CN117892172A - Livestock breeding supervision method and device, electronic equipment and storage medium - Google Patents
Livestock breeding supervision method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117892172A CN117892172A CN202410057987.4A CN202410057987A CN117892172A CN 117892172 A CN117892172 A CN 117892172A CN 202410057987 A CN202410057987 A CN 202410057987A CN 117892172 A CN117892172 A CN 117892172A
- Authority
- CN
- China
- Prior art keywords
- data
- livestock
- growth
- behavior
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 244000144972 livestock Species 0.000 title claims abstract description 200
- 238000000034 method Methods 0.000 title claims abstract description 71
- 238000003860 storage Methods 0.000 title claims abstract description 9
- 238000009395 breeding Methods 0.000 title abstract description 23
- 230000001488 breeding effect Effects 0.000 title abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 72
- 230000003190 augmentative effect Effects 0.000 claims abstract description 57
- 238000013145 classification model Methods 0.000 claims abstract description 37
- 238000003062 neural network model Methods 0.000 claims abstract description 30
- 230000006399 behavior Effects 0.000 claims description 199
- 238000013179 statistical model Methods 0.000 claims description 36
- 238000004422 calculation algorithm Methods 0.000 claims description 30
- 238000007781 pre-processing Methods 0.000 claims description 21
- 238000012706 support-vector machine Methods 0.000 claims description 18
- 238000009304 pastoral farming Methods 0.000 claims description 15
- 239000013598 vector Substances 0.000 claims description 15
- 238000000691 measurement method Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 238000003066 decision tree Methods 0.000 claims description 12
- 238000013136 deep learning model Methods 0.000 claims description 12
- 238000007619 statistical method Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 11
- 238000002372 labelling Methods 0.000 claims description 10
- 238000010801 machine learning Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 6
- 238000012417 linear regression Methods 0.000 claims description 6
- 238000003672 processing method Methods 0.000 claims description 6
- 238000007637 random forest analysis Methods 0.000 claims description 6
- 238000012300 Sequence Analysis Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 5
- 230000035611 feeding Effects 0.000 description 23
- 241001465754 Metazoa Species 0.000 description 18
- 238000012545 processing Methods 0.000 description 16
- 239000011521 glass Substances 0.000 description 11
- 230000008569 process Effects 0.000 description 9
- 241000283690 Bos taurus Species 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 230000036541 health Effects 0.000 description 6
- 244000309464 bull Species 0.000 description 5
- 244000309466 calf Species 0.000 description 5
- 230000006872 improvement Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 2
- 238000007635 classification algorithm Methods 0.000 description 2
- 230000035622 drinking Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000000284 resting effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000000540 analysis of variance Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 230000007937 eating Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000037406 food intake Effects 0.000 description 1
- 235000012631 food intake Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005802 health problem Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000001121 heart beat frequency Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 238000002255 vaccination Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2203/00—Indexing scheme relating to G06F3/00 - G06F3/048
- G06F2203/01—Indexing scheme relating to G06F3/01
- G06F2203/012—Walk-in-place systems for allowing a user to walk in a virtual environment while constraining him to a given position in the physical environment
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/70—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in livestock or poultry
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Pure & Applied Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Mathematics (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Biophysics (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Biomedical Technology (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
Abstract
The embodiment of the application provides a method and a device for supervising livestock breeding, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring growth data of each livestock, and generating a first growth curve according to the growth data; classifying the growth data of each livestock according to a pre-trained classification model to obtain livestock categories corresponding to the growth data; determining a first similarity result according to a first growth curve and a pre-trained second growth curve corresponding to the livestock category, wherein the second growth curve is obtained by training a training model by adopting sample growth data, and is a statistical module or a neural network model; through the augmented reality equipment, show the growth condition of livestock, the user can look over by this augmented reality equipment, in time knows the growth condition of each livestock.
Description
Technical Field
The application relates to the technical field of augmented reality, in particular to a method and a device for supervising livestock breeding, electronic equipment and a storage medium.
Background
At present, along with the continuous improvement of the living standard of people, the breeding industry also obtains rapid development, the quantity of livestock is also increased, and the requirements on livestock breeding are also increased. However, most farmers still rely on traditional feeding methods and mechanical equipment to perform the tasks, but the growth state of each livestock cannot be accurately known, so that the problem of how to intelligently feed the livestock and improve the feeding accuracy of the livestock is an urgent need to be solved.
Disclosure of Invention
Some embodiments of the present application are directed to providing a method, an apparatus, an electronic device, and a storage medium for supervising livestock breeding, by which growth data of each livestock is obtained and a first growth curve is generated according to the growth data; classifying the growth data of each livestock according to a pre-trained classification model to obtain livestock categories corresponding to the growth data; determining a first similarity result according to the first growth curve and a pre-trained second growth curve corresponding to the livestock category, wherein the second growth curve is obtained by training a training model by adopting sample growth data, and the training model comprises a statistical module or a neural network model; through augmented reality equipment, show the growth condition of livestock, wherein, the growth condition knowledge of livestock includes first similarity result with first growth curve, this application embodiment is through augmented reality equipment, acquires the growth data of livestock, generates first growth curve, then judges the livestock class of this livestock, carries out similarity calculation with first growth curve and the second growth curve that corresponds with the livestock class, obtains first similarity result to show on augmented reality equipment, the user can look over by this augmented reality equipment, in time knows the growth condition of each livestock.
In a first aspect, some embodiments of the present application provide a method for supervising livestock farming, comprising:
acquiring growth data of each livestock, and generating a first growth curve according to the growth data;
classifying the growth data of each livestock according to a pre-trained classification model to obtain livestock categories corresponding to the growth data;
determining a first similarity result according to the first growth curve and a pre-trained second growth curve corresponding to the livestock category, wherein the second growth curve is obtained by training a training model by adopting sample growth data, and the training model comprises a statistical module or a neural network model;
displaying the growth condition of the livestock through an augmented reality device, wherein the knowledge of the growth condition of the livestock comprises the first similarity result and the first growth curve.
According to some embodiments of the method, the device and the system, through the augmented reality device, growth data of livestock are obtained, a first growth curve is generated, then the livestock category of the livestock is judged, similarity calculation is conducted on the first growth curve and a second growth curve corresponding to the livestock category, a first similarity result is obtained, the first similarity result is displayed on the augmented reality device, and a user can check the augmented reality device and know the growth condition of each livestock in time.
Optionally, the second growth curve is obtained by:
acquiring first sample growth data, wherein the first sample growth data includes height and weight;
preprocessing the first sample growth data to obtain processed sample growth data;
classifying the processed sample growth data to obtain a classification result;
training the statistical model or the neural network model according to the classification result to obtain the second growth curve, wherein the statistical model comprises a linear regression model or a polynomial regression model; the neural network model includes a decision tree or a support vector machine.
According to some embodiments of the method, the statistical model and the neural network model are trained by acquiring the first sample growth data, so that a second growth curve is obtained, and the second growth curve is used for judging the first growth curve, so that the growth state of livestock is judged.
Optionally, the determining the first similarity result according to the first growth curve and the pre-trained second growth curve corresponding to the livestock category includes:
and calculating the similarity of the first growth curve and the second growth curve by adopting a curve similarity measurement method to obtain the first similarity result, wherein the curve similarity measurement method comprises cosine similarity or Euclidean distance.
Some embodiments of the present application calculate the similarity of the first growth curve and the second growth curve by using a curve similarity measurement method, if the similarity is smaller than a preset value, it indicates that the growth condition of the livestock meets the expected requirement, and if the similarity is larger than the preset value, it indicates that the growth condition of the livestock is worse, and it is necessary to adjust the feeding plan.
Optionally, the classification model is obtained by:
acquiring second sample data and labeling sample data, wherein the second sample data comprises data of different categories;
preprocessing the second sample data to obtain processed second sample data;
performing feature extraction on the second sample data by adopting an image processing method or a deep learning model to obtain feature data corresponding to the second sample data, wherein the feature data comprises color features, texture features and shape features;
selecting target characteristic data from the characteristic data by adopting a statistical method or a machine learning algorithm;
classifying the target feature data by adopting a preset selection algorithm to obtain a classification result, wherein the preset selection algorithm at least comprises any one of a support vector machine, a random forest, a naive Bayes classifier or a deep learning model;
And determining the classification model according to the classification result and the labeling sample data.
According to some embodiments of the application, the second sample data are adopted, the second sample data comprise data of different types, target feature data in the second sample data are extracted, a preset selection algorithm is adopted to classify the target feature data, a classification result is obtained, a classification model is determined according to the classification result and the marked sample data, and through the classification model, the type of livestock data can be accurately judged, and classification accuracy is improved.
Optionally, the method further comprises:
acquiring behavior data of livestock;
determining a first behavior mode corresponding to the behavior data according to a pre-trained behavior recognition model, wherein the pre-trained behavior recognition model is obtained by training a neural network model or a statistical model through sample behavior data;
comparing according to the first behavior mode and a preset behavior mode to obtain a behavior comparison result, wherein the behavior comparison result at least comprises behavior change data, frequency and duration;
and displaying the behavior comparison result through the augmented reality equipment, and determining feeding information corresponding to the behavior comparison result according to the behavior comparison result.
According to some embodiments of the application, the first behavior pattern corresponding to the livestock behavior data is identified according to the pre-trained behavior identification model, then the first behavior pattern is compared with the preset behavior pattern to obtain a behavior comparison result, and corresponding feeding information is determined according to the behavior comparison result.
Optionally, the behavior recognition model is obtained by:
acquiring sample behavior data;
preprocessing the sample behavior data to obtain processed sample behavior data;
determining a behavior feature vector corresponding to the sample behavior data according to the processed sample behavior data by adopting a statistical method or a time sequence analysis method;
training a training model or a statistical model according to the behavior feature vector to obtain the behavior recognition model, wherein the training model comprises a decision tree, a support vector machine or a neural network, and the statistical model comprises a hidden Markov model.
According to some embodiments of the application, the behavior recognition model is obtained by acquiring sample behavior data and behavior feature vectors of the sample behavior data and then training a training model or a statistical model, and the behavior recognition model is used for recognizing specific behaviors of livestock, so that a specific feeding mode is determined according to the specific behaviors.
Optionally, the method further comprises:
acquiring livestock field data, wherein the livestock field data at least comprises field boundary areas, terrains and obstacle data;
setting a virtual boundary area in a virtual environment by adopting augmented reality equipment according to the livestock field data;
mapping the virtual boundary area and the field boundary area by adopting a map construction algorithm positioned at the same time;
and if the livestock is not in the boundary area of the field, displaying alarm information through the augmented reality equipment.
Some embodiments of the present application provide for setting a virtual boundary region in a virtual environment by acquiring livestock farm data, using an augmented reality device, and mapping the virtual boundary region to an actual farm boundary region, and displaying alarm information by the augmented reality device if the livestock is not within the farm boundary region.
In a second aspect, some embodiments of the present application provide a supervision apparatus for livestock farming, comprising:
the acquisition module is used for acquiring the growth data of each livestock and generating a first growth curve according to the growth data;
the classification model is used for classifying the growth data of each livestock according to a pre-trained classification model to obtain livestock types corresponding to the growth data;
The determining module is used for determining a first similarity result according to the first growth curve and a pre-trained second growth curve corresponding to the livestock category, wherein the second growth curve is obtained by training a training model by adopting sample growth data, and the training model comprises a statistical module or a neural network model;
and the display module is used for displaying the growth condition of the livestock through the augmented reality equipment, wherein the knowledge of the growth condition of the livestock comprises the first similarity result and the first growth curve.
According to some embodiments of the method, the device and the system, through the augmented reality device, growth data of livestock are obtained, a first growth curve is generated, then the livestock category of the livestock is judged, similarity calculation is conducted on the first growth curve and a second growth curve corresponding to the livestock category, a first similarity result is obtained, the first similarity result is displayed on the augmented reality device, and a user can check the augmented reality device and know the growth condition of each livestock in time.
Optionally, the apparatus further comprises a model training module for:
acquiring first sample growth data, wherein the first sample growth data includes height and weight;
Preprocessing the first sample growth data to obtain processed sample growth data;
classifying the processed sample growth data to obtain a classification result;
training the statistical model or the neural network model according to the classification result to obtain the second growth curve, wherein the statistical model comprises a linear regression model or a polynomial regression model; the neural network model includes a decision tree or a support vector machine.
According to some embodiments of the method, the statistical model and the neural network model are trained by acquiring the first sample growth data, so that a second growth curve is obtained, and the second growth curve is used for judging the first growth curve, so that the growth state of livestock is judged.
Optionally, the determining module is configured to:
and calculating the similarity of the first growth curve and the second growth curve by adopting a curve similarity measurement method to obtain the first similarity result, wherein the curve similarity measurement method comprises cosine similarity or Euclidean distance.
Some embodiments of the present application calculate the similarity of the first growth curve and the second growth curve by using a curve similarity measurement method, if the similarity is smaller than a preset value, it indicates that the growth condition of the livestock meets the expected requirement, and if the similarity is larger than the preset value, it indicates that the growth condition of the livestock is worse, and it is necessary to adjust the feeding plan.
Optionally, the model training module is further configured to:
acquiring second sample data and labeling sample data, wherein the second sample data comprises data of different categories;
preprocessing the second sample data to obtain processed second sample data;
performing feature extraction on the second sample data by adopting an image processing method or a deep learning model to obtain feature data corresponding to the second sample data, wherein the feature data comprises color features, texture features and shape features;
selecting target characteristic data from the characteristic data by adopting a statistical method or a machine learning algorithm;
classifying the target feature data by adopting a preset selection algorithm to obtain a classification result, wherein the preset selection algorithm at least comprises any one of a support vector machine, a random forest, a naive Bayes classifier or a deep learning model;
and determining the classification model according to the classification result and the labeling sample data.
According to some embodiments of the application, the second sample data are adopted, the second sample data comprise data of different types, target feature data in the second sample data are extracted, a preset selection algorithm is adopted to classify the target feature data, a classification result is obtained, a classification model is determined according to the classification result and the marked sample data, and through the classification model, the type of livestock data can be accurately judged, and classification accuracy is improved.
Optionally, the determining module is further configured to:
acquiring behavior data of livestock;
determining a first behavior mode corresponding to the behavior data according to a pre-trained behavior recognition model, wherein the pre-trained behavior recognition model is obtained by training a neural network model or a statistical model through sample behavior data;
comparing according to the first behavior mode and a preset behavior mode to obtain a behavior comparison result, wherein the behavior comparison result at least comprises behavior change data, frequency and duration;
and displaying the behavior comparison result through the augmented reality equipment, and determining feeding information corresponding to the behavior comparison result according to the behavior comparison result.
According to some embodiments of the application, the first behavior pattern corresponding to the livestock behavior data is identified according to the pre-trained behavior identification model, then the first behavior pattern is compared with the preset behavior pattern to obtain a behavior comparison result, and corresponding feeding information is determined according to the behavior comparison result.
Optionally, the model training module is further configured to:
acquiring sample behavior data;
Preprocessing the sample behavior data to obtain processed sample behavior data;
determining a behavior feature vector corresponding to the sample behavior data according to the processed sample behavior data by adopting a statistical method or a time sequence analysis method;
training a training model or a statistical model according to the behavior feature vector to obtain the behavior recognition model, wherein the training model comprises a decision tree, a support vector machine or a neural network, and the statistical model comprises a hidden Markov model.
According to some embodiments of the application, the behavior recognition model is obtained by acquiring sample behavior data and behavior feature vectors of the sample behavior data and then training a training model or a statistical model, and the behavior recognition model is used for recognizing specific behaviors of livestock, so that a specific feeding mode is determined according to the specific behaviors.
Optionally, the determining module is further configured to:
acquiring livestock field data, wherein the livestock field data at least comprises field boundary areas, terrains and obstacle data;
setting a virtual boundary area in a virtual environment by adopting augmented reality equipment according to the livestock field data;
Mapping the virtual boundary area and the field boundary area by adopting a map construction algorithm positioned at the same time;
and if the livestock is not in the boundary area of the field, displaying alarm information through the augmented reality equipment.
Some embodiments of the present application provide for setting a virtual boundary region in a virtual environment by acquiring livestock farm data, using an augmented reality device, and mapping the virtual boundary region to an actual farm boundary region, and displaying alarm information by the augmented reality device if the livestock is not within the farm boundary region.
In a third aspect, some embodiments of the present application provide an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the program, may implement a method of supervising livestock farming according to any one of the embodiments of the first aspect.
In a fourth aspect, some embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which when executed by a processor may implement a method of supervision of livestock farming according to any of the embodiments of the first aspect.
In a fifth aspect, some embodiments of the present application provide a computer program product comprising a computer program, wherein the computer program when executed by a processor is capable of implementing a method of supervision of livestock farming according to any one of the embodiments of the first aspect.
Drawings
In order to more clearly illustrate the technical solutions of some embodiments of the present application, the drawings that are required to be used in some embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort to a person having ordinary skill in the art.
Fig. 1 is a schematic flow chart of a method for supervising livestock breeding according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a supervision apparatus for livestock breeding according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in some embodiments of the present application will be described below with reference to the drawings in some embodiments of the present application.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
At present, along with the continuous improvement of the living standard of people, the breeding industry also obtains rapid development, the quantity of livestock is also increased, and the requirements on livestock breeding are also increased. However, most farmers now rely on traditional feeding methods and mechanical equipment to perform these tasks, but the growth status of each animal cannot be accurately known, affecting the feeding of the animal, and in view of this, some embodiments of the present application provide a method of supervising the feeding of animals, the method comprising obtaining growth data of each animal, and generating a first growth curve from the growth data; classifying the growth data of each livestock according to a pre-trained classification model to obtain livestock categories corresponding to the growth data; determining a first similarity result according to a first growth curve and a pre-trained second growth curve corresponding to the livestock category, wherein the second growth curve is obtained by training a training model by adopting sample growth data, and is a statistical module or a neural network model; through augmented reality equipment, show the growth condition of livestock, wherein, the growth condition knowledge of livestock includes first similarity result and first growth curve, this application embodiment obtains the growth data of livestock through augmented reality equipment, generate first growth curve, then judge the livestock category of this livestock, calculate the similarity with the second growth curve that corresponds with the livestock category with first growth curve, obtain first similarity result, and show on augmented reality equipment, the user can look over by this augmented reality equipment, in time know the growth condition of each livestock.
As shown in fig. 1, an embodiment of the present application provides a method for supervising livestock breeding, the method including:
s101, acquiring growth data of each livestock, and generating a first growth curve according to the growth data;
specifically, the embodiment of the application is applied to a data processing terminal, receives data sent by an augmented reality device, namely an AR device, for example, the augmented reality device can be AR glasses, acquires growth data of each livestock through a sensor, for example, the growth data comprise weight and height, and then processes the growth data to generate a first growth curve.
S102, classifying the growth data of each livestock according to a pre-trained classification model to obtain livestock types corresponding to the growth data;
specifically, the data processing terminal trains a classification model in advance, the classification model is used for classifying livestock, such as cows, calves or bulls, and the classification model is obtained by acquiring data of different categories and processing the data of the different categories by adopting a preset selection algorithm.
After the data processing terminal acquires the growth data, the pre-trained classification model is adopted to classify the growth data of each livestock, so that livestock types corresponding to the growth data are obtained, wherein the livestock types comprise cows, calves or bulls.
S103, determining a first similarity result according to a first growth curve and a pre-trained second growth curve corresponding to the livestock category, wherein the second growth curve is obtained by training a training model by adopting sample growth data, and the training model wave comprises a statistical module or a neural network model;
specifically, training a training model on the data processing terminal by adopting sample growth data in advance to obtain a second growth curve, wherein the training model comprises a statistical module or a neural network model;
the data processing terminal acquires a second growth curve corresponding to the livestock category, and then performs similarity calculation on the first growth curve and the second growth curve to obtain a first similarity result.
S104, displaying the growth condition of the livestock through the augmented reality equipment, wherein the knowledge of the growth condition of the livestock comprises a first similarity result and a first growth curve.
Specifically, the data processing terminal transmits the generated first similarity result and the first growth curve to the augmented reality device, and the user can display the growth condition of the livestock, for example, the growth curve and the standard growth curve of the livestock through the augmented reality device, and the first similarity result can track the growth curve of each livestock and the comparison with other similar livestock through the AR glasses in real time.
In this embodiment of the present invention, a tag or a sensor is installed on each livestock, the AR glasses acquire relevant data, such as growth data, from the tag or the sensor, and the data processing terminal can receive and process the data transmitted from the AR glasses in real time, and through the AR glasses, the farmer can see the basic health index (such as body temperature, heartbeat frequency, etc.) of each livestock.
According to some embodiments of the method, the device and the system, through the augmented reality device, growth data of livestock are obtained, a first growth curve is generated, then the livestock category of the livestock is judged, similarity calculation is conducted on the first growth curve and a second growth curve corresponding to the livestock category, a first similarity result is obtained, the first similarity result is displayed on the augmented reality device, and a user can check the augmented reality device and know the growth condition of each livestock in time.
The method for supervising the livestock breeding provided by the embodiment is further described in a further embodiment.
Alternatively, the second growth curve is obtained by:
acquiring first sample growth data, wherein the first sample growth data includes height and weight;
preprocessing the first sample growth data to obtain processed sample growth data;
Classifying the processed sample growth data to obtain a classification result;
training a statistical model or a neural network model according to the classification result to obtain a second growth curve, wherein the statistical model comprises a linear regression model or a polynomial regression model; the neural network model includes a decision tree or support vector machine.
Specifically, the data processing terminal trains the second growth curve by:
1. and (3) data collection: growth data, such as weight, height, etc., for each animal is collected using sensors or other devices and stored in a database.
2. Data preprocessing: and preprocessing the collected data, including removing abnormal values, filling missing values and the like, to obtain processed sample growth data.
3. Classification of livestock: livestock are classified by category, and can be classified according to male and female categories, or according to the length of growing time, such as cows, calves, breeding bulls, etc.
4. Modeling a growth curve: the growth curve modeling is performed on each type of livestock, and a statistical model (such as linear regression, polynomial regression) or a machine learning algorithm (such as decision tree, support vector machine) can be used to generate a second growth curve.
5. Curve comparison: comparing the growth curve of each animal, i.e. the first growth curve, with the curve of the same kind of animal, i.e. the second growth curve, a curve similarity measure (e.g. cosine similarity, euclidean distance) can be used to evaluate the similarity between them, i.e. the first similarity.
The comparison result is visually presented to the farmer through the AR glasses, for example, the growth curve of each livestock and the average curve of the same type of livestock are displayed on the AR interface, and the information such as similarity score and the like is displayed.
According to some embodiments of the method, the statistical model and the neural network model are trained by acquiring the first sample growth data, so that a second growth curve is obtained, and the second growth curve is used for judging the first growth curve, so that the growth state of livestock is judged.
Optionally, determining the first similarity result according to the first growth curve and the pre-trained second growth curve corresponding to the livestock category includes:
and calculating the similarity of the first growth curve and the second growth curve by adopting a curve similarity measurement method to obtain a first similarity result, wherein the curve similarity measurement method comprises cosine similarity or Euclidean distance.
Some embodiments of the present application calculate the similarity of the first growth curve and the second growth curve by using a curve similarity measurement method, if the similarity is smaller than a preset value, it indicates that the growth condition of the livestock meets the expected requirement, and if the similarity is larger than the preset value, it indicates that the growth condition of the livestock is worse, and it is necessary to adjust the feeding plan.
Alternatively, the classification model is obtained by:
acquiring second sample data and labeling sample data, wherein the second sample data comprises data of different categories;
preprocessing the second sample data to obtain processed second sample data;
performing feature extraction on the second sample data by adopting an image processing method or a deep learning model to obtain feature data corresponding to the second sample data, wherein the feature data comprises color features, texture features and shape features;
selecting target characteristic data from the characteristic data by adopting a statistical method or a machine learning algorithm;
classifying the target feature data by adopting a preset selection algorithm to obtain a classification result, wherein the preset selection algorithm at least comprises any one of a support vector machine, a random forest, a naive Bayes classifier or a deep learning model;
And determining a classification model according to the classification result and the labeling sample data.
Specifically, the data processing terminal can automatically identify and classify livestock, such as cows, calves, breeding bull, etc., using AR glasses.
The data processing terminal is used for classifying livestock, and training a classification model is needed in advance, and specifically comprises the following steps:
1. and (3) data acquisition: a sufficient image or video dataset, i.e. second sample data, is collected containing samples of different kinds of livestock, e.g. cows, calves, breeding bulls etc.
2. Data preprocessing: preprocessing the collected image or video data, including image enhancement, noise reduction, size normalization, etc., to obtain processed second sample data.
3. Feature extraction: features of the livestock sample are extracted using image processing methods or deep learning models (e.g., convolutional neural networks). This may be done by extracting features of color, texture, shape, etc. of the image.
4. Feature selection: the most discriminating features from the extracted features can be selected using statistical methods (e.g., analysis of variance) or machine learning algorithms (e.g., recursive feature elimination).
5. Classification algorithm: the characteristics are classified by selecting a proper classification algorithm, and common algorithms comprise a support vector machine, a random forest, a naive Bayesian classifier, a deep learning model and the like.
6. Model training and evaluation: training the model by using the marked sample data, evaluating the model by using the unmarked data, and selecting the model with the best performance, namely the classification model.
After the classification model is trained, the data processing terminal applies the trained classification model to real-time data, such as real-time video streams in AR glasses, and performs classification recognition on livestock.
According to some embodiments of the application, the second sample data are adopted, the second sample data comprise data of different types, target feature data in the second sample data are extracted, a preset selection algorithm is adopted to classify the target feature data, a classification result is obtained, a classification model is determined according to the classification result and the marked sample data, and through the classification model, the type of livestock data can be accurately judged, and classification accuracy is improved.
Optionally, the method further comprises:
acquiring behavior data of livestock;
determining a first behavior mode corresponding to behavior data according to a pre-trained behavior recognition model, wherein the pre-trained behavior recognition model is obtained by training a neural network model or a statistical model through sample behavior data;
Comparing according to the first behavior mode and a preset behavior mode to obtain a behavior comparison result, wherein the behavior comparison result at least comprises behavior change data, frequency and duration;
and displaying the behavior comparison result through the augmented reality equipment, and determining feeding information corresponding to the behavior comparison result according to the behavior comparison result.
Specifically, the data processing terminal may further perform behavior analysis on the livestock, for example, analyze behaviors of the livestock, such as feeding, drinking, resting and interaction, to determine health and comfort of the livestock, including:
acquiring behavioral data of the livestock, for example, video data by a sensor or a camera; determining a first behavior mode corresponding to behavior data according to a pre-trained behavior recognition model, wherein the pre-trained behavior recognition model is obtained by training a neural network model or a statistical model through sample behavior data; comparing according to the first behavior mode and a preset behavior mode to obtain a behavior comparison result, wherein the behavior comparison result at least comprises behavior change data, frequency and duration; and displaying the behavior comparison result through the augmented reality equipment, and determining feeding information corresponding to the behavior comparison result according to the behavior comparison result.
In a specific real-time process, the data processing terminal compares the observed animal behaviors with an established behavior recognition model, and analyzes the changes, frequency, duration and the like of the animal behaviors to evaluate the health and comfort of the animal.
That is, the data processing terminal judges the health and comfort of the animal according to the result of the behavioral analysis in combination with previous experience and expertise. For example, if a significant decrease in the food intake of an animal is found, it may be indicative of physical discomfort or health problems, and based on the health and comfort judgment, targeted feedback and intervention is performed, such as advice to adjust diet, environment or behavior, to improve the health and comfort of the animal.
According to some embodiments of the application, the first behavior pattern corresponding to the livestock behavior data is identified according to the pre-trained behavior identification model, then the first behavior pattern is compared with the preset behavior pattern to obtain a behavior comparison result, and corresponding feeding information is determined according to the behavior comparison result.
Alternatively, the behavior recognition model is obtained by:
acquiring sample behavior data;
Preprocessing sample behavior data to obtain processed sample behavior data;
determining a behavior feature vector corresponding to the sample behavior data according to the processed sample behavior data by adopting a statistical method or a time sequence analysis method;
training a training model or a statistical model according to the behavior feature vector to obtain a behavior recognition model, wherein the training model comprises a decision tree, a support vector machine or a neural network, and the statistical model comprises a hidden Markov model.
Specifically, the data processing terminal trains the sample behavior data in advance, and the training process comprises the following steps:
1. and (3) data acquisition: sensors, cameras or other devices are used to collect data concerning animal behavior, i.e. sample behavior data such as eating, drinking, resting, activity, etc.
2. Data preprocessing: preprocessing the acquired data, including data cleaning, abnormal value removal and the like, to obtain processed sample behavior data.
3. Feature extraction: features are extracted from raw data, and behavior feature vectors can be extracted using statistical methods (e.g., mean, standard deviation) or time series analysis methods (e.g., spectral analysis, waveform analysis).
4. Building a behavior recognition model: a machine learning algorithm (e.g., decision tree, support vector machine, neural network) or a statistical model (e.g., hidden markov model) is used to build a behavior recognition model, which is used to learn animal behavior patterns by training the model, i.e., to generate the behavior recognition model.
According to some embodiments of the application, the behavior recognition model is obtained by acquiring sample behavior data and behavior feature vectors of the sample behavior data and then training a training model or a statistical model, and the behavior recognition model is used for recognizing specific behaviors of livestock, so that a specific feeding mode is determined according to the specific behaviors.
Optionally, the method further comprises:
acquiring livestock field data, wherein the livestock field data at least comprises field boundary areas, terrains and obstacle data;
setting a virtual boundary area in a virtual environment by adopting augmented reality equipment according to livestock field data;
mapping the virtual boundary area and the site boundary area by adopting a map construction algorithm positioned at the same time;
in areas where the livestock is not located in the field boundary area, alarm information is displayed by the augmented reality device.
Specifically, the embodiments of the present application use AR technology to set virtual boundaries for livestock, and when the livestock exceeds these boundaries, the system will issue a warning, including:
1. collecting site information: first, information about the location of livestock is collected, including the size of the location, terrain, obstacle location, etc., which may be obtained by site surveying or using a laser rangefinder or the like.
2. Designing a boundary area: based on the site information, the bounding region is designed for use in the virtual environment by AR development tools or software.
3. Site mapping and positioning: the virtual boundary region is mapped with the actual field. This can be achieved by SLAM (simultaneous localization and mapping) algorithms in AR technology, where real-time scene images are acquired by cameras and correspond to virtual boundaries.
4. Calibrating and calibrating: calibration and calibration of the AR device is performed to ensure accurate alignment of the virtual boundary with the actual site. This may be accomplished by calibration tools provided by the AR device or by computer vision based methods.
5. Boundary setting and prompting: and displaying a virtual boundary in a real scene where the livestock is located by using an AR technology, and setting a corresponding prompt for the livestock. The cues may include sound, light, vibration, etc. to attract the livestock to notice the virtual boundary, avoiding out of bounds.
In particular real-time processes, where the position and behavior of the animal is monitored using sensors or cameras or the like, the AR system may provide corresponding feedback, such as warning cues or assistance in driving the animal away from boundary crossing as the animal approaches the virtual boundary. The specific setting of the virtual boundary can be adjusted and optimized according to the actual use condition and the habit and response of the livestock. This can be achieved by collecting feedback data, analyzing the behavior patterns and making improvements.
According to the embodiment of the application, the food sources, the drug use records and the like of livestock can be tracked by the AR glasses, so that the food safety is ensured, the novice farmers can obtain real-time guidance and advice through the AR glasses, the breeding efficiency is improved, and errors are reduced.
Illustratively, farmers wear AR glasses into the cowshed, which automatically identify each cow and display information about the cow, such as health status, last vaccination time, etc.
Some embodiments of the present application provide for setting a virtual boundary region in a virtual environment by acquiring livestock farm data, using an augmented reality device, and mapping the virtual boundary region to an actual farm boundary region, and displaying alarm information by the augmented reality device if the livestock is not within the farm boundary region.
It should be noted that, in this embodiment, each of the possible embodiments may be implemented separately, or may be implemented in any combination without conflict, which is not limited to the implementation of the present application.
Another embodiment of the present application provides a supervision apparatus for livestock breeding, configured to execute the supervision method for livestock breeding provided in the foregoing embodiment.
Fig. 2 is a schematic structural diagram of a supervision apparatus for livestock breeding according to an embodiment of the present disclosure. The supervision device for livestock breeding comprises an acquisition module 201, a classification model 202, a determination module 203 and a display module 204, wherein:
The acquisition module 201 is used for acquiring growth data of each livestock and generating a first growth curve according to the growth data;
the classification model 202 is used for classifying the growth data of each livestock according to a pre-trained classification model to obtain livestock categories corresponding to the growth data;
the determining module 203 is configured to determine a first similarity result according to a first growth curve and a pre-trained second growth curve corresponding to a livestock category, where the second growth curve is obtained by training a training model with sample growth data, and the statistical module or the neural network model;
the display module 204 is configured to display, via the augmented reality device, a growth of the livestock, wherein the knowledge of the growth of the livestock includes a first similarity result and a first growth curve.
The specific manner in which the individual modules perform the operations of the apparatus of this embodiment has been described in detail in connection with embodiments of the method and will not be described in detail herein.
According to some embodiments of the method, the device and the system, through the augmented reality device, growth data of livestock are obtained, a first growth curve is generated, then the livestock category of the livestock is judged, similarity calculation is conducted on the first growth curve and a second growth curve corresponding to the livestock category, a first similarity result is obtained, the first similarity result is displayed on the augmented reality device, and a user can check the augmented reality device and know the growth condition of each livestock in time.
In another embodiment of the present application, the supervision device for livestock cultivation provided in the foregoing embodiment is further described in a supplementary manner.
Optionally, the apparatus further comprises a model training module for:
acquiring first sample growth data, wherein the first sample growth data includes height and weight;
preprocessing the first sample growth data to obtain processed sample growth data;
classifying the processed sample growth data to obtain a classification result;
training a statistical model or a neural network model according to the classification result to obtain a second growth curve, wherein the statistical model comprises a linear regression model or a polynomial regression model; the neural network model includes a decision tree or support vector machine.
According to some embodiments of the method, the statistical model and the neural network model are trained by acquiring the first sample growth data, so that a second growth curve is obtained, and the second growth curve is used for judging the first growth curve, so that the growth state of livestock is judged.
Optionally, the determining module is configured to:
and calculating the similarity of the first growth curve and the second growth curve by adopting a curve similarity measurement method to obtain a first similarity result, wherein the curve similarity measurement method comprises cosine similarity or Euclidean distance.
Some embodiments of the present application calculate the similarity of the first growth curve and the second growth curve by using a curve similarity measurement method, if the similarity is smaller than a preset value, it indicates that the growth condition of the livestock meets the expected requirement, and if the similarity is larger than the preset value, it indicates that the growth condition of the livestock is worse, and it is necessary to adjust the feeding plan.
Optionally, the model training module is further configured to:
acquiring second sample data and labeling sample data, wherein the second sample data comprises data of different categories;
preprocessing the second sample data to obtain processed second sample data;
performing feature extraction on the second sample data by adopting an image processing method or a deep learning model to obtain feature data corresponding to the second sample data, wherein the feature data comprises color features, texture features and shape features;
selecting target characteristic data from the characteristic data by adopting a statistical method or a machine learning algorithm;
classifying the target feature data by adopting a preset selection algorithm to obtain a classification result, wherein the preset selection algorithm at least comprises any one of a support vector machine, a random forest, a naive Bayes classifier or a deep learning model;
And determining a classification model according to the classification result and the labeling sample data.
According to some embodiments of the application, the second sample data are adopted, the second sample data comprise data of different types, target feature data in the second sample data are extracted, a preset selection algorithm is adopted to classify the target feature data, a classification result is obtained, a classification model is determined according to the classification result and the marked sample data, and through the classification model, the type of livestock data can be accurately judged, and classification accuracy is improved.
Optionally, the determining module is further configured to:
acquiring behavior data of livestock;
determining a first behavior mode corresponding to behavior data according to a pre-trained behavior recognition model, wherein the pre-trained behavior recognition model is obtained by training a neural network model or a statistical model through sample behavior data;
comparing according to the first behavior mode and a preset behavior mode to obtain a behavior comparison result, wherein the behavior comparison result at least comprises behavior change data, frequency and duration;
and displaying the behavior comparison result through the augmented reality equipment, and determining feeding information corresponding to the behavior comparison result according to the behavior comparison result.
According to some embodiments of the application, the first behavior pattern corresponding to the livestock behavior data is identified according to the pre-trained behavior identification model, then the first behavior pattern is compared with the preset behavior pattern to obtain a behavior comparison result, and corresponding feeding information is determined according to the behavior comparison result.
Optionally, the model training module is further configured to:
acquiring sample behavior data;
preprocessing sample behavior data to obtain processed sample behavior data;
determining a behavior feature vector corresponding to the sample behavior data according to the processed sample behavior data by adopting a statistical method or a time sequence analysis method;
training a training model or a statistical model according to the behavior feature vector to obtain a behavior recognition model, wherein the training model comprises a decision tree, a support vector machine or a neural network, and the statistical model comprises a hidden Markov model.
According to some embodiments of the application, the behavior recognition model is obtained by acquiring sample behavior data and behavior feature vectors of the sample behavior data and then training a training model or a statistical model, and the behavior recognition model is used for recognizing specific behaviors of livestock, so that a specific feeding mode is determined according to the specific behaviors.
Optionally, the determining module is further configured to:
acquiring livestock field data, wherein the livestock field data at least comprises field boundary areas, terrains and obstacle data;
setting a virtual boundary area in a virtual environment by adopting augmented reality equipment according to livestock field data;
mapping the virtual boundary area and the site boundary area by adopting a map construction algorithm positioned at the same time;
in areas where the livestock is not located in the field boundary area, alarm information is displayed by the augmented reality device.
Some embodiments of the present application provide for setting a virtual boundary region in a virtual environment by acquiring livestock farm data, using an augmented reality device, and mapping the virtual boundary region to an actual farm boundary region, and displaying alarm information by the augmented reality device if the livestock is not within the farm boundary region.
The specific manner in which the individual modules perform the operations of the apparatus of this embodiment has been described in detail in connection with embodiments of the method and will not be described in detail herein.
It should be noted that, in this embodiment, each of the possible embodiments may be implemented separately, or may be implemented in any combination without conflict, which is not limited to the implementation of the present application.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, can implement the operations of the method corresponding to any embodiment in the livestock breeding supervision method provided in the above embodiment.
The embodiment of the application also provides a computer program product, which comprises a computer program, wherein the computer program can realize the operation of the method corresponding to any embodiment in the livestock breeding supervision method provided by the embodiment when being executed by a processor.
As shown in fig. 3, some embodiments of the present application provide an electronic device 300, the electronic device 300 comprising: memory 310, processor 320, and a computer program stored on memory 310 and executable on processor 320, wherein processor 320, when reading the program from memory 310 and executing the program via bus 330, may implement the method of any of the embodiments as included in the above-described methods of supervising livestock farming.
Processor 320 may process digital signals and may include various computing structures. Such as a complex instruction set computer architecture, a reduced instruction set computer architecture, or an architecture that implements a combination of instruction sets. In some examples, processor 320 may be a microprocessor.
Memory 310 may be used for storing instructions to be executed by processor 320 or data related to execution of the instructions. Such instructions and/or data may include code to implement some or all of the functions of one or more modules described in embodiments of the present application. The processor 320 of the disclosed embodiments may be configured to execute instructions in the memory 310 to implement the methods shown above. Memory 310 includes dynamic random access memory, static random access memory, flash memory, optical memory, or other memory known to those skilled in the art.
The above is only an example of the present application, and is not intended to limit the scope of the present application, and various modifications and variations will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application. It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Claims (10)
1. A method of supervising livestock farming, the method comprising:
acquiring growth data of each livestock, and generating a first growth curve according to the growth data;
classifying the growth data of each livestock according to a pre-trained classification model to obtain livestock categories corresponding to the growth data;
Determining a first similarity result according to the first growth curve and a pre-trained second growth curve corresponding to the livestock category, wherein the second growth curve is obtained by training a training model by adopting sample growth data, and the training model comprises a statistical module or a neural network model;
displaying the growth condition of the livestock through an augmented reality device, wherein the knowledge of the growth condition of the livestock comprises the first similarity result and the first growth curve.
2. The method of supervising livestock farming of claim 1, wherein the second growth curve is obtained by:
acquiring first sample growth data, wherein the first sample growth data includes height and weight;
preprocessing the first sample growth data to obtain processed sample growth data;
classifying the processed sample growth data to obtain a classification result;
training the statistical model or the neural network model according to the classification result to obtain the second growth curve, wherein the statistical model comprises a linear regression model or a polynomial regression model; the neural network model includes a decision tree or a support vector machine.
3. The method of claim 1, wherein determining a first similarity result from the first growth curve and a pre-trained second growth curve corresponding to a livestock category comprises:
and calculating the similarity of the first growth curve and the second growth curve by adopting a curve similarity measurement method to obtain the first similarity result, wherein the curve similarity measurement method comprises cosine similarity or Euclidean distance.
4. The method of supervising livestock farming according to claim 1, wherein the classification model is obtained by:
acquiring second sample data and labeling sample data, wherein the second sample data comprises data of different categories;
preprocessing the second sample data to obtain processed second sample data;
performing feature extraction on the second sample data by adopting an image processing method or a deep learning model to obtain feature data corresponding to the second sample data, wherein the feature data comprises color features, texture features and shape features;
selecting target characteristic data from the characteristic data by adopting a statistical method or a machine learning algorithm;
Classifying the target feature data by adopting a preset selection algorithm to obtain a classification result, wherein the preset selection algorithm at least comprises any one of a support vector machine, a random forest, a naive Bayes classifier or a deep learning model;
and determining the classification model according to the classification result and the labeling sample data.
5. The method of supervising livestock farming of claim 1, wherein the method further comprises:
acquiring behavior data of livestock;
determining a first behavior mode corresponding to the behavior data according to a pre-trained behavior recognition model, wherein the pre-trained behavior recognition model is obtained by training a neural network model or a statistical model through sample behavior data;
comparing according to the first behavior mode and a preset behavior mode to obtain a behavior comparison result, wherein the behavior comparison result at least comprises behavior change data, frequency and duration;
and displaying the behavior comparison result through the augmented reality equipment, and determining feeding information corresponding to the behavior comparison result according to the behavior comparison result.
6. The method of supervising livestock farming of claim 5, wherein the behavior recognition model is obtained by:
acquiring sample behavior data;
preprocessing the sample behavior data to obtain processed sample behavior data;
determining a behavior feature vector corresponding to the sample behavior data according to the processed sample behavior data by adopting a statistical method or a time sequence analysis method;
training a training model or a statistical model according to the behavior feature vector to obtain the behavior recognition model, wherein the training model comprises a decision tree, a support vector machine or a neural network, and the statistical model comprises a hidden Markov model.
7. The method of supervising livestock farming of claim 1, wherein the method further comprises:
acquiring livestock field data, wherein the livestock field data at least comprises field boundary areas, terrains and obstacle data;
setting a virtual boundary area in a virtual environment by adopting augmented reality equipment according to the livestock field data;
mapping the virtual boundary area and the field boundary area by adopting a map construction algorithm positioned at the same time;
And if the livestock is not in the boundary area of the field, displaying alarm information through the augmented reality equipment.
8. A supervision apparatus for livestock farming, the apparatus comprising:
the acquisition module is used for acquiring the growth data of each livestock and generating a first growth curve according to the growth data;
the classification model is used for classifying the growth data of each livestock according to a pre-trained classification model to obtain livestock types corresponding to the growth data;
the determining module is used for determining a first similarity result according to the first growth curve and a pre-trained second growth curve corresponding to the livestock category, wherein the second growth curve is obtained by training a training model by adopting sample growth data, and the training model comprises a statistical module or a neural network model;
and the display module is used for displaying the growth condition of the livestock through the augmented reality equipment, wherein the knowledge of the growth condition of the livestock comprises the first similarity result and the first growth curve.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor is operable to implement the method of supervising livestock farming according to any one of claims 1-7 when executing the program.
10. A computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, characterized in that the program, when executed by a processor, implements the method of supervising livestock farming according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410057987.4A CN117892172A (en) | 2024-01-15 | 2024-01-15 | Livestock breeding supervision method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410057987.4A CN117892172A (en) | 2024-01-15 | 2024-01-15 | Livestock breeding supervision method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117892172A true CN117892172A (en) | 2024-04-16 |
Family
ID=90645325
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410057987.4A Pending CN117892172A (en) | 2024-01-15 | 2024-01-15 | Livestock breeding supervision method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117892172A (en) |
-
2024
- 2024-01-15 CN CN202410057987.4A patent/CN117892172A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bao et al. | Artificial intelligence in animal farming: A systematic literature review | |
| González et al. | Behavioral classification of data from collars containing motion sensors in grazing cattle | |
| Cangar et al. | Automatic real-time monitoring of locomotion and posture behaviour of pregnant cows prior to calving using online image analysis | |
| JP7470203B2 (en) | Analysis and selection in aquaculture | |
| US20170124727A1 (en) | Method and device for automated parameters calculation of an object | |
| US20040131254A1 (en) | System and method for object identification and behavior characterization using video analysis | |
| MX2015006775A (en) | Systems and methods for predicting the outcome of a state of a subject. | |
| Qiao et al. | Intelligent perception-based cattle lameness detection and behaviour recognition: A review | |
| Wang et al. | An automated behavior analysis system for freely moving rodents using depth image | |
| CN113662530B (en) | Pig physiological growth state monitoring and early warning method | |
| CN111297367A (en) | Animal state monitoring method and device, electronic equipment and storage medium | |
| Shakeel et al. | A deep learning-based cow behavior recognition scheme for improving cattle behavior modeling in smart farming | |
| JP6618631B2 (en) | Computer system, animal diagnosis method and program | |
| Xiong et al. | Estimating body weight and body condition score of mature beef cows using depth images | |
| Azarpajouh et al. | Farm 4.0: innovative smart dairy technologies and their applications as tools for welfare assessment in dairy cattle | |
| CN110532854B (en) | Live pig crawling and crossing behavior detection method and system | |
| US20230154617A1 (en) | Method and System for Examining Health Conditions of an Animal | |
| CN113516139A (en) | Data processing method, device, equipment and storage medium | |
| CN117892172A (en) | Livestock breeding supervision method and device, electronic equipment and storage medium | |
| CN115830078A (en) | Live pig multi-target tracking and behavior recognition method, computer equipment and storage medium | |
| Cai et al. | A night-time anomaly detection system of hog activities based on passive infrared detector | |
| Leroy et al. | Computer vision based recognition of behavior phenotypes of laying hens | |
| Bati et al. | SHEEPFEARNET: Sheep fear test behaviors classification approach from video data based on optical flow and convolutional neural networks | |
| CN113989745A (en) | Non-contact monitoring method for feeding condition of ruminants | |
| Yeşil et al. | Recognition of Hereford and Simmental cattle breeds via computer vision. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |