Computer-implemented method for determining at least one physical state of a farm animal to be checked

Abstract

The invention relates to a computer-implemented method for determining at least one physical state of a farm animal (2) to be checked at a checking time (T1), comprising: determining temporally successive values of at least one physical parameter within the gastrointestinal tract (3) of the farm animal (2) to be checked by a probe device arranged therein (1); transferring the values to an evaluation unit (12); determining the likelihood of the existence of at least one physical state of the farm animal (2) to be checked by applying a trained artificial neural network to the transferred values; and generating a message about the existence of a physical state of the farm animal (2) to be checked at the checking time (T1) when the likelihood determined in step c) exceeds a predefined threshold value, wherein information about the performing of herd management measures and farm animals (2) affected by this is stored in the evaluation unit (12) and before the likelihood is determined, a check is carried out to determine whether the time (TH) of performing herd management measures falls within the checking period (TR) and the farm animal (2) to be checked is affected by the herd management measure, wherein if the time (TH) of performing the herd management measure falls in the checking period (TR) and the farm animal (2) to be checked is affected, the values determined in step a) which fall in a predefined time interval after the time (TH) of the herd management measure are removed and in step c) the neural network is only applied to the remaining values.

Description

[0001] Computer-implemented method for determining at least one physical condition of a farm animal to be examined

[0002] The invention relates to a computer-implemented method for determining at least one physical condition of a farm animal to be examined at a time of examination, comprising the following steps: a) determining temporally successive values ​​of at least one physical parameter within the gastrointestinal tract of the farm animal to be examined by means of a probe device arranged in the gastrointestinal tract of the farm animal to be examined, at least in a period of examination prior to the time of examination, b) transmitting the values, preferably at least the values ​​within the period of examination, from the probe device to an evaluation unit arranged outside the farm animal to be examined,c) Determining the probability of the presence of at least one physical condition of the farm animal to be checked at the time of the check by applying a trained artificial neural network to at least part of the values ​​transmitted in step b) for the predefined check period in the evaluation unit, d) Generating a message about the presence of a physical condition of the farm animal to be checked at the time of the check if the probability determined in step c) exceeds a predefined limit.

[0003] The invention further relates to a system for determining at least one physical condition of a farm animal to be examined, comprising at least one probe device and at least one evaluation unit, a computer program product and a computer-readable data carrier.

[0004] Worldwide, livestock farming is trending toward large-scale operations with hundreds, sometimes thousands, of animals. At the same time, even smaller herds require optimized management, not least due to increasing cost pressures, for example, with regard to feeding and knowledge of the general physical condition of individual animals.

[0005] For this reason, livestock farming is increasingly turning to electronic management aids to utilize the benefits of information technology. This approach is known under the generic term "smart farming," while specialization in the context of livestock husbandry is referred to as "livestock management." For example, DE 199 01 124 A1 describes a bolus-shaped probe that can be used for such purposes. Inserted into the gastrointestinal tract of a cow, sensors measure various physical parameters such as pressure, temperature, conductivity, pH value, or ammonia content. AT 509255 B1 by the applicant describes a similar probe unit in which measurement data can be transmitted wirelessly. The measuring sensors are at least partially enclosed by a cylindrical protective device within an acid-resistant housing to protect them from mechanical damage.The probe unit can transmit measured values ​​to base stations distributed throughout a stable and can be operated or read out via these stations by a control device.

[0006] The data obtained in this way allows for the application of modern information and communication technologies, especially those for analyzing large amounts of data. For example, machine learning algorithms can be trained using statistical methods to learn from data and make predictions, or to interpret new, unknown data based on the training.

[0007] Measurements from the aforementioned probes or probe units can be used as training data, which are additionally labeled with information – so-called "labels" – on the physical conditions of the farm animals. The artificial neural networks (ANNs) used in this process are now state-of-the-art for many applications – modern architectures of this type include convolutional neural networks (CNNs). US 2022 / 0310259 A1 describes a system and method for livestock monitoring: A measuring device records biometric data – e.g., heart and respiration rate, body weight, and rectal temperature – from farm animals that, for example, gather at a feeding station, in order to identify animals suffering from respiratory diseases.The recorded values ​​are used as input data for a trained algorithm to give a user a recommendation as to whether or not the respective farm animal needs to be treated for respiratory diseases.

[0008] There's a high risk of incorrect recommendations here, as the recorded values ​​are used as input data without context. For example, a farm animal that has just been moved to a new pasture may be identified as sick due to elevated heart and respiratory rates, even though these are caused by the rapid movement and excitement of the change of location.

[0009] The disadvantage of the known solutions is that the poor quality of the input data for such algorithms or the small amount of biometric data used can lead to incorrect results regarding the physical condition of a farm animal.

[0010] It is therefore an object of the invention to remedy the above-mentioned disadvantages of the prior art and to provide a computer-implemented method, a system, a computer program product and a computer-readable data carrier which reliably allow the determination of a physical condition of a farm animal to be examined.

[0011] This object is achieved according to the invention by the method mentioned at the outset in that information at least about the time of implementation of a herd management measure and about farm animals affected thereby is stored and / or can be stored in the evaluation unit and before implementation of step c) it is checked whether the time of implementation of the herd management measure lies within the review period and the farm animal to be checked is affected by the herd management measure, wherein in the event that the time lies within the review period and the farm animal to be checked is affected, those values ​​determined in step a) which lie within a predefined time interval following the time of the herd management measure are removed and in step c) the neural network is only applied to the remaining values.

[0012] The inventive solution thus allows for the consideration of the influence that herd management measures have on the physical parameters of a farm animal, and erroneous statements about the probabilities of certain physical conditions of the farm animal being examined can be prevented. As a result, incorrect, unnecessary measures on the farm animal are avoided, thus saving effort and costs and preventing unnecessary animal suffering, e.g., due to overfeeding or underfeeding, incorrect medication, etc. This allows livestock farming to be optimized.

[0013] In particular, the physical parameters in step a) are at least one of the following parameters: temperature within the gastrointestinal tract of the farm animal; body temperature of the farm animal; pH value within the gastrointestinal tract of the farm animal; acceleration of the probe device; motility, determined from the acceleration of the probe device; activity of the farm animal, determined, among other things, from the acceleration of the probe device. The acceleration is determined in at least one spatial direction, preferably in three spatial directions of a Cartesian coordinate system or as the result of such measurements.

[0014] Preferably, the physical parameters in step a) include at least the parameters temperature within the gastrointestinal tract of the farm animal and motility, determined from the acceleration of the probe device, and activity of the farm animal. Other parameters may also be used, but the aforementioned parameters are present in a preferred variant of the invention.

[0015] In a further variant of the invention, after the values ​​have been transmitted to the evaluation unit in step b) and before the probabilities have been determined in step c), the transmitted values ​​are processed in a step cO) by carrying out at least one of the following steps: - checking whether a predefined number of values ​​has been determined in the checking period and discarding all values ​​if the number is not reached;

[0016] - Filling data holes in the data determined in step a), preferably by means of linear interpolation;

[0017] - Replacing non-numeric values ​​in the data determined in step a), preferably with a predefined numeric value.

[0018] In this way, data quality can be significantly improved and proper execution can be ensured, especially in step c), i.e., the application of the trained artificial neural network. A data gap here refers to a time when no value is recorded in a temporal sequence of values ​​at a point in time when a measurement should actually be taken. Non-numerical values ​​are erroneous measured values ​​or artifacts that can occur during the operation of a probe device.

[0019] In principle, artificial neural networks of various architectures can be used, for example, "long short-term memory" networks (LSTM). Other architectures can also be used, e.g., a recurrent neural network (RNN) or a deep neural network (DNN), in the form of a "fully connected DNN." Preferably, the artificial neural network trained in step c) is a convolutional artificial neural network or networks. The English term for this is "convolutional neural networks," with the acronym CNN. Such ANNs are well-researched in the state of the art and enable accurate and reproducible results.

[0020] In order to allow a simple and rapid identification of the livestock affected by herd management measures, the information stored on the evaluation unit about livestock affected by herd management measures is in the form of:

[0021] 1) lists of individual farm animals; or

[0022] 2) lists of groups of farm animals, whereby the evaluation unit further stores which farm animals belong to which group; or 3) lists of organizations, whereby the evaluation unit stores which farm animals and / or which groups of farm animals belong to which organizations.

[0023] In this way, it is possible to quickly determine whether the farm animal being inspected was subjected to a herd management measure during the inspection period.

[0024] The predefined time interval, whose values ​​are removed before performing step c), is preferably specified by a user of the method or, depending on the herd management measure, predefined and stored on the evaluation unit. This measure allows for adequate mapping of the fact that different herd management measures influence the physical parameters in the gastrointestinal tract of a farm animal for different durations. In particular, users can also take into account farm animal-, herd-, or organization-specific characteristics.

[0025] The above-mentioned object is also achieved according to the invention by the system mentioned at the outset in that the at least one probe device and the at least one evaluation unit are configured such that they carry out the steps of the above-mentioned method.

[0026] Furthermore, the above-mentioned object is achieved according to the invention by the computer program product mentioned at the outset in that it comprises instructions which, when the program is executed by a computer, cause the computer to carry out the steps of the above-mentioned method.

[0027] The above-mentioned task is also solved by the computer-readable data carrier mentioned at the beginning, on which the above-mentioned computer program product is stored.

[0028] The invention is explained in more detail below using a non-limiting embodiment shown in the drawings. The drawings are for illustrative purposes only and therefore do not limit the invention in any way. Figure 1 shows a cow as an exemplary farm animal and the arrangement of a probe unit in its gastrointestinal tract;

[0029] Fig. 2 is a schematic representation of a probe device according to the invention and its components;

[0030] Fig. 3 is a schematic representation of a system according to the invention with several probe devices and an evaluation unit;

[0031] Fig. 4 is a flow chart of the method according to the invention;

[0032] Fig. 5 schematic representation of an embodiment of an evaluation unit according to the invention; and

[0033] Fig. 6 Flowchart for training an artificial neural network.

[0034] The inventive solution is explained below using an example, where the described farm animal is a cow. However, the invention is also generally applicable to other farm animals, in particular ruminant farm animals such as sheep, goats, or even wild ruminants such as red deer.

[0035] Fig. 1 shows a schematic cross-sectional view of a cow 2. The feed ingested and - at least partially - chewed by the cow 2 enters its gastrointestinal tract 3, for example, the rumen or reticulum (also called the hood or reticulum). From the reticulum, the ingested feed can be transported further into the rumen or back into the mouth of the cow 2 for rumination. A probe device 1 is inserted into the gastrointestinal tract 3 of the cow 2, with which values ​​of physical parameters within the gastrointestinal tract 3 can be measured. From the values ​​of one or more physical parameters within the gastrointestinal tract 3 of the cow 2, the presence of a physical condition of the cow 2 at a particular time can be determined using a trained artificial neural network. In particular, good results can be achieved if the probe device 1 is permanently in a final position in the reticulum.This makes it possible to inspect the cow and determine its physical condition. The cow will therefore be referred to below as the livestock animal to be inspected or cow to be inspected 2.

[0036] Physical states such as being awake or asleep can be identified, and the presence of estrus can also be detected. A pH value that is too low, for example, can indicate an illness, specifically rumen acidosis; changes in heart rate, rumen motility, rumination, and locomotor activity allow conclusions to be drawn, for example, about the presence of milk fever or mastitis. These states are also divided into classes. In other words, the term "physical state" within the scope of the present disclosure essentially encompasses the status of the organism of the body of the farm animal, which can be assigned to certain predefined classes so that subsequent assessments, diagnoses, and recommendations for action can be made. This, however, is not part of the present invention.

[0037] Probe devices 1 for determining the values ​​of physical parameters are known from the prior art, for example from the applicant's earlier patent applications such as AT 509255 B1, AT 517 847 B1, and AT 521 597 B1. A possible embodiment is outlined in Fig. 2, which shows a schematic, partially transparent view of the probe device 1:

[0038] A first sensor element 5a and a second sensor element 5b are arranged within a housing 4 with a first closure element 4a and a second closure element 4b. The first sensor element 5a is, for example, an acceleration sensor, while the second sensor element 5b is designed as a temperature sensor. In addition to or instead of the sensor element, other sensors can also be used, e.g., those for measuring temperature, pH, density, pressure, conductivity, sound, optical properties, or oxygen, CO2, ammonia, glucose, volatile fatty acids, acetate, propionate, butyrate, and lactate.

[0039] Physical parameters, whose values ​​are directly or indirectly determined by the sensor elements 5a, 5b, are understood to be parameters that characterize the physical conditions in the gastrointestinal tract 3 of the farm animal, e.g., temperature, pH value, acceleration values, image information, and the like. In particular, the acceleration in all three spatial directions of a Cartesian coordinate system in which the probe device 1 is located is used, which, in the illustrated embodiment, is determined with the first sensor element 5a, the acceleration sensor, or a resulting spatial acceleration.

[0040] The probe device 1 also allows the determination of values ​​of physical parameters that are not directly measured but calculated from the measured values ​​of the probe device 1, such as motility, rumination, heart rate, eating and drinking times of the farm animal 1, or variables relating to the condition and progress of the digestive tract Z process, for example, the duration of the contractions of a motility and / or their periodicity or frequency. Motility refers to the rumen or stomach activity, essentially intestinal movements of the gastrointestinal tract 3 of the farm animal 2, which are manifested by corresponding contractions. In other words, motility, in the context of the present disclosure, refers to contractions of the gastrointestinal tract 3 that act on the probe device 1 in the form of acceleration forces.Motility, as a physical parameter, is therefore expressed as acceleration forces with specific characteristics, which are measurable by the acceleration sensor of the probe device 1 due to the contractions of the gastrointestinal tract 3, which propagate, among other things, through the stomach contents. Motility is the characteristic acceleration forces of the contractions of the gastrointestinal tract 3.

[0041] From the pulse width and thus the duration of the contractions and / or their periodicity - i.e., the time elapsed between two consecutive contraction phases - and / or their frequency, the rumination or chewing activity can be determined, in particular the periods during which the farm animal 2 devotes itself to chewing. In the context of the present disclosure, rumination refers to the rumination activity of the farm animal, in particular its intensity, duration, and periodicity or frequency. In addition, further behavioral information in the form of activities such as standing, slow / fast movement, and lying down can be determined from the acceleration measurements, which can be summarized under the term "activity of the farm animal": The activity of the farm animal 2 comprises the characteristic acceleration forces that result from physical movement of the farm animal 2 and are measurable by means of the probe device 1.

[0042] While motility, rumination, and activity of the farm animal 2 are all measured by acceleration sensors, differentiation in the measurement signal is possible based on the characteristic properties of the acceleration patterns of motility, rumination, and activity. In particular, these characteristic properties include the frequency range of the acceleration signals (i.e., the frequency at which acceleration peaks occur), the periodicity, and the amplitudes.

[0043] Furthermore, a timer in the form of a clock generator 5c, e.g. an RTC (“Real Time Clock”), is provided in the probe device 1.

[0044] The sensor elements 5a, 5b of the probe device 1 determine temporally successive values ​​of the physical parameters. This can occur continuously, in particular with defined sampling rates (e.g., 100 Hz), so that measurements are taken in immediate succession, and the determined values ​​are stored or transmitted to an evaluation unit 12 (see Fig. 3). However, it is also possible for the measurements to be taken at regular intervals—for example, every minute, hourly, after certain time intervals, e.g., every few minutes, every few hours, etc., or triggered by certain events, e.g., feeding, drinking, etc. This results in time series data of values ​​of the physical parameters, supported by the clock generator 5c. The clock generator 5c can output absolute time values ​​and / or relative time information such as the time elapsed since the last measurement, the number of measurements performed, etc.

[0045] Sensor elements 5a, 5b and clock generator 5c are connected to a probe control unit 6, which serves to control the probe device 1. The probe control unit 6 is embodied, for example, as a correspondingly programmed microprocessor. The probe control unit 6 monitors and processes the data from the sensor elements 5a, 5b and the clock generator 5c.

[0046] A storage element 7 can be provided for storing the data, for example, a memory chip, an SD card, or comparable technologies known to those skilled in the art. The storage element 7 stores both measured values ​​of the sensor elements 5a, 5b, in particular also time-coded using the clock generator 5c, as well as operating parameters of the probe device 1, such as radio frequency (for communication with an evaluation unit 12 described further below in connection with Fig. 3), transmission channel, system time, but also configuration parameters such as the sampling rate of the acceleration sensor, the sampling rate of the conversion to the first state variable, and others.

[0047] Data is transmitted via a transmitting device 8, which has at least one antenna 9 (only sketched in Fig. 2), for example, to an evaluation unit 12 (Fig. 3) located outside the farm animal to be tested. The evaluation unit 12 can be located in the immediate vicinity of the cow 2, but can also be arranged far away and accessible via appropriate wired or wireless communication connections. The transmitting device 8 is advantageously designed as a transceiver that can both transmit and receive data.

[0048] The probe device 1 is supplied with power, for example, via a power supply device 10, which can be designed as a battery, accumulator, or capacitor (advantageously a thin-film or supercapacitor). The power supply device 10 can also be designed to be rechargeable; for example, recharging is possible through energy harvesting or other methods.

[0049] In the illustrated embodiment, the components described in the above-mentioned AT 509255 B1 are enclosed within the housing 4 by a hollow protective device 11 which surrounds at least the energy supply device 10 and protects against mechanical impact, e.g., from biting. The protective device 11 can be made of any robust material, such as plastic or metal. While Fig. 2 shows a very detailed variant of a probe device 1, the probe device 1 can also be designed more simply to implement the invention. It is sufficient if values ​​of physical parameters in the gastrointestinal tract 3 of a farm animal 2 can be measured and transmitted to an evaluation unit 12, or if the probe device 1 has means with which these tasks can be fulfilled.

[0050] Fig. 3 shows an embodiment of a system 100 for determining the physical condition of several farm animals to be examined using several described probe devices 1—for reasons of clarity, the farm animals in whose gastrointestinal tract 3 the probe devices 1 are arranged are not shown. The probe devices 1 communicate wirelessly with an evaluation unit 12. The aggregation of larger data sets and their evaluation, or the application of the trained artificial neural network to the measured values ​​of the probe devices 1, takes place in the evaluation unit 12.

[0051] The values ​​are preferably transmitted from the probe device 1 to the evaluation unit 12 by radio using a suitable protocol (e.g. LoRa, ZigBee, RFiD, WLAN, or others), preferably using a suitable frequency range, e.g. 300 MHz to 450 MHz, in which the permeability for radio waves in animals is particularly high, since the data from the probe devices 1 are sent from the gastrointestinal tract 3 of the farm animals.

[0052] This transmission can occur continuously, but in reality transmission is not always possible or desired because cow 2 is not within the reception range of the evaluation unit 12 or because the data should only be sent in packets to save energy. For this reason, the memory element 7 is provided, which can be implemented as RAM and / or ROM. For example, values ​​can be stored in the random access memory ("RAM") during a measuring interval, with them then being transferred from the temporary memory to an EEPROM, i.e. a read-only memory. The intermediate step with the EEPROM is particularly advantageous in order to be able to store sufficient amounts of data before the next transmission to the evaluation unit 12 is possible.

[0053] In order to increase the range or to reduce the necessary transmission power, in the illustrated embodiment, a plurality of transmitting / receiving units 13 are provided between the evaluation unit 12 and the probe devices 1, which can function as relays. This makes it possible to implement a star-shaped architecture for using the LoRa network protocol (or “LoRaWAN” - “Long Range Wide Area Network”), with the probe devices 1 representing the end devices and the transmitting / receiving units 13 being gateways that send data packets to the evaluation unit 12, e.g. a network server. The transmitting / receiving units 13, particularly in the function as relays, are optional and not absolutely necessary. A typical system 100, however, will consist of probe units 1 on the one hand and at least one or more evaluation units 12, with communication between probe units 1 and evaluation unit 12 or

[0054] Evaluation units 12 are transmitted via transmitting / receiving units 13, which forward the measured values ​​or values ​​from probe units 1 within their reception range to the evaluation unit 12. Typically, therefore, there is no transmission between transmitting / receiving units 13, but rather from probe units 1 via an assigned transmitting / receiving unit 13 and an evaluation unit 12.

[0055] The evaluation unit 12 can, for example, be a mobile or stationary computer on which the method according to the invention and further control and evaluation routines run, or a server that can be connected via corresponding network connections, possibly with several processors or program logics, or several such servers.

[0056] In a system 100 comprising probe unit 1 (or multiple probe units) and evaluation unit 12, the computer-implemented method according to the invention for determining at least one physical condition of at least one farm animal 2 to be checked at a check time is carried out, as schematically shown in Fig. 4 and explained below. In particular, the evaluation unit 12 determines and outputs a message about a physical condition of a farm animal 2 to be checked. The described method is computer-implemented, i.e. a method is proposed that is carried out with or on a computer system (evaluation unit 12) or with computer support. The trained artificial neural network described below is therefore implemented in the computer system - the evaluation unit 12 - and is designed to be trainable.

[0057] In other words, a physical condition of a farm animal 2 to be examined is detected using deep learning by applying a trained model in the form of a trained artificial neural network—in the illustrated embodiment based on a CNN architecture, i.e., a "convolutional neural network"—to values ​​for physical parameters in the gastrointestinal tract 3 of a farm animal 2, which are determined by a probe device 1 arranged in the gastrointestinal tract 3. Alternatively, the condition can be detected using statistical methods by applying a statistical model in the form of a trained artificial neural network to the values.

[0058] The initial situation is a farm animal 2, in this case a cow, in whose gastrointestinal tract 3 a probe device 1 is located as described above. A first step, considered already completed here and therefore not shown, consists in inserting a probe device 1 into the gastrointestinal tract 3 of a farm animal 2 to be examined.

[0059] 20: In a step a), the determination of temporally successive values ​​of at least one physical parameter within the gastrointestinal tract 3 of the farm animal 2 to be tested is carried out by the probe device 1 arranged in the gastrointestinal tract 3 of the farm animal 2, at least in a testing period TR prior to the testing time Ti. In other words, values ​​of physical parameters prevalent in the gastrointestinal tract 3 are recorded. The values ​​can be determined continuously or at fixed or varying time intervals. Examples of the physical parameters are described above. As already explained, these can be directly measured physical parameters or parameters that can be determined or calculated from the measured values, e.g. motility, activity, rumination, acceleration.In any case, a time series of values ​​of physical parameters results, which can cover a period of minutes, hours, days, weeks, or months to years. At least part of this time series is then the verification period TR, the values ​​of which must be available to determine a physical condition at a verification time Ti. The verification period TR can be fixedly defined and typically amount to a number of days, in particular seven days, but can be freely selectable by a user of the method or system 100 according to the invention. The verification period TR or its duration, regardless of whether it is fixed or selected by a user, is stored on the evaluation unit 12.

[0060] 30: In a step b), the values, preferably at least those within the verification period TR, are transmitted from the probe device 1 to the evaluation unit 12 located outside the farm animal 2 to be tested. As already explained above, this transmission can occur continuously, i.e., the values ​​are sent immediately after determination; however, it is also possible to aggregate the values ​​in the memory 7 of the probe device 1 and then send them in packets, i.e., in the form of time series. The values ​​can be transmitted directly to the evaluation unit 12 via a transmission path; in variants, however, the transmission from the farm animal 2 can be wireless, and the further transmission path to the evaluation unit 12 can then occur via wireless and wired transmission paths. In any case, the values ​​are transmitted from the probe device 1 to the evaluation unit 12, directly or via one or more stations.In the illustrated embodiment, the transmitted values ​​include values ​​for the temperature within the gastrointestinal tract 3 of the farm animal 2, motility, determined from the acceleration of the probe device 1, and activity of the farm animal.

[0061] 40: In a step c), the probability of the presence of at least one physical condition of the farm animal 2 to be checked at the check time Ti is determined by applying a trained artificial neural network to at least some of the values ​​transmitted in step b) in the evaluation unit 12. The trained neural network is thus applied in the evaluation unit 12 to a time series of values ​​of physical parameters that in any case cover the check period TR. The trained artificial neural network can be a suitable network from the state of the art, which the expert selects accordingly. Preferably, the trained artificial neural network is a convolutional neural network (CNN). Details of the trained neural network are explained in detail below.

[0062] For example, to detect a physical condition at the review period Ti, values ​​from the review period TR are used, where the period is, for example, seven days and the time of onset is designated as To.

[0063] Therefore, TR = [To, Ti], where To = Ti - 7 days.

[0064] In order to cover all aspects that may influence the physical condition, the solution according to the invention allows for the consideration of herd management measures that were carried out on the farm animal 2 during the review period TR.

[0065] Herd management measures are actions that are carried out directly on the farm animal 2 or on a group of farm animals 2 and that have an impact on physical parameters in the gastrointestinal tract 3 of the farm animal 2 and are therefore measurable by the probe device 1. In other words, herd management measures are external influences that act on the farm animal 2 at a set time or within a defined period of time. Examples of herd management measures are the administration of vaccinations, the performance of hoof care or other prophylactic measures carried out on the farm animal 2, group changes, i.e. when the farm animal 2 moves from one group or herd to another, grazing (i.e. the movement from a stable situation to a pasture or an outdoor location), feed changes (if, for example,a feed composition is changed or feed is taken from a different silo on a farm), storms, heat or cold waves, heat stress in demanding climatic conditions or the reaction to them, for example when ventilation is activated in a stable and has a cooling effect on individual farm animals 2 or entire groups or herds.

[0066] Herd management measures influence physical parameters or can cause physical parameters that are very similar to certain body conditions, although they do not correspond to them - this can lead to step c) not being carried out correctly and can lead to incorrect results regarding the existence of a body condition of the farm animal 2.

[0067] For example, a vaccination reaction may cause a fever spike leading to elevated temperatures in the gastrointestinal tract 3, which could be identified as an inflammatory condition, even though the farm animal 2 is actually in good physical condition.

[0068] Hoof trimming may cause increased stress in farm animal 2, resulting in increased activity, which could be identified as an abnormal body condition and interpreted as the presence of milk fever, even though farm animal 2 is actually in good body condition.

[0069] The relocation of livestock, i.e. when a livestock 2 or a group of livestock 2 are driven to a new pasture or similar, is also referred to as a herd management measure and has an influence on the physical parameters measured in the gastrointestinal tract 3 of a livestock 2.

[0070] Herd management measures implemented during the review period TR can therefore result in the artificial neural network calculating incorrect probabilities and determining an incorrect physical condition of farm animal 2. This is often the case in the state of the art.

[0071] The inventive solution is now suitable for preventing these previous disadvantages. For this purpose, information about at least the time TH of the implementation of a herd management measure and information about the farm animals 2 affected by it is stored or can be stored in the evaluation unit 12. In other words, the evaluation unit contains data about when a herd management measure was implemented and which farm animals 2 were affected. Advantageously, further details are also stored, e.g., which herd management measure was implemented and how long it may affect physical parameters in the gastrointestinal tract 3 of the farm animal 2.

[0072] Before determining the probabilities in step c) - 40 - a verification step 99 is carried out in which it is checked whether the time TH of the implementation of the herd management measure lies within the verification period TR and whether the farm animal 2 to be checked was or is affected by the herd management measure. If both are true, i.e. if the farm animal 2 to be checked was subjected to a herd management measure in the verification period TR, those values ​​that lie within a predefined time interval following the time TH of the herd management measure are removed from the time series of values ​​of physical parameters from the verification period TR, and the artificial neural network is only applied to the remaining values ​​of the time series. In other words, the artificial neural network is only applied to values ​​of the time series that were not affected by the herd management measure.

[0073] The values ​​of all physical parameters can be removed, but in one variant only values ​​of certain, previously defined parameters can be removed.

[0074] The length of the time interval following the time TH of the herd management measure, in which the measured values ​​are removed from the time series used for step c), can, for example, be specified by a user of the method on an ad hoc basis and stored on the evaluation unit 12, or a length of the time interval is stored on the evaluation unit 12 depending on the type of herd management measure. In other words, the evaluation unit 12 basically applies the trained artificial neural network to all values ​​of a time series of a farm animal 2 to be tested from a testing period TR.

[0075] Before determining the probabilities, however, according to the invention, a check is carried out in a check step 99 to determine whether the time TH of a herd management measure lies in the check period TR and whether the farm animal 2 to be checked was affected by the herd management measure.

[0076] The information stored on the evaluation unit 12 regarding farm animals 2 affected by the herd management measure can be present in various forms: as lists of individual farm animals 2, where for each farm animal 2 it is stored when which herd management measure was applied; as a list of groups of farm animals 2, where herd management measures for groups of farm animals 2 are stored on the evaluation unit 12, with the evaluation unit 12 further storing which farm animals 2 belong to which group; lists of organizations, with the evaluation unit 12 storing which farm animals 2 and / or which groups of farm animals 2 belong to which organizations.

[0077] If the two conditions mentioned above are met, those values ​​recorded in a time interval following the time TH of the herd management measure are removed from the time series of the review period TR. The time interval can be one day, for example. This is the case, for example, if the herd management measure involves hoof trimming, and experience shows that the treated farm animal 2 exhibits increased stress and thus increased activity for approximately 24 hours due to the hoof trimming.

[0078] In step c), the artificial neural network is applied to the remaining values, i.e. the values ​​of the original time series of the review period TR minus the values ​​from the time interval following the time TH of the herd management measure.

[0079] This means that the values ​​of the time series that are distorted or potentially distorted by the herd management measure are no longer in the time series from which the probabilities for the presence of a physical condition are determined, and the risk of an erroneous result is eliminated.

[0080] Of course, the described procedure can also be carried out several times if several herd management measures were carried out during the review period TR.

[0081] The result of step c) - 40 - is thus a probability for a physical condition for which the artificial neural network was trained. If it was trained for multiple physical conditions, the probabilities result for each physical condition defined during training (see further description in connection with Fig. 6). The probability of a physical condition corresponds to the probability that the values ​​used in the time series, which, for example, cover a review period TR of seven days, correspond to a physical condition - if necessary, minus the values ​​following the time TH of a herd management measure in a time interval.

[0082] 40': In an optional step cO), which is carried out after the values ​​have been transmitted to the evaluation unit 12 - 30 - and before the probabilities - 40 - are determined, the values ​​transmitted in step b) - 30 - are processed by performing at least one of the following steps:

[0083] - Check whether a predefined number of values ​​has been determined in the review period and discard all values ​​if the number is not reached;

[0084] - Filling data holes in the data determined in step a), preferably by means of linear interpolation;

[0085] - Replacing non-numeric values ​​in the data determined in step a), preferably with a predefined numeric value.

[0086] This ensures that the probabilities can be determined correctly. In Fig. 4, step 40' is shown before the verification step 99 - in a variant not shown, step 40' can also be performed after the verification step 99 has been carried out. 50: In a step d), a message about the presence of a physical condition of the farm animal 2 to be checked at the check time Ti is then generated in the evaluation unit 12 if the probability determined in step c) - 40 - exceeds a predefined limit. The predefined limit values ​​for the probabilities of different physical conditions are stored in the evaluation unit 12. The limit values ​​can generally be specified, defined by users, or determined from measured values ​​using algorithms.It is also possible for existing, predefined limit values ​​on the evaluation unit 12 to be changed by users, e.g. if specific characteristics of farm animals 2 or groups or herds are to be taken into account.

[0087] Alternatively or in addition to generating the message, the message can be output on a display unit not shown in the figures, which may be, for example, a screen that is part of the evaluation unit 12 or is connected to the evaluation unit 12 by wires or wirelessly. For example, the display unit may be a mobile phone of a user of the method or system according to the invention.

[0088] In addition or alternatively to generating the message and / or outputting the message on a display unit, a measure can be triggered if a physical condition of the farm animal 2 to be checked is present, for example opening a gate, raising the temperature of a stable building, increasing the flow rate of a drinking system, dispensing additional or alternative feed or administering nutritional supplements or medication, in each case by means of suitable actuators.

[0089] Step a) - 20 - is carried out in the probe device 1, while step 99, step c) - 40 -, step d) - 50 - and the optional step c0) - 40' - are carried out in the evaluation unit 12, which is shown in Fig. 4 by dotted boxes.

[0090] An exemplary structure of the evaluation unit 12 is shown in Fig. 6: The time series with values ​​of the physical parameters for the review period TR and, if applicable, meta data of the farm animal 2 such as age, number of calvings or number of lactations, days in milk (“days in milk”) of the current lactation, as well as the information on the herd management measures are fed to a first program logic 60, so that the optional step cO) - 40' - and the review step 99 take place in the first program logic.

[0091] The correspondingly cleaned time series is then fed to a second program logic 70 on which the trained artificial neural network runs, so that step c) - 40 - can take place.

[0092] The probability for a physical condition or the probabilities for several physical conditions resulting from the model are then fed to a third program logic 80, which generates and, if necessary, outputs a message when a predefined limit value for a physical condition is exceeded.

[0093] The trained artificial neural network used in step c) - 40 - and its training are described in more detail below.

[0094] Basically, the determination of physical conditions is carried out by ANN or artificial intelligence models, which are trained with the help of annotated training data sets for the most important physical conditions of a farm animal 1. This process is shown schematically in Fig. 6. The physical parameters used for this purpose include, in particular, those that can be measured with the probe device 1 (e.g., temperature, motility, activity, ...) or calculated from them (e.g., rumination events, water intake). This also allows the so-called hood-rumen motor function, i.e., the sequence of movements of the hood and rumen, to be described. These special, defined, and regular contraction sequences serve to mix and re-sort the feed and are an important component in the process of processing the feed into components usable for a cow 2. Other animal-specific characteristics such as lactation number, season, etc., are taken into account. The starting point for the creation or training of the model in the form of an artificial neural network is a central database located in the evaluation unit 12 or connected to it.

[0095] This database consists, on the one hand, of time series of values ​​for physical parameters for a large number of farm animals 2, including in particular values ​​for the physical parameters temperature measured in the gastrointestinal tract 3, especially in the forestomach system, activity and motility.

[0096] On the other hand, the database contains labels, i.e., data records on known physical conditions of the farm animal 2 with associated details, such as illnesses with medical treatments, estrus times, and the like, which consist of at least a time of the physical condition, an identification of the affected farm animal 2, and, if applicable, a note on the illness, medical treatment, or estrus. In addition, so-called

[0097] Metadata of the farm animals 2 must be included, for example the organization or group to which a farm animal 2 is assigned, the number and date of calvings, the date of insertion of the probe device 1 and the time of the last estrus.

[0098] The first step 90 of training the model consists of loading the time series and labels from the database.

[0099] In a second step 91, the labels are processed. This involves at least one or more of the following steps:

[0100] - Check to ensure that sufficient time series data are available for the farm animal 1 identified in the dataset at the time indicated in the dataset. Several days around the identified time are preferred. If insufficient time series data are available, the dataset is discarded.

[0101] - Loading time series data for the farm animal 1 identified in the dataset around the time point identified in the dataset. The scope of the time series data corresponds to a predefined time interval, e.g., seven days;

[0102] - Filling data gaps in the time series data caused by missing data points, provided these do not exceed a maximum duration of several hours. Linear interpolation is used as the filling method. Other methods are also possible, such as constant interpolation or backfilling, i.e., adding the missing data where possible or available. If filling the data gaps is not possible or the data gap is too long, the data set is discarded.

[0103] - Replacing non-numeric measurement data caused by measurement errors. Affected data is replaced with a predefined numeric value.

[0104] In a third step 92, the loaded and cleaned labels are divided into different categories ("classes") based on the information in the data set. The classes correspond to the physical conditions that the model allows for estimation.

[0105] For example, if a physical condition consistent with mastitis needs to be detected, possible classes are "Mastitis" and "Non-Mastitis." Alternatively, multiple classes can be defined, such as "Severe Mastitis," "Mild Mastitis," "Estrus," "Pneumonia," "Livestock Sleeping," "Livestock Walking," and "Other," whereby the first two classes can be used for positive mastitis detection.

[0106] The fourth step (93) is training. For this purpose, the dataset resulting from the previous steps is divided into training and validation datasets and used to train the artificial neural network. A convolutional neural network is used here. Hyperparameter tuning can be used according to the ML software library used.

[0107] In a final step 94, the trained model is validated. For this purpose, it is subjected to several plausibility checks in which the model's accuracy is compared with known physical conditions. The resulting model, called the "general model," is selected for the classification of real-time data and as a trained artificial neural network for operation in the process described above if its accuracy is satisfactory.

[0108] In an optional step 95, which is shown in Fig. 6 with a dashed line, the general model can be refined by using "transfer learning" to refine it for a specific livestock species, a specific group of livestock 2, a farm, a customer group, or a specific organization. To do this, the third step 92 is repeated with a selection of data sets representative of the customer group / farm / organization, and the resulting data set is used in the fourth step 93 to further train the general model, which is referred to as "transfer learning." In contrast to the general model, this results in a "special model" that, when applied to the customer group / livestock species / organization / etc., has a higher accuracy than the general model.

[0109] In the sequence of the method according to the invention described above with reference to Fig. 4, the general model as well as the specific model can be used depending on the application.

[0110] In addition to the training procedure described, a variant using statistical methods can also be used.

[0111] According to the above statements, the invention thus relates to a computer-implemented method for determining a physical condition of a farm animal and a system 100 configured therefor, which comprises at least one probe device 1 and at least one evaluation unit 12. Accordingly, the invention also relates to a computer program product (not shown in detail in the figures), comprising instructions which, when executed by a computer, cause the computer to carry out the steps of the method described above, as well as a computer-readable data carrier on which this computer program product is stored, and a data carrier signal which this computer program product transmits.

[0112] One possible application of the described method of determining the physical condition of a farm animal 2 is to make a diagnosis of a possible disease based on the condition and to suggest a response thereto in a subsequent step which is not part of the protected invention.

[0113] Detecting animal diseases at an early stage and responding to them early and appropriately is of great importance in livestock farming. It reduces the incidence of disease and increases the success rate of treatments while shortening treatment duration. As a further consequence, the need for medications, especially antibiotics, is reduced.

[0114] If the physical condition of the farm animal 2 indicates a disease, a treatment recommendation is proposed based on the measured parameters and values. This treatment may vary depending on the country, the schemes chosen by the farm, etc.

[0115] This proposed treatment, for example administration of a special or supplementary feed, addition of a special feed or medication, is carried out either manually (by a person) or automatically, e.g. via a concentrate feeding station or a feeding robot.

[0116] The treatment performed is confirmed by observing the physical condition of the farm animal 2, based on which further steps are then taken to reach a diagnosis, or, if necessary, adapted and suggested / modified. A change is triggered by a change / non-change in the physical condition and a subsequent diagnosis. The new treatment plan is selected based on this calculated result and the therapy / treatment already administered.

[0117] If a normal physical condition is measured again and no disease is diagnosed, the treatment plan may be shortened or discontinued.

[0118] Treatment plans can change depending on how the physical condition develops (i.e. the treatment plans take the histones into account). Accordingly, the dosage of a medication can be adjusted or the administration of a medication can be stopped completely. It can also be recognized that the treatment is not sufficient and another medication should be given or a change to a different treatment plan must be made (“Standard Operating Procedure” - SOP). A treatment plan can recommend the administration of medication or be based on a different therapy. The invention thus allows the physical condition of a farm animal 2 to be examined to be recognized by applying a trained artificial neural network to values ​​for physical parameters in the gastrointestinal tract 3 of a farm animal 2, which values ​​are determined by a probe device 1 arranged in the gastrointestinal tract 3.The invention does not allow for the diagnosis of a disease - as shown above, this requires additional steps that are not part of the method or system according to the invention.

Claims

PATENT CLAIMS 1. A computer-implemented method for determining at least one physical condition of a farm animal (2) to be examined at a checking time (Ti), comprising the following steps: a) determining temporally successive values of at least one physical parameter within the gastrointestinal tract (3) of the farm animal (2) to be examined by means of a probe device (1) arranged in the gastrointestinal tract (3) of the farm animal (2) to be examined, at least in a checking period (TR) prior to the checking time (Ti), b) transmitting the values, preferably at least the values lying in the checking period (TR), from the probe device (1) to an evaluation unit (12) arranged outside the farm animal (2) to be examined,c) determining the probability of the presence of at least one physical condition of the farm animal (2) to be checked at the time of checking (Ti) by applying a trained artificial neural network to at least some of the values transmitted in step b) in the evaluation unit (12), d) generating a message about the presence of a physical condition of the farm animal (2) to be checked at the time of checking (Ti) if the probability determined in step c) exceeds a predefined limit value, characterized in that information at least about the time (TH) of carrying out a herd management measure and about farm animals (2) affected thereby is stored and / or can be stored in the evaluation unit (12) and is checked before carrying out step c),whether the time (TH) of implementation of the herd management measure is within the review period (TR) and the farm animal (2) to be reviewed is affected by the herd management measure, whereby in the event that the time (TH) of implementation of the herd management measure is within the review period (TR) and the farm animal (2) to be reviewed is affected, the values determined in step a) which are within, a predefined time interval following the time (TH) of the herd management measure, are removed and in step c) the neural network is applied only to the remaining values.

2. Method according to claim 1, characterized in that the physical parameters in step a) are at least one of the following parameters: temperature within the gastrointestinal tract (3) of the farm animal (2); body temperature of the farm animal (2); pH value within the gastrointestinal tract (3) of the farm animal (2); acceleration of the probe device (1); motility, determined from the acceleration of the probe device (1); activity of the farm animal (2), determined, among other things, from the acceleration of the probe device (1).

3. Method according to claim 1 or 2, characterized in that the physical parameters in step a) comprise at least the parameters temperature within the gastrointestinal tract (3) of the farm animal (2) and motility, determined from the acceleration of the probe device (1) and activity of the farm animal (2).

4. Method according to one of claims 1 to 3, characterized in that after transmitting the values to the evaluation unit (12) in step b) and before determining the probabilities in step c), in a step cO) the transmitted values are processed by carrying out at least one of the following steps: - Check whether a predefined number of values has been determined in the verification period (TR) and discard all values if the number is not reached; - Filling data holes in the data determined in step a), preferably by means of linear interpolation; - Replacing non-numeric values in the data determined in step a), preferably with a predefined numeric value.

5. Method according to one of claims 1 to 4, characterized in that the trained artificial neural network in step c) is a convolutional artificial neural network.

6. Method according to one of claims 1 to 5, characterized in that the information stored on the evaluation unit (12) about farm animals (2) affected by herd management measures is in the form of: 1 ) Lists of individual farm animals (2); or 2) lists of groups of farm animals (2), whereby the evaluation unit further stores which farm animals (2) belong to which group; or 3) Lists of organisations, whereby the evaluation unit (12) stores which farm animals (2) and / or which groups of farm animals (2) belong to which organisations.

7. Method according to one of claims 1 to 6, characterized in that the predefined time interval, the values of which are removed before carrying out step c), can be specified by a user of the method or is specified depending on the herd management measure and is stored on the evaluation unit (12).

8. System for determining at least one physical condition of a farm animal (2) to be checked, comprising at least one probe device (1) and at least one evaluation unit (12) which are configured to carry out the steps of the method according to one of claims 1 to 7.

9. A computer program product comprising instructions which, when executed by a computer, cause the computer to carry out the steps of the method according to any one of claims 1 to 7.

10. A computer-readable data carrier on which the computer program product according to claim 9 is stored.

Images