Automatic real-time monitoring method of feed intake of grazing livestock based on Beidou navigation positioning

Abstract

The present application provides a method for automatically monitoring the feed intake of grazing livestock in real time based on Beidou navigation and positioning. The Beidou navigation and positioning collar is used to monitor the movement behavior of livestock, and accurate movement data can be obtained. At the same time, a feed intake model for grazing livestock is constructed by considering livestock weight, movement distance, feeding time, rest time, vegetation height and coverage. The constructed model comprehensively considers various factors that may affect the feed intake of livestock, can obtain accurate livestock feed intake data, and can realize automatic and real-time monitoring of livestock feed intake.

Description

Technical Field

[0001] The present application belongs to the field of automation, satellite navigation and remote sensing technology, and in particular to a method for automatically monitoring the feed intake of grazing livestock in real time based on Beidou navigation and positioning. Background Art

[0002] Grassland is the largest terrestrial ecosystem in my country. It is not only the country's ecological security barrier, but also plays an irreplaceable and important role in the construction of ecological civilization. It also provides one-third of the country's beef and mutton and one-quarter of dairy products, and is an important part of national food security.

[0003] The balance between grass and livestock is the most critical issue in my country's grassland ecological construction and pastoral animal husbandry development. As the main way to utilize my country's grassland ecosystem, the measurement of grazing livestock feed intake is of great significance for formulating livestock nutrition standards and supplementary feeding amounts and achieving grass-livestock balance.

[0004] There are two main methods for measuring feed intake of grazing livestock at present. One is to indirectly measure feed intake by using the amount of vegetation consumed (moving cage method), and the other is to calculate feed intake by using the amount of livestock excrement and indigestible indicators such as saturated alkanes and acid-insoluble ash. However, both methods require a huge workload and it is difficult to measure feed intake of livestock over a large area and for a long time, let alone real-time monitoring of feed intake of grazing livestock.

[0005] In addition, the feed intake of grazing livestock is affected by many factors, such as grazing season, grazing intensity, grassland conditions, livestock physiological conditions, movement and feeding behavior. In particular, the feeding behavior of livestock (including feeding time, movement distance, movement speed, etc.) is closely related to the measurement of the feed intake of grazing livestock, and the existing feed intake measurement methods do not fully consider the above factors. In addition, the existing technology usually obtains livestock movement data based on motion sensors such as acceleration sensors, and the movement data obtained by such sensors tends to be chewing, rumination and other behaviors.

[0006] Therefore, it is necessary to propose a new technical solution to overcome the above technical problems and realize real-time automatic monitoring of the feed intake of grazing livestock to obtain accurate feed intake data of grazing livestock. Summary of the invention

[0007] The method for automatic real-time monitoring of the feed intake of grazing livestock based on Beidou navigation positioning is used to solve the above technical problems. By using Beidou navigation positioning collars to monitor the movement behavior of livestock, accurate movement data can be obtained. At the same time, a feed intake model for grazing livestock is constructed by considering the livestock weight, movement distance, feeding time, rest time, vegetation height and coverage. The constructed model comprehensively considers various factors that may affect the feed intake of livestock, can obtain accurate livestock feed intake data, and can realize automatic and real-time monitoring of livestock feed intake.

[0008] In a first aspect, an embodiment of the present application provides a method for automatically monitoring the feed intake of grazing livestock in real time based on Beidou navigation positioning, characterized in that it includes the following steps:

[0009] S1. Randomly select N livestock and use the indicator method to measure the actual feed intake of each livestock per day;

[0010] S2. regularly measuring the weight of each of the livestock, and evaluating the body condition of the livestock based on the weight;

[0011] S3, obtaining the continuous position information of each livestock every day based on the Beidou navigation positioning collar, calculating the movement speed and movement distance of each livestock, and dividing the movement behavior of the livestock into resting, feeding, and wandering based on the movement speed;

[0012] S4, obtaining the vegetation height and vegetation coverage of the grazing grassland;

[0013] S5. Constructing a livestock feed intake monitoring model based on the actual feed intake of each livestock, as well as livestock weight, livestock body condition, movement distance, feeding time, rest time, vegetation height, and vegetation coverage;

[0014] S6. Use the livestock feed intake monitoring model in combination with the Beidou navigation positioning collar to perform real-time automatic monitoring of livestock feed intake.

[0015] Furthermore, the step S1 specifically includes:

[0016] S11. Collect all feces of each livestock on the day of testing;

[0017] S12, measuring the concentration of saturated alkanes in the forage and the whole manure by using an extraction method combined with a gas chromatography-mass spectrometer;

[0018] S13. Calculate the actual feed intake of each livestock. The calculation formula is as follows:

[0019]

[0020] Among them, Intake 测量 is the actual feed intake of livestock on that day, Total Fecal is the total amount of livestock feces on that day, Cn1 and Cn2 are the concentrations of saturated alkanes in livestock feces and forage respectively, and Re is the recovery efficiency of saturated alkanes.

[0021] Furthermore, the step S2 specifically includes:

[0022] S21. Regularly measure the weight of each livestock;

[0023] S22. If the weight of the livestock is more than 20% higher than the average weight of the livestock of this type, it is evaluated as being in good physical condition. If the weight of the livestock is more than 20% lower than the average weight of the livestock of this type, it is evaluated as being in poor physical condition. Otherwise, it is evaluated as being in normal physical condition.

[0024] Furthermore, the step S3 specifically includes:

[0025] S31, setting the working frequency of the Beidou navigation positioning collar to m minutes, recording the longitude and latitude information of the position of each livestock every m minutes within 24 hours, and drawing a movement trajectory diagram of each livestock on that day;

[0026] S32, calculating the movement speed and movement distance of each livestock, the calculation formula is as follows:

[0027]

[0028] Among them, Sij is the movement distance of the jth period at the i-th time, Vij is the movement speed of the jth period at the i-th time, L is the total movement distance of the day, the distance unit is meter, and the speed unit is meter / second;

[0029] S33, based on the movement speed, performing livestock movement information recognition and automatic classification, obtaining the critical point of livestock movement speed, and classifying livestock movement behaviors into resting, feeding, and wandering based on the critical point of movement speed, specifically:

[0030] Vij < α1, rest;

[0031] α1 < Vij < α2, feeding;

[0032] Vij > α2, wandering;

[0033] Wherein, α1 and α2 are critical points of the movement speed of the livestock. Further, the step S4 specifically includes:

[0034] Forage grasses within a certain range were selected as samples, and the natural height of the community was measured using a tape measure. The community coverage was estimated using the acupuncture method, and the average values ​​of the measured natural height of the community and community coverage were calculated as the vegetation height and vegetation coverage, respectively.

[0035] Furthermore, the step S5 specifically includes:

[0036] The importance of livestock weight, livestock body condition, movement distance, feeding time, rest time, vegetation height, and vegetation coverage was calculated based on the multiple regression model, and livestock weight, movement distance, feeding time, rest time, vegetation height, and vegetation coverage were selected as independent variables according to the order of importance;

[0037] Taking the actual feed intake of each livestock as the dependent variable, a livestock feed intake monitoring model was constructed:

[0038] Livestock feed intake = f(livestock weight, exercise distance, feeding time, rest time, vegetation height and coverage).

[0039] Furthermore, the step S5 specifically includes:

[0040] S51, dividing the acquired actual feed intake, livestock weight, feeding time, rest time, vegetation height, and vegetation coverage of each livestock into a training set and a test set;

[0041] S52, constructing a livestock feed intake monitoring model using the livestock weight, movement distance, feeding time, rest time, vegetation height, and vegetation coverage as independent variables;

[0042] S53, training the livestock feed intake monitoring model using a training set to obtain a trained livestock feed intake monitoring model;

[0043] S54. Using a test set to test the trained livestock feed intake monitoring model to obtain the model accuracy.

[0044] Furthermore, the livestock feed intake monitoring model in step S5 is a multivariate linear model.

[0045] Furthermore, the trained livestock feed intake monitoring model is:

[0046] y=0.028LW-0.003D-0.830R-0.631G+0.188H-0.020Cov+83.14;

[0047] Among them, y represents livestock feed intake, LW represents livestock weight, D represents exercise distance, R represents rest time, G represents feeding time, and H and Cov represent vegetation height and coverage, respectively.

[0048] In a second aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and wherein the computer program, when executed by a processor, implements the method described in the first aspect.

[0049] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0050] The present invention provides an automatic real-time monitoring method for the feed intake of grazing livestock based on Beidou navigation positioning. Compared with traditional feed intake detection methods, by constructing a robust livestock feed intake monitoring model, it can solve the problems that traditional methods have a huge workload when measuring livestock feed intake and are difficult to measure accurately and quickly.

[0051] The present invention monitors livestock movement behavior through Beidou navigation positioning collars, and can obtain accurate movement data. When constructing the model, livestock weight, movement distance, feeding time, rest time, vegetation height and coverage are considered at the same time. The constructed model comprehensively considers various factors that may affect livestock feed intake, and can obtain accurate livestock feed intake data. The constructed livestock feed intake monitoring model can provide automatic, accurate, and real-time monitoring of grazing livestock feed intake, which is a significant improvement over traditional methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0053] Figure 1 It is a flow chart of a method for automatically monitoring the feed intake of grazing livestock in real time based on Beidou navigation positioning provided in an embodiment of the present application;

[0054] Figure 2 It is a ranking diagram of the importance of each variable factor calculated based on the multivariate regression model provided in the embodiment of the present application;

[0055] Figure 3(a)-Figure 3(d) It is a comparison chart of the accuracy evaluation of the model constructed according to the method provided in the embodiment of the present application and other models;

[0056] Figure 4(a)-Figure 4(d) This is an example of estimating the feed intake of beef cattle using the livestock feed intake monitoring model constructed in this application. DETAILED DESCRIPTION

[0057] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0058] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0059] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0060] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0061] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", "fourth", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0062] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways. Specific embodiment:

[0064] Figure 1 A flowchart of a method for automatically monitoring the feed intake of grazing livestock in real time based on Beidou navigation positioning is shown in Example 1 of the present application. Figure 1 As shown, specifically including:

[0065] S1. Randomly select N livestock and use the indicator method to determine the actual feed intake of each livestock per day.

[0066] Among them, 27 livestock were selected for measurement.

[0067] Wherein, the livestock may be grazing beef cattle.

[0068] The step S1 specifically includes:

[0069] S11. Collect all feces of each livestock on the day of testing;

[0070] Among them, the whole manure of the day is collected by bagging method for small livestock and tracking method for large livestock;

[0071] S12, measuring the concentration of saturated alkanes in the forage and the whole manure by using an extraction method combined with a gas chromatography-mass spectrometer;

[0072] Saturated alkanes refer to normal alkanes in the waxy layer of plant epidermis. 21 ~C 36 , livestock are difficult to digest and excrete through feces after eating, so it can be used to measure livestock feed intake.

[0073] S13. Calculate the actual feed intake of each livestock. The calculation formula is as follows:

[0074]

[0075] Among them, Intake 测量 is the actual feed intake of livestock on that day, Total Fecal is the total amount of livestock feces on that day, Cn1 and Cn2 are the concentrations of saturated alkanes in livestock feces and forage respectively, and Re is the recovery efficiency of saturated alkanes.

[0076] Among them, Re is obtained through feeding experiments with determined forage amount and total manure amount.

[0077] S2. Regularly measure the weight of each livestock, and evaluate the body condition of the livestock based on the weight.

[0078] The step S2 specifically includes:

[0079] S21. Regularly measure the weight of each livestock; the livestock weight can be measured using a floor scale.

[0080] S22. If the weight of the livestock is more than 20% higher than the average weight of the livestock of this type, it is evaluated as being in good physical condition. If the weight of the livestock is more than 20% lower than the average weight of the livestock of this type, it is evaluated as being in poor physical condition. Otherwise, it is evaluated as being in normal physical condition.

[0081] Among them, the body condition assessment method is a combination of livestock body condition divided according to international livestock body condition diagnostic standards.

[0082] S3, obtaining the continuous position information of each livestock every day based on the Beidou navigation positioning collar, calculating the movement speed and movement distance of each livestock, and dividing the movement behavior of the livestock into resting, feeding, and wandering based on the movement speed;

[0083] The step S3 specifically includes:

[0084] S31, setting the working frequency of the Beidou navigation positioning collar to m minutes, recording the longitude and latitude information of the position of each livestock every m minutes within 24 hours, and drawing a movement trajectory diagram of each livestock on that day;

[0085] Among them, the working frequency of the Beidou navigation positioning collar can be set to 5 minutes, and the movement trajectory diagram can be drawn through the positioning data of the livestock recorded every 5 minutes. The positioning data includes the positioning time and longitude and latitude information.

[0086] S32, calculating the movement speed and movement distance of each livestock, the calculation formula is as follows:

[0087]

[0088] Among them, Sij is the movement distance of the jth period at the i-th time, Vij is the movement speed of the jth period at the i-th time, L is the total movement distance of the day, the distance unit is meter, and the speed unit is meter / second;

[0089] S33, based on the movement speed, performing livestock movement information recognition and automatic classification, obtaining the critical point of livestock movement speed, and classifying livestock movement behaviors into resting, feeding, and wandering based on the critical point of movement speed, specifically:

[0090] Vij < α1, rest;

[0091] α1 < Vij < α2, feeding;

[0092] Vij > α2, wandering;

[0093] Among them, α1 and α2 are critical points of the movement speed of the livestock. Specifically, α1 and α2 can be set to 0.075 m / s and 0.195 m / s respectively.

[0094] Among them, based on the movement speed, livestock movement information recognition and automatic classification are performed, and obtaining the livestock movement speed critical point specifically includes: using unsupervised classification, such as the K-means method, to classify the obtained movement speed to indicate different movement behaviors, and at the same time using supervised classification, such as the random forest method, to perform a ten-fold cross-validation on the livestock behavior corresponding to the movement speed value, with a kappa coefficient of 85% and an accuracy of 91%. It can be seen that the movement speed critical point calculated in this embodiment has a high accuracy and can more accurately identify the movement behavior of livestock.

[0095] S4. Obtain the vegetation height and vegetation coverage of the grazing grassland.

[0096] The step S4 specifically includes:

[0097] Forage grasses within a certain range were selected as samples, and the natural height of the community was measured using a tape measure. The community coverage was estimated using the acupuncture method, and the average values ​​of the measured natural height of the community and community coverage were calculated as the vegetation height and vegetation coverage, respectively.

[0098] Specifically, 10 representative plots can be selected as samples to measure vegetation height and vegetation coverage, and finally the average of the 10 plots is used as the measurement value of vegetation height and vegetation coverage.

[0099] S5. Construct a livestock feed intake monitoring model based on the actual feed intake of each livestock, as well as livestock weight, livestock body condition, exercise distance, feeding time, rest time, vegetation height, and vegetation coverage.

[0100] The step S5 specifically includes:

[0101] The importance of livestock weight, livestock body condition, movement distance, feeding time, rest time, vegetation height, and vegetation coverage was calculated based on the multiple regression model, and livestock weight, movement distance, feeding time, rest time, vegetation height, and vegetation coverage were selected as independent variables according to the order of importance;

[0102] Among them, since the wandering time of livestock contained in the measurement data usually accounts for a very small proportion, about 5% of 24 hours, and livestock do not eat during the wandering time, the wandering time of livestock is not considered when selecting independent variables in this embodiment;

[0103] The importance ranking of the above measurement data calculated by the multivariate regression model is as follows: Figure 2 As shown in the figure, it can be seen that the importance of livestock body condition is the lowest. Therefore, in this embodiment, other measurement data except livestock body condition are selected as independent variables to construct a livestock feed intake monitoring model;

[0104] The actual feed intake of each livestock was used as the dependent variable, and the livestock weight, movement distance, feeding time, rest time, vegetation height, and vegetation coverage were used as independent variables to construct a livestock feed intake monitoring model:

[0105] Livestock feed intake = f(livestock weight, exercise distance, feeding time, rest time, vegetation height and coverage).

[0106] Furthermore, the step S5 specifically includes:

[0107] S51, dividing the acquired actual feed intake, livestock weight, feeding time, rest time, vegetation height, and vegetation coverage of each livestock into a training set and a test set;

[0108] Specifically, 70% of the collected data is used as a training set and 30% as a test set;

[0109] S52, constructing a livestock feed intake monitoring model using the livestock weight, movement distance, feeding time, rest time, vegetation height, and vegetation coverage as independent variables;

[0110] S53, training the livestock feed intake monitoring model using a training set to obtain a trained livestock feed intake monitoring model;

[0111] S54. Using a test set to test the trained livestock feed intake monitoring model to obtain the model accuracy.

[0112] Specifically, the model accuracy measurement criteria include: mean absolute error MAE, root mean square error RMSE, determination coefficient R 2 And the bias Bias is calculated as:

[0113]

[0114]

[0115]

[0116]

[0117] Among them, X model,i is the livestock feed intake calculated by the model, X obs,i is the measured feed intake of livestock, N is the number of livestock used for accuracy evaluation, is the mean of the measured feed intake of N livestock.

[0118] Among them, the constructed livestock feed intake monitoring model is a multivariate linear model;

[0119] The trained livestock feed intake monitoring model is specifically:

[0120] y=0.028LW-0.003D-0.830R-0.631G+0.188H-0.020Cov+83.14;

[0121] Among them, y represents livestock feed intake, LW represents livestock weight, D represents exercise distance, R represents rest time, G represents feeding time, and H and Cov represent vegetation height and coverage, respectively.

[0122] S6. Using the trained livestock feed intake monitoring model in combination with the Beidou navigation positioning collar to perform real-time automatic monitoring of livestock feed intake.

[0123] Specifically, when conducting real-time monitoring, the livestock weight, vegetation height and coverage measured in advance are used to obtain the real-time movement data of the monitored livestock through the Beidou navigation positioning collar, and then the movement distance, feeding time and rest time are obtained. These parameters are input into the trained livestock feed intake monitoring model to obtain the real-time feed intake data of the livestock.

[0124] On the other hand, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and wherein when the computer program is executed by a processor, the method described in the first embodiment is implemented.

[0125] Experimental results analysis

[0126] The same training set as that used to construct the livestock feed intake monitoring model described in this application was used to construct a ridge regression model, a random forest model, and an XGBoost model, respectively. The test set was used to obtain the accuracy evaluation data of the three models, as well as the accuracy evaluation data of the multivariate linear model constructed in this application, as shown in FIG3( a ), which is an accuracy evaluation graph of the multivariate linear model constructed in this application. Figure 3(b)-Figure 3(d) These are the accuracy evaluation graphs for the ridge regression model, random forest model, and XGBoost model. The red straight line in the figure is the model fitting line, the gray shadow is the 95% confidence interval of the model, the dotted line is the 1:1 line, and the dots are the feed intake of each livestock.

[0127] The accuracy evaluation data of the four models in the figure are shown in the following table:

[0128]

[0129] Based on the accuracy data of the above four models, it can be seen that the multivariate linear model constructed in this application has the highest accuracy.

[0130] Figure 4(a)-Figure 4(d) This is an example of estimating the feed intake of beef cattle using the constructed livestock feed intake monitoring model, namely the multivariate linear model, where Figure 4(a) is the statistical analysis of the 24-hour collected data. Figure 4(b)-Figure 4(d) They are real-time monitoring data of movement speed, walking distance, and feed intake. As can be seen from the figure, based on the feed intake monitoring model, the movement data of livestock can be obtained in real time, including walking distance, movement speed, etc., and real-time feeding monitoring data, that is, real-time feed intake data, can be obtained; in addition, based on real-time monitoring, data of a certain period of time can also be analyzed, such as 24 hours of data on a certain day, to obtain the total walking distance, average speed, feed intake estimation, and rest time, feeding time, and wandering time data for that period of time.

[0131] It can be seen that the livestock feed intake monitoring model constructed by the present invention can automatically, accurately and real-time obtain livestock feed intake data.

[0132] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0133] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0134] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for automatically monitoring the feed intake of grazing livestock in real time based on Beidou navigation positioning, characterized in that: The following steps are involved: S1. Randomly select N livestock and use the indicator method to measure the actual feed intake of each livestock per day; S2. regularly measuring the weight of each of the livestock, and evaluating the body condition of the livestock based on the weight; S3, obtaining the continuous position information of each livestock every day based on the Beidou navigation positioning collar, calculating the movement speed and movement distance of each livestock, and dividing the movement behavior of the livestock into resting, feeding, and wandering based on the movement speed; S4, obtaining the vegetation height and vegetation coverage of the grazing grassland; S5. Constructing a livestock feed intake monitoring model based on the actual feed intake of each livestock, as well as livestock weight, livestock body condition, movement distance, feeding time, rest time, vegetation height, and vegetation coverage; S6. Using the livestock feed intake monitoring model and combining it with Beidou navigation positioning collar to automatically monitor livestock feed intake in real time; The step S3 classifies the movement behaviors of livestock into resting, feeding, and wandering based on the movement speed, including: Based on the movement speed, the livestock movement information is identified and classified to obtain the critical point of the livestock movement speed; Based on the critical point of livestock movement speed, livestock movement behaviors are divided into resting, feeding, and wandering; Step S5 includes: The importance of livestock weight, livestock body condition, movement distance, feeding time, rest time, vegetation height, and vegetation coverage was calculated based on the multiple regression model, and livestock weight, movement distance, feeding time, rest time, vegetation height, and vegetation coverage were selected as independent variables according to the order of importance; Taking the actual feed intake of each livestock as the dependent variable, a livestock feed intake monitoring model was constructed: Livestock feed intake = f(livestock weight, exercise distance, feeding time, rest time, vegetation height and coverage).

2. The method according to claim 1, characterized in that The step S1 specifically includes: S11. Collect all feces of each livestock on the day of testing; S12, measuring the concentration of saturated alkanes in the forage and the whole manure by using an extraction method combined with a gas chromatography-mass spectrometer; S13. Calculate the actual feed intake of each livestock. The calculation formula is as follows: , where Intake 测量 is the actual feed intake of livestock on that day, TotalFecal is the total amount of livestock manure on that day, Cn1 and Cn2 are the concentrations of saturated alkanes in livestock manure and forage, respectively, and Re is the recovery efficiency of saturated alkanes.

3. The method according to claim 1, characterized in that The step S2 specifically includes: S21. Regularly measure the weight of each livestock; S22. If the weight of the livestock is more than 20% higher than the average weight of the livestock of this type, it is evaluated as being in good physical condition. If the weight of the livestock is more than 20% lower than the average weight of the livestock of this type, it is evaluated as being in poor physical condition. Otherwise, it is evaluated as being in normal physical condition.

4. The method according to claim 1, characterized in that: The step S3 specifically includes: S31, setting the working frequency of the Beidou navigation positioning collar to m minutes, recording the longitude and latitude information of the position of each livestock every m minutes within 24 hours, and drawing a movement trajectory diagram of each livestock on that day; S32, calculating the movement speed and movement distance of each livestock, the calculation formula is as follows: , where Sij is the movement distance of the jth period at the i-th time, Vij is the movement speed of the jth period at the i-th time, L is the total movement distance of the day, the distance unit is meter, and the speed unit is meter / second; S33, based on the movement speed, performing livestock movement information recognition and automatic classification, obtaining the critical point of the livestock movement speed, and classifying the livestock movement behavior into resting, feeding, and wandering based on the critical point of the movement speed, specifically: Vij < α1, rest; α1 < Vij < α2, feeding; Vij > α2, wandering; Among them, α1 and α2 are critical points of the movement speed of the livestock.

5. The method according to claim 1, characterized in that The step S4 specifically includes: Forage grasses within a certain range were selected as samples, and the natural height of the community was measured using a tape measure. The community coverage was estimated using the acupuncture method, and the average values ​​of the measured natural height of the community and community coverage were calculated as the vegetation height and vegetation coverage, respectively.

6. The method according to claim 1, characterized in that The step S5 specifically includes: S51, dividing the acquired actual feed intake, livestock weight, feeding time, rest time, vegetation height, and vegetation coverage of each livestock into a training set and a test set; S52, constructing a livestock feed intake monitoring model using the livestock weight, movement distance, feeding time, rest time, vegetation height, and vegetation coverage as independent variables; S53, training the livestock feed intake monitoring model using a training set to obtain a trained livestock feed intake monitoring model; S54. Using a test set to test the trained livestock feed intake monitoring model to obtain model accuracy.

7. The method according to claim 6, characterized in that The livestock feed intake monitoring model in step S5 is a multivariate linear model.

8. The method according to claim 7, characterized in that The trained livestock feed intake monitoring model is: y=0.028LW-0.003D-0.830R-0.631G+0.188H-0.020Cov+83.14; Among them, y represents livestock feed intake, LW represents livestock weight, D represents exercise distance, R represents rest time, G represents feeding time, and H and Cov represent vegetation height and coverage, respectively.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images