SE2350725A1

SE2350725A1 - Methods and systems for animal keeping

Info

Publication number: SE2350725A1
Application number: SE2350725A
Authority: SE
Inventors: Katja Lindvall; Peg Söderberg
Original assignee: Lindvalls Patentbolag Ab
Priority date: 2023-06-14
Filing date: 2023-06-14
Publication date: 2024-12-15
Also published as: WO2024258338A1

Abstract

Method for controlling livestock functions of a livestock facility including at least one animal box comprising a surface being an endless belt supporting at least one animal and a belt cleaner. The method comprises sensing and obtaining animal environment parameter data using at least one sensor device, collecting animal environment parameter data from the sensor device(s), processing the animal environment parameter data, providing control information using an adaptive trained model of how to control functions of said livestock facility to maximize/optimize at least one animal environment score, determining control commands instructing how to control and adapt livestock functions of the livestock facility based on said processed animal environment parameter data and said control information from said adaptive trained model, and controlling said endless belt and/or belt cleaner by sending control commands thereto in order to maximize/optimize said at least one animal environment score. A corresponding system is also provided.

Description

METHODS AND SYSTEMS FOR ANIMAL KEEPING Technical field The present invention generally relates to the field of animal breeding and for controlling livestock functions of a livestock facility such as a barn including at least one animal box for animal breeding.

Background art Animals need to be kept on a suitable surface that is continuously cleaned. Some kind of bedding material can be continuously strewn over the reclining areas. Some animals require such material to be strewn continuously to give them opportunity for normal behaviour as regards their instinct to root or scratch, for instance. The tending measures for feeding, strewing bedding, Cleaning, etc. are traditionally extremely laborious. As animal production becomes increasingly rationalised, ways have been sought to fully or partially automate this tending. Examples of devices whereby cleaning ofthe ﬂoor is automated are described in SU 1230 559, SU 1327 855, SU 1667 760, SU 1774 845 and SE 508 770. All these publications describe how a stall or animal box is provided with a movable ﬂoor in the form of an endless conveyor belt. This enables animal droppings to be continuously or intermittently removed and bedding can be fed forwards. The devices known through the above publications entail expensive investment in order to connect external systems for supplying energy and suitable drive equipment. Added to this there is the cost ofthe energy supplied. Examples are also known through RU 2038 764, SU 1456 069, SU 1797 798 and SU 1535 483 in which the animals' movement is utilised for tending measures. ln US 7,051,680, an animal keeping device is described where an energy-storage unit supplies energy to drive various functions such as a movable ﬂoor, a scraper, a fodder supply means and a straw feeder. The supply of energy for these functions is controlled by a control unit that receives signals from a program in a microprocessor and also from sensors. ln response to these signals the control unit opens valves, switches a coupling, releases a back wheel ratchet or closes an electric circuit, depending on the type ofthe above-exemplified energy-storage principles applied. The device illustrated by the block diagram is relatively sophisticated and it should be understood that it may be reduced to varying extents as regards functions and method of control.

Hence, there have been attempts to automate and control the environment of the animals in order to address problems associated with poor hygienic conditions associated with conventional animal breeding, in particular pig breeding, with the resulting considerable risk of infection, administration of antibiotics, poor working environment and low animal growth. However, there is still a need within the field for improved systems and methods for animal breeding that provides a holistic approach of the animal environment and animal well-being and offers far-reaching automation of animal tending in a cost-effective manner.

Summary of the invention An object of the present invention is to provide improved methods and systems for animal breeding that provides an adaptive and fully automated control of the animal environment to maximize animal welfare and/or performance and/ or minimize energy consumption and/or operational costs and/ or minimizes negative environmental impact.

The present invention takes on an adaptive and holistic accroach to animal environment by a trained system that provides an adaptive control of functions affecting the animal welfare and environment based on sensor input from the animal environment. The adaptive trained system may be trained how to adapt the functions to continuously optimize the animal environment.

The invention is based on the insight that improvements of at least one ofbarn environment, animal welfare, animal performance, energy consumption, operational costs and environmental impact can be achieved by an adaptive trained system that automatically controls functions in the barn and animal box including the belt drive based on sensor input, and that also continuously adapt the control to optimize the animal environment based on changing environment in the barn and outside the barn. The adaptive trained automatic control is configured to continuously improve and adapt the control of functions in the barn to changing conditions inside and outside the barn. For example, in response to one or more signals indicative of parameters such as animal size, animal behaviour, ammonia level, temperature, cleanliness of ﬂoor, fodder distribution, humidity, water level, etc. The one or more signals can be received either directly from sensors connected to the computer/ PLC / electronic control unit controlling the belt drive, or indirectly via for instance another system for monitoring the barn environment, or indirectly via one or more distributed I /O systems. The sensors may be selected from a group comprising cameras, optical sensors, microphones, monitor/tracking systems (such as RFID systems), and/or 3-D machine vision systems. The sensors may be analog and/or digital.

The present innovation thus relates to a method of controlling animal environment and in specific cases in a barn including animal boxes with rotating conveyors for animal breeding. ln today 's barns with rotating conveyors the problem is that the computer/PLC only have manual setting possibilities. Hence, the cleaning intervals are not changed often enough in order to optimize the animal welfare and performance and minimize energy consumption and operational costs as well as negative environmental impact.

The manual changes are not performed often enough by the user which makes the user choose standard settings that are not adapted to either climate parameters, temperature control, cleanliness ofthe ﬂoor, etc. The user does not have the time to continuously change the settings during the day. Neither does the user have the capability to judge if more cleanings should be performed in order to receive the optimal environment as control devices are needed to measure the need. ln today's application with rotating conveyors no other external devices are connected to the system which excludes the possibilities to receive important data from the other functions of the barn and thereby the possibilities to adapt the cleaning of the rotating ﬂoors in accordance with the actual cleaning need is impossible. By connecting external devices to the computer that drives the rotating ﬂoor, a more accurate analysis of the animals, cleanliness of the rotating ﬂoor and barn environment can be done, and cleaning intervals can be controlled by this data collected by the external devices. Further, optimized cleaning and thereby reduction of ammonia emissions in- and outside the barn in favor for both the environment as well as the farmer's profit making as the exited manure contains higher levels of nitrogen. Lowered energy consumption through the optimized cleaning in favor for both environment as well profit wise. Data from the barn which enables certification of the animal production, the user can show the cleanliness, level of ammonia, amount ofbedding, weight gain ofthe animals, amount of ammonia emissions, etc. This enables a certification that can favor the entire value chain from the user to the end consumer. An increased animal welfare as the environment and conditions in the barn is always optimized in real-time in accordance with the animal's behavior, health and climate situation. Potentially increasing the sales price of the end product due to the certification system as a lower carbon footprint and higher animal welfare can also be obtained.

According to one aspect of the present invention, a method for controlling livestock functions of a livestock facility such as a barn is provided. The livestock facility includes at least one animal box for animal breeding, wherein the animal box comprises a surface supporting at least one animal, wherein the surface is an endless belt intermittently movable in a longitudinal direction of said box, and a belt cleaner arranged to clean said endless belt. The method comprises the steps of sensing and obtaining animal environment parameter data using at least one sensor device; - collecting animal environment parameter data reﬂecting an environment of said at least one animal from said at least one sensor device; - processing said animal environment parameter data; - providing control information using an adaptive trained model of how to control functions of said livestock facility to maximize/optimize at least one animal environment score reﬂecting desired levels of said at least one animal environment parameter; - determining control commands instructing how to control and adapt livestock functions of said livestock facility based on said processed animal environment parameter data and said control information from said adaptive trained model, wherein said livestock functions comprises a motion of said endless belt and/or a cleaning action of said belt cleaner; and - controlling said endless belt and/or belt cleaner by sending control commands to said endless belt to instruct said endless belt to adapt a motion and/or to said belt cleaner to adapt cleaning actions in order to maximize/optimize said at least one animal environment score. ln embodiments, the at least one sensor device may be selected from a group comprising:: - temperature SeIISOFS, - humidity sensors, - camera devices or similar devices for capturing 2D or 3D images or image data including live feed image data as well as infra-red camera devices and/or - devices for capturing or sensing sound such as microphones, - water consumption sensors, - light detection devices, - monitoring/tracking sensors such as RFID sensors/tags, - ammonia detection sensors, - gas sensors for detecting one or more of CO, C02, NOX, CH4 or other gases - optical/optoelectronic/photocell sensors for detecting a position ofthe animal or other objects such as machines, - inductive sensors for detecting a position of the animal or other objects such as machines, - weight sensors/cells for sensing an animal weight, - dust sensors for sensing the dust level in or outside the barn, - air pressure sensors, - air ﬂow sensors, - sensors for detecting outdoor wind force and/or wind direction, - outdoor air pressure sensors, - means for sensing or measuring energy consumption, - means for sensing or measuring water consumption, - motor sensors for detecting rotation or position of motor(s) driving the endless belt or motor(s) actuating a manure removal device (such as a scraper), - wear sensors for detecting wear of motor(s) driving the endless belt or motor(s) actuating a manure removal device (such as a scraper), - invasive or non-invasive sensors such as accelerometers, motion sensors, biometric sensors, biosensors, pedometers, body temperature sensors, heart rate sensors, photoplethysmographic sensors, and - position sensors using the GPS system.

One or more ofthe at least one sensor may be integrated in the animal box (for example weight sensor(s)). One or more ofthe at least one sensor may be of microelectromechanical (MEMS) type. The sensors may be analog and/or digital. ln embodiments, animal environment parameter data includes, for example, fodder level, growth rate of animals, temperature, humidity, manure level, bedding level, cleanliness level, emissions level etc. ln embodiments of the present invention, livestock functions may include endless belt motion and/or belt cleaning and/or fodder distribution and/or bedding distribution and /or temperature level and /or ventilation level and /or manure removal/treatment. ln embodiments ofthe present invention, animal environment score includes a function based on at least one animal environment parameter, e.g. belt cleaning as a function of cleanliness (i.e. x% ofbelt is covered with dung), belt motion as a function of manure level, and/or belt motion as a function of animal position. ln embodiments of the present invention, livestock facility unit comprises, for example, ventilation system, and/ or fodder distribution device, and/or bedding distribution device and/or manure removal/treatment device. ln addition, a function of a livestock facility unit may include increase/decrease ventilation, and/or handling fodder distribution, and/or bedding distribution and/ or handling manure removal/treatment.

According to embodiment of the present invention, the method includes training said adaptive trained model by means of a training system how to adapt functions of said livestock facility to maximize/optimize at least one animal environment score based on collected information from said processing unit including animal environment parameter data and identifying and determining adaptions of functions of livestock facility that maximizes/optimizes said at least one animal environment score in a decision and calculation model of said training system based on animal environment parameter data.

According to still other embodiments, the training comprises applying object detection models using computer vision based decisions and calculations, or applying prediction models using statistical and rule based decisions and calculations, or applying decision models using statistics and rules and historical input data including animal environment parameter data and data from object detection models and/ or prediction models. ln further embodiments ofthe present invention, the method comprises providing command signals to said control unit based on said processed information instructing said control unit how to control said at least one livestock facility unit and providing control commands to said at least one livestock facility unit to instruct respective unit to adapt a function in order to maximize/optimize said at least one animal environment score.

According to embodiments of the present invention, the method further comprising providing information of how to control functions of said livestock facility units to maximize/optimize said at least one animal environment score to said processing unit.

According to embodiment of the present, wherein the method comprises exchanging third party information data with at least one third party interface, and using said third party information data in said processing of animal environment parameter data. Third party information data includes for example weather forecast data, and/or nutrition data of fodder. ln embodiments ofthe present invention, wherein the method comprises exchanging third party information data with at least one third party interface, and maximizing/optimizing at least one animal environment score reﬂecting desired levels of said at least one animal environment parameter based also on received information from said at least one third party interface.

According to another aspect of the present invention, a system for controlling livestock functions of a livestock facility including at least one animal box for animal breeding, said animal box comprises a surface supporting at least one animal, wherein the surface is an endless belt intermittently movable in a longitudinal direction of said box, and a belt cleaner arranged to clean said endless belt. The system comprises a control unit configured to send control commands to control livestock functions of said livestock facility, wherein said livestock functions comprises a motion of said endless belt and/or a cleaning action of said belt cleaner, wherein said control unit communicates with said endless belt and belt cleaner, at least one sensor device arranged to obtain animal environment parameter data reﬂecting an environment of said at least one animal, a processing unit configured to collect animal environment parameter data from said at least one sensor device and to process said animal environment parameter data, wherein said processing unit receives control information from an adaptive trained model of how to control functions of said livestock facility to maximize/optimize at least one animal environment score reﬂecting desired levels of said at least one animal environment parameter;, wherein said processing unit is further configured to send command signals to said control unit instructing said control unit how to control and adapt said livestock functions of said livestock facility based on said processed animal environment parameter data and said control information from said adaptive trained model; and wherein said control unit, based on control information of said adaptive trained model and command signals from said processing unit, sends control commands to said endless belt to instruct said endless belt to adapt a motion and/or to said belt cleaner to adapt cleaning actions in order to maximize/optimize said at least one animal environment score.

According to embodiments of the present invention, the adaptive trained model is trained by means of a training system how to adapt functions of said livestock facility to maximize/optimize at least one animal environment score based on collected information from said processing unit including animal environment parameter data, wherein said training system comprises a decision and calculation model configured to use animal environment parameter data for identifying and determining adaptions of functions of livestock facility that maximizes/optimizes said at least one animal environment score. ln embodiments ofthe present invention, the training system comprises a decision and calculation model including at least one of object detection models using computer vision based decisions and calculations, prediction models using statistical and rule based decisions and calculations, or decision models using statistics and rules and historical input data including animal environment parameter data and data from object detection models and/or prediction models. ln further embodiments of the present invention, the control unit communicates with at least one livestock facility unit arranged in said livestock facility to control functions of said at least one livestock facility unit, wherein said processing unit is configured to, based on said processed information, send command signals to said control unit instructing said control unit how to control said at least one livestock facility unit and wherein said control unit sends control commands to said at least one livestock facility unit to instruct respective unit to adapt a function in order to maximize/optimize said at least one animal environment score.

Furthermore, in embodiments of the present invention, the adaptive trained model is configured to provide information of how to control functions of said livestock facility units to maximize/optimize said at least one animal environment score to said processing unit.

According to embodiments ofthe present invention, the processing unit is configured to communicate with at least one third party interface, to exchange third party information data, and to use said third party information data in said processing of animal environment parameter data. ln yet other embodiments of the present invention, the adaptive trained model is configured to communicate with at least one third party interface, to exchange third party information data, and to maximize/optimize at least one animal environment score reﬂecting desired levels of said at least one animal environment parameter based also on received information from said at least one third party interface.

According to still other embodiments of the present invention, the at least one sensor unit comprises a camera device configured to capture images data of said at least one animal box and/or said livestock facility, wherein said animal environment parameter data comprises image data from said at least one camera device.

Moreover, in further embodiments ofthe present invention, the at least one camera device includes an infra-red camera device. ln further embodiments, the surface including an endless belt intermittently movable in a longitudinal direction ofthe animal box comprises sensor devices. For example, sensors for measuring the pressure or weight on the endless belt may be included. Furthermore, sensors for detecting movements may be included in the endless belt.

Yet other embodiments ofthe present invention, analysis can be made of gathered data or information. For example, measurements of presence of antibiotics and/ or pathogens can be used to provide information to certification procedures. Other examples, are to utilize nutrition data from fodder to analyze and optimize fodder distribution.

As the skilled person realizes, steps ofthe methods according to the present invention, as well as preferred embodiments thereof, are suitable to realize as computer program or as a computer readable medium.

Generally, all terms used in the claims and description are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a/an/the [element, device, component, unit, means, step, etc.]" are to be interpreted openly as referring to at least one instance of the element, device, component, unit, means, step, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed unless explicitly defined otherwise herein.

Further objects and advantages of the present invention will be discussed below by means of exemplifying embodiments.

Brief description of the drawings Exemplifying embodiments ofthe invention will be described below with reference to the accompanying drawings, in which: Fig. 1 is a schematic block diagram of one embodiment of a system for controlling livestock functions of a livestock facility according to the present invention; Fig. 2 is a general high-level description of a method according to one embodiment ofthe present invention; Fig. 3 is a schematic block diagram of another embodiment of a system for controlling livestock functions of a livestock facility according to the present invention; Fig. 4 is a schematic block diagram of one embodiment of a control software for a system for controlling livestock functions of a livestock facility according to the present invention.

Fig. 5 schematically illustrates an embodiment of a control sequence according to the present invention.

Fig. 6 schematically illustrates a further embodiment of a control sequence according to the present invention.

Fig. 7 schematically illustrates another embodiment of a control sequence according to the present invention.

Fig. 8 schematically illustrates yet another embodiment of a control sequence according to the present invention.

Fig. 9 schematically illustrates still another embodiment of a control sequence according to the present invention. 11 Description of exemplifying embodiments The following is a description of exemplifying embodiments in accordance with the present invention. This description is not to be taken in limiting sense, but is made merely for the purposes of describing the general principles ofthe invention. Even though particular types of probes including micro-invasive as well as non-invasive will be described, the invention is also applicable to other types of such as invasive probes.

Thus, preferred embodiments of the present invention will now be described for the purpose of exemplification with reference to the accompanying drawings, wherein like numerals indicate the same elements throughout the views. lt should be understood that the present invention encompasses other exemplary embodiments that comprise combinations of features as described in the following. Additionally, other exemplary embodiments ofthe present invention are defined in the appended claims. ln accordance with a first and general embodiment of the present invention, a system 100 for controlling livestock functions of a livestock facility 101, such as a barn or similar, including at least one animal box 102, 103 for animal breeding will be described with reference to Fig. 1. The system 100 for controlling livestock functions of a livestock facility 101 including at least one animal box 102, 103 for animal breeding. Preferred embodiments ofthe animal box 102, 103 are described in patent publication EP 0 973 378 B1. Generally, the animal box 102, 103 comprises a surface supporting at least one animal 104, 105, where the surface is an endless belt 106, 107 intermittently movable in a longitudinal direction ofthe box. Furthermore, a belt cleaner 108, 109 is arranged to clean the endless belt 106, 107. Preferred embodiments ofthe belt cleaner 108, 109 is described in patent publication EP 1 377 158 B1. On a high and general level the system 100 comprises: - A control unit 110 configured to send control commands to control livestock functions of the livestock facility 101, wherein the livestock functions comprises a motion ofthe endless belt 106, 107 and/or a cleaning action of the belt cleaner 108, 109. The control unit 110 communicates with the endless belt 106, 107 and belt cleaner 108, 109. The control unit 110 may for example communicate with the endless belt 106, 107 and the belt cleaner 108, 109 via a wired or wireless connection. 12 - At least one sensor device 111, 112, 113 arranged to obtain animal environment parameter data reﬂecting an environment of the at least one animal 104, 105. The at least one sensor device 111, 112, 113 may, for example, comprise of a camera device, temperature sensor, ammonia sensor, humidity sensor, carbon dioxide sensor, microphone and/or any other suitable sensing device able to obtain animal environment parameter data reﬂecting an environment of the at least one animal 104, 105.

- A processing unit 114 configured to collect animal environment parameter data from the at least one sensor device 111, 112, 113 and to process the animal environment parameter data.

- An adaptive trained model 115 configured to communicate control information to the processing unit 114, wherein the control information comprises instruction of how to control functions of the livestock facility 101 to maximize/optimize at least one animal environment parameter.

Wherein the processing unit 114 is further configured to send command signals to the control unit 110 instructing the control unit 110 how to control and adapt the livestock functions ofthe livestock facility 101 based on the processed animal environment parameter data and the control information from the adaptive trained model 115. ln Fig. 1 the processing unit 114 is illustrated as being arranged in a local unit 115, however the function of processing unit 114, or part ofthe functions of the processing unit, may be arranged to run in a cloud environment 118. For example, unprocessed animal environment parameter data from the sensor device 111, 112, 113 may be pre- processed by a processing unit arranged in the local unit 115, and further processed and combined with the control information by a processing unit arranged in the cloud environment 118. How much is processed locally versus in a cloud environment may, for example, be adapted to: the size/volume of unprocessed animal parameter data, the required processing capacity ofthe processing unit, as well as the speed and stability of the internet connection of the local unit 1 15.

The control unit 110 is further configured to send control commands based on control information of the adaptive trained model 115 and command signals from the processing unit 114. The control commands are at least sent to the endless belt 106, 107 13 to instruct the endless belt 106, 107 to adapt a motion and/or to the belt cleaner 108, 109 to adapt cleaning actions in order to maximize/optimize the at least one animal environment score. Control commands could further be sent to other animal facility functions such as a fodder distributer, ventilation system, lightning system and/ or other animal facility functions which affect the animal environment.

The system 100, may further comprise a training system 116 which is adapted to train models 117. Models 117 may include object detection models or computer vision models for handling image data, and/or prediction based models based on statistical models to predict behavior, situations, events etc., and/ or decision models for decision based on historical data and/ or rules how to respond to certain input. The adaptive trained model 115, training system 116 and models 117 may be arranged in a cloud environment 118 as shown in figure 1, or may be arranged in the local unit 115.

According to embodiments ofthe present invention, the sensor device 111, 112, 113 may include any one of the following, or a combination of any one ofthe following sensor devices: Temperature sensor: This sensor may be arranged inside the livestock facility 101, or outside, or on both locations. The temperature may be observed, measured and collected inside and/or outside the livestock facility 101. For example, the temperature may be used to observe and inﬂuence a behavior ofthe animals 104, 105 and cleanliness ofthe animal box 102, 103. This sensor may be part of a third party equipment communicating with the system 100 ofthe present invention or may be a part ofthe system 100 ofthe present invention.

Humidity sensor: This sensor may be arranged inside the livestock facility 101, or outside, or on both locations. The humidity may be observed, measured and collected inside and/or outside the livestock facility 101. For example, the humidity may be used to observe and inﬂuence a behavior ofthe animals 104, 105 and cleanliness of the animal box 102, 103. This sensor may be part of a third party equipment communicating with the system 100 ofthe present invention or may be a part ofthe system 100 ofthe present invention. 14 Carbon dioxide sensor: A level of carbon dioxide may be measured, registered and collected inside the livestock facility 101. For example, a separate sensor may be used, or a sensor of a third party equipment (e.g. the ventilation system) may be used. The carbon dioxide level or amount can be used to observe, and control the ventilation system, for example, in combination with other sensor data such as temperature and/or ammonia. This sensor may be part of a third party equipment communicating with the system 100 ofthe present invention or may be a part of the system 100 ofthe present invention.

Ammonia sensor: The ammonia level can be measured, registered, and collected inside the livestock facility 101. For example, the ammonia level may be used to control cleaning, and/or ventilation and/or fodder distribution when a certain level is reached or exceeded. ln one embodiment ofthe present invention, one control sequence can be executed as follows. The animals 104, 105 are getting too warm at a certain temperature level (e.g. 24 degrees Celsius) in combination with a certain level of humidity. The behavior ofthe animals 104, 105 is then a need for cooling down which is illustrated in that the animals 104, 105 lay down in a moisture part of the animal box 102, 103. That is, the dirty end of the animal box 102, 103. The fact that the animals 104, 105 are laying down in the dirty end can be registered by for example a camera device. The livestock function that is controlled and adapted can be increase ventilation and/or initiate a showering process in a water distribution system. These systems, i.e. the ventilation and water distribution system, may be third party equipment communicating with the system 100 ofthe present invention, or may be a part ofthe system 100. Furthermore, this sensor may be part of a third party equipment communicating with the system 100 ofthe present invention or may be a part of the system 100 ofthe present invention.

Camera device: A camera device may be arranged to register, gather and collect image data. The camera device may be designed for visible wavelengths and/or infra-red wavelengths, or several cameras may be used, for different wavelengths and locations. For example, a camera device may be used to identify that a certain percentage of part of the surface in the animal box 102, 103 is dirty (i.e. covered with dirty bedding, feces or other types of dirt) and this may trigger a cleaning process or action. Further, the image data may be used to observe and identify a growth ofthe animals 104, 105. The growth data may be used to, for example, to trigger third party equipment such as a fodder distribution device to adapt a fodder distribution, and/ or to provide information to a slaughterhouse whether an animal is ready for slaughter. As mentioned above, the image data may be used to identify whether the animals 104, 105 are laying in a dirty part ofthe animal box 102, 103, which is an indication of overheated animals. This may in turn trigger an increase of the ventilation by communicating with the ventilation system, which often is a third party equipment. The image data may also be used to observe and register a behavior/activity of the animals 104, 105. This may in turn be used to indicate for example illness of an animal. A prolonged low activity or absence of activity may be a sign or indication of illness, which may trigger an alarm function. If infra-red image data is collected, this can be used to measure a temperature of the animals 104, 105. If a temperature exceeds a certain level, this may indicate illness, which may in turn trigger an alarm function. Furthermore, the image data may be used to identify behavior disturbances or misbehavior such as tail-biting behavior of the animals 104, 105, which may trigger an alarm function and/or livestock functions such as increasing a bedding distribution to the animal box 102, 103. The image data also be used to provide security data, for example, that an animal is not moving too close to , or gets stuck, in an output end of the animal box 102, 103. Image data may also be used to further function such as identifying a number of animals 104, 105 in an animal box 102, 103.

RFID: A RFID tag may be used to identify and track animals 104, 105 inside the animal boxes 102, 103. For example, RFID tags enables for identification of animals 104, 105 and to track the animals 104, 105 movements within the animal boxes 102, 103. This may in turn be used to determine how many animals 104, 105 are positioned in each animal box 102, 103 at any given time as well as how much each individual animal 104, 105 has eaten or moved. A prolonged low activity or absence of activity, as well as low fodder consumption may be a sign o indication of illness, which may trigger an alarm function. Furthermore, RFID tags can be used to store additional information about the animals 104, 105, such as weight, age, sex, birthing time, offspring and medical records. Furthermore, the RFID tag and accompanying reader may be part of a third party equipment communicating with the system 100 ofthe present invention or may be a part of the system 100 of the present invention. 16 Water and/or fodder consumption sensor: A water and/or fodder consumption sensor may measure, register, and collect data indicating amount of water and/or fodder consumed by the animals 104, 105 inside the animal box 102, 103. For example, the amount ofwater and/or fodder consumed by the animals 104, 105 may be used to predict the amount of future waste and consequently the amount ofbedding and/or cleaning required in the close future. Further, the water and/ or fodder consumption may be adapted as to measure the animals 104, 105 individual consumption of water and/or fodder, in which case the individual water and/or fodder consumption may be used to identify illness resulting in the animals 104, 105 not eating and/or drinking correctly. Furthermore, this sensor may be part of a third party equipment communicating with the system 100 ofthe present invention or may be a part ofthe system 100 ofthe present invention.

Microphone: A microphone may be arranged as to register, gather and collect noise recordings ofthe animals 104, 105. For example, a microphone may be used to identify an emergency, such as an injury, and/or general unwellness, such as an illness, causing the animals 104, 105 to make excessive noise, high pitch noises or other noises indicating an emergency or general unwellness. An identified emergency or general unwellness may trigger an alarm function. Furthermore, this sensor may be part of a third party equipment communicating with the system 100 of the present invention or may be a part ofthe system 100 of the present invention.

Light level sensor: The light level can be measured, registered, and collected inside the livestock facility 101. For example, the light level may be used to control the lightning and/or other livestock functions inside the livestock facility 101. A light level sensor may for example be used to enable the livestock facility 101 to save energy by utilizing both natural and artificial light while ensuring the animals 104, 105 do not receive too much or too little light. The light level sensor may also be used in combination with other sensors, such as a fodder consumption sensor and camera device, to derive insights into animal behavior and optimize the environment in the animal boxes 102, 103. Some animals might for example benefit from a dimmer light after feeding as to encourage rest and relaxation. Furthermore, this sensor may be part of a third party equipment communicating with the system 100 ofthe present invention or may be a part of the system 100 of the present invention. 17 Turning now to Fig. 2, a general high-level description of a method according to one embodiment of the present invention will be given.

Fig. 2 illustrates a method for controlling livestock functions of a livestock facility including at least one animal box comprising a surface supporting at least one animal. The surface according to the proposed method is an endless belt intermittently movable in a longitudinal direction of the box. The livestock functions further comprise a belt cleaner arranged to clean the endless belt. The proposed method according to one embodiment illustrated in fig. 2 comprises the steps of: - sensing and obtaining animal environment parameter data S10 using at least one sensor device; - collecting and processing animal environment parameter data S21 reﬂecting an environment ofthe at least one animal from the at least one sensor device; - providing control information S22 using an adaptive trained model of how to control functions of the livestock facility to maximize/optimize at least one animal environment score reﬂecting desired levels ofthe at least one animal environment parameter; - determining control commands S30 instructing how to control and adapt livestock functions ofthe livestock facility based on the processed animal environment parameter data and the control information from the adaptive trained model, wherein the livestock functions comprises at least a motion ofthe endless belt and/or a cleaning action ofthe belt cleaner; - controlling the endless belt and/or belt cleaner S40 by sending control commands to the endless belt to instruct the endless belt to adapt a motion and/or to the belt cleaner to adapt cleaning actions in order to maximize/optimize the at least one animal GIIVlFOIIITIGIIt SCOFG] - evaluate the controlling action based on animal environment parameter data obtained during the controlling ofthe endless belt and/or belt cleaner S50, and if the controlling action has a undesirable effect: interrupt the process S60, otherwise; 18 - repeat the method starting with step of sensing and obtaining animal environment parameter data S10.

With reference now to Fig. 3, a further embodiment ofa system 200 of the present invention will be described. A control unit 201 configured to send control commands to control livestock functions of the livestock facility 203, wherein the livestock functions comprises at least a motion ofthe endless belt 230 and/or a cleaning action ofthe belt cleaner 223 arranged in an animal box 202 housing at least one animal 232. Further, the control unit 201 may be configured to collect animal environment parameter data from different sensor devices 204 arranged in or outside the livestock facility 203. The control unit 201 communicates with a computer system 205, which may be located locally. The computer system 205 comprises a processing unit or processor 206, local storage 207, and local control software 208. The computer system 205 may be arranged to communicate directly with sensor devices 204, or via the control unit 201 with a sensor data unit 209. ln addition, the computer system 205 comprises a third party interface 210 configured to communicate, for example, with third party equipment 211 such as ventilation system, fodder distribution device etc. Further, the computer system 205 comprises a network interface 212 for communication with, for example, the control unit 201. Moreover, the computer system 205 may comprise further interface 213 for communication with a user interface 226 comprising, for example, a user for data visualization 214 and/or system settings 215, and/or alarm function 216. The computer system 205 may further communicate with a control software 220 including, for example, an adaptive trained model 221 and training system 222. The training system 222 may be based on machine-learning models, rule-based systems and/or artificial intelligence. Models 227 include object detection models or computer vision models for handling image data, and/or prediction based models based on statistical models to predict behavior, situations, events etc., and/ or decision models for decision based on historical data and/or rules how to respond to certain input. Furthermore, the control software 220 may further include storage 223, which may store the adaptive trained model 221, as well as, sensor data 224. Further, a third party interface 225 may be arranged to communicate with third party systems or equipment 226. The computer system 205 and controller unit 201 may be part ofa local unit 228 as shown in figure 3. 19 The control software 220 may be running on a cloud environment 229 as shown in figure 3, or may be part ofthe local unit 228.

With reference now to Fig. 4, a further embodiment of a control software 301 ofthe present invention will be described. The control software 301 may comprise a client specific module 302 and a shared module 303. The shared module 303 may comprise a training system 304 which may be based on machine-learning models, rule-based systems and/or artificial intelligence, the training system 304 may further comprise models 314 which may include object detection models or computer vision models for handling image data, and/or prediction based models based on statistical models to predict behavior, situations, events etc., and/ or decision models for decision based on historical data and/or rules how to respond to certain input. The shared module 303 may further comprise a third party interface 306 and certification portal 307 for communicating with external parties 313. The certification portal 307 may in another embodiment be arranged in the client specific module 302. ln the embodiment illustrated in fig. 4 the shared module also comprises a storage 304 which may for example store model predictions and decision logic and/or sensor data for training and/ or for communicating to the third party interface 306 and/or certification portal 307. Collected data can, for example, be used for certifying parameters such as animal health, animal environment, animal handling, fodder consumption, and/ or bedding consumption and/or water consumption. The client specific module 302 may comprise the adaptive trained module 308 and storage 309 for storing, for example, sensor data 310 and/or model predictions and decision logic 311 configured to collect sensor data from the local computer system 312 and to send control data to the computer system 312 based on data and decisions from the adaptive trained module 308.

Turning now to Fig. 5 which illustrates a possible control sequence of the proposed system. The control sequence illustrated in Fig. 5 comprises the steps of: - Sensing and obtaining animal environment parameter data S110 using a temperature sensor, a humidity sensor and a camera device.

- Obtain a temperature S111 and humidity level S112 and estimate experienced temperature level by animals in the animal facility. Different animals may have different resilience towards high temperatures or humidity levels. The proposed system adapts according to which kind of animal is housed in the animal facility. lf the estimated experienced temperature level is above, or nearly above, a preferred level the system may obtain additional information from, for example a camera device which is arranged as to determine animal position and/or behavior disturbance S114. For example, if animals are overheated they may cease moving and/or seek to cool themselves by laying down in a damp part of the animal box, meaning the dirty end ofthe box. ln some cases other sensor device could be used to obtain further indication of overheating, for example a microphone which identifies panting.

- A possible action following the identification of high temperature and/ or overheated animals could be to increase ventilation and/or turn on a showering unit S120 arranged to shower the animals.

- Evaluate the controlling action based on animal environment parameter data obtained during the controlling ofthe ventilation and/or showering unit S130, and if the controlling action has an undesirable effect: interrupt the process S140, otherwise; - repeat the method starting with step of sensing and obtaining animal environment parameter data S110.

Fig. 6 illustrates another possible control sequence ofthe proposed system comprising the steps: - Sensing and obtaining animal environment parameter data S210 using at least a camera device.

- Estimate the growth/size of the at least one animal S220 based on data from the camera device. The growth/size of the at least one animal may for example be estimated using machine learning models or any other suitable image analysis method.

- The system may then adapt to the estimated growth/size of the at least one animals by, for example, adapting the cleaning interval S231 or fodder distribution S232. Larger animals may for example require more cleaning and/or fodder than smaller animals. ln some embodiments ofthe present invention the proposed system comprises a third party interface. Fig. 7 illustrates a possible sequence wherein a third party interface 21 obtains a weather forecast to optimize the animal environment. The sequence comprises the steps: - Obtain a weather forecast S310 and based on the weather forecast; - estimate future bedding usage S320. For example, if the weather forecast indicates 24 degrees Celsius and rain in two days, and the system has observed that these conditions indicate increased generation of feces and/or urine for the kind of animal currently housed in the animal facility, the estimated future bedding usage is higher than a baseline usage ofbedding.

- A possible action following the estimation of future bedding usage might be to compare the estimation to current inventory levels of bedding 330. Current inventory levels could for example be obtained by subtracting the used amount of bedding from the purchased amount ofbedding, wherein the purchased amount ofbedding may be obtained through the third party interface communicating with the bedding supplier. lf the current bedding inventory isn't sufficient for future requirements the system may; - notify the user S341 and/or notify the bedding supplier S342. The system may be further configured to automatically order additional bedding according to estimated future needs.

Fig. 8 illustrates a sequence wherein data is aggregated to create useful insight for the user and/or other actors parts ofthe value chain, such as a farmer or manure/fertilizer distributer. The illustrated sequence comprises the steps of: - Sensing and obtaining animal environment parameter data S410 using at least a ammonia sensor.

- Obtain ammonia level data S411 and fodder consumption data S412. Fodder consumption data may for example be obtained by measuring the volume and/ or weight of fodder served to the animals, or by manually entering a amount of fodder consumption in a user interface.

- Obtain fodder composition data S420 indicating the composition ofthe fodder served to the animals. Fodder consumption data S420 might for example be obtained through a 22 third party interface communicating with a fodder supplier or by manually entering fodder composition data in the user interface.

- Estimating amount of nutrient (nitrogen for example) in manure S430. For example, the amount of ammonia in manure could be estimated by subtracting the amount of ammonia which has left via ammonia emissions from the ammonia available in the fodder. The amount of ammonia that has left via emission can for example be obtained from ammonia level data.

-The amount of nutrients in the manure may then be communicated to the user S441 and/or a manure purchaser/supplier and/or other external parties. Additionally, by predicting the quantity and composition of manure, including its ammonia level, it is possible to determine the appropriate amount of fertilizer to be applied to a specific plot of arable land. This information can also be utilized to optimize supply chain management.

Fig. 9 illustrates another sequence wherein data is aggregated to create useful insight for the user or other actors, such as a certifier and/or a butcher. The illustrated sequence comprises the steps of: - Sensing and obtaining animal environment parameter data S510 using at least a camera device and ammonia sensor. - Obtain footage of at least one animal in the animal facility S511.

- Obtain ammonia level data S512, fodder consumption data 513 and bedding usage data S514, and may be based on the data; - estimate an environmental impact score S520. For example, an environmental impact score may be expressed as a Global Warming Potential (GWP) score, or a carbon dioxide equivalent score, commonly referred to as CO footprint.

- Communicate the environmental impact score and footage of animal living condition to the user S532 and/or an external party S531, such as a slaughterhouse, a government organization or a certifier. The proposed sequence enables for government organization and/ or certifiers to obtain reliable and unbiased data in regard to ammoniac emissions 23 and/ or animal welfare. lt may furthermore allow for a slaughterhouse to increase transparency towards consumer and/ or to determine acquisition price even before receiving the animal.

The hardware components of control unit, control software and computer systems may include one or more computers (e.g., general purpose computers, workstations, servers, terminals, portable /mobile devices, etc.) ; processor devices (e.g., central processing units (CPUs), graphics processing units (GPUs), microprocessors, digital signal processors (DSPs), field programmable gate arrays (FPGAs), special- purpose or specially-designed processors, etc.); memory/storage devices (e.g., read-only memories (ROMs), random access memories (RAMs), ﬂash memories, hard drives, optical disks, solid-state drives (SSDs), etc.); input devices (e.g., keyboards, mice, touch screens, mics, buttons, knobs, trackballs, levers, handles, joysticks, etc.) ; output devices (e.g., displays, printers, speakers, vibration devices, etc.) ; or other suitable hardware. The software components of control console 210 may include operation system software, application software, etc. For example, as shown in FIG. 3, computer system 205 and control software 220 includes computer structures or software that may be stored in a memory/storage 207 and/or 223. The software may include computer readable and executable codes or instructions for performing the processes described in detail in this application. For example, a processing unit 206 may be communicatively connected to a memory/storage storing software to access and execute the codes or instructions. The execution of the codes or instructions may cause the processor device 218 to perform operations to achieve one or more functions consistent with the disclosed embodiments. Various operations or functions are described herein, which may be implemented or defined as software code or instructions. Such content may be directly executable ("object" or "executable" form), source code, or difference code ("delta" or "patch" code). Software implementations ofthe embodiments described herein may be provided via an article of manufacture with the code or instructions stored thereon, or via a method of operating a communication interface to send data via the communication interface. A machine or computer readable storage medium may cause a machine to perform the functions or operations described, and includes any mechanism that stores information in a form accessible by a machine (e.g., computing device, electronic system, and the like), such as recordable/non-recordable media (e.g., 24 read only memory (ROM), random access memory (RAM), magnetic disk storage media, optical storage media, flash memory devices, and the like). A communication interface includes any mechanism that interfaces to any of a hardwired, wireless, optical, and the like, medium to communicate to another device, such as a memory bus interface, a processor bus interface, an Internet connection, a disk controller, and the like. The communication interface can be configured by providing configuration parameters and/ or sending signals to prepare the communication interface to provide a data signal describing the software content. The communication interface can be accessed via one or more commands or signals sent to the communication interface.

The present disclosure also relates to systems for performing the operations described herein. This system may be specially constructed for the required purposes, or it may comprise a general-purpose computer selectively activated or reconfigured by a computer program stored in the computer. Such a computer program may be stored in a computer readable storage medium, such as, but not limited to, any type of disk including ﬂoppy disks, optical disks, CDROMs, and magnetic-optical disks, read-only memories (ROMs), random access memories (RAMs), EPROMs, EEPROMs, magnetic or optical cards, or any type of media suitable for storing electronic instructions, each coupled to a computer system bus.

The order of execution or performance ofthe operations in embodiments ofthe present disclosure illustrated and described herein is not essential, unless otherwise specified. That is, the operations may be performed in any order, unless otherwise specified, and embodiments ofthe present disclosure may include additional or fewer operations than those disclosed herein. For example, it is contemplated that executing or performing a particular operation before, contemporaneously with, or after another operation is within the scope of aspects ofthe present disclosure.

Embodiments ofthe present disclosure may be implemented with computer- executable instructions. The computer-executable instructions may be organized into one or more computer-executable components or modules. Aspects ofthe present disclosure may be implemented with any number and organization of such components or modules. For example, aspects ofthe present disclosure are not limited to the specific computer-executable instructions or the specific components or modules illustrated in the figures and described herein. Other embodiments ofthe present disclosure may include different computer-executable instructions or components having more or less functionality than illustrated and described herein.

When introducing elements of aspects ofthe present disclosure or the embodiments thereof, the articles "a," "an," "the," and "said" are intended to mean that there are one or more ofthe elements. The terms "comprising," "including," and "having" are intended to be inclusive and mean that there may be additional elements other than the listed elements.

Having described aspects ofthe present disclosure in detail, it will be apparent that modifications and variations are possible without departing from the scope of aspects ofthe present disclosure as defined in the appended claims. As various changes could be made in the above constructions, products, and methods without departing from the scope of aspects ofthe present disclosure, it is intended that all matter contained in the above description and shown in the accompanying drawings shall be interpreted as illustrative and not in a limiting sense. lt is to be understood that in the context ofthe present invention and in relation to electrical components electrically connected to each other, the term connected is not limited to mean directly connected, but also encompasses functional connections having intermediate components. For example, on one hand, if an output of a first component is connected to an input of a second component, this comprises a direct connection. On the other hand, if an electrical conductor directly supplies a signal from the output of the first component substantially unchanged to the input of the second component, alternatively via one or more additional components, the first and second components are also connected. However, the connection is functional in the sense that a gradual or sudden change in the signal from the output ofthe first component results in a corresponding or modified change in the signal that is input to the second component.

Although exemplary embodiments of the present invention have been shown and described, it will be apparent to those having ordinary skill in the art that a number of changes, modifications, or alterations to the inventions as described herein may be made. Thus, it is to be understood that the above description ofthe invention and the accompanying drawings is to be regarded as a non-limiting example thereof and that the scope of protection is defined by the appended patent claims.

Claims

1. A method for controlling livestock functions of a livestock facility including at least one animal box for animal breeding, said animal box comprises a surface supporting at least one animal, wherein the surface is an endless belt intermittently movable in a longitudinal direction of said box, and a belt cleaner arranged to clean said endless belt, said method comprising the steps of: sensing and obtaining animal environment parameter data using at least one sensor device; - collecting animal environment parameter data reﬂecting an environment of said at least one animal from said at least one sensor device; - processing said animal environment parameter data; - providing control information using an adaptive trained model of how to control functions of said livestock facility to maximize/optimize at least one animal environment score reﬂecting desired levels of said at least one animal environment parameter; - determining control commands instructing how to control and adapt livestock functions of said livestock facility based on said processed animal environment parameter data and said control information from said adaptive trained model, wherein said livestock functions comprises a motion of said endless belt and/or a cleaning action of said belt cleaner; and - controlling said endless belt and/or belt cleaner by sending control commands to said endless belt to instruct said endless belt to adapt a motion and/or to said belt cleaner to adapt cleaning actions in order to maximize/optimize said at least one animal environment score.

2. The method according to claim 1, training said adaptive trained model by means of a training system how to adapt functions of said livestock facility to maximize/optimize at least one animal environment score based on collected information from said processing unit including animal environment parameter data and identifying and determining adaptions of functions of livestock facility that maximizes/optimizes said at least one animal environment score in adecision and calculation model of said training system based on animal environment parameter data.

3. The method according to claim 1, wherein said training comprises applying object detection models using computer vision based decisions and calculations, or applying prediction models using statistical and rule based decisions and calculations, or applying decision models using statistics and rules and historical input data including animal environment parameter data and data from object detection models and/or prediction models.

4. The method according to claim 1, further comprising providing command signals to said control unit based on said processed information instructing said control unit how to control said at least one livestock facility unit and providing control commands to said at least one livestock facility unit to instruct respective unit to adapt a function in order to maximize/optimize said at least one animal GIIVlFOIIITIEIIt SCOTG.

5. The method according to claim 1, further comprising providing information of how to control functions of said livestock facility units to maximize/optimize said at least one animal environment score to said processing unit.

6. The method according to claim 1, further comprising exchanging third party information data with at least one third party interface, and using said third party information data in said processing of animal environment parameter data.

7. The system according to claim 1, further comprising exchanging third party information data with at least one third party interface, and maximizing/optimizing at least one animal environment score reﬂecting desired levels of said at least one animal environment parameter based also on received information from said at least one third party interface.

8. A system for controlling livestock functions of a livestock facility including at least one animal box for animal breeding, said animal box comprises a surfacesupporting at least one animal, wherein the surface is an endless belt intermittently movable in a longitudinal direction of said box, and a belt cleaner arranged to clean said endless belt, said system comprising: - a control unit configured to send control commands to control livestock functions of said livestock facility, wherein said livestock functions comprises a motion of said endless belt and/or a cleaning action of said belt cleaner, wherein said control unit communicates with said endless belt and belt cleaner; - at least one sensor device arranged to obtain animal environment parameter data reﬂecting an environment of said at least one animal; - a processing unit configured to collect animal environment parameter data from said at least one sensor device and to process said animal environment parameter data; - wherein said processing unit receives control information from an adaptive trained model of how to control functions of said livestock facility to maximize/optimize at least one animal environment score reﬂecting desired levels of said at least one animal environment parameter; - wherein said processing unit is further configured to send command signals to said control unit instructing said control unit how to control and adapt said livestock functions of said livestock facility based on said processed animal environment parameter data and said control information from said adaptive trained model; and - wherein said control unit, based on control information of said adaptive trained model and command signals from said processing unit, sends control commands to said endless belt to instruct said endless belt to adapt a motion and/or to said belt cleaner to adapt cleaning actions in order to maximize/optimize said at least one animal environment score.

9. The system according to claim 8, wherein said adaptive trained model is trained by means of a training system how to adapt functions of said livestock facility to maximize/optimize at least one animal environment score based on collected information from said processing unit including animal environment parameter data, wherein said training system comprises a decision and calculation modelconfigured to use animal environment parameter data for identifying and determining adaptions of functions of livestock facility that maximizes/optimizes said at least one animal environment score.

10. The system according to claim 8, wherein said training system comprises a decision and calculation model including at least one of object detection models using computer vision based decisions and calculations, prediction models using statistical and rule based decisions and calculations, or decision models using statistics and rules and historical input data including animal environment parameter data and data from object detection models and/or prediction models.

11. The system according to claim 8, wherein said control unit communicates with at least one livestock facility unit arranged in said livestock facility to control functions of said at least one livestock facility unit, wherein said processing unit is configured to, based on said processed information, send command signals to said control unit instructing said control unit how to control said at least one livestock facility unit and wherein said control unit sends control commands to said at least one livestock facility unit to instruct respective unit to adapt a function in order to maximize/optimize said at least one animal environment SCOTG.

12. The system according to claim 8, wherein said adaptive trained model is configured to provide information of how to control functions of said livestock facility units to maximize/optimize said at least one animal environment score to said processing unit.

13. The system according to claim 8, wherein said processing unit is configured to communicate with at least one third party interface, to exchange third party information data, and to use said third party information data in said processing of animal environment parameter data.

14. The system according to claim 8, wherein said adaptive trained model is configured to communicate with at least one third party interface, to exchange third party information data, and to maximize/optimize at least one animal environment score reﬂecting desired levels of said at least one animal environment parameter based also on received information from said at least one third party interface.

15. The system according to claim 8, wherein said at least sensor unit comprises a camera device configured to capture images data of said at least one animal box and/ or said livestock facility, wherein said animal environment parameter data comprises image data from said at least one camera device.

16. The system according to claim 8, wherein said at least one camera device includes an infra-red camera device.