grassland attenuation coefficient of the current supervised grassland. Next, generate the grassland health coefficient corresponding to the current example according to the grassland attenuation coefficient and the standard soil humidity, standard terrain slope, standard vegetation cover, standard precipitation, and standard temperature. Finally, set the grassland health quality factor according to the mean value of each grassland health coefficient.

[0115] In one embodiment, based on the following formula, the grassland health coefficient is generated:

[0116]

[0117] where Qt is the grassland health coefficient, λ is the grassland attenuation coefficient, Qpr is the original health coefficient, M is the number of standard grassland parameters, αi is the grassland health impact weight corresponding to the i-th standard grassland parameter, p is the identifier of the standard grassland parameter, Zp(t) is the parameter value of the standard grassland parameter p at the time point t in the sampling time period, κi is the exponential coefficient of the i-th standard grassland parameter, m is the number of influence parameters related to the i-th standard grassland parameter, Zpj(t) is the parameter value of the j-th standard grassland parameter that interacts with the standard grassland parameter p at the time point t in the sampling time period, and νij is the influence index coefficient between the i-th standard grassland parameter and the j-th standard grassland parameter.

[0118] In this embodiment, the original health coefficient Qpr is a preset reference value, indicating the original health degree of the current supervised grassland. αi is the preset grassland health impact weight corresponding to the i-th standard grassland parameter, p is the identifier of the standard grassland parameter. For example, p can be the markers of the standard soil humidity, standard terrain slope, standard vegetation cover, standard precipitation, and standard temperature, and can be specifically marked as p1 - p5 to represent them respectively. κi is the exponential coefficient of the i-th standard grassland parameter, indicating the non-linear influence degree of the i-th standard grassland parameter on the grassland health. The influence index coefficient νij between the i-th standard grassland parameter and the j-th standard grassland parameter indicates the influence degree of the interaction between the i-th standard grassland parameter and the j-th standard grassland parameter on the grassland health.

[0119] Specifically, by calculating Zpj(t) νij to represent the interaction between different standard grassland parameters, and by calculating to represent the calculation of the exponential value of each standard grassland parameter, and then aggregating them by combining their respective grassland health impact weights, and finally generating the current original health coefficient by combining the grassland decay coefficient and the original health coefficient.

[0120] Therefore, by comprehensively considering each standard grassland parameter and the interaction between the standard grassland parameters, the generation of the grassland health coefficient is realized, enabling a more accurate representation of the health degree of the grassland.

[0121] In one embodiment, in step S214, obtaining the grassland decay coefficient of the current supervised grassland includes:

[0122] Step S2141: Obtain the recovery half-life of the current supervised grassland;

[0123] Step S2142: Based on the recovery half-life, generate the grassland decay coefficient according to the following formula:

[0124] λ = e -ln(2) / Tah ;

[0125] where λ is the grassland decay coefficient, e is the base of the natural logarithm, and Tah is the recovery half-life.

[0126] In this embodiment, the recovery half-life of the current supervised grassland refers to the time required for the current supervised grassland to recover to half of its initial state, which is used to represent the ecological recovery ability of the current supervised grassland. The recovery half-life is set by measuring the current supervised grassland before livestock grazing or by measuring a grassland similar to the current supervised grassland in advance. Then, the impact of time on grassland health is represented by generating the grassland decay coefficient.

[0127] In one embodiment, the enhanced grassland-livestock balance model is as follows:

[0128]

[0129] where G(x) is the biomass of the current supervised grassland, x is time, Rrs is the grassland growth factor, K is the carrying capacity of the current supervised grassland, c is the grassland consumption coefficient, ΔQ is the grassland health quality factor, and N(x) is the number of livestock in the current supervised grassland.

[0130] In this embodiment, the enhanced grassland-livestock balance model is set based on the logistic growth model, where the grassland consumption coefficient is set based on the actual environment of the current supervised grassland. Specifically, by setting to represent the situation of grassland growth, and by calculating To represent the grass consumption situation.

[0131] Furthermore, when the grass-livestock balance is achieved, the value of is 0. Substituting it into the above formula, we can get:

[0132]

[0133] Through further calculation, we can get:

[0134] Through further calculation, we can get:

[0135] Therefore, if we need to ensure that G is greater than 0, then we need to make: That is to say, it can be understood that the maximum livestock carrying capacity of the currently supervised grassland is

[0136] Furthermore, when the actual number of livestock is less than or equal to the livestock balance is achieved. When the actual number of livestock is greater than there is an overgrazing situation.

[0137] Therefore, in one embodiment, in steps S300 - S400, when obtaining the real-time livestock patrol data of the currently supervised grassland and generating grass-livestock balance livestock suggestions according to the real-time livestock patrol data and the enhanced grass-livestock balance model, by obtaining the actual number of livestock from the real-time livestock patrol data, comparing it with the maximum livestock carrying capacity, and judging whether it is less than or equal to the maximum livestock carrying capacity or greater than the maximum livestock carrying capacity, and further generating livestock suggestions, including reducing the livestock quantity or increasing the livestock quantity.

[0138] In another embodiment, in steps S300 - S400, when obtaining the real-time livestock patrol data of the currently supervised grassland and generating grass-livestock balance livestock suggestions according to the real-time livestock patrol data and the enhanced grass-livestock balance model,

[0139] It is also possible to first extract the specific data of the currently supervised grassland from the real-time livestock patrol data, fit the current data with the data during the historical patrol supervision time period, further update the model, and then judge the livestock balance according to the real-time data, which can also achieve accurate provision of suggestions.

[0140] In one embodiment, in step S214, the method further includes obtaining the carrying capacity of the currently supervised grassland:

[0141] Step S261: Extract the grassland environment data according to the historical grassland livestock data, where the grassland environment data includes a temperature information set, a precipitation information set, and a sunshine information set;

[0142] Step S262: Generate a temperature average value according to the temperature information set;

[0143] Step S263: Generate a precipitation average value according to the precipitation information set;

[0144] Step S264: Generate an average sunshine duration according to the sunshine information set;

[0145] Step S265: Generate the carrying capacity of the currently supervised grassland based on the temperature average value, precipitation average value, and average sunshine duration, according to the following formula:

[0146]

[0147] where K is the carrying capacity of the currently supervised grassland, Pot is the theoretical maximum biomass, ΔTavr is the temperature average value, Tmin is the standard minimum growth temperature, Tmax is the standard maximum growth temperature, ΔRavr is the precipitation average value, Rot is the optimal precipitation, ΔSavr is the average sunshine duration, Sot is the optimal sunshine duration, and Cres is the unit biological resource.

[0148] In this embodiment, the theoretical maximum biomass Pot is the potential biomass of the grassland under optimal conditions, which is determined and set in advance by monitoring the biomass data of the currently supervised grassland before grazing. It is a fixed value set in advance. The standard minimum growth temperature, the standard maximum growth temperature, the optimal precipitation, and the optimal sunshine duration are all set in advance. The unit biological resource Cres is the grassland resource required for unit biomass.

[0149] Specifically, by calculating to represent the growth situation of the currently supervised grassland under the conditions of the temperature average value, precipitation average value, and average sunshine duration. Then, divide it by the unit biological resource Cres to generate the carrying capacity K representing the currently supervised grassland.

[0150] In one embodiment, as Figure 2 shown, there is also provided a grass-livestock balance patrol and supervision system, which includes:

[0151] A historical livestock data acquisition module, configured to acquire the historical grassland livestock data of the currently supervised grassland during the historical patrol and supervision time period;

[0152] An enhanced balance model generation module, configured to update the original grass-livestock balance model according to the historical grassland livestock data and generate an enhanced grass-livestock balance model, where the original grass-livestock balance model is set in advance;

[0153] A real-time livestock data acquisition module for acquiring real-time livestock patrol data of the current supervised grassland;

[0154] A grassland-livestock balance recommendation generation module for generating grassland-livestock balance recommendations according to the real-time livestock patrol data and the enhanced grassland-livestock balance model, wherein the grassland-livestock balance recommendations are used to assist grassland-livestock balance supervisors in adjusting livestock.

[0155] In another embodiment, the enhanced balance model generation module is further configured to: generate a grassland growth factor according to the historical grassland livestock data; generate a grassland health quality factor according to the historical grassland livestock data; update the original grassland-livestock balance model according to the grassland growth factor and the grassland health quality factor, and generate an enhanced grassland-livestock balance model.

[0156] In another embodiment, the enhanced balance model generation module is further configured to: extract grassland growth environment data according to the historical grassland livestock data in a sampling time period; perform normalization processing on the grassland growth environment data, and generate standard grassland growth environment data; extract and generate grassland plant amounts according to the standard grassland growth environment data at preset data collection points; calculate the plant growth rates of the grassland plant amounts corresponding to two adjacent data collection points respectively; calculate the average value of each plant growth rate, and set the average value as the grassland growth factor.

[0157] In another embodiment, two adjacent data collection points are a first time point and a second time point respectively, the grassland plant amount corresponding to the first time point is a first plant amount, and the grassland plant amount corresponding to the second time point is a second plant amount; the enhanced balance model generation module is further configured to: calculate the plant growth rate of the grassland plant amounts corresponding to two adjacent data collection points based on the following formula:

[0158]

[0159] where rs is the plant growth rate, Uaf is the second plant amount, Ube is the first plant amount, Taf is the second time point, and Tbe is the first time point.

[0160] In another embodiment, the enhanced balance model generation module is further configured to: extract original grassland basic data from the historical grassland livestock data according to sampling time periods, where the number of sampling time periods is multiple, one sampling time period corresponds to one piece of original grassland basic data, and one piece of original grassland data includes multiple grassland original parameters; perform normalization processing on the grassland original parameters corresponding to each piece of original grassland data and generate standard grassland parameters respectively; obtain the grassland health impact weights corresponding to each standard grassland parameter; obtain the grassland attenuation coefficient of the currently supervised grassland; generate a grassland health coefficient according to the grassland attenuation coefficient, the standard grassland parameters corresponding to each piece of original grassland data, and the grassland health impact weights, where one piece of original grassland basic data corresponds to one grassland health coefficient; generate a grassland health quality factor according to each grassland health coefficient.

[0161] In another embodiment, the enhanced balance model generation module is further configured to: generate a grassland health coefficient based on the following formula:

[0162]

[0163] where Qt is the grassland health coefficient, λ is the grassland attenuation coefficient, Qpr is the original health coefficient, M is the number of standard grassland parameters, αi is the grassland health impact weight corresponding to the i-th standard grassland parameter, p is the identifier of the standard grassland parameter, Zp(t) is the parameter value of the standard grassland parameter p at the time point t in the sampling time period, κi is the exponential coefficient of the i-th standard grassland parameter, m is the number of impact parameters related to the i-th standard grassland parameter, Zpj(t) is the parameter value of the j-th standard grassland parameter that interacts with the standard grassland parameter p at the time point t in the sampling time period, and νij is the impact index coefficient between the i-th standard grassland parameter and the j-th standard grassland parameter.

[0164] In another embodiment, the enhanced balance model generation module is further configured to: obtain the recovery half-life of the currently supervised grassland; generate a grassland attenuation coefficient based on the following formula according to the recovery half-life:

[0165] λ = e -ln(2) / Tah ;

[0166] where λ is the grassland attenuation coefficient, e is the base of the natural logarithm, and Tah is the recovery half-life.

[0167] In another embodiment, the enhanced balance model generation module is further configured to update the model as follows:

[0168]

[0169] Among them, G(x) is the biomass of the currently supervised grassland, x is time, Rrs is the grassland growth factor, which is, K is the carrying capacity of the currently supervised grassland, c is the grassland consumption coefficient, ΔQ is the grassland health quality factor, and N(x) is the livestock quantity of the currently supervised grassland.

[0170] In another embodiment, the enhanced balance model generation module is further configured to: extract grassland environment data according to the historical grassland livestock data, where the grassland environment data includes a temperature information set, a precipitation information set, and a sunshine duration information set; generate a temperature average value according to the temperature information set; generate a precipitation average value according to the precipitation information set; generate a sunshine duration average value according to the sunshine duration information set; and generate the carrying capacity of the currently supervised grassland based on the following formula according to the temperature average value, the precipitation average value, and the sunshine duration average value:

[0171]

[0172] Among them, K is the carrying capacity of the currently supervised grassland, Pot is the theoretical maximum biomass, ΔTavr is the temperature average value, Tmin is the standard minimum growth temperature, Tmax is the standard maximum growth temperature, ΔRavr is the precipitation average value, Rot is the optimal precipitation, ΔSavr is the sunshine duration average value, Sot is the optimal sunshine duration, and Cres is the unit biological resource.

[0173] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned grass-livestock balance patrol and supervision method are implemented.

[0174] In one embodiment, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned grass-livestock balance patrol and supervision method are implemented.

[0175] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0176] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0177] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for monitoring and patrolling a grass-livestock balance, characterized in that: The method comprises: Obtain historical grassland animal husbandry data of the currently supervised grassland during the historical patrol and supervision period; The original grass-livestock balance model is updated according to the historical grassland animal husbandry data, and an enhanced grass-livestock balance model is generated, wherein the original grass-livestock balance model is preset; Obtaining real-time animal husbandry patrol data of the currently supervised grassland; A grass-livestock balance livestock husbandry suggestion is generated based on the real-time livestock patrol data and the enhanced grass-livestock balance model, wherein the grass-livestock balance livestock husbandry suggestion is used to assist grass-livestock balance supervisors in adjusting livestock husbandry.

2. The grass-livestock balance patrol and supervision method according to claim 1 is characterized in that: The original grass-livestock balance model is updated according to the historical grassland animal husbandry data, and an enhanced grass-livestock balance model is generated, including: generating a grassland growth factor based on the historical grassland livestock data; generating a grassland health quality factor based on the historical grassland livestock data; The original grass-livestock balance model is updated according to the grassland growth factor and the grassland health quality factor, and an enhanced grass-livestock balance model is generated.

3. The grass-livestock balance patrol and supervision method according to claim 2 is characterized in that: The grassland growth factor is generated based on the historical grassland livestock data, including: Extracting grassland growth environment data according to the historical grassland animal husbandry data according to the sampling time period; Normalizing the grassland growth environment data and generating grassland growth standard environment data; Extracting and generating the grassland plant quantity according to the grassland growth standard environment data according to the preset data collection points; Calculate the plant growth rate of the grassland plant quantity corresponding to two adjacent data collection points respectively; The mean of the growth rates of the plants is calculated and set as the grassland growth factor.

4. The method for monitoring and controlling grass-livestock balance patrol according to claim 3 is characterized in that: Two adjacent data collection points are respectively a first time point and a second time point, the grassland plant amount corresponding to the first time point is a first plant amount, and the grassland plant amount corresponding to the second time point is a second plant amount; Based on the following formula, the plant growth rate of the grassland plant volume corresponding to two adjacent data collection points is calculated: Among them, rs is the plant growth rate, Uaf is the second plant amount, Ube is the first plant amount, Taf is the second time point, and Tbe is the first time point.

5. The method for monitoring and controlling grass-livestock balance patrol according to claim 2 is characterized in that: The grassland health quality factors are generated based on the historical grassland livestock data, including: Extracting original grassland basic data according to the historical grassland animal husbandry data according to sampling time periods, wherein the number of the sampling time periods is multiple, one sampling time period corresponds to one original grassland basic data, and one original grassland data includes multiple grassland original parameters; Normalizing the original grassland parameters corresponding to each of the original grassland data and generating standard grassland parameters respectively; Obtaining grassland health impact weights corresponding to each of the standard grassland parameters; Obtaining the grassland attenuation coefficient of the currently supervised grassland; Generate a grassland health coefficient according to the grassland attenuation coefficient, the standard grassland parameter corresponding to each of the original grassland data, and the grassland health impact weight, wherein one original grassland basic data corresponds to one grassland health coefficient; A grassland health quality factor is generated according to each of the grassland health coefficients.

6. The method for monitoring and controlling the balance between grass and livestock according to claim 5, characterized in that: The grassland health factor is generated based on the following formula: Wherein, Qt is the grassland health coefficient, λ is the grassland attenuation coefficient, Qpr is the original health coefficient, M is the number of standard grassland parameters, αi is the grassland health impact weight corresponding to the i-th standard grassland parameter, p is the identifier of the standard grassland parameter, Zp(t) is the parameter value of the standard grassland parameter p at time point t in the sampling time period, κi is the exponential coefficient of the i-th standard grassland parameter, m is the number of influencing parameters related to the i-th standard grassland parameter, Zpj(t) is the parameter value of the j-th standard grassland parameter that interacts with the standard grassland parameter p at time point t in the sampling time period, and νij is the influence exponential coefficient between the i-th standard grassland parameter and the j-th standard grassland parameter.

7. The method for monitoring and controlling grass-livestock balance patrol according to claim 6 is characterized in that: Obtaining the grassland attenuation coefficient of the current supervised grassland, including: Obtaining the recovery half-life of said currently regulated grassland; From the recovery half-life, the grassland attenuation coefficient is generated based on the following formula: λ=e -ln(2) / Tah ; Where λ is the grassland attenuation coefficient, e is the base of the natural logarithm, and Tah is the recovery half-life.

8. The method for monitoring and controlling the balance between grass and livestock according to claim 7, characterized in that: The enhanced grass-livestock balance model is as follows: Among them, G(x) is the biomass of the current regulated grassland, x is time, Rrs is the grassland growth factor, K is the carrying capacity of the current regulated grassland, c is the grassland consumption coefficient, ΔQ is the grassland health quality factor, and N(x) is the number of livestock on the current regulated grassland.

9. The method for monitoring and controlling grass-livestock balance patrol according to claim 8, characterized in that: The method further includes obtaining the carrying capacity of the current supervised grassland: Extracting grassland environment data according to the historical grassland animal husbandry data, wherein the grassland environment data includes a temperature information set, a precipitation information set and a sunshine information set; generating a temperature mean value according to the temperature information set; generating a precipitation mean value according to the precipitation information set; Generate a sunshine duration average according to the sunshine information set; According to the average temperature, average precipitation, and average sunshine duration, the carrying capacity of the current supervised grassland is generated based on the following formula: Among them, K is the carrying capacity of the current regulated grassland, Pot is the theoretical maximum biomass, ΔTavr is the mean temperature, Tmin is the standard minimum growth temperature, Tmax is the standard maximum growth temperature, ΔRavr is the mean precipitation, Rot is the optimal precipitation, ΔSavr is the mean sunshine duration, Sot is the optimal sunshine duration, and Cres is the unit biological resource.

10. A grass-livestock balance patrol and supervision system, characterized in that: The system comprises: The historical animal husbandry data acquisition module is used to obtain the historical grassland animal husbandry data of the current supervised grassland within the historical patrol and supervision time period; An enhanced balance model generation module, used for updating the original grass-livestock balance model according to the historical grassland animal husbandry data, and generating an enhanced grass-livestock balance model, wherein the original grass-livestock balance model is preset; A real-time animal husbandry data acquisition module, used to acquire real-time animal husbandry patrol data of the currently supervised grassland; A grass-livestock balance suggestion generation module is used to generate grass-livestock balance animal husbandry suggestions based on the real-time animal husbandry patrol data and the enhanced grass-livestock balance model, wherein the grass-livestock balance animal husbandry suggestions are used to assist grass-livestock balance supervisors in adjusting animal husbandry.

Images