WO2017131575A1 - Decision support system and method of providing decision support with respect to a herd of animals - Google Patents

Decision support system and method of providing decision support with respect to a herd of animals Download PDF

Info

Publication number
WO2017131575A1
WO2017131575A1 PCT/SE2017/050070 SE2017050070W WO2017131575A1 WO 2017131575 A1 WO2017131575 A1 WO 2017131575A1 SE 2017050070 W SE2017050070 W SE 2017050070W WO 2017131575 A1 WO2017131575 A1 WO 2017131575A1
Authority
WO
WIPO (PCT)
Prior art keywords
animal
animals
unit
herd
data
Prior art date
Application number
PCT/SE2017/050070
Other languages
French (fr)
Inventor
Anders UMEGÅRD
Bohao Liao
Original Assignee
Delaval Holding Ab
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Delaval Holding Ab filed Critical Delaval Holding Ab
Priority to EP17704325.4A priority Critical patent/EP3407706A1/en
Publication of WO2017131575A1 publication Critical patent/WO2017131575A1/en

Links

Classifications

    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01KANIMAL HUSBANDRY; CARE OF BIRDS, FISHES, INSECTS; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
    • A01K29/00Other apparatus for animal husbandry
    • A01K29/005Monitoring or measuring activity, e.g. detecting heat or mating
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61DVETERINARY INSTRUMENTS, IMPLEMENTS, TOOLS, OR METHODS
    • A61D17/00Devices for indicating trouble during labour of animals ; Methods or instruments for detecting pregnancy-related states of animals
    • A61D17/002Devices for indicating trouble during labour of animals ; Methods or instruments for detecting pregnancy-related states of animals for detecting period of heat of animals, i.e. for detecting oestrus

Definitions

  • the present invention relates generally to solutions for impro- ving the milk production efficiency. More particularly the invention relates to a decision support system according to the preamble of claim 1 and a corresponding method. The invention also relates to a system for identifying animals in heat, a computer program and a processor-readable medium. To attain a high overall yield in milk production it is important that each animal is inseminated at a point in time which is most suitable with respect to the animal's lactation cycle. Namely, a cow normally produces the most milk during the second and third months of lactation. Thereafter, the production decreases gradually; and approximately two months prior to calving , the cow is dried off. During the dry period, the cow produces no, or very little milk.
  • any unnecessary prolongation of the lactation is highly undesired.
  • the next lactation period can be initiated as soon as possible.
  • accurate knowledge about the animal's reproduction cycle is required. More preci- sely, at each point in time, the farmer must know whether or not a particular cow is in heat, so that if needed, he/she can effect insemination in due time.
  • the estrous period occurs approximately every 21 days in non-pregnant animals, and the estrous period usually lasts only 12 to 1 8 hours, with a peak estrus being about six hours in duration.
  • successful insemination requires delicate timing .
  • the prior art includes various examples of solutions for determining the behavior of the animals to provide a basis for insemination decisions.
  • WO 2008/1 13556 describes an animal monitoring system with a real time location system for individually identifying and tracking the movements of tagged animals in three dimensions within a monitoring zone. Means are also described for discriminating between different activities of at least one animal based upon the location of the animal's tag within the zone.
  • WO 2009/135493 shows a system for detecting and determining the position of moving objects, where electronic transceiver units communicate with at least two fixed transceiver stations to perform a constant position determination of movable objects within a delimited area.
  • the communication between the fixed transceiver stations and the electronic transceiver units occurs in the form of transient pulses emitted from the electronic transceiver units.
  • the position determination is performed by calculating time or phase difference between receptions of a signal at at least two transceiver facilities, respectively. Indications of animal behavior are based on an acceleration detector carried by the animal and communication performed by a short-range radio system.
  • WO 2014/067897 discloses a solution for real time detection of the position and behavior of a plurality of animals.
  • Radio trans- mitter tags are carried by the animals and sensors receive signals from the tags. Based on time delay of received signals at the sensors from the tags, the positions of the animals are calculated.
  • Fixed reference radio transmitter tags and fixed placed sensors are used for reference.
  • WO 2014/067896 relates to a computer system for measuring real time position of a plurality of animals, which system receives input from a plurality of sensors, communicating with tags carried by the animals. Based on measurement of delay in radio communication, the system calculates the actual position of the animals. Based on the real time position , the behavior of each of the animals is further analyzed .
  • the computer system performs an automatic calibration of all received signals from the animals.
  • US 9, 1 1 9,379 reveals methods, devices and systems for identifying estrus or onset of estrus in a female animal.
  • a patch is attached at the animal's tailhead.
  • the patch contains a pressure switch and an accelerometer to register any indication that the animal has been mounted by another animal, and a transceiver for forwarding this indication to a central server. Namely, if a mounted female allows the mount to continue for more than a few seconds, then the mounted female is likely in estrus.
  • females may be mounted at times outside of estrus, fe- males will allow themselves to be heat mounted for relatively prolonged times.
  • an animal is not in estrus, she will try to move out from under a mount (a false mount or false positive). Accordingly, by registering mounts and their duration , conclusions can be drawn as to whether or not an animal should be in- seminated.
  • the object of the present invention is therefore to offer an improved solution for identifying animals truly in heat in due time to allow successful insemination; and thus also reduce the risk of inseminating any animals that are not in heat.
  • the object is achieved by the initially described system, wherein the data processor is configured to associate a respective time stamp with each entry in the database.
  • each entry represents one event concerning an animal in the herd.
  • the event in turn, relates to an emitted signal, a registered position and/or acceleration data registered for an animal.
  • the data processor is also configured to identify candidate mounting animals as members of a first group based on the entries in the database, and identify candidate mounted animals as members of a second group based on the entries in the database.
  • the data processor is further configured to match the members of the first and second groups with one another to determine any animals potentially in heat. An animal is deemed to be potentially in heat, if the animal is estimated to have been mounted by at least one other animal during a particular interval of time.
  • This system is advantageous because it provides a reliable basis for singling out animals that may be suitable for insemination without requiring complex technical equipment.
  • an animal is deemed to be potentially in heat if and only if the animal is estimated to have been mounted by at least one other animal during an uninterrupted period of a predefined length, say three seconds. Typically, this reduces the number of false positives because also animals that are not in heat may be subjected to mounting, however these animals only accept the situation for a relatively short period of time.
  • each unit in the set of animal units contains at least one accelerometer configured to register a rate of change of velocity along three independent axes in space.
  • accelerometer configured to register a rate of change of velocity along three independent axes in space.
  • the data processor is configured to identify an animal to which an animal unit is attached where the at least one ac- celerometer has registered an acceleration vector within a first space sector as a candidate mounting animal, say an acceleration vector of at least a particular magnitude, and at least a given positive angle relative to a reference plane.
  • the data processor is configured to identify an animal to which an animal unit is attached where the at least one accelerometer has registered an acceleration vector within a second space sector as a candidate mounted animal.
  • each unit in the set of animal units contains a transmitter configured to emit a wireless signal that uniquely represents the unit within the set of animal units. Consequently, the animal units can be positioned via three or more distributed recei- vers.
  • the proposed set of data read-out devices includes at least three separate data read-out devices each of which is configured to receive the wireless signals emitted from the set of animal units.
  • the wireless signals are synchronized to a system time reference.
  • the data processor is configured to process a wireless signal emitted by a particular unit in the set of animal units, which wireless signal has been received by at least three of the at least three separate data read-out devices at respective time instances relative to the system time reference to derive a position for the particular unit at a specific time instance.
  • Such positioning is advantageous because it facilitates pairing the mounting and moun- ted candidates with one another.
  • the data processor is configured to identify an animal to which an animal unit is attached whose position is ele- vated a threshold distance above a nominal height at the specific time instance as a candidate mounting animal, and identify an animal to which an animal unit is attached whose position is within a threshold range from the animal unit of a candidate mounting animal at the specific time instance as a candidate mounted ani- mal.
  • relevant candidate animals can be distinguished accurately, either as an alternative or as a complement to the above-described acceleration-based approach.
  • the system contains at least three signal beacons that are synchronized to a system time reference, and which are configured to emit a respective wireless beacon signal uniquely identifying the signal beacon.
  • Each unit in the set of animal units further contains a receiver, a processor and a transmitter.
  • the receiver is configured to receive wireless beacon signals emitted from at least three of the at least three signal beacons at a specific time instance of the system time reference.
  • the processor is configured to process the received wireless beacon signals to derive a position for the unit, and the transmitter is configured to transmit a wireless position message reflecting the derived position.
  • at least one data read-out device in the set of data read-out devices is configured to receive the wireless position message to read out the position for the unit in question.
  • the object is achieved by a system for identifying animals in a herd of animals, which identified animals are considered to be in heat.
  • the system includes first and second interfaces.
  • the first interface is configured to receive a preliminary classification concerning at least one animal that has been identified as potentially in heat by the above-described decision support system.
  • the second interface is configured to receive auxiliary information concerning the animals in the herd of animals.
  • the auxiliary information describes one or more of the following: a respective activity level of the animals in the herd; at least one group identifier collectively identifying two or more of the animals in the herd as members of a particular subdivision within the herd, which subdivision is physically restricted from being mixed with animals in the herd that are not members of the particular subdivision; position data linking two or more animals in the herd to a particular location within a specified time period; and a data record describing reproduction data for one or more animals in the herd.
  • the system also includes a data processor, which is configured to coordinate the preliminary classification with the auxiliary information to establish which animals in the herd of animals that are considered to be in heat.
  • This system is advantageous because it is capable of reducing the number of so-called false positives which may result from the proposed decision support system.
  • the proportion of true positives increases and the output data quality improves.
  • the object is achieved by the method described initially, wherein a respective time stamp is associated with each entry in the database.
  • Each entry here represents one event concerning an animal in the herd.
  • the event relates to an emitted signal, a registered position and/or acceleration data registered for an animal.
  • the method further involves identifying candidate mounting animals as members of a first group based on the entries in the database, and identifying candidate mounted animals as members of a second group of based on the entries in the database. Based on the time stamps, the members of the first and second groups are matched with one another to determine any animals potentially in heat. An animal is deemed to be potentially in heat, if the animal is estimated to have been mounted by at least one other animal during a par- ticular interval.
  • the object is achieved by a computer program loadable into the memory of at least one processor, and includes software adapted to implement the method proposed above when said program is run on at least one processor.
  • the object is achieved by a processor-readable medium, having a program recor- ded thereon, where the program is to control at least one processor to perform the method proposed above when the program is loaded into the at least one processor.
  • Figure 1 illustrates how a first animal is mounted by a second animal
  • Figure 2 shows an overview of one embodiment of the proposed system
  • Figure 3 shows a graph illustrating how a cow's milk production may vary over time in relation to a heat- and-calving cycle
  • Figure 4 illustrates, by means of a flow diagram , the general method according to the invention .
  • first animal unit 1 01 is attached to the first animal A1 (e.g. to its ear, around its neck or leg), and a second animal unit 102 is attached to the second animal A2. It is further presumed that the first and second animals A1 and A2 belong to a herd of animal in which each animal carries a corresponding animal unit.
  • Figure 2 shows an overview a decision support system according to one embodiment of the invention, where a set of such animal units 101 , 102, 103, 104, 105, 106, 107 and 108 is illustrated.
  • the decision support system also contains a set of data read-out devices 210, 21 1 , 212, 213, 214 and 215, a data processor 220 and a database 230.
  • Each animal unit 101 , 102, 103, 104, 105, 106, 107 and 108 res- pectively is configured to repeatedly perform at least one of the following actions:
  • the data read-out devices 210, 21 1 , 212, 213, 214 and 215 are configured to wirelessly read out information from the set of ani- mal units 101 , 102, 103, 104, 1 05, 106, 107 and 108.
  • the data read-out devices 210, 21 1 , 212, 213, 214 and 215 are preferably distributed around an area 200 where the herd of animals roam, e.g.
  • the data read-out devices 210, 21 1 , 212, 213, 214 and 21 5 can record data from the animal units 1 01 , 102, 103, 104, 105, 106, 107 and 108 irrespective of where each animal is located, for instance based on triangulation, as will be described below.
  • the data processor 220 is configured to receive the information read out from the set of animal units 101 , 102, 103, 104, 1 05, 106, 107 and 108; generate entries in a database 230, which entries reflect the information read out from the set of animal units; and based on the entries in the database 230, identify animals potentially in heat.
  • the data processor 220 is configured to associate a respective time stamp with each entry in the database 230.
  • each entry represents one event concerning an animal, e.g. A1 or A2, in the herd.
  • the event in turn, relates to an emitted signal S 1 or S2, a registered position P 1 or P2 and/or registered acceleration data a1 or a2 as described above.
  • the data processor 220 is further configured to identify candidate mounting animals as members of a first group based on the entries in the database 230, and identify candidate mounted animals as members of a second group of based on the entries in the database 230.
  • the data processor 220 is further configured to match the members of the first and second groups with one another to determine any animals potentially in heat.
  • an animal is deemed to be potentially in heat if the animal, say A1 , is estimated to have been mounted by at least one other animal, say A2, during a particular interval of time, which preferably likewise is defined based on the time stamps.
  • an animal is deemed to be potentially in heat if and only if the animal, say A1 , is estimated to have been mounted by at least one other animal, say A2, during an uninterrupted period of a predefined length, for instance 3 seconds.
  • any other threshold in a range from 2 to 12 seconds may be used here.
  • each unit in the set of animal units 101 , 102, 103, 104, 105, 106, 107 and 108 contains at least one accelerometer configured to register a rate of change of velocity along three independent axes in space.
  • the animal units may contain a respective 3D accelerometer.
  • the data processor 220 is configured to identify an animal A2 as a candidate mounting animal, if the animal A2 car- ries an animal unit 102 where the at least one accelerometer has registered an acceleration vector a2 within a first space sector (e.g. an acceleration vector a2 above a first angle of elevation and having a magnitude above a first level).
  • the data processor 220 is preferably configured to identify an animal A1 as a candidate mounted animal, if the animal A1 carries an animal unit 101 where the at least one accelerometer has registered an acceleration vector a1 within a second space sector (e.g. an acceleration vector a1 below a second angle of elevation and having a magnitude above a second level).
  • each animal unit 101 , 102, 103, 104, 105, 106, 107 and 108 respectively contains a transmitter configured to emit a wireless signal, e.g. S1 and S2, (i.e. having a radio, light, inductive or acoustic format), which wireless signal uniquely represents the unit, here 101 and 102, within the set of animal units.
  • a wireless signal e.g. S1 and S2
  • S1 and S2 i.e. having a radio, light, inductive or acoustic format
  • the set of data readout devices includes at least three separate data read-out devices, here exemplified by 201 , 21 1 , 212, 213, 214 and 215 respectively.
  • Each data read-out device 201 , 21 1 , 212, 213, 214 and 215 is configured to receive the wireless signals, S1 and S2 emitted from the set of animal units, here exemplified by 101 and 102.
  • the data read-out device 201 , 21 1 , 212, 213, 214 and 215 are configured to receive radio, light, inductive and/or acoustic signals from the animal units.
  • each of the data read-out device 201 , 21 1 , 212, 213, 214 and 215 is synchronized to a system time reference, for example in the form of a common clock signal received in all data read-out devices.
  • the data processor 220 is configured to process the wireless sig- nal, e.g. S1 or S2, emitted by a particular animal unit 101 or 102, and which wireless signal S1 or S2 has been received by at least three separate data read-out devices, say 210, 21 1 and 215; and 210, 21 1 and 214 respectively. Depending on the different distances between the animal unit 101 or 102 and said data read out devices 210, 21 1 , 214 and 215 the emitted signals S1 or S2 will be received at different time instances relative to the system time reference.
  • the wireless sig- nal e.g. S1 or S2
  • the data processor 220 may derive a position P1 or P2 for the particular animal unit 101 and 102 respectively at a specific time instance, namely the time instance indicated by the system time reference as the point in time when the signals S1 or S2 were emitted.
  • the positions P1 and P2 for the animal units 101 and 102 respectively may be determined in the animal units 101 and 102.
  • the decision support system includes at least three signal beacons, say 210, 21 1 , 214 and 215, which is each synchronized to a system time reference and is configured to emit a respective wireless beacon signal B0, B 1 , B4 and B5.
  • the wireless beacon signals B0, B1 , B4 and B5 uniquely identify the respective signal beacon 210, 2 1 , 214 and 215 from which they have been emitted.
  • each animal unit e.g . 101 , 102, includes a receiver, a processor and a transmitter.
  • the receiver is configured to receive the wireless beacon signals B0, B1 , B4 and B5 emitted from at least three signal beacons, say 210, 21 1 and 215; and 210, 21 1 and 214 respectively, at a specific time instance as indicated by the system time reference.
  • the processor is configured to pro- cess the wireless beacon signals B0, B1 and B5; and B0, B1 and B4 respectively, to derive a position P1 and P2 for the unit 101 and 1 02 respectively.
  • the transmitter is configured to transmit a wireless position message m[P1 ] and m[P2] reflecting the derived position P1 and P2 respectively.
  • At least one data read-out device e.g. 214 and/or 215 for example located near an exit from the area 200, is configured to receive the wireless position message m[P1 ] and m[P2] to read out the position P1 and P2 for the unit 101 and 102 respectively.
  • all the data read-out devices 201 , 21 1 , 212, 213, 214 and 215 in the set of data read-out devices may equally well be configured to receive the wireless position message m[P1 ] and m[P2] for improved flexibility and/or redundancy.
  • the data processor 220 is configured to identify an animal A2 as a candidate mounting animal, if the animal A2 carries an animal unit 102 whose position P2 is elevated a threshold distance h E above a nominal height h N at a specific time instance.
  • the data processor 220 is configured to identify an animal A1 as a candidate mounted animal, if the animal A1 carries an animal unit 101 whose position P1 is within a threshold range R from the animal unit 102 of a candidate mounting animal A2 at the specific time instance.
  • this provides highly relevant estima- tes of candidate mounted and mounting animals.
  • the decision support system may be supplemented by a system for identifying animals in a herd of animals, which identified animals are considered to be in heat.
  • This system has first and second interfaces plus a da- ta processor.
  • the first interface is configured to receive a preliminary classification concerning at least one animal identified as potentially in heat by the above-described decision support system.
  • the second interface is configured to receive auxiliary information concerning the animals in the herd of animals.
  • the auxiliary information describes at least one of:
  • the group identi- fier may be dynamic, and for example reflect the fact that two or more animals have been located at the same feeding or milking station within a particular interval of time);
  • the data processor is configured to coordinate the preliminary classification received via the first interface with the auxiliary information received via the second interface to establish which animals in the herd of animals that are considered to be in heat.
  • the animals' activity level may be registered by a respective activity meter preferably integrated into the animal units 101 , 102, 103, 104, 105, 106, 107 and 1 08. Since a cow's activity level nor- mally increases in connection with estrus, the activity level is therefore one appropriate parameter by which a preliminary classification concerning whether an animal should be considered to be in heat may either be strengthened or weakened.
  • the group identifier represents a parameter which may exclusi- vely eliminate two animals a members of a mounting-mounted pair. Namely, if the animals in question belong to different groups, they cannot have been engaged in the same mounting activity.
  • the data record that describes the animals reproduction data may however both strengthen and weaken a preliminary classification concerning whether an animal should be considered to be in heat depending on what these data say in relation to what the preliminary classification is.
  • the coordination effected by the data processor involves eliminating one or more so-called false positi- ves, i.e. reducing the number of animals identified as potentially in heat to a smaller group of animals in which the members are in heat at a higher degree of confidence.
  • the data processor 220 may be communicatively connected to a memory unit 225 storing a computer program product SW, which, in turn, contains software for making at least one processor in the data processor 220 execute the above-described actions when the computer program product is run on the data processor 220.
  • a representative signal In a first step 410 , it is checked if a representative signal has been received in respect of an animal.
  • the representative signal reflects the animal's position and/or acceleration data related to the animal , e.g. data reflecting that the animal has been moun- ted by another animal, or that the animal itself has mounted another animal. If in step 41 0 it is found that a representative signal has been received , a step 420 follows. Otherwise, the procedure loops back and stays in step 41 0.
  • step 420 event data generated based on the representative signal is stored in a database together with a time stamp, i.e. an indicator of when the event occurred.
  • steps 430 and 440 follow, preferably in parallel.
  • any candidate mounting animals are identified based on the contents of the database.
  • any candidate mounted animals are identified based on the contents of the database.
  • any animals potentially in heat are determined by matching the candidate mounting animals with the candidate mounted animals.
  • the matching is here effected by using the time stamps. For example, the fact that a first animal is mounted during a particular (and relatively short interval) and a second animal is mounting during the same interval may be interpreted as the second animal mounting the first animal during this interval. Especially, such a conclusion can be made if also the animals' positions simultaneously overlap, or at least lie within a threshold distance from one another.
  • step 450 the procedure loops back to step 410.
  • All of the process steps, as well as any sub-sequence of steps, described with reference to Figure 4 above may be controlled by means of a programmed processor.
  • the embodiments of the invention described above with reference to the drawings comprise processor and processes performed in at least one processor, the invention thus also extends to computer programs, particularly computer programs on or in a carrier, adapted for putting the invention into practice.
  • the program may be in the form of source code, object code, a code intermediate source and object code such as in partially compiled form , or in any other form suitable for use in the implementation of the pro- cess according to the invention .
  • the program may either be a part of an operating system , or be a separate application.
  • the carrier may be any entity or device capable of carrying the program .
  • the carrier may comprise a storage medium, such as a Flash memory, a ROM (Read Only Memory), for ex- ample a DVD (Digital Video/Versatile Disk), a CD (Compact Disc) or a semiconductor ROM, an EPROM (Erasable Programmable Read-Only Memory), an EEPROM (Electrically Erasable Programmable Read-Only Memory), or a magnetic recording medium, for example a floppy disc or hard disc.
  • the carrier may be a transmissible carrier such as an electrical or optical signal which may be conveyed via electrical or optical cable or by radio or by other means.
  • the carrier may be constituted by such cable or device or means.
  • the carrier may be an integrated circuit in which the program is embedded, the integrated circuit being adapted for performing, or for use in the performance of, the relevant processes.
  • the invention is advantageous in connection with cow milking, the invention is equally well adapted for implementation in milking machines for any other kind of mammals, such as goats, sheep or buffaloes.

Abstract

A respective animal unit (101, 102) is attached to the animals (A1, A2) in a herd of animals. Each unit (101, 102) is configured to repeatedly: emit a signal (S1; S2) representing the unit (101, 102), register a position (P1; P2) and/or register acceleration data (a1; a2) related to the animal (A1; A2) to which the unit (101, 102) is attached. A set of data read-out devices wirelessly reads out information from the set of animal units (101, 102) into a database. A data processor identifies animals potentially in heat by: - associating a respective time stamp with each entry in the database, each entry representing one event concerning an animal (A1, A2) in the herd, which event relates to an emitted signal (S1, S2), a registered position (P1, P2) and/or registered acceleration data (a1, a2); - identifying candidate mounting animals as members of a first group based on the entries in the database; - identifying candidate mounted animals as members of a second group of based on the entries in the database, and - based on the time stamps, matching the members of the first and second groups with one another to determine any animals potentially in heat, wherein an animal is deemed to be potentially in heat if the animal (A1) is estimated to have been mounted by at least one other animal (A2) during a particular interval of time.

Description

Decision Support System and Method of providing Decision Support with respect to a Herd of Animals
THE BACKGROU ND OF THE INVENTION AND PRIOR ART
The present invention relates generally to solutions for impro- ving the milk production efficiency. More particularly the invention relates to a decision support system according to the preamble of claim 1 and a corresponding method. The invention also relates to a system for identifying animals in heat, a computer program and a processor-readable medium. To attain a high overall yield in milk production it is important that each animal is inseminated at a point in time which is most suitable with respect to the animal's lactation cycle. Namely, a cow normally produces the most milk during the second and third months of lactation. Thereafter, the production decreases gradually; and approximately two months prior to calving , the cow is dried off. During the dry period, the cow produces no, or very little milk. Therefore, from a production point-of-view, any unnecessary prolongation of the lactation is highly undesired. Thus, it is key that the next lactation period can be initiated as soon as possible. In other words, it is desirable that the calving intervals are shortened as much as possible, because this means that the next high-productive second and third months are advanced in time. To achieve this, accurate knowledge about the animal's reproduction cycle is required. More preci- sely, at each point in time, the farmer must know whether or not a particular cow is in heat, so that if needed, he/she can effect insemination in due time. In cattle, the estrous period occurs approximately every 21 days in non-pregnant animals, and the estrous period usually lasts only 12 to 1 8 hours, with a peak estrus being about six hours in duration. Hence, successful insemination requires delicate timing . The prior art includes various examples of solutions for determining the behavior of the animals to provide a basis for insemination decisions.
WO 2008/1 13556 describes an animal monitoring system with a real time location system for individually identifying and tracking the movements of tagged animals in three dimensions within a monitoring zone. Means are also described for discriminating between different activities of at least one animal based upon the location of the animal's tag within the zone.
WO 2009/135493 shows a system for detecting and determining the position of moving objects, where electronic transceiver units communicate with at least two fixed transceiver stations to perform a constant position determination of movable objects within a delimited area. The communication between the fixed transceiver stations and the electronic transceiver units occurs in the form of transient pulses emitted from the electronic transceiver units. The position determination is performed by calculating time or phase difference between receptions of a signal at at least two transceiver facilities, respectively. Indications of animal behavior are based on an acceleration detector carried by the animal and communication performed by a short-range radio system.
WO 2014/067897 discloses a solution for real time detection of the position and behavior of a plurality of animals. Radio trans- mitter tags are carried by the animals and sensors receive signals from the tags. Based on time delay of received signals at the sensors from the tags, the positions of the animals are calculated. Fixed reference radio transmitter tags and fixed placed sensors are used for reference. WO 2014/067896 relates to a computer system for measuring real time position of a plurality of animals, which system receives input from a plurality of sensors, communicating with tags carried by the animals. Based on measurement of delay in radio communication, the system calculates the actual position of the animals. Based on the real time position , the behavior of each of the animals is further analyzed . By using fixed reference tags together with tags, the computer system performs an automatic calibration of all received signals from the animals.
US 9, 1 1 9,379 reveals methods, devices and systems for identifying estrus or onset of estrus in a female animal. Here, a patch is attached at the animal's tailhead. The patch contains a pressure switch and an accelerometer to register any indication that the animal has been mounted by another animal, and a transceiver for forwarding this indication to a central server. Namely, if a mounted female allows the mount to continue for more than a few seconds, then the mounted female is likely in estrus. Although females may be mounted at times outside of estrus, fe- males will allow themselves to be heat mounted for relatively prolonged times. When an animal is not in estrus, she will try to move out from under a mount (a false mount or false positive). Accordingly, by registering mounts and their duration , conclusions can be drawn as to whether or not an animal should be in- seminated.
PROBLEMS ASSOCIATED WITH TH E PRIOR ART
Although relatively precise and valuable information about the animals' respective reproduction cycles can be obtained by collecting mounting data as described above, there is still room for improvement. For example, the registered data as such may not be sufficiently reliable. More important, however, attaching and maintaining the patch at each animal's tailhead is associated with many practical problems.
S UMMARY OF TH E I NVENTION
The object of the present invention is therefore to offer an improved solution for identifying animals truly in heat in due time to allow successful insemination; and thus also reduce the risk of inseminating any animals that are not in heat.
According to one aspect of the invention, the object is achieved by the initially described system, wherein the data processor is configured to associate a respective time stamp with each entry in the database. Here, each entry represents one event concerning an animal in the herd. The event, in turn, relates to an emitted signal, a registered position and/or acceleration data registered for an animal. The data processor is also configured to identify candidate mounting animals as members of a first group based on the entries in the database, and identify candidate mounted animals as members of a second group based on the entries in the database. Based on the time stamps, the data processor is further configured to match the members of the first and second groups with one another to determine any animals potentially in heat. An animal is deemed to be potentially in heat, if the animal is estimated to have been mounted by at least one other animal during a particular interval of time.
This system is advantageous because it provides a reliable basis for singling out animals that may be suitable for insemination without requiring complex technical equipment.
According to a preferred embodiment of this aspect of the invention , an animal is deemed to be potentially in heat if and only if the animal is estimated to have been mounted by at least one other animal during an uninterrupted period of a predefined length, say three seconds. Typically, this reduces the number of false positives because also animals that are not in heat may be subjected to mounting, however these animals only accept the situation for a relatively short period of time.
According to another preferred embodiment of this aspect of the invention, each unit in the set of animal units contains at least one accelerometer configured to register a rate of change of velocity along three independent axes in space. Thus, complex patterns of movements can be registered and discriminated to deter- mine whether or not an animal is engaged in a mounting activity.
According to yet another preferred embodiment of this aspect of the invention, the data processor is configured to identify an animal to which an animal unit is attached where the at least one ac- celerometer has registered an acceleration vector within a first space sector as a candidate mounting animal, say an acceleration vector of at least a particular magnitude, and at least a given positive angle relative to a reference plane. Analogously, the data processor is configured to identify an animal to which an animal unit is attached where the at least one accelerometer has registered an acceleration vector within a second space sector as a candidate mounted animal. Hence, provided a balanced selection of thresholds, relevant candidate animals can be found with high accuracy. According to a further preferred embodiment of this aspect of the invention, each unit in the set of animal units contains a transmitter configured to emit a wireless signal that uniquely represents the unit within the set of animal units. Consequently, the animal units can be positioned via three or more distributed recei- vers.
In particular, according to one preferred embodiment of this aspect of the invention, the proposed set of data read-out devices includes at least three separate data read-out devices each of which is configured to receive the wireless signals emitted from the set of animal units. Further, to enable unambiguous calculation of respective distances to the data read-out devices, the wireless signals are synchronized to a system time reference. More precisely, the data processor is configured to process a wireless signal emitted by a particular unit in the set of animal units, which wireless signal has been received by at least three of the at least three separate data read-out devices at respective time instances relative to the system time reference to derive a position for the particular unit at a specific time instance. Such positioning is advantageous because it facilitates pairing the mounting and moun- ted candidates with one another.
According to still another preferred embodiment of this aspect of the invention, the data processor is configured to identify an animal to which an animal unit is attached whose position is ele- vated a threshold distance above a nominal height at the specific time instance as a candidate mounting animal, and identify an animal to which an animal unit is attached whose position is within a threshold range from the animal unit of a candidate mounting animal at the specific time instance as a candidate mounted ani- mal. Hence, relevant candidate animals can be distinguished accurately, either as an alternative or as a complement to the above-described acceleration-based approach.
According to another preferred embodiment of this aspect of the invention, the system contains at least three signal beacons that are synchronized to a system time reference, and which are configured to emit a respective wireless beacon signal uniquely identifying the signal beacon. Each unit in the set of animal units further contains a receiver, a processor and a transmitter. The receiver is configured to receive wireless beacon signals emitted from at least three of the at least three signal beacons at a specific time instance of the system time reference. The processor is configured to process the received wireless beacon signals to derive a position for the unit, and the transmitter is configured to transmit a wireless position message reflecting the derived position. Moreover, at least one data read-out device in the set of data read-out devices is configured to receive the wireless position message to read out the position for the unit in question. Hence, an alternative is provided to the above-described means of determining the animals' positions. According to another aspect of the invention, the object is achieved by a system for identifying animals in a herd of animals, which identified animals are considered to be in heat. The system includes first and second interfaces. The first interface is configured to receive a preliminary classification concerning at least one animal that has been identified as potentially in heat by the above-described decision support system. The second interface is configured to receive auxiliary information concerning the animals in the herd of animals. Here, the auxiliary information describes one or more of the following: a respective activity level of the animals in the herd; at least one group identifier collectively identifying two or more of the animals in the herd as members of a particular subdivision within the herd, which subdivision is physically restricted from being mixed with animals in the herd that are not members of the particular subdivision; position data linking two or more animals in the herd to a particular location within a specified time period; and a data record describing reproduction data for one or more animals in the herd. The system also includes a data processor, which is configured to coordinate the preliminary classification with the auxiliary information to establish which animals in the herd of animals that are considered to be in heat.
This system is advantageous because it is capable of reducing the number of so-called false positives which may result from the proposed decision support system. Thus, the proportion of true positives increases and the output data quality improves.
According to another aspect of the invention, the object is achieved by the method described initially, wherein a respective time stamp is associated with each entry in the database. Each entry here represents one event concerning an animal in the herd. The event relates to an emitted signal, a registered position and/or acceleration data registered for an animal. The method further involves identifying candidate mounting animals as members of a first group based on the entries in the database, and identifying candidate mounted animals as members of a second group of based on the entries in the database. Based on the time stamps, the members of the first and second groups are matched with one another to determine any animals potentially in heat. An animal is deemed to be potentially in heat, if the animal is estimated to have been mounted by at least one other animal during a par- ticular interval. The advantages of this method, as well as the preferred embodiments thereof, are apparent from the discussion above with reference to the proposed system.
According to a further aspect of the invention the object is achieved by a computer program loadable into the memory of at least one processor, and includes software adapted to implement the method proposed above when said program is run on at least one processor.
According to another aspect of the invention the object is achieved by a processor-readable medium, having a program recor- ded thereon, where the program is to control at least one processor to perform the method proposed above when the program is loaded into the at least one processor.
Further advantages, beneficial features and applications of the present invention will be apparent from the following description and the dependent claims.
BRI EF DESCRIPTION OF THE DRAWI NGS
The invention is now to be explained more closely by means of preferred embodiments, which are disclosed as examples, and with reference to the attached drawings.
Figure 1 illustrates how a first animal is mounted by a second animal;
Figure 2 shows an overview of one embodiment of the proposed system;
Figure 3 shows a graph illustrating how a cow's milk production may vary over time in relation to a heat- and-calving cycle; and
Figure 4 illustrates, by means of a flow diagram , the general method according to the invention . DESCRIPTION OF PREFERRED EMBODIMENTS OF THE INVENTION
As explained above, if a mounted cow allows the mount to continue for more than a few seconds, this can be an indicator of that the mounted cow is in estrus. Therefore, we will elaborate upon strategies to determine whether or not a mounting has occurred; and if so, whether or not the mounted animal should be regarded as a candidate for insemination .
First, however, referring to Figure 3 we see a graph exemplify- ing how a cow's milk production Y may vary over time t in relation to a heat-and-calving cycle. We presume that the cow gives birth to a first calf at t = 0. Then , at later point in time t = t1 , say two to three months after t = 0, the cow has a production peak Yp. Around t = t1 is normally also an appropriate time to insemi- nate the cow, so that she gives birth to a second calf at a point in time t = t4 (typically 283 days after t = t1 ), while allowing a prior low-production dry period TD (of about 60 days) starting at t = t3 (i .e. approximately 223 days after the insemination at t = t1 ). A first production period TP thus extends from t = 0 to t = t3. If, for some reason, the insemination which should have been effected at t = t1 is missed, the next opportunity to succeed with the insemination occurs approximately 21 days later, at t = t2. In such a case, the lactation period is prolonged to TDd , and the second calf is born first at t = t6. Consequently, instead of an expected second production peak at t = t5, the production peak comes first at t = t7 (as indicated by the dashed graph), and around 21 days of high production around t = t5 are "lost." Instead, the cow only produces very little milk, as indicated by the dotted line. This is a scenario that the present invention seeks to avoid.
I n Figure 1 , we see an example of a first animal A1 being mounted by a second animal A2. A first animal unit 1 01 is attached to the first animal A1 (e.g. to its ear, around its neck or leg), and a second animal unit 102 is attached to the second animal A2. It is further presumed that the first and second animals A1 and A2 belong to a herd of animal in which each animal carries a corresponding animal unit.
Figure 2 shows an overview a decision support system according to one embodiment of the invention, where a set of such animal units 101 , 102, 103, 104, 105, 106, 107 and 108 is illustrated. The decision support system also contains a set of data read-out devices 210, 21 1 , 212, 213, 214 and 215, a data processor 220 and a database 230.
Each animal unit 101 , 102, 103, 104, 105, 106, 107 and 108 res- pectively is configured to repeatedly perform at least one of the following actions:
(i) emit a signal e.g. S 1 or S2 representing the unit in 1 01 or 102 respectively,
(ii) register a position e.g. P1 or P2 for the unit in 101 or 102 respectively, and
(iii) register acceleration data a1 or a2 related to the animal A1 or A2 to which the unit 101 or 102 respectively is attached.
The data read-out devices 210, 21 1 , 212, 213, 214 and 215 are configured to wirelessly read out information from the set of ani- mal units 101 , 102, 103, 104, 1 05, 106, 107 and 108. The data read-out devices 210, 21 1 , 212, 213, 214 and 215 are preferably distributed around an area 200 where the herd of animals roam, e.g. a corral or a farm building, so that the data read-out devices 210, 21 1 , 212, 213, 214 and 21 5 can record data from the animal units 1 01 , 102, 103, 104, 105, 106, 107 and 108 irrespective of where each animal is located, for instance based on triangulation, as will be described below.
The data processor 220 is configured to receive the information read out from the set of animal units 101 , 102, 103, 104, 1 05, 106, 107 and 108; generate entries in a database 230, which entries reflect the information read out from the set of animal units; and based on the entries in the database 230, identify animals potentially in heat. Specifically, according to the invention, the data processor 220 is configured to associate a respective time stamp with each entry in the database 230. Here, each entry represents one event concerning an animal, e.g. A1 or A2, in the herd. The event, in turn, relates to an emitted signal S 1 or S2, a registered position P 1 or P2 and/or registered acceleration data a1 or a2 as described above. The data processor 220 is further configured to identify candidate mounting animals as members of a first group based on the entries in the database 230, and identify candidate mounted animals as members of a second group of based on the entries in the database 230.
Based on the time stamps, the data processor 220 is further configured to match the members of the first and second groups with one another to determine any animals potentially in heat. Here, an animal is deemed to be potentially in heat if the animal, say A1 , is estimated to have been mounted by at least one other animal, say A2, during a particular interval of time, which preferably likewise is defined based on the time stamps. According to one preferred embodiment of the invention, an animal is deemed to be potentially in heat if and only if the animal, say A1 , is estimated to have been mounted by at least one other animal, say A2, during an uninterrupted period of a predefined length, for instance 3 seconds. However, according to the inven- tion, any other threshold in a range from 2 to 12 seconds may be used here.
Moreover, it is advantageous if each unit in the set of animal units 101 , 102, 103, 104, 105, 106, 107 and 108 contains at least one accelerometer configured to register a rate of change of velocity along three independent axes in space. In other words, the animal units may contain a respective 3D accelerometer.
Preferably, the data processor 220 is configured to identify an animal A2 as a candidate mounting animal, if the animal A2 car- ries an animal unit 102 where the at least one accelerometer has registered an acceleration vector a2 within a first space sector (e.g. an acceleration vector a2 above a first angle of elevation and having a magnitude above a first level). Analogously, the data processor 220 is preferably configured to identify an animal A1 as a candidate mounted animal, if the animal A1 carries an animal unit 101 where the at least one accelerometer has registered an acceleration vector a1 within a second space sector (e.g. an acceleration vector a1 below a second angle of elevation and having a magnitude above a second level).
Further preferably, each animal unit 101 , 102, 103, 104, 105, 106, 107 and 108 respectively contains a transmitter configured to emit a wireless signal, e.g. S1 and S2, (i.e. having a radio, light, inductive or acoustic format), which wireless signal uniquely represents the unit, here 101 and 102, within the set of animal units.
To enable positioning based on triangulation, the set of data readout devices includes at least three separate data read-out devices, here exemplified by 201 , 21 1 , 212, 213, 214 and 215 respectively. Each data read-out device 201 , 21 1 , 212, 213, 214 and 215 is configured to receive the wireless signals, S1 and S2 emitted from the set of animal units, here exemplified by 101 and 102. I.e. depending on the wireless signal format, the data read-out device 201 , 21 1 , 212, 213, 214 and 215 are configured to receive radio, light, inductive and/or acoustic signals from the animal units. Ad- ditionally, to enable the triangulation-based positioning, each of the data read-out device 201 , 21 1 , 212, 213, 214 and 215 is synchronized to a system time reference, for example in the form of a common clock signal received in all data read-out devices.
The data processor 220 is configured to process the wireless sig- nal, e.g. S1 or S2, emitted by a particular animal unit 101 or 102, and which wireless signal S1 or S2 has been received by at least three separate data read-out devices, say 210, 21 1 and 215; and 210, 21 1 and 214 respectively. Depending on the different distances between the animal unit 101 or 102 and said data read out devices 210, 21 1 , 214 and 215 the emitted signals S1 or S2 will be received at different time instances relative to the system time reference. Consequently, based on the time instances in question (and given that the propagation speed for the signals S 1 and S2 is known), the data processor 220 may derive a position P1 or P2 for the particular animal unit 101 and 102 respectively at a specific time instance, namely the time instance indicated by the system time reference as the point in time when the signals S1 or S2 were emitted. Alternatively, or additionally, the positions P1 and P2 for the animal units 101 and 102 respectively may be determined in the animal units 101 and 102. In such a case, the decision support system includes at least three signal beacons, say 210, 21 1 , 214 and 215, which is each synchronized to a system time reference and is configured to emit a respective wireless beacon signal B0, B 1 , B4 and B5. The wireless beacon signals B0, B1 , B4 and B5 uniquely identify the respective signal beacon 210, 2 1 , 214 and 215 from which they have been emitted.
Furthermore, each animal unit, e.g . 101 , 102, includes a receiver, a processor and a transmitter. The receiver is configured to receive the wireless beacon signals B0, B1 , B4 and B5 emitted from at least three signal beacons, say 210, 21 1 and 215; and 210, 21 1 and 214 respectively, at a specific time instance as indicated by the system time reference. The processor is configured to pro- cess the wireless beacon signals B0, B1 and B5; and B0, B1 and B4 respectively, to derive a position P1 and P2 for the unit 101 and 1 02 respectively. The transmitter is configured to transmit a wireless position message m[P1 ] and m[P2] reflecting the derived position P1 and P2 respectively. At least one data read-out device, e.g. 214 and/or 215 for example located near an exit from the area 200, is configured to receive the wireless position message m[P1 ] and m[P2] to read out the position P1 and P2 for the unit 101 and 102 respectively. Naturally, all the data read-out devices 201 , 21 1 , 212, 213, 214 and 215 in the set of data read-out devices may equally well be configured to receive the wireless position message m[P1 ] and m[P2] for improved flexibility and/or redundancy.
According to one preferred embodiment of the invention, the data processor 220 is configured to identify an animal A2 as a candidate mounting animal, if the animal A2 carries an animal unit 102 whose position P2 is elevated a threshold distance hE above a nominal height hN at a specific time instance. Analogously, the data processor 220 is configured to identify an animal A1 as a candidate mounted animal, if the animal A1 carries an animal unit 101 whose position P1 is within a threshold range R from the animal unit 102 of a candidate mounting animal A2 at the specific time instance. Especially if combined with the above-described acceleration measurements, this provides highly relevant estima- tes of candidate mounted and mounting animals.
To further enhance the proposed solution, the decision support system may be supplemented by a system for identifying animals in a herd of animals, which identified animals are considered to be in heat. This system has first and second interfaces plus a da- ta processor.
The first interface is configured to receive a preliminary classification concerning at least one animal identified as potentially in heat by the above-described decision support system.
The second interface is configured to receive auxiliary information concerning the animals in the herd of animals. Here, the auxiliary information describes at least one of:
- a respective activity level of the animals in the herd;
- at least one group identifier collectively identifying two or more of the animals in the herd as members of a particular subdivision within the herd, which subdivision is physically restricted from being mixed with animals in the herd that are not members of the particular subdivision (the group identi- fier may be dynamic, and for example reflect the fact that two or more animals have been located at the same feeding or milking station within a particular interval of time);
- position data linking two or more animals in the herd to a particular location within a specified time period; and
- a data record describing reproduction data for one or more animals in the herd.
The data processor is configured to coordinate the preliminary classification received via the first interface with the auxiliary information received via the second interface to establish which animals in the herd of animals that are considered to be in heat.
The animals' activity level may be registered by a respective activity meter preferably integrated into the animal units 101 , 102, 103, 104, 105, 106, 107 and 1 08. Since a cow's activity level nor- mally increases in connection with estrus, the activity level is therefore one appropriate parameter by which a preliminary classification concerning whether an animal should be considered to be in heat may either be strengthened or weakened.
The group identifier represents a parameter which may exclusi- vely eliminate two animals a members of a mounting-mounted pair. Namely, if the animals in question belong to different groups, they cannot have been engaged in the same mounting activity.
The data record that describes the animals reproduction data may however both strengthen and weaken a preliminary classification concerning whether an animal should be considered to be in heat depending on what these data say in relation to what the preliminary classification is.
In the light of the above, even though some parameters received via the second interface, as such , may strengthen an assumption of heat for a given animal, the coordination effected by the data processor involves eliminating one or more so-called false positi- ves, i.e. reducing the number of animals identified as potentially in heat to a smaller group of animals in which the members are in heat at a higher degree of confidence.
It is generally advantageous if the data processor 220 is confi- gured to effect the above-mentioned procedure in a fully automatic manner, for instance by an executing computer program . Therefore, the data processor 220 may be communicatively connected to a memory unit 225 storing a computer program product SW, which, in turn, contains software for making at least one processor in the data processor 220 execute the above-described actions when the computer program product is run on the data processor 220.
In order to sum up, and with reference to the flow diagram in Figure 4, we will now describe the general method according to the invention.
In a first step 410 , it is checked if a representative signal has been received in respect of an animal. The representative signal reflects the animal's position and/or acceleration data related to the animal , e.g. data reflecting that the animal has been moun- ted by another animal, or that the animal itself has mounted another animal. If in step 41 0 it is found that a representative signal has been received , a step 420 follows. Otherwise, the procedure loops back and stays in step 41 0.
In step 420, event data generated based on the representative signal is stored in a database together with a time stamp, i.e. an indicator of when the event occurred. Thereafter, steps 430 and 440 follow, preferably in parallel.
In step 430, any candidate mounting animals are identified based on the contents of the database. In step 440, any candidate mounted animals are identified based on the contents of the database. Subsequently, in a step 450, any animals potentially in heat are determined by matching the candidate mounting animals with the candidate mounted animals. The matching is here effected by using the time stamps. For example, the fact that a first animal is mounted during a particular (and relatively short interval) and a second animal is mounting during the same interval may be interpreted as the second animal mounting the first animal during this interval. Especially, such a conclusion can be made if also the animals' positions simultaneously overlap, or at least lie within a threshold distance from one another.
Then, after step 450, the procedure loops back to step 410.
All of the process steps, as well as any sub-sequence of steps, described with reference to Figure 4 above may be controlled by means of a programmed processor. Moreover, although the embodiments of the invention described above with reference to the drawings comprise processor and processes performed in at least one processor, the invention thus also extends to computer programs, particularly computer programs on or in a carrier, adapted for putting the invention into practice. The program may be in the form of source code, object code, a code intermediate source and object code such as in partially compiled form , or in any other form suitable for use in the implementation of the pro- cess according to the invention . The program may either be a part of an operating system , or be a separate application. The carrier may be any entity or device capable of carrying the program . For example, the carrier may comprise a storage medium, such as a Flash memory, a ROM (Read Only Memory), for ex- ample a DVD (Digital Video/Versatile Disk), a CD (Compact Disc) or a semiconductor ROM, an EPROM (Erasable Programmable Read-Only Memory), an EEPROM (Electrically Erasable Programmable Read-Only Memory), or a magnetic recording medium, for example a floppy disc or hard disc. Further, the carrier may be a transmissible carrier such as an electrical or optical signal which may be conveyed via electrical or optical cable or by radio or by other means. When the program is embodied in a signal which may be conveyed directly by a cable or other device or means, the carrier may be constituted by such cable or device or means. Alternatively, the carrier may be an integrated circuit in which the program is embedded, the integrated circuit being adapted for performing, or for use in the performance of, the relevant processes.
Although the invention is advantageous in connection with cow milking, the invention is equally well adapted for implementation in milking machines for any other kind of mammals, such as goats, sheep or buffaloes.
The term "comprises/comprising" when used in this specification is taken to specify the presence of stated features, integers, steps or components. However, the term does not preclude the presence or addition of one or more additional features, integers, steps or components or groups thereof.
The invention is not restricted to the described embodiments in the figures, but may be varied freely within the scope of the claims.

Claims

Claims
1 . A decision support system comprising :
a set of animal units (101 , 102, 103, 104, 105, 106, 107, 108), wherein each animal unit is attached to an animal (A1 , A2) in a herd of animals, and each of which units is configured to repeatedly: emit a signal (S1 ; S2) representing the unit (101 , 102), register a position (P1 ; P2) and/or register acceleration data (a1 ; a2) related to the animal (A1 ; A2) to which the unit (101 , 102) is attached;
a set of data read-out devices (210, 21 1 , 212, 213, 214,
215) configured to wirelessly read out information from the set of animal units (101 , 102, 103, 104, 105, 106, 1 07, 108); and
a data processor (220) configured to receive the information read out from the set of animal units, generate entries in a data- base (230), which entries reflect the information read out from the set of animal units, and based on the entries in the database, identify animals potentially in heat, characterized i n that the data processor (220) is configured to:
associate a respective time stamp with each entry in the da- tabase (230), each entry representing one event concerning an animal (A1 , A2) in the herd, which event relates to an emitted signal (S 1 , S2), a registered position (P 1 , P2) and/or registered acceleration data (a1 , a2),
identify candidate mounting animals as members of a first group based on the entries in the database (230),
identify candidate mounted animals as members of a second group of based on the entries in the database, and
based on the time stamps, match the members of the first and second groups with one another to determine any animals po- tentially in heat, wherein an animal is deemed to be potentially in heat if the animal (A1 ) is estimated to have been mounted by at least one other animal (A2) during a particular interval of time.
2. The decision support system according to claim 1 , wherein an animal is deemed to be potentially in heat if and only if the ani- mal (A1 ) is estimated to have been mounted by at least one other animal (A2) during an uninterrupted period of a predefined length.
3. The decision support system according to any one of claims 1 or 2, wherein each unit (101 , 102) in the set of animal units comprises at least one accelerometer configured to register a rate of change of velocity along three independent axes in space.
4. The decision support system according to claim 3, wherein the data processor (220) is configured to:
identify an animal (A2) to which an animal unit (102) is attached where the at least one accelerometer has registered an ac- celeration vector (a2) within a first space sector as a candidate mounting animal, and
identify an animal (A1 ) to which an animal unit (101 ) is attached where the at least one accelerometer has registered an acceleration vector (a1 ) within a second space sector as a candi- date mounted animal.
5. The decision support system according to any one of the preceding claims, wherein each unit in the set of animal units (1 01 , 1 02, 103, 104, 105, 1 06, 107, 108) comprises a transmitter configured to emit a wireless signal (S1 , S2) uniquely represen- ting the unit (101 ; 102) within the set of animal units.
6. The decision support system according to claim 5, wherein: the set of data read-out devices (201 , 21 1 , 212, 213, 214,
215) comprises at least three separate data read-out devices each of which is configured to receive the wireless signals (S 1 , S2) emitted from the set of animal units (101 , 102), and each of which is synchronized to a system time reference; and
the data processor (220) is configured to process a wireless signal (S1 , S2) emitted by a particular unit (101 ; 102) in the set of animal units, which wireless signal (S 1 , S2) has been received by at least three of the at least three separate data read-out devices (210, 2 1 , 214, 21 5) at respective time instances relative to the system time reference to derive a position (P1 , P2) for the parti- cular unit (101 ; 102) at a specific time instance.
7. The decision support system according to claim 6, wherein the data processor (220) is configured to:
identify an animal (A2) to which an animal unit (102) is atta- ched whose position (P2) is elevated a threshold distance (hE) above a nominal height (hN) at the specific time instance as a candidate mounting animal, and
identify an animal (A1 ) to which an animal unit (101 ) is attached whose position (P1 ) is within a threshold range (R) from the animal unit (102) of a candidate mounting animal (A2) at the specific time instance as a candidate mounted animal.
8. The decision support system according to any one of the preceding claims, comprising at least three signal beacons (210, 21 1 , 214, 215) synchronized to a system time reference and con- figured to emit a respective wireless beacon signal (B0, B1 , B4, B5) uniquely identifying the signal beacon, each unit in the set of animal units (101 , 102) further comprising:
a receiver configured to receive wireless beacon signals (B0, B1 , B4, B5) emitted from at least three of the at least three signal beacons at a specific time instance of the system time reference,
a processor configured to process said wireless beacon signals(B0, B 1 , B4, B5) to derive a position (P1 , P2) for the unit (101 ; 102), and
a transmitter configured to transmit a wireless position message (m[P 1 ], m[P2]) reflecting the derived position (P1 ; P2); and
at least one data read-out device (214, 215) in the set of data read-out devices (201 , 21 1 , 212, 213, 214, 215) is configured to receive the wireless position message(m[P1 ], m[P2]) to read out the position (P1 , P2) for the unit (101 , 102).
9. A system for identifying animals in a herd of animals, which identified animals are considered to be in heat, the system comprising:
a first interface configured to receive a preliminary classifi- cation concerning at least one animal identified as potentially in heat by the decision support system according to any one of the claims 1 to 8;
a second interface configured to receive auxiliary information concerning the animals in the herd of animals, the auxiliary information describing at least one of:
a respective activity level of the animals in the herd, at least one group identifier collectively identifying two or more of the animals in the herd as members of a particular subdivision within the herd, which subdivision is physi- cally restricted from being mixed with animals in the herd that are not members of the particular subdivision,
position data linking two or more animals in the herd to a particular location within a specified time period, and
a data record describing reproduction data for one or more animals in the herd; and
a data processor configured to coordinate the preliminary classification with the auxiliary information to establish which animals in the herd of animals that are considered to be in heat.
10. A method of providing decision support with respect to a herd of animals wherein a respective animal unit (1 01 , 102, 103,
104, 105, 106, 107, 108) is attached to each animal (A1 , A2), the method comprising:
repeatedly emitting a representative signal (S1 , S2) from each animal unit (101 , 102), repeatedly registering a position (P1 , P2) for each animal unit (101 , 102) and/or repeatedly registering acceleration data (a1 , a2) related to the animal (A1 ; A2) to which the unit (101 , 102) is attached
wirelessly reading out information from the set of animal units (1 91 , 102) via a set of data read-out devices (210, 21 1 , 212, 213, 214, 215); and generating entries in a database (230), which entries reflect the information read out from the set of animal units, and
identifying animals potentially in heat based on the entries in the database,
characterized by:
associating a respective time stamp with each entry in the database (230), each entry representing one event concerning an animal in the herd, which event relates to an emitted signal (S 1 , S2), a registered position (P1 , P2) and/or registered acceleration data (a1 , a2),
identifying candidate mounting animals as members of a first group based on the entries in the database (230),
identifying candidate mounted animals as members of a second group of based on the entries in the database (230), and
based on the time stamps, matching the members of the first and second groups with one another to determine any animals potentially in heat, wherein an animal is deemed to be potentially in heat if the animal (A1 ) is estimated to have been mounted by at least one other animal (A2) during a particular in- terval.
1 1 . The method according to claim 10, wherein an animal is deemed to be potentially in heat if and only if the animal (A1 ) is estimated to have been mounted by at least one other animal (A2) during an uninterrupted period of a predefined length.
12. The method according to any one of claims 10 or 1 1 , wherein in each unit in the set of animal units (101 , 102, 103, 104, 105, 106, 107, 1 08) a rate of change of velocity is registered along three independent axes in space.
13. The method according to claim 12, comprising :
identifying a candidate mounting animal (A2) as an animal to which an animal unit (102) is attached where an acceleration vector (a2) has been registered within a first space sector, and identifying a candidate mounted animal (A1 ) as an animal to which an animal unit (101 ) is attached where an acceleration vector (a1 ) has been registered within a second space sector.
14. The method according to any one of claims 10 to 13, comprising emitting, from each unit (101 , 102) in the set of animal units, a wireless signal (S1 , S2) uniquely representing the unit (101 ; 102) within the set of animal units.
15. The method according to claim 14, wherein the set of data read-out devices comprises at least three separate data read-out devices (210, 21 1 , 214, 215) each of which is synchronized to a system time reference, and the method comprises:
receiving the wireless signals (S1 , S2) emitted from the set of animal units (101 , 102) in each of the at least three separate data read-out devices (210, 21 1 , 214, 215), and
deriving a position (P1 , P2) for a particular unit (101 ; 102) in the set of animal units at a specific time instance of the system time reference based on a wireless signal (S 1 , S2) received by at least three of the at least three separate data read-out devices (210, 21 1 , 214, 21 5) at a respective time instance relative to the system time reference.
16. The method according to claim 15, wherein:
an animal (A2) to which an animal unit (102) is attached whose position (P2) is elevated a threshold distance (hE) above a nominal height (hN) at the specific time instance is identified as a candidate mounting animal, and
an animal (A1 ) to which an animal unit (101 ) is attached whose position (P1 ) is within a threshold range (R) from the animal unit (1 02) of a candidate mounting animal (A2) at the specific time instance is identified as a candidate mounted animal.
17. A method of identifying animals in a herd of animals, which identified animals are considered to be in heat, the method comprising:
receiving a preliminary classification concerning two or more animals identified as potentially in heat by the method according to any one of the claims 10 to 16;
receiving auxiliary information concerning the animals in the herd of animals, the auxiliary information describing at least one of: a respective activity level of the animals in the herd, at least one group identifier collectively identifying two or more of the animals in the herd as members of a particular subdivision within the herd, which subdivision is physically restricted from being mixed with animals in the herd that are not members of the particular subdivision, position data linking two or more animals in the herd to a particular location within a specified time period, and a data record describing reproduction data for one or more animals in the herd; and
establishing which animals in the herd of animals that are considered to be in heat by coordinating the preliminary classification with the auxiliary information.
18. A computer program (SW) loadable into the memory (225) of at least one processor (220), comprising software for controlling the steps of any of the claims 10 to 16 or 17 when the program is run on the at least one processor (220).
19. A processor-readable medium (225), having a program recorded thereon, where the program is to make at least one processor (220) control the steps of any of the claims 10 to 16 or 17 when the program is loaded into the at least one processor (220).
PCT/SE2017/050070 2016-01-29 2017-01-26 Decision support system and method of providing decision support with respect to a herd of animals WO2017131575A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP17704325.4A EP3407706A1 (en) 2016-01-29 2017-01-26 Decision support system and method of providing decision support with respect to a herd of animals

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
SE1650118 2016-01-29
SE1650118-1 2016-01-29

Publications (1)

Publication Number Publication Date
WO2017131575A1 true WO2017131575A1 (en) 2017-08-03

Family

ID=58010353

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/SE2017/050070 WO2017131575A1 (en) 2016-01-29 2017-01-26 Decision support system and method of providing decision support with respect to a herd of animals

Country Status (2)

Country Link
EP (1) EP3407706A1 (en)
WO (1) WO2017131575A1 (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2554468A (en) * 2016-09-30 2018-04-04 Moocall Ltd A method, system and apparatus for detecting when an animal is in heat
CN108477069A (en) * 2018-03-05 2018-09-04 广东荷创农牧科技有限公司 Improve the breeding method of sow fertility rate
CN108668944A (en) * 2018-03-14 2018-10-19 魏长同 A kind of device improving sow breeding
WO2020188735A1 (en) * 2019-03-19 2020-09-24 三菱電機ビルテクノサービス株式会社 Bovine monitoring system
US11353539B2 (en) 2018-05-23 2022-06-07 Delaval Holding Ab System for positioning animal tags, method of determining a location of an intermediate basis station and a computer program therefor
US11483678B2 (en) 2018-05-23 2022-10-25 Delaval Holding Ab System, method and computer program for positioning animal tags

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080128486A1 (en) * 2006-11-10 2008-06-05 Breedcare Pty Ltd. Livestock breeding and management system
WO2008113556A1 (en) 2007-03-22 2008-09-25 Faire (Ni) Limited An animal monitoring system and method
WO2009135493A1 (en) 2008-05-05 2009-11-12 Smarter Farming A/S Detection of moving objects
US20110298619A1 (en) * 2008-12-11 2011-12-08 Faire (Ni) Limited Animal monitoring system and method
WO2014067896A1 (en) 2012-10-31 2014-05-08 Gea Farm Technologies Gmbh Computer system for measuring real time position of a plurality of animals
WO2014067897A1 (en) 2012-10-31 2014-05-08 Gea Farm Technologies Gmbh A system and a method for real time detection of the position and behaviour of a plurality of animals
US9119379B1 (en) 2011-10-05 2015-09-01 William B. Yancey Systems and methods for detecting estrus

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080128486A1 (en) * 2006-11-10 2008-06-05 Breedcare Pty Ltd. Livestock breeding and management system
WO2008113556A1 (en) 2007-03-22 2008-09-25 Faire (Ni) Limited An animal monitoring system and method
WO2009135493A1 (en) 2008-05-05 2009-11-12 Smarter Farming A/S Detection of moving objects
US20110298619A1 (en) * 2008-12-11 2011-12-08 Faire (Ni) Limited Animal monitoring system and method
US9119379B1 (en) 2011-10-05 2015-09-01 William B. Yancey Systems and methods for detecting estrus
WO2014067896A1 (en) 2012-10-31 2014-05-08 Gea Farm Technologies Gmbh Computer system for measuring real time position of a plurality of animals
WO2014067897A1 (en) 2012-10-31 2014-05-08 Gea Farm Technologies Gmbh A system and a method for real time detection of the position and behaviour of a plurality of animals

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2554468A (en) * 2016-09-30 2018-04-04 Moocall Ltd A method, system and apparatus for detecting when an animal is in heat
CN108477069A (en) * 2018-03-05 2018-09-04 广东荷创农牧科技有限公司 Improve the breeding method of sow fertility rate
CN108668944A (en) * 2018-03-14 2018-10-19 魏长同 A kind of device improving sow breeding
US11353539B2 (en) 2018-05-23 2022-06-07 Delaval Holding Ab System for positioning animal tags, method of determining a location of an intermediate basis station and a computer program therefor
US11483678B2 (en) 2018-05-23 2022-10-25 Delaval Holding Ab System, method and computer program for positioning animal tags
WO2020188735A1 (en) * 2019-03-19 2020-09-24 三菱電機ビルテクノサービス株式会社 Bovine monitoring system

Also Published As

Publication number Publication date
EP3407706A1 (en) 2018-12-05

Similar Documents

Publication Publication Date Title
WO2017131575A1 (en) Decision support system and method of providing decision support with respect to a herd of animals
US10779753B2 (en) System for analyzing a condition of an animal
US11751537B2 (en) Method for matching a sensor device to an identity (ID) tag for animals and system for performing such method
NL2017104B1 (en) A system for linking an identity of an animal that is in a certain position to information about that animal.
WO2021118442A1 (en) Method and system for tracking position of a livestock animal
WO2010108496A1 (en) System and method for detecting behaviour of animals
US11483678B2 (en) System, method and computer program for positioning animal tags
NL1031625C2 (en) Diagnostic method as well as diagnostic device for an animal identification system, in particular an animal identification system of a milking installation and milking installation with an animal identification system.
WO2008156416A1 (en) Positioning and tracking of animals
WO2019226106A1 (en) Holding area and method executed in a holding area
JP6714726B2 (en) Individual specifying device, individual specifying system, control method of individual specifying device, and control program
CN110286625A (en) A kind of raising Object Management System and management method
US11317595B2 (en) Methods and apparatuses for providing a reference value to be used for controlling the calibration of a milk meter
EP3797312B1 (en) System for positioning animal tags, method of determining a location of an intermediate base station
RU2757683C1 (en) Method for determining the state of estrus of an agricultural animal
EP3681274B1 (en) Animal tag for monitoring animal behavior
WO2017217902A1 (en) Method and arrangement for dairy animal management
CA3222307A1 (en) System for determining a walked distance of an animal within a barn
KR20140105054A (en) RFID based Estrus Detection System for Sow
EP2111100B1 (en) System for detecting an animal passing a defined area in or opposite to a walk-through direction of the area
NZ741825B2 (en) System and method for imaging and processing animal data

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17704325

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2017704325

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2017704325

Country of ref document: EP

Effective date: 20180829