CN114209310A - Animal health state tracking method - Google Patents
Animal health state tracking method Download PDFInfo
- Publication number
- CN114209310A CN114209310A CN202111542951.8A CN202111542951A CN114209310A CN 114209310 A CN114209310 A CN 114209310A CN 202111542951 A CN202111542951 A CN 202111542951A CN 114209310 A CN114209310 A CN 114209310A
- Authority
- CN
- China
- Prior art keywords
- health
- value
- animal
- statistical period
- data
- 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
- 241001465754 Metazoa Species 0.000 title claims abstract description 101
- 230000036541 health Effects 0.000 title claims abstract description 89
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000013210 evaluation model Methods 0.000 claims abstract description 36
- 238000007619 statistical method Methods 0.000 claims abstract description 17
- 230000003862 health status Effects 0.000 claims abstract description 16
- 230000007246 mechanism Effects 0.000 claims abstract description 5
- 230000001133 acceleration Effects 0.000 claims description 24
- 230000012173 estrus Effects 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 12
- 102100037651 AP-2 complex subunit sigma Human genes 0.000 description 6
- 101000806914 Homo sapiens AP-2 complex subunit sigma Proteins 0.000 description 6
- 230000008569 process Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000009395 breeding Methods 0.000 description 2
- 230000001488 breeding effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000003975 animal breeding Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/01—Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/40—Animals
Abstract
The invention discloses a method for tracking the health status of an animal, which can continuously acquire one or more items of physiological data of the animal through a wireless sensor worn on the animal body; setting an animal health state evaluation model, wherein the animal health state evaluation model comprises one or more single-value evaluation models, each single-value evaluation model takes one physiological data as input to carry out statistical analysis, and outputs a statistical analysis result; the statistical analysis results of the single-value evaluation models are integrated to automatically judge whether the animal is normal or not; and establishing a regression mechanism, and automatically updating the parameters of each single-value evaluation model according to the statistical analysis result. The invention constructs an algorithm framework combining multiple models with judgment, and can conveniently add or delete the models according to the types and characteristics of the collected data so as to avoid huge workload and risk caused by reconstructing codes and rewriting the architecture.
Description
Technical Field
The invention relates to the field of data processing, in particular to an animal health state tracking method.
Background
The prior animal breeding needs the traceable breeding management in the whole life cycle, but generally adopts the house and the group as the unit to carry out unified management by deploying cameras, temperature sensors and the like. While monitoring the setting of the parameters.
In order to realize traceable management of the single animals, single data acquisition can be carried out by arranging foot rings, ear rings and other modes at present, and the foot rings and the ear rings are provided with sensors such as motion sensors and temperature sensors and can monitor the temperature, the activity state and other information of the single animals.
Disclosure of Invention
In view of the above-mentioned defects of the prior art, the present invention aims to provide a method for tracking the health status of an animal based on a wireless sensor, which can realize the traceable management of a single animal in the whole life cycle.
In order to achieve the purpose, the invention provides the following technical scheme:
a method of animal health status tracking, comprising:
periodically acquiring a data sequence of one or more items of physiological data of the animal through a wireless sensor arranged on the animal body; setting an animal health state evaluation model, wherein the animal health state evaluation model comprises one or more single-value evaluation models, each single-value evaluation model takes one physiological data as input to carry out statistical analysis, and outputs a statistical analysis result; the statistical analysis results of the single-value evaluation models are integrated to automatically judge whether the animal is normal or not; and establishing a regression mechanism, and automatically updating the parameters of each single-value evaluation model according to the statistical analysis result.
Further, the single-value evaluation model takes a data sequence of single physiological data as input, and executes:
periodically intercepting physiological data from the data sequence according to a set first statistical period, calculating the average value and standard deviation of the physiological data in the first statistical period, and giving a first classification result according to the average value and/or standard deviation;
according to a set second statistical period, counting first classification results in the second statistical period, and giving time distribution of the first classification results in the second statistical period;
carrying out weighted summation on the time distribution of each first classification result in the second statistical period to obtain a first health value of the animal;
comparing the current first health value with the previous first health value or the previous N first health values, and giving the current health state of the animal according to the difference obtained by comparison;
and updating the classification threshold value of the first classification in the first statistical period according to the average value of the first M health values, and updating the weighted value in the second statistical period.
Further, the wireless sensor comprises a motion monitoring function, the physiological data is acceleration data, and the first classification result comprises an animal motion state, an animal feeding state and an animal sleeping state.
Further, in the first statistical period, the first classification result is obtained by an average value and/or a standard deviation of the acceleration.
Further, the interval between the current first health value and the previous first health value is a second statistical period or a third statistical period, where the third statistical period includes a plurality of second statistical periods.
Further, the value range of the second statistical period is 1 minute to 4 hours; the value of the third statistical period is one day.
Further, the wireless sensor comprises a temperature monitoring function, the physiological data is temperature data, and the first classification result is divided into a plurality of temperature sections according to a temperature threshold value.
Further, the animal health state evaluation model takes the output of a plurality of single-value evaluation models as input, and executes: carrying out weighted summation on first health values given by various physiological data in the same time period in a second statistical period to obtain second health values; comparing the current second health value with the previous second health value or the previous N second health values, and giving the current health state of the animal according to the difference obtained by comparison; and updating the weighted value of each physiological data in the comprehensive evaluation according to the mean value of the first M second health values.
Further, the animal health state evaluation model is used for evaluating the movement condition of the animal, and comprises the following steps:
first single-valued evaluation model: the method comprises the steps that acceleration data are adopted, and in a first statistic period, a first classification result is given according to the average value and/or standard deviation of acceleration; in a second statistical period, carrying out weighted summation on the first classification result, wherein the weighted value is the time ratio of each data interval, and obtaining a first health value; and comparing the current first health value with the average value of the previous N first health values, and outputting a comparison result, wherein the current first health value and the previous first health value are spaced by a second statistical period.
Further, the animal health status evaluation model is used for evaluating the oestrus probability or the morbidity probability of the animal, and comprises the following steps:
first single-valued evaluation model: the method comprises the steps that acceleration data are adopted, and in a first statistic period, a first classification result is given according to the average value and/or standard deviation of acceleration; in a second statistical period, carrying out weighted summation on the first classification result, wherein the weighted value is the time ratio of each data interval, and obtaining a first health value; comparing the current first health value with an average value of the previous N first health values, wherein the current first health value and the previous first health value are spaced by a second statistical period;
second single-valued evaluation model: the method comprises the steps that acceleration data are adopted, and in a first statistic period, a first classification result is given according to the average value and/or standard deviation of acceleration; in a second statistical period, carrying out weighted summation on the first classification result to obtain a first health value; comparing the current first health value with an average value of the previous N first health values, wherein the current first health value and the previous first health value are spaced by a third statistical period;
third single-valued evaluation model: a first classification result is given according to the average value of the temperature in a first statistic period by adopting temperature data; in a second statistical period, carrying out weighted summation according to the time distribution of the first classification result in the second statistical period, wherein the time ratio of each temperature interval is the weighted value of each temperature interval; comparing the current first health value with an average of the previous N first health values, wherein the current first health value and the previous first health value are spaced apart by a third statistical period.
The invention realizes the following technical effects:
the animal health state tracking method can continuously acquire one or more items of physiological data of the animal through the wireless sensor worn on the animal, thereby carrying out statistical analysis on the data and automatically judging whether the animal is normal or not from the statistical data. In the statistical process, a regression mechanism is also set, the learning function is realized, and parameters such as a classification threshold value and the like can be automatically updated according to the statistical analysis result.
The animal health tracking method constructs an algorithm framework combining multiple models with judgment, and the models can be conveniently added or deleted according to the types and characteristics of the acquired data so as to avoid huge workload and risk caused by reconstructing codes and rewriting the framework.
Drawings
FIG. 1 is an algorithmic model for animal health tracking using single physiological data-motion acceleration data;
fig. 2 is an algorithmic model for animal estrus tracking using multiple physiological data.
Detailed Description
To further illustrate the various embodiments, the invention provides the accompanying drawings. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the embodiments. Those skilled in the art will appreciate still other possible embodiments and advantages of the present invention with reference to these figures. Elements in the figures are not drawn to scale and like reference numerals are generally used to indicate like elements.
The invention will now be further described with reference to the accompanying drawings and detailed description.
As shown in figure 1 of the drawings, in which,
in order to track the health status of an animal, a wireless sensor is worn on the animal, and one or more physiological data of the animal are collected, wherein the currently conveniently collected data comprise motion data, temperature data and the like, wherein the motion data are obtained through the motion sensor in the wireless sensor. The animal health state tracking system periodically reads physiological data acquired by the wireless sensor and stores the physiological data; when data is collected for a certain length of time, statistical analysis can be performed on the data.
In this embodiment, the wireless sensor may be an RFID tag, such as an ear tag, disposed on the animal. The RFID tag can get electricity from read and write electromagnetic waves during reading and writing so as to execute physiological data acquisition functions such as motion monitoring, temperature acquisition and the like. The temperature monitoring and the motion monitoring can be performed on one wireless sensor or different wireless sensors.
In this embodiment, the motion sensor is an acceleration sensor, and acquires the acceleration of 3 axes of the animal motion. Each data contains (t, x, y, z, r), where t is the sample time, x/y/z represents the x/y/z axis acceleration value at time t, r is equal to sqrt (x ^2+ y ^2+ z ^2), representing the magnitude of the 3 axis acceleration. These raw data are not processed in the algorithm, but rather processed, the mean and standard deviation of r are calculated over a period of time dt, and the data are uploaded to the server. Denoted by R and sigma, respectively, and dt, R and sigma are the inputs to the algorithm, as shown in fig. 1.
In this embodiment, the temperature sensor collects the temperature of the surface of the animal body, for example, the temperature sensor is fixed on the ear of the animal in the manner of an earring, so as to collect the temperature of the ear of the animal.
Now, taking a motion sensor and a temperature sensor as examples, the following health tracking method is given.
Example 1 animal health tracking using single motion acceleration data:
given the threshold values sigma1 and sigma2 of the acceleration standard deviation sigma, statistics are carried out every 15 minutes, wherein the sigma < the proportion p1 of sigma1, the sigma1< the proportion p2 of sigma < sigma2, and the proportion p3 of sigma > sigma 2. Defining p1 as the time probability of an animal resting, p2 as the time probability of an animal eating, and p3 as the time probability of an animal moving.
Assuming sigma1 is 50 and sigma2 is 250.
Measurement data was acquired as shown in table 1 (the head and tail portions of the 15 minute test data are given in table 1), at 2021/9/230: 15-2021/9/230: there were 103 data in 30 sessions, with <50 total 99, 50-250 total 3, >250 total 1, p 1-99/103-0.96, p 2-3/103-0.03, and p 3-1/103-0.01.
TABLE 1
According to the acceleration value r of the animal movement and/or the standard deviation sigma thereof, the animal state can be divided into an animal rest state, an animal feeding state and an animal movement state; and obtaining the probability of the rest time of the animal, the probability of the eating time of the animal and the probability of the movement time of the animal according to the ratio of the state time of the animal in the time period.
The data for the whole day are accumulated to obtain the rest time T1, eating time T2 and exercise time T3 of the animal all day. Since the daily life of the animal is regular, when T1, T2, and T3 significantly deviate from the values of the previous day (or the average value of the previous 7 days), it can be judged that the animal is abnormal. The deviation value may be calculated by (Tx _ current-Tx _ mean7)/Tx _ mean7 as follows, and is abnormal if the change > some threshold, such as 25%. X may be 1, 2, 3, Tx _ current represents the current day's T1, T2, T3, Tx _ mean7 represents the previous 7 days' T1 average, T2 average, T3 average.
Note that although T is made 15min here, as long as the time period T is not too short, 1min to 240min may be arbitrarily selected. The threshold is different for different T. If T is 120min, sigma1 is about 30-100, and sigma2 is about 250-300.
The animal health state tracking method can continuously acquire one or more items of physiological data of the animal through the wireless sensor worn on the animal, thereby carrying out statistical analysis on the data and automatically judging whether the animal is normal or not from the statistical data. In the statistical process, a regression mechanism is also set, the learning function is realized, and parameters such as a classification threshold value and the like can be automatically updated according to the statistical analysis result.
The animal health tracking method analyzes the state distribution of the animal through a large amount of data without concerning the specific action of the animal.
Example 2 animal estrus and/or morbidity tracking using multiple physiological data:
after an animal is in heat or has an illness, the characteristics of the animal, such as the motion state, the body surface temperature and the like, are obviously different from the original characteristics of the motion state and the body surface temperature, therefore, the algorithm in the embodiment judges whether the animal is in heat or has an illness by comprehensively considering a plurality of models so as to obtain a more accurate judgment result, and the breeding or epidemic prevention of the animal is conveniently managed in a targeted manner.
Considering the data of each model over a period of time, giving the current estrus/morbidity probability pi, the total estrus/morbidity probability is p ═ wi × pi, where wi is the weight of the model, where i is summed up using einstein summation notation. This algorithm does not require the sum of wi to be 1.
As shown in fig. 2, taking estrus as an example, in this embodiment, specifically, 3 models are used for determination, and the time period is defined as one determination every 2 hours. But more models can be added and different time intervals can be used.
Model one: similar to the algorithm in example 1, the ratio p3, f (p3) of sigma > sigma2 in 2 hours is counted as pi of the model. The function f is defined later.
Model two: a day is divided into 12 segments, 0 point-2 point, 2 point-4 point, … … and so on. The average value of R over this time period was calculated and recorded for 7 (or 14) days. The following data were obtained:
the bottom column of "average" is the average over the first 7 days. Thereafter, as time goes on, the average column always calculates the average value of the corresponding time period of the previous 7 days, namely 7-day moving average.
The average over the current2 hour period was compared to the average of 7 values over the same period over the last 7 days and the change p ═ Mean _ current2-Mean _ Mean7)/Mean _ Mean7 was calculated. Where Mean _ current2 is the average over the current two hours and Mean _ Mean7 is the corresponding value in the last line of the table above. Then f (p) is pi for this model. The function f is defined later.
And (3) model III: similar to model two, but the data is no longer motion data, but temperature data.
The function f in the above model is a normalized function, and a suitable choice is the sigmoid function, i.e. f (x) 1/(1+ e ^ (-x)). But other functions such as tanh (x) (e x-e x (x))/(e x + e x (x)) and even different models using different normalization functions may be used.
After obtaining pi for all models, p wi pi can be used to obtain the total oestrus probability p. One suitable choice of wi is [0.3,0.4,0.3], but different weights may be used. When the oestrus probability is greater than a certain threshold, for example 80%, the animal may oestrus, and when 2 consecutive (i.e. 4 hours) p segments are both greater than the threshold (80%), a prompt is made and the person is dispatched to look at it.
More models may be added, such as considering sigma for r in model two, or r for sigma in model one. At the moment, the results of all models can be comprehensively considered only by increasing and modifying the value of wi, and more accurate judgment is given.
In embodiment 2, the invention constructs an algorithm framework, which includes a plurality of parallel algorithm models, obtains classification results by weighted summation at the output of each algorithm, and can perform iterative optimization according to historical data. By the algorithm framework, better results can be obtained by continuously evolving the increasing and decreasing algorithm models on the basis of not changing the advantages of the previous models. To avoid the huge workload and the huge risk caused by reconstructing the code and rewriting the architecture.
The incidence conditions are similar, a model which is the same as or similar to the oestrus can be adopted, and the final model weight wi and/or the judgment threshold value are only required to be modified, so that the processing and judgment can be synchronously carried out in the process of calculating the oestrus.
While the invention has been particularly shown and described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A method for animal health status tracking, comprising:
periodically acquiring a data sequence of one or more items of physiological data of the animal through a wireless sensor arranged on the animal body;
setting an animal health state evaluation model, wherein the animal health state evaluation model comprises one or more single-value evaluation models, each single-value evaluation model takes one physiological data as input to carry out statistical analysis, and outputs a statistical analysis result; the statistical analysis results of the single-value evaluation models are integrated to automatically judge whether the animal is normal or not;
and establishing a regression mechanism, and automatically updating the parameters of each single-value evaluation model according to the statistical analysis result.
2. The animal health status tracking method of claim 1, wherein the single value evaluation model takes as input a data sequence of single physiological data, performing:
periodically intercepting physiological data from the data sequence according to a set first statistical period, calculating the average value and standard deviation of the physiological data in the first statistical period, and giving a first classification result according to the average value and/or standard deviation;
according to a set second statistical period, counting first classification results in the second statistical period, and giving time distribution of the first classification results in the second statistical period;
carrying out weighted summation on the time distribution of each first classification result in the second statistical period to obtain a first health value of the animal;
comparing the current first health value with the previous first health value or the previous N first health values, and normalizing the difference value obtained by comparison to give the current health state of the animal;
and updating the classification threshold value of the first classification in the first statistical period according to the average value of the first M health values, and updating the weighted value in the second statistical period.
3. The animal health tracking method of claim 2, wherein the wireless sensor includes a motion monitoring function, the physiological data is acceleration data, and the first classification result includes an animal motion state, an animal feeding state, and an animal sleeping state.
4. The animal health status tracking method of claim 3, wherein the first classification result is obtained by a mean and/or a standard deviation of acceleration at the first statistical period.
5. The animal health status tracking method of claim 3, wherein the current first health value and the previous first health value are separated by a second statistical period or a third statistical period, the third statistical period comprising a plurality of second statistical periods.
6. The animal health status tracking method of claim 5, wherein the second statistical period ranges from 1 minute to 4 hours; the value of the third statistical period is one day.
7. The animal health tracking method of claim 2, wherein the wireless sensor includes a temperature monitoring function, the physiological data is temperature data, and the first classification result is divided into a plurality of temperature zones according to a temperature threshold.
8. The animal health status tracking method of claim 2, wherein the animal health status evaluation model takes as input the outputs of a plurality of single-valued evaluation models and performs: carrying out weighted summation on first health values given by various physiological data in the same time period in a second statistical period to obtain second health values; comparing the current second health value with the previous second health value or the previous N second health values, and giving the current health state of the animal according to the difference obtained by comparison; and updating the weighted value of each physiological data in the comprehensive evaluation according to the mean value of the first M second health values.
9. The animal health status tracking method of claim 8, wherein the animal health status evaluation model is used to evaluate the movement of the animal, comprising:
first single-valued evaluation model: the method comprises the steps that acceleration data are adopted, and in a first statistic period, a first classification result is given according to the average value and/or standard deviation of acceleration; in a second statistical period, carrying out weighted summation on the first classification result, wherein the weighted value is the time ratio of each data interval, and obtaining a first health value; and comparing the current first health value with the average value of the previous N first health values, and outputting a comparison result, wherein the current first health value and the previous first health value are spaced by a second statistical period.
10. The animal health status tracking method of claim 8, wherein the animal health status evaluation model is used to evaluate the estrus probability or the incidence probability of the animal, and comprises:
first single-valued evaluation model: the method comprises the steps that acceleration data are adopted, and in a first statistic period, a first classification result is given according to the average value and/or standard deviation of acceleration; in a second statistical period, carrying out weighted summation on the first classification result, wherein the weighted value is the time ratio of each data interval, and obtaining a first health value; comparing the current first health value with an average value of the previous N first health values, wherein the current first health value and the previous first health value are spaced by a second statistical period;
second single-valued evaluation model: the method comprises the steps that acceleration data are adopted, and in a first statistic period, a first classification result is given according to the average value and/or standard deviation of acceleration; in a second statistical period, carrying out weighted summation on the first classification result to obtain a first health value; comparing the current first health value with an average value of the previous N first health values, wherein the current first health value and the previous first health value are spaced by a third statistical period;
third single-valued evaluation model: a first classification result is given according to the average value of the temperature in a first statistic period by adopting temperature data; in a second statistical period, carrying out weighted summation according to the time distribution of the first classification result in the second statistical period, wherein the time ratio of each temperature interval is the weighted value of each temperature interval; comparing the current first health value with an average of the previous N first health values, wherein the current first health value and the previous first health value are spaced apart by a third statistical period.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111542951.8A CN114209310A (en) | 2021-12-16 | 2021-12-16 | Animal health state tracking method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111542951.8A CN114209310A (en) | 2021-12-16 | 2021-12-16 | Animal health state tracking method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114209310A true CN114209310A (en) | 2022-03-22 |
Family
ID=80703139
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111542951.8A Pending CN114209310A (en) | 2021-12-16 | 2021-12-16 | Animal health state tracking method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114209310A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116313094A (en) * | 2023-03-21 | 2023-06-23 | 江苏二郎神塑业有限公司 | Remote pet treatment detection system and method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2019122368A (en) * | 2018-01-12 | 2019-07-25 | デザミス株式会社 | Health state management system and management method for cattle and health state management program |
CN110741962A (en) * | 2019-10-15 | 2020-02-04 | 北京九九融科科技有限公司 | Oestrus and health monitoring method based on cow behavior recognition algorithm |
CN111246730A (en) * | 2017-08-23 | 2020-06-05 | 毕尚博特公司 | Method and system for tracking the health of a population of animals |
-
2021
- 2021-12-16 CN CN202111542951.8A patent/CN114209310A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111246730A (en) * | 2017-08-23 | 2020-06-05 | 毕尚博特公司 | Method and system for tracking the health of a population of animals |
JP2019122368A (en) * | 2018-01-12 | 2019-07-25 | デザミス株式会社 | Health state management system and management method for cattle and health state management program |
CN110741962A (en) * | 2019-10-15 | 2020-02-04 | 北京九九融科科技有限公司 | Oestrus and health monitoring method based on cow behavior recognition algorithm |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116313094A (en) * | 2023-03-21 | 2023-06-23 | 江苏二郎神塑业有限公司 | Remote pet treatment detection system and method |
CN116313094B (en) * | 2023-03-21 | 2023-11-07 | 江苏二郎神塑业有限公司 | Remote pet treatment detection system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11163853B2 (en) | Sensor design support apparatus, sensor design support method and non-transitory computer readable medium | |
EP3482630A1 (en) | Method, system and computer program for performing a pest forecast | |
Calviño-Cancela et al. | Effectiveness of a varied assemblage of seed dispersers of a fleshy‐fruited plant | |
CN105091938A (en) | Poultry health monitoring method and system | |
BE1026887B1 (en) | METHOD OF INTELLIGENT MONITORING OF ONE OR MULTIPLE COMMERCIAL SITES FOR CREATIVE ANIMALS | |
Arablouei et al. | Animal behavior classification via deep learning on embedded systems | |
CN114209310A (en) | Animal health state tracking method | |
JPH078128A (en) | Breeding control system for livestock and poultry | |
KR20200117610A (en) | Electronic Sow Management Apparatus | |
CN117114913A (en) | Intelligent agricultural data acquisition system based on big data | |
CN106821349A (en) | For the event generation method and device of wearable custodial care facility | |
CN112883999A (en) | Pedometer system and method for detecting abnormal movement of dairy cow | |
Hemeryck et al. | 5.4. Pig cough monitoring in the EU-PLF project: First results | |
CN116469148A (en) | Probability prediction system and prediction method based on facial structure recognition | |
AURASOPON | Classification of the cattle behaviors by using magnitude and variance of accelerometer signal | |
CN115553742A (en) | Human body microenvironment data acquisition system for building intelligent operation and maintenance and operation and maintenance method | |
US20190327938A1 (en) | A method for customized monitoring of sounds caused by respiratory distress | |
CN115035590A (en) | Method, device and system for detecting cow state | |
Poh et al. | Anomaly detection for home activity based on sequence pattern | |
US20230200697A1 (en) | Automatic evolution method for brainwave database and automatic evolving system for detecting brainwave | |
Thomson et al. | Breeding success and survival in the common swift Apus apus: a long‐term study on the effects of weather | |
Singhal et al. | Cattle Collar: An End-to-End Multi-Model Framework for Cattle Monitoring | |
Birzniece et al. | Time Series Forecast Model Application for Broiler Weight Prediction Using Environmental Factors | |
Tudor-Locke | Protocols for data collection, management and treatment | |
JP7426015B1 (en) | Healthcare data analysis system |
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 |