CN110059781A - Cow digitalization Activity recognition device - Google Patents
Cow digitalization Activity recognition device Download PDFInfo
- Publication number
- CN110059781A CN110059781A CN201910289459.0A CN201910289459A CN110059781A CN 110059781 A CN110059781 A CN 110059781A CN 201910289459 A CN201910289459 A CN 201910289459A CN 110059781 A CN110059781 A CN 110059781A
- Authority
- CN
- China
- Prior art keywords
- cow
- milk cow
- data
- milk
- feature vector
- 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
- 230000000694 effects Effects 0.000 title claims abstract description 43
- 241000283690 Bos taurus Species 0.000 claims abstract description 153
- 239000008267 milk Substances 0.000 claims abstract description 102
- 235000013336 milk Nutrition 0.000 claims abstract description 102
- 210000004080 milk Anatomy 0.000 claims abstract description 102
- 238000000034 method Methods 0.000 claims abstract description 18
- 230000009027 insemination Effects 0.000 claims abstract description 5
- 241000232136 Primulina Species 0.000 claims abstract description 4
- 238000013499 data model Methods 0.000 claims abstract description 4
- 230000001133 acceleration Effects 0.000 claims description 24
- 238000007726 management method Methods 0.000 claims description 19
- 238000001514 detection method Methods 0.000 claims description 17
- 230000012173 estrus Effects 0.000 claims description 13
- 238000013523 data management Methods 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 12
- 210000000664 rectum Anatomy 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 10
- 241001465754 Metazoa Species 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 235000013365 dairy product Nutrition 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000036760 body temperature Effects 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 230000003203 everyday effect Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 230000000737 periodic effect Effects 0.000 claims description 3
- 230000002085 persistent effect Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 241000283725 Bos Species 0.000 claims description 2
- 230000003542 behavioural effect Effects 0.000 abstract 1
- 230000006399 behavior Effects 0.000 description 14
- 238000010586 diagram Methods 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 210000003423 ankle Anatomy 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002618 waking effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisions for transferring data to distant stations, e.g. from a sensing device
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of cow digitalization Activity recognition device, which includes: ear tag, for being bundled in milk ivory-white chirita herb, acquires the behavior state data of milk cow in real time；Reader obtains the behavior state data of milk cow for obtaining the ear tag by radio frequency method, and carries out model conversation；Cloud Server, for wirelessly obtaining the data after the reader model conversation, and to milk cow current behavior, whether heat carries out intelligent decision.The present invention generates its behavioral data model and then accurately collecting every behavior state data of milk cow, judge whether milk cow is in heat, calculate best time of insemination, improves the conception rate of individual milk cow, shorten the calving interval, can be widely applied in milk cattle cultivating.
Description
Technical field
The present invention relates to a kind of cow digitalization Activity recognition devices, are related to Intelligent pasture technical field.
Background technique
For large-scale dairy cow farm, the conception rate of milk cow and calving interval are the deciding factors of the output of milk.But
It is since every cow head estrus time is widely different.Milk cow row is checked mainly by animal doctor's timing inspection cowshed in past, cattle farm
For, for example, by the behaviors such as feeding, rest, mounting sentence come at the beginning of milk cow whether heat.Since there are time interval and visually observe
The reasons such as covering surface, cow oestrus exposure rate is substantially below 70%.
With the fast development of embedded hardware and sensor technology, domestic and international cattle farm gradually starts using electronic device
(pedometer) come assist animal doctor judge milk cow whether heat.Pedometer is usually tied up is hung on ox neck at ox ankle or in the form of necklace
Neck records milk cow step number per hour, and by wireless network transmissions to the end PC, the end PC combines corresponding according to the variable quantity of step number
Rule carries out heat identification decision.But above-mentioned data acquisition modes collection is in the form of a single, to acquire based on the mobile data of ox,
Similar function of passometer, and judge with this data the oestrus of ox, equally exist biggish error.
Summary of the invention
In view of the above-mentioned problems, the object of the present invention is to provide the milk cow numbers that one kind can significantly improve cow oestrus judgement rate
Word Activity recognition device.
To achieve the above object, the present invention takes following technical scheme: a kind of cow digitalization Activity recognition device, the knowledge
Other device includes:
Ear tag acquires the behavior state data of milk cow for being bundled in milk ivory-white chirita herb in real time；
Reader for obtaining the milk cow behavior state data of the ear tag acquisition by radio frequency method, and carries out model
Conversion；
Cloud Server, for wirelessly obtaining the data after the reader model conversation, and it is current to milk cow
Whether heat carries out intelligent decision for behavior.
The cow digitalization Activity recognition device, further, the behavior state data of milk cow include feeding, rest,
Activity is ruminated and body temperature feature.
The cow digitalization Activity recognition device, further, the ear tag includes shell, the hull outside setting
There is onboard antenna, master controller, radio-frequency module, sensor controller, acceleration transducer and temperature are provided in the shell
Sensor, the radio-frequency module pin connect the onboard antenna；The acceleration transducer for acquiring the dynamic of milk cow in real time
Make data, the temperature sensor for acquiring the shell temperature of milk cow, the acceleration transducer and temperature sensor in real time
It is all connected with the sensor controller, the sensor controller is by received action data and temperature data through filtering, modulus
Conversion and compensation for calibrating errors, which calculate, generates master controller described in normalization data and periodic wakeup；The master controller wakes up
Afterwards, it reads the normalization data merging ear tag ID data packing and the reading is sent to by the radio-frequency module and onboard antenna
Write device.
The cow digitalization Activity recognition device, further, the reader includes shell, and the case top is set
It is equipped with antenna, is provided with controller, radio-frequency module and 4G/WIFI transparent transmission module in the shell, the controller is by milk cow
The 4G/WIFI transparent transmission module is sent to by serial ports after the conversion of behavior state data model.
The cow digitalization Activity recognition device, further, the detailed process of model conversion are as follows: the milk cow that will acquire
Acceleration information sequence tests the obtained corresponding acceleration threshold of the various attitudes vibrations of milk cow in conjunction with history as input parameter
Value, judges milk cow active state:
For walking states, acceleration, which first increases, to be reduced afterwards until speed reaches maximum value, then in the opposite manner plus
Speed until it arrives again at 0, and reaches stable displacement and new position, and persistent loop is then determined as walking states, according to
Cycle-index obtains step number；
For state of couching, acceleration generation rapidly increases, and reduces up to being 0, next continues slightly to hesitate at 0 value
It wanders, is then determined as state of couching；
For aggravating activities, default is determined with a preset high threshold；
For the state of ruminating, acceleration is exported always with very stable small ripple, is ruminated when accelerating degree series to show
When ripple magnitude consistency, that is, regard as the activity of ruminating；
Wherein, the data output of above-mentioned all milk cow states is the structured data based on time shaft.
The cow digitalization Activity recognition device, further, the Cloud Server includes data management system and intelligence
It can oestrous detection module；
The data management system is used for the data being packaged by reader described in data reception module real-time reception, and solves
Correspondence database is written according to ear tag ID, wherein the data reception module uses TCP transmission agreement, passes through volume in code data packet
Cheng Shixian listens to designated port；
The intelligence oestrous detection system is used to obtain the feature vector of certain milk cow by the data management system, in conjunction with
The feature vector of intelligent oestrous detection model analysis milk cow, using model prediction result as judgement result, if it is decided that the milk
Ox is in heat state, calculates the best time of insemination of the milk cow, and sends cow oestrus warning message.
The cow digitalization Activity recognition device, further, the establishment process of the intelligence oestrous detection model are as follows:
Step S1: randomly selecting m timing node, chooses n cow head every time by animal doctor, at some in n oxen
In heat state, animal doctor detected by rectum determine milk cow whether heat, selected timing node is obtained from data management system
With the one-to-one p=m*n feature vector of milk cow, each feature vector is normalized using the standardized method of min-max
Processing, the feature vector combination rectum testing result that will have been handled, composition have exemplar collection Dl={ (x1,y1),(x2,
y2),…,(xp,yp)},xiIt is the feature vector of milk cow, yiIndicate rectum testing result；Q feature is randomly choosed from database
Vector is removed from this q feature vector and is standardized with sample duplicate in Dl, remaining u feature vector using min-max
Method to each feature vector normalized, the feature vector handled is formed into unlabeled exemplars collection Du={ xp+1,
xp+2,…,xp+u, u is much larger than p；
Step S2: classification based training is carried out to the sample set Dl and Du that step S1 is obtained using S3VM algorithm, determines that heat is known
Other model；
Step S3: acquisition milk cow feature vector is carried out in advance as input with the heat identification model that step S2 is obtained in real time
It surveys, obtains the prediction result of cow oestrus.
The cow digitalization Activity recognition device, further, the Cloud Server further include cattle farm information management system
System, the cattle farm information management system include milk cow information management module, milk cow monitoring module, OA system module and report mould
Block；
The milk cow information management module is used to store the relevant information of milk cow, archive information, history hair including milk cow
The activity data and temperature data of feelings data and every day；
The monitoring result that the milk cow monitoring module is used to obtain intelligent oestrous detection system monitors each cow head in real time
Information and state, find milk cow in time ruminates situations such as time is very little or operation is insufficient and estrus behavior；
The OA system is for carrying out cattle farm office；
The reporting modules are for periodically concluding the traffic-operating period of cattle farm.
The cow digitalization Activity recognition device, further, the identification device are additionally provided with mobile terminal, the cloud
Server by judging result by App or by wechat in a manner of by heat alarm prompt send mobile terminal notice Management in dairy farm people
Member.
The invention adopts the above technical scheme, which has the following advantages:
1, the ear tag that the present invention is arranged can identify subtle movement, be defined knowledge to deliberate action by model conversation
The different physiological status of other milk cow, therefore data acquisition is detailed, multiplicity, can be defined according to different demands and choose different models point
Analysis, and as data acquisition increases, the accuracy of model conversation is higher；
2, the present invention can with 24 hours real time monitoring milk cow physiologic information, by monitoring data to cow oestrus situation with
And the problems such as disease, is measured in real time, and effectively increases cow oestrus judgement rate；
3, the present invention establishes news file, personalized identification to every ox in a manner of machine learning and artificial intelligence
The difference of body and group provides basic data for scientific cultivation；
To sum up, the present invention generates intelligent heat inspection by the every exercise data and temperature data of accurately collecting milk cow
Model is surveyed, judges whether milk cow is in heat by intelligent oestrous detection model, calculates best time of insemination, improves individual milk
The conception rate of ox shortens the calving interval, can be widely applied in milk cattle cultivating.
Detailed description of the invention
Fig. 1 is the configuration diagram of cow digitalization Activity recognition device of the invention；
Fig. 2 is ear tag structural schematic diagram of the invention；
Fig. 3 is reader architecture diagram of the invention；
Fig. 4 is Cloud Server workflow schematic diagram of the invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiments of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
Member's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
As shown in Figure 1, cow digitalization Activity recognition device provided by the invention, including ear tag 1, reader 2 and cloud clothes
Business device 3.
Ear tag 1, for being bundled in milk ivory-white chirita herb, the behavior state data of round-the-clock real-time acquisition milk cow, behavior state
Data may include activity datas and the body temperature feature such as search for food, rest, is movable, ruminating.
Reader 2, for periodically obtaining the activity data that ear tag 1 acquires by radio frequency method, by being built in reader 2
Model conversation algorithm convert the milk cow activity data of acquisition to the digitlization behavior state of milk cow, will output after model conversation
Digitlization behavior state data be sent to Cloud Server 3, wherein the present invention realized on reader 2 data model convert, subtract
The light operation pressure of ear tag 1 increases 1 operating time of ear tag to reduce the power consumption of ear tag 1.
Data of the Cloud Server 3 for wirelessly acquisition reader 2, and by based on big data excavation and behavior
To milk cow current behavior, whether heat judges the intelligent oestrous detection model of model, and by App or by wechat in a manner of will
Heat alarm prompt notifies Management in dairy farm personnel, and Management in dairy farm personnel is facilitated to be managed milk cow information, forms full-automatic intelligent
It can closed loop heat monitoring system.
Above-mentioned cow digitalization Activity recognition device, it is preferable that as shown in Fig. 2, ear tag 1 includes shell, case top
It is provided with onboard antenna 11, enclosure interior is provided with master controller 12, acceleration transducer 13, temperature sensor 14, radio frequency mould
Block 15, sensor controller 16 and battery 17.Wherein, acceleration transducer 13 and temperature sensor 14 pass through IIC interface and biography
Sensor controller 16 is communicated, and 15 pin of radio-frequency module is connected to 433M onboard antenna 11.1 workflow of ear tag are as follows: accelerate
The action data (x, y, z 3-axis acceleration value) that sensor 13 acquires milk cow in real time is spent, temperature sensor 14 acquires milk cow in real time
Shell temperature；After sensor controller 16 is by IIC interface action data and temperature data, turn by filtering, modulus
It changes and compensation for calibrating errors calculates and generates normalization data and be cached, periodic wakeup master controller 12；Master controller 12 is called out
After waking up, reading normalization data merging ear tag ID, (unique 6 character strings, be can be set according to actual needs, for identification ear
Mark), current electric quantity, the data such as signal strength be packaged, notify radio-frequency module 15 using radio-frequency command and sent through onboard 11 line of day
Data packet is to reader, in addition, battery is used to be powered for each device.
Above-mentioned cow digitalization Activity recognition device, it is preferable that as shown in figure 3, reader 2 mainly includes shell, shell
It is provided with antenna 21 at the top of body, controller 22, radio-frequency module 23 and 4G/WIFI transparent transmission module 24, controller are provided in shell
22 can use single-chip microcontroller 2, and radio-frequency module 23 is responsible for receiving the data that surrounding ear tag 1 sends over, and single-chip microcontroller 2 is for carrying out mould
Type, which converts and passes through serial ports peripheral hardware 25, is sent to 4G or WIFI transparent transmission module 24 for packaged data.In addition, reader 2 is for timing
The data that the ear tag 1 of reception peripheral region is sent, about 100 meters of signal covering radius or so.Wherein, the specific work of model conversion
Make process:
Reader 2 receives the model conversion algorithm activated after data in reader 2, and model conversion algorithm is with acceleration information
Sequence is input parameter, and the corresponding acceleration rate threshold of various attitudes vibrations of obtained milk cow is tested in conjunction with history, carries out milk
The active state of ox judges:
For walking states, acceleration first increases reduces that (acceleration is positive representative always until speed reaches maximum value afterwards
Accelerate toward same direction), then accelerate in the opposite manner, until it arrives again at 0.Reach in this regard one it is stable
Displacement and new position, persistent loop are then determined as walking states, obtain step number according to cycle-index；
For state of couching, acceleration has one rapidly to increase, and reduces up to being 0, next continues slightly to hesitate at 0 value
It wanders, is determined as state of couching；
It aggravating activities, the algorithm default such as jumps for running and is determined with preset high threshold；
For the state of ruminating, acceleration is exported always with very stable small ripple, is ruminated when accelerating degree series to show
When ripple magnitude consistency, that is, regard as the activity of ruminating；
It is above to calculate structured data of the output based on time shaft, it is packaged the data after model conversion mould and is tcp message and leads to
It crosses 4G or WIFI is wirelessly transmitted to Cloud Server.
Above-mentioned cow digitalization Activity recognition device, it is preferable that as shown in figure 4, Cloud Server 3 includes data management system
System, intelligent oestrous detection module and cattle farm information management system.
Data management system is used for the ear tag data uploaded by data reception module real-time reception reader 2, and passes through
Decoding data packet is written data base management system according to ear tag ID and corresponds in table, which can use TCP transmission
Agreement listens to designated port by Windows Sockets realization.
Intelligent oestrous detection system is used to obtain the feature vector of certain milk cow by data management system, in conjunction with intelligent heat
Detection model analyzes the feature vector of certain milk cow, using model prediction result as judgement result, if it is decided that the milk cow is in hair
Situation state calculates the best time of insemination of the milk cow, is sent to cattle farm information management system by way of mail and wechat notice
System sends heat warning message to the related management personnel of cattle farm.
The dimension of feature vector be chosen for by walk per hour in continuous 6 hours step number s1, s2, s3, s4, s5, s6, this
Accumulation lying period t1, accumulation in 6 hours ruminate time t2 and accumulation stand up time t3, feature vector symbolization x table
Show.
Wherein, the establishment process of intelligent oestrous detection model are as follows:
S1: randomly selecting m timing node, chooses n cow head according to the working experience of animal doctor every time, guarantees this n ox
In some be in heat state, animal doctor detected by rectum determine milk cow whether heat.It is obtained from data management system
Selected timing node and the one-to-one p=m*n feature vector of milk cow, using the standardized method of min-max to each spy
Vector normalized, the feature vector combination rectum testing result that will have been handled are levied, composition has exemplar collection Dl={ (x1,
y1),(x2,y2),…,(xp,yp), wherein xiIt is the feature vector of milk cow, yiIndicate rectum testing result, yi∈{0,1},yi=
0 indicates that rectum testing result is non-heat, yi=1 indicates that rectum testing result is heat.Q spy is randomly choosed from database
Vector is levied, removes from this q feature vector and uses min-max standard with sample duplicate in Dl, remaining u feature vector
The method of change forms unlabeled exemplars collection Du={ x to each feature vector normalized, by the feature vector handledp+1,
xp+2,…,xp+u, u is much larger than p.
S2: it uses S3VM (Semi-supervised Support Vector Machines, semisupervised support vector machines)
Algorithm carries out classification based training to the sample set Dl and Du that S1 is obtained, and determines heat identification model.
S3: milk cow feature vector is acquired in real time as input, is predicted with the model that S2 is obtained, prediction knot is obtained
Fruit.
Cattle farm information management system includes milk cow information management module, milk cow monitoring module, OA system module and report mould
Block.
Milk cow information management module is used to store the relevant information of milk cow, archive information, history heat number including milk cow
According to the activity data and temperature data with every day.
The monitoring result that milk cow monitoring module is used to obtain intelligent oestrous detection system monitors the information of every a head of cattle in real time
And state, find milk cow in time ruminates situations such as time is very little or operation is insufficient and estrus behavior.
OA system makes cattle farm office more convenient, improves the collaboration efficiency in the links of cattle farm operation process.
Reporting modules are for periodically giving a report and simple statistical query and analysis to the traffic-operating period of cattle farm.
Above-mentioned cow digitalization Activity recognition device, it is preferable that be also provided with mobile terminal 4 and select wechat little Cheng
The mode of sequence is developed, and can complete milk cow data input and inquiry in mobile terminal 4, check the notification message of abnormal milk cow and and
When make feedback.
Finally it should be noted that: the above examples are only used to illustrate the technical scheme of the present invention rather than to its protection scope
Limitation, although the application is described in detail referring to above-described embodiment, those of ordinary skill in the art should
Understand: those skilled in the art read the specific embodiment of application can still be carried out after the application various changes, modification or
Person's equivalent replacement, but these changes, modification or equivalent replacement, are applying within pending claims.
Claims (9)
1. a kind of cow digitalization Activity recognition device, which is characterized in that the identification device includes:
Ear tag acquires the behavior state data of milk cow for being bundled in milk ivory-white chirita herb in real time；
Reader for obtaining the milk cow behavior state data of the ear tag acquisition by radio frequency method, and carries out model conversation；
Cloud Server, for wirelessly obtaining the data after the reader model conversation, and to milk cow current behavior
Whether heat carries out intelligent decision.
2. cow digitalization Activity recognition device according to claim 1, which is characterized in that the behavior state data of milk cow
Including feeding, rest, activity, ruminate and body temperature feature.
3. cow digitalization Activity recognition device according to claim 1, which is characterized in that the ear tag includes shell,
The hull outside is provided with onboard antenna, and master controller is provided in the shell, radio-frequency module, sensor controller, is added
Velocity sensor and temperature sensor, the radio-frequency module pin connect the onboard antenna；The acceleration transducer is used for
The action data of acquisition milk cow in real time, the temperature sensor are passed for acquiring the shell temperature of milk cow, the acceleration in real time
Sensor and temperature sensor are all connected with the sensor controller, and the sensor controller is by received action data and temperature
Data calculate through filtering, analog-to-digital conversion and compensation for calibrating errors and generate master controller described in normalization data and periodic wakeup；Institute
After stating master controller wake-up, reads the normalization data merging ear tag ID data and be packaged through the radio-frequency module and onboard day
Line is sent to the reader.
4. cow digitalization Activity recognition device according to claim 1, which is characterized in that the reader includes shell
Body, the case top are provided with antenna, and controller, radio-frequency module and 4G/WIFI transparent transmission module, institute are provided in the shell
It states and the 4G/WIFI transparent transmission module is sent to by serial ports after controller converts the behavior state data model of milk cow.
5. cow digitalization Activity recognition device according to any one of claims 1 to 4, which is characterized in that model conversion
Detailed process are as follows: the milk cow acceleration information sequence that will acquire tests obtained milk cow in conjunction with history as input parameter
The corresponding acceleration rate threshold of various attitudes vibrations, judges milk cow active state:
For walking states, acceleration, which first increases, to be reduced afterwards until speed reaches maximum value, is then accelerated in the opposite manner, directly
0 is arrived again to it, and reaches stable displacement and new position, and persistent loop is then determined as walking states, according to circulation time
Number obtains step number；
For state of couching, acceleration generation rapidly increases, and reduces up to being 0, next continues slightly to hover at 0 value, then
It is determined as state of couching；
For aggravating activities, default is determined with a preset high threshold；
For the state of ruminating, acceleration is exported always with very stable small ripple, ruminates ripple when accelerating degree series to show
When amplitude coincidence, that is, regard as the activity of ruminating；
Wherein, the data output of above-mentioned all milk cow states is the structured data based on time shaft.
6. cow digitalization Activity recognition device according to any one of claims 1 to 4, which is characterized in that the cloud clothes
Business device includes data management system and intelligent oestrous detection module；
The data management system is used for the data being packaged by reader described in data reception module real-time reception, and solves yardage
According to packet, correspondence database is written according to ear tag ID, wherein the data reception module uses TCP transmission agreement, real by programming
Now designated port is listened to；
The intelligence oestrous detection system is used to obtain the feature vector of certain milk cow by the data management system, in conjunction with intelligence
The feature vector of oestrous detection model analysis milk cow, using model prediction result as judgement result, if it is decided that at the milk cow
In heat state, the best time of insemination of the milk cow is calculated, and sends cow oestrus warning message.
7. cow digitalization Activity recognition device according to claim 6, which is characterized in that the intelligence oestrous detection mould
The establishment process of type are as follows:
Step S1: randomly selecting m timing node, chooses n cow head every time by animal doctor, some in n oxen is in hair
Situation state, animal doctor detected by rectum determine milk cow whether heat, selected timing node and milk are obtained from data management system
The one-to-one p=m*n feature vector of ox, using the standardized method of min-max to each feature vector normalized,
The feature vector combination rectum testing result that will have been handled, composition have exemplar collection Dl={ (x1,y1),(x2,y2),…,(xp,
yp)},xiIt is the feature vector of milk cow, yiIndicate rectum testing result；Q feature vector is randomly choosed from database, from this q
Remove in a feature vector and sample duplicate in Dl, remaining u feature vector, using the standardized method of min-max to every
The feature vector handled is formed unlabeled exemplars collection Du={ x by a feature vector normalizedp+1,xp+2,…,xp+u}；
Step S2: classification based training is carried out to the sample set Dl and Du that step S1 is obtained using S3VM algorithm, determines that heat identifies mould
Type；
Step S3: acquisition milk cow feature vector as input, predicted, is obtained by the heat identification model obtained with step S2 in real time
To the prediction result of cow oestrus.
8. cow digitalization Activity recognition device according to claim 6, which is characterized in that the Cloud Server further includes
Cattle farm information management system, the cattle farm information management system include milk cow information management module, milk cow monitoring module, OA system
Module and reporting modules；
The milk cow information management module is used to store the relevant information of milk cow, archive information, history heat number including milk cow
According to the activity data and temperature data with every day；
The monitoring result that the milk cow monitoring module is used to obtain intelligent oestrous detection system monitors the letter of each cow head in real time
Breath and state, find milk cow in time ruminates situations such as time is very little or operation is insufficient and estrus behavior；
The OA system is for carrying out cattle farm office；
The reporting modules are for periodically concluding the traffic-operating period of cattle farm.
9. cow digitalization Activity recognition device according to any one of claims 1 to 4, which is characterized in that identification dress
Set and be additionally provided with mobile terminal, the Cloud Server by judging result by App or by wechat in a manner of heat alarm prompt is sent out
It is sent to mobile terminal notice Management in dairy farm personnel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910289459.0A CN110059781A (en) | 2019-04-11 | 2019-04-11 | Cow digitalization Activity recognition device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910289459.0A CN110059781A (en) | 2019-04-11 | 2019-04-11 | Cow digitalization Activity recognition device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110059781A true CN110059781A (en) | 2019-07-26 |
Family
ID=67318717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910289459.0A Pending CN110059781A (en) | 2019-04-11 | 2019-04-11 | Cow digitalization Activity recognition device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110059781A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110728268A (en) * | 2019-11-29 | 2020-01-24 | 东北农业大学 | Milk cow rumination identification method based on decision tree classifier and bridle pressure envelope signal |
| CN112348135A (en) * | 2020-11-26 | 2021-02-09 | 中国科学院空天信息创新研究院 | Individual behavior data identification method based on wireless sensor network |
| CN112535113A (en) * | 2020-11-18 | 2021-03-23 | 中国农业科学院北京畜牧兽医研究所 | Intelligent ear tag and intelligent ear tag system |
| US10986816B2 (en) | 2014-03-26 | 2021-04-27 | Scr Engineers Ltd. | Livestock location system |
| US10986817B2 (en) | 2014-09-05 | 2021-04-27 | Intervet Inc. | Method and system for tracking health in animal populations |
| CN112986504A (en) * | 2019-12-12 | 2021-06-18 | 阿里巴巴集团控股有限公司 | Method, equipment and storage medium for determining honey maturity and target object attribute |
| CN112970620A (en) * | 2019-12-17 | 2021-06-18 | 中移(成都)信息通信科技有限公司 | Estrus detection method, apparatus, system, device and medium |
| US11071279B2 (en) | 2014-09-05 | 2021-07-27 | Intervet Inc. | Method and system for tracking health in animal populations |
| CN113407118A (en) * | 2021-06-24 | 2021-09-17 | 九江职业技术学院 | Data storage device |
| CN113705528A (en) * | 2021-09-08 | 2021-11-26 | 内蒙古工业大学 | Time prediction method and device, storage medium and electronic equipment |
| CN114330390A (en) * | 2021-12-06 | 2022-04-12 | 东北农业大学 | Milk cow activity monitoring technology based on RFID passive sensing technology |
| CN114586701A (en) * | 2022-04-15 | 2022-06-07 | 东南大学 | Milk cow oestrus prediction device based on body temperature and exercise amount data |
| USD990062S1 (en) | 2020-06-18 | 2023-06-20 | S.C.R. (Engineers) Limited | Animal ear tag |
| USD990063S1 (en) | 2020-06-18 | 2023-06-20 | S.C.R. (Engineers) Limited | Animal ear tag |
| CN117094836A (en) * | 2023-10-17 | 2023-11-21 | 北京九牧星科技有限公司 | Intelligent assessment system and method for dairy cow state |
| US11832587B2 (en) | 2020-06-18 | 2023-12-05 | S.C.R. (Engineers) Limited | Animal tag |
| US11832584B2 (en) | 2018-04-22 | 2023-12-05 | Vence, Corp. | Livestock management system and method |
| US11864529B2 (en) | 2018-10-10 | 2024-01-09 | S.C.R. (Engineers) Limited | Livestock dry off method and device |
| CN117828480A (en) * | 2024-03-04 | 2024-04-05 | 中国农业科学院农业信息研究所 | Beef cattle estrus state identification and assessment method based on deep learning |
| US11960957B2 (en) | 2020-11-25 | 2024-04-16 | Identigen Limited | System and method for tracing members of an animal population |
| US12099893B2 (en) | 2020-07-01 | 2024-09-24 | S.C.R. (Engineers) Limited | Device assignment system and method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103150578A (en) * | 2013-04-09 | 2013-06-12 | 山东师范大学 | Training method of SVM (Support Vector Machine) classifier based on semi-supervised learning |
-
2019
- 2019-04-11 CN CN201910289459.0A patent/CN110059781A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103150578A (en) * | 2013-04-09 | 2013-06-12 | 山东师范大学 | Training method of SVM (Support Vector Machine) classifier based on semi-supervised learning |
Non-Patent Citations (3)
| Title |
|---|
| 刘忠超等: "基于物联网和云端的奶牛发情体征监测系统设计", 《江苏农业科学》 * |
| 王俊等: "基于半监督模糊聚类算法的奶牛行为判别系统", 《中国畜牧兽医》 * |
| 谭益等: "基于Storm的奶牛发情实时监测系统设计与实现", 《中国优秀硕士学位论文全文数据库 (农业科技辑)》 * |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11963515B2 (en) | 2014-03-26 | 2024-04-23 | S.C.R. (Engineers) Limited | Livestock location system |
| US10986816B2 (en) | 2014-03-26 | 2021-04-27 | Scr Engineers Ltd. | Livestock location system |
| US10986817B2 (en) | 2014-09-05 | 2021-04-27 | Intervet Inc. | Method and system for tracking health in animal populations |
| US11071279B2 (en) | 2014-09-05 | 2021-07-27 | Intervet Inc. | Method and system for tracking health in animal populations |
| US11832584B2 (en) | 2018-04-22 | 2023-12-05 | Vence, Corp. | Livestock management system and method |
| US11864529B2 (en) | 2018-10-10 | 2024-01-09 | S.C.R. (Engineers) Limited | Livestock dry off method and device |
| CN110728268A (en) * | 2019-11-29 | 2020-01-24 | 东北农业大学 | Milk cow rumination identification method based on decision tree classifier and bridle pressure envelope signal |
| CN112986504A (en) * | 2019-12-12 | 2021-06-18 | 阿里巴巴集团控股有限公司 | Method, equipment and storage medium for determining honey maturity and target object attribute |
| CN112986504B (en) * | 2019-12-12 | 2023-11-07 | 阿里巴巴集团控股有限公司 | Method, equipment and storage medium for determining honey maturity and target object attribute |
| CN112970620B (en) * | 2019-12-17 | 2023-07-21 | 中移(成都)信息通信科技有限公司 | Method, apparatus, system, device and medium for detecting estrus status |
| CN112970620A (en) * | 2019-12-17 | 2021-06-18 | 中移(成都)信息通信科技有限公司 | Estrus detection method, apparatus, system, device and medium |
| US11832587B2 (en) | 2020-06-18 | 2023-12-05 | S.C.R. (Engineers) Limited | Animal tag |
| USD990062S1 (en) | 2020-06-18 | 2023-06-20 | S.C.R. (Engineers) Limited | Animal ear tag |
| USD990063S1 (en) | 2020-06-18 | 2023-06-20 | S.C.R. (Engineers) Limited | Animal ear tag |
| US12099893B2 (en) | 2020-07-01 | 2024-09-24 | S.C.R. (Engineers) Limited | Device assignment system and method |
| CN112535113B (en) * | 2020-11-18 | 2021-12-14 | 中国农业科学院北京畜牧兽医研究所 | Intelligent ear tag and intelligent ear tag system |
| CN112535113A (en) * | 2020-11-18 | 2021-03-23 | 中国农业科学院北京畜牧兽医研究所 | Intelligent ear tag and intelligent ear tag system |
| US11960957B2 (en) | 2020-11-25 | 2024-04-16 | Identigen Limited | System and method for tracing members of an animal population |
| CN112348135B (en) * | 2020-11-26 | 2021-08-10 | 中国科学院空天信息创新研究院 | Individual behavior data identification method based on wireless sensor network |
| CN112348135A (en) * | 2020-11-26 | 2021-02-09 | 中国科学院空天信息创新研究院 | Individual behavior data identification method based on wireless sensor network |
| CN113407118A (en) * | 2021-06-24 | 2021-09-17 | 九江职业技术学院 | Data storage device |
| CN113407118B (en) * | 2021-06-24 | 2022-11-01 | 九江职业技术学院 | Data storage device |
| CN113705528A (en) * | 2021-09-08 | 2021-11-26 | 内蒙古工业大学 | Time prediction method and device, storage medium and electronic equipment |
| CN114330390A (en) * | 2021-12-06 | 2022-04-12 | 东北农业大学 | Milk cow activity monitoring technology based on RFID passive sensing technology |
| CN114586701A (en) * | 2022-04-15 | 2022-06-07 | 东南大学 | Milk cow oestrus prediction device based on body temperature and exercise amount data |
| CN117094836A (en) * | 2023-10-17 | 2023-11-21 | 北京九牧星科技有限公司 | Intelligent assessment system and method for dairy cow state |
| CN117094836B (en) * | 2023-10-17 | 2024-02-13 | 北京九牧星科技有限公司 | Intelligent assessment system and method for dairy cow state |
| CN117828480A (en) * | 2024-03-04 | 2024-04-05 | 中国农业科学院农业信息研究所 | Beef cattle estrus state identification and assessment method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110059781A (en) | Cow digitalization Activity recognition device | |
| Tran et al. | An iot-based design using accelerometers in animal behavior recognition systems | |
| CN208273869U (en) | Electron ear tage and ear tag monitor system | |
| CN207201700U (en) | The wearable device of milk cow | |
| CN109145032A (en) | A kind of bee raising intelligent monitoring method and system | |
| CN102333117B (en) | Poultry breeding and selecting system based on the Internet of things (IOT) | |
| KR102117092B1 (en) | System for detecting cow estrus using recognition of behavior pattern | |
| CN105091938B (en) | Livestock birds health condition monitoring method and system | |
| CN105997015A (en) | Wearable device for animal vital sign multi-parameter monitoring | |
| CN107094653A (en) | A kind of animal free-ranging monitoring system | |
| CN107157458A (en) | The sensor-based system and method for a kind of animal individual feed intake and health monitoring | |
| CN107318694A (en) | The wearable device and its management system for breeding and method of milk cow | |
| Pratama et al. | Designing of a smart collar for dairy cow behavior monitoring with application monitoring in microservices and internet of things-based systems | |
| CN110506656A (en) | A kind of multi-functional herding intelligence ear tag and its collecting method of low-power consumption | |
| CN108207700B (en) | Cow information monitoring method and system | |
| CN206696643U (en) | A kind of automatic breeding monitoring system based on Internet of Things | |
| CN107550479A (en) | A kind of herding maintenance device | |
| CN210746677U (en) | Health monitoring system for livestock animals | |
| CN109691397A (en) | A kind of animal electronic necklace information management system | |
| Suresh et al. | An IoT solution for cattle health monitoring | |
| CN204811463U (en) | Live pig heart rate monitor system and live pig living or death state monitoring system | |
| Jemila et al. | A sensor-based forage monitoring of grazing cattle in dairy farming | |
| CN106614071A (en) | System and method for monitoring pre-natal behaviors of sow | |
| Nootyaskool et al. | Smart collar design to predict cow behavior | |
| CN103315729A (en) | Remote livestock heartbeat monitoring system based on internet of things |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190726 |
|
| WD01 | Invention patent application deemed withdrawn after publication |