WO2025010009A1

WO2025010009A1 - Milk system for controlling diversion of a milk sample to a cell count device

Info

Publication number: WO2025010009A1
Application number: PCT/SE2024/050633
Authority: WO
Inventors: John M Christensen
Original assignee: Delaval Holding Ab
Priority date: 2023-07-05
Filing date: 2024-06-26
Publication date: 2025-01-09

Abstract

A milk system (100) used for milking individual animals (101) The milk system (100) com- prises: A milk extracting arrangement (110), a milk forwarding entity (114), a cell count device (113); a milk diverting mechanism (115) connected to the milk forwarding entity (114) and the cell count device (113); an animal identifier device (116); a database (130); milk meters (112a, 112b, 112c, 112d); a time measurement device (119); and a controller (120). The controller (120) calculates teat-specific milk secretion rates and compares them to rolling milk secretion rate deviation limits. If any teat-specific milk secretion rate is lower than the limit, the controller (120) activates the milk diverting mechanism (115) in future milking sessions after a specific time limit to measure the somatic cell count in the milk sample.

Description

MILK SYSTEM FOR CONTROLLING DIVERSION OF A MILK SAMPLE TO A CELL COUNT DEVICE

TECHNICAL FIELD

This document discloses a milk system. More particularly, a milk system is described, for milking a herd of individual animals, and divert milk of a future milking session to a cell count device based on milk secretion rate of each teat of the individual animal.

A milk secretion rate of each teat of the individual animal is determined, during each milking session. The teat specific milk secretion rate is compared with a repeatedly updated rolling milk secretion rate deviation limit. When the teat specific milk secretion rate is lower than the rolling milk secretion rate deviation limit, activation of a milk diverting mechanism during a future milking session of the individual animal is triggered, otherwise not.

BACKGROUND

An often-used indicator of milk quality is somatic cell count. Most somatic cells are leukocytes, i.e. , white blood cells, which may become present in increasing numbers in milk as an immune response to a mastitis-causing pathogen.

Farmers may be financially rewarded for low herd somatic cell counts and/ or penalized for high herd somatic cell count, as the somatic cell count is considered to, in some meaning, reflect the quality of the milk. The herd somatic cell count is made on milk extracted from a bulk tank, comprising milk of several animals.

In case the herd somatic cell count is too high, e.g., higher than a threshold level of 400 000 cells per ml of milk, the milk is deemed unfit for human consumption and consequently has to be wasted, leading to an economic loss. Different legislations may apply different threshold levels for somatic cell count.

Somatic cell count may also/ alternatively be applied on milk of an individual animal, in order to detect the risk of an infections/ mastitis at an early stage and take appropriate measures to cure the animal. The milk of the sick animal/ animal with high somatic cell count may be wasted without being allowed to enter the bulk tank, or possibly be diverted and used for other purpose than for human consumption. The somatic cell count, (individual/ herd level) may be determined in several different ways and many times expensive chemicals are required. The known somatic cell count methods are also more or less time consuming.

One methodology for performing somatic cell count is suggested in document CN102819765A. A colouring agent is applied into a milk sample. The colouring agent acts on the somatic cells, marking them with a distinguishing colour. The milk sample with the colouring agent is dropped into a slide. Cell images in colour may then be taken of the milk sample in the slide, and a cell image counting process may be applied for counting the number of somatic cells based on image recognition.

Another solution to make the somatic cell count is suggested in WO2019082178A1. The number of somatic cells within a milk sample is estimated by mixing the milk sample with a reagent, detergent and/ or caustic soda, forming a test sample. Any somatic cells within the milk sample will cause the milk sample to thicken. Severe cases of infection/ mastitis will cause the milk to form a gel consistency. The viscosity of the test sample is therefore correlated to the somatic cell count.

Repeating the somatic cell count at every milking session for every animal at the farm will be expensive, resource demanding, time consuming and in addition probably unnecessary in the meaning that most somatic cell counts of most animals will indicate that the somatic cell count is low, i.e. , lower than a threshold limit such as e.g., 300 000 cells per ml of milk (or any other selected threshold limit).

To instead repeat the somatic cell count at some predetermined time interval for each animal, for example once every 10 days, may lead to undetected mastitis for several days for an infected animal, causing unnecessary suffering for the animal, besides extended and more expensive curing process, and decreased milk yield of the farm. It may also result in economical penalisation by the dairy producer due to high herd somatic cell count. Yet, the mentioned possible solutions would still result in a lot of unnecessary somatic cell counts on healthy animals, and thereby also unnecessary usage of expensive and/ or environment unfriendly chemicals.

It would thus be desired to find a way to reduce the amount of unnecessary measurements of somatic cell counts, while at the same time detect animals with a mastitis infection risk at an early stage. SUMMARY

It is therefore an object of this invention to solve at least some of the above problems and determine when to measure somatic cell count and when not to, for individual animals at a dairy farm, thereby minimising or at least reducing the usage of chemicals involved when measuring the somatic cell count.

According to a first aspect of the invention, this objective is achieved by a milk system. The milk system intends to extract milk from a herd of individual animals. The milk system comprises a milk extracting arrangement configured to extract milk from each individual animal during a milking session via teat cups. The milk extracting arrangement may for example be a milking robot or a rotary parlour. The teat cups are attached to a respective teat of the individual animal. The milk extracting arrangement is also configured to provide the extracted milk to a milk forwarding entity. The milk forwarding entity is configured to temporarily store and/ or transport milk from one animal at a time from the milk extracting arrangement to a bulk tank. Another terminology for the milk forwarding entity may be a milk line or similar expression.

The milk system also comprises a cell count device. The cell count device is configured to receive a milk sample or a sub sample of the milk sample and measure a number of somatic cells in the milk sample.

The milk system in addition comprises a milk diverting mechanism. The milk diverting mechanism is connected to the milk forwarding entity and to the cell count device. The milk diverting mechanism is configured to divert the milk sample from the milk forwarding entity and forward the milk sample or the sub sample of the milk sample to the cell count device.

The milk system comprises an animal identifier device, configured to determine identity of the individual animal to be milked, i.e., when the animal is entering the milk extracting arrangement.

The milk system comprises a database. Also, the milk system comprises a set of milk meters. Each milk meter is arranged to measure an extracted amount of milk of each respective teat of the individual animal during the milking session. The milk system furthermore comprises a time measurement device configured to measure time. The milk system additionally comprises a controller. The controller is communicatively connected to the milk extracting arrangement, the animal identifier device, the milk meters, the time measurement device, the milk diverting mechanism and the database. The controller is configured to, repeatedly for every milking session, store the extracted amount of milk of each respective teat of the individual animal in the database, associated with the identity of the individual animal, an identity of the respective teat, i.e., rear left, rear right, front left, front right and a time stamp of the milking session.

The controller is also configured to determine, via the time measurement device, an intermilking session time period between two consecutive milking sessions, without any milking session in between, of the individual animal.

In addition, the controller is also configured to store the inter-milking session time period at least temporarily, associated with the identity of the individual animal and the time stamps of the two consecutive milking sessions.

The controller is configured to determine days in lactation of the identified individual animal to be milked. In case the determined days in lactation does not exceed a day threshold limit, no more action is performed.

However, in case the determined days in lactation exceeds a day threshold limit, the controller is additionally configured to perform a number of subsequently mentioned additional actions. Thus, the controller is additionally configured to calculate a teat specific milk secretion rate by dividing the amount of extracted milk of each teat during the latest milking session, with the associated inter-milking session time period. The controller is also configured to store the calculated teat specific milk secretion rate, associated with the identity of the individual animal and the latest milking session in the database. The controller is also configured to calculate a rolling milk secretion rate deviation limit, which is animal specific and teat specific and updated at each milking session, based on stored teat specific milk secretion rates, obtained from the database, from a number of previous milking sessions within a rolling time period, closest in time to the latest milking session. The controller is configured to compare each teat specific milk secretion rate of the latest milking session with the corresponding teat specific rolling milk secretion rate deviation limit. The controller is also configured to, based on the made comparison, determine whether any one of the compared teat specific milk secretion rates is lower than the corresponding teat specific rolling milk secretion rate deviation limit.

The controller is also configured to trigger activation of the milk diverting mechanism during at least one future milking session of the individual animal after a first time limit from the latest milking session, to divert the milk sample from the milk forwarding entity and forward the milk sample or the sub sample of the milk sample to the cell count device, thereby enabling a cell count measurement of the number of somatic cells in the milk extracted from the individual animal, when any one of the compared teat specific milk secretion rates of the latest milking session is lower than the rolling milk secretion rate deviation limit for the specific teat, the latest milking session becomes the triggering milking session.

It has been observed through inventive research that the teat specific milk secretion rate of an animal suffering from mastitis is reduced early in the inflammation process, i.e., some days before a significant increase in somatic cell count could be observed. By performing somatic cell count only after having detected a decrease in teat specific milk secretion rate of the animal, the number of somatic cell count measurements is reduced in comparison with prior art. Thereby, costs associated with the somatic cell count measurements are reduced. Less chemicals are consumed for the somatic cell count yet, not detecting an animal with infection/ mastitis risk is very low. Early detection of an infected animal is ameliorated.

Optionally, the rolling time period may comprise the previous milking sessions closest in time to the latest milking session that have been performed during the latest 3-10 days, for example the latest 5-8 days, the latest week, etc.

By calculating the rolling milk secretion rate deviation limit based on at least three days, a reference criterion interval is created which is large enough for not allowing one singular odd measurement influence the rolling milk secretion rate deviation limit too much. At the same time, it is desired not to use milk data which is too old, i.e., older than for example 10 days, as the milk secretion rate of the animal may vary over the lactation period.

Optionally, the controller may be configured to calculate an average for the teat specific milk secretion rates of the number of the previous milking sessions closest in time to the latest milking session leaving outliers out of the calculation. The controller may also be configured to set the rolling milk secretion rate deviation limit for the respective teat to a value with a margin below the calculated average.

The teat specific rolling milk secretion rate deviation limit is hereby set in a way that excludes or at least minimises the risk that a measurement of a healthy animal is lower than the teat specific rolling milk secretion rate deviation limit.

Optionally, the controller may be configured to calculate the inter percentile range for the teat specific milk secretion rates of the number of the previous milking sessions closest in time to the latest milking session, wherein the inter percentile range has a lower limit value and/ or an upper limit value. The controller may also be configured to recalculate the rolling milk secretion rate deviation limit for the respective teat based on multiplication of the inter percentile range with a factor.

Optionally, the first time limit may be set between 1-2 days from the triggering milking session.

Inventive research has shown that a decrease in teat specific milk secretion rate of the animal suffering from mastitis occurs a couple of days before a significant increase in somatic cell count could is observed. By starting to make somatic cell count after 1 or 2 days, the number of required somatic cell count measurements is minimised, yet the risk of missing an increased cell count is small.

Optionally, the controller may be communicatively connected to the cell count device. The controller may be configured to detect when the cell count measurement of the future milking session occurring after the first time limit from the triggering milking session exceeds a cell count threshold limit. The cell count threshold limit may be configurable by the farmer and be set to for example 300 000 cells per ml of milk (non-limiting example). The controller may in addition be configured to deactivate the milk diverting mechanism and/ or the cell count device upon the detection of the cell count measurement exceeding the cell count threshold limit.

When having concluded that the animal has an increased somatic cell count, there is no point in repeating additional somatic cell counts. By immediately inhibit any additional somatic cell count measurements for the animal for which an increased somatic cell count has been concluded, the number of measurements of somatic cell counts is minimised, or at least reduced.

Optionally, the controller may be configured to alert a farmer upon detection of the cell count measurement of the future milking session, exceeding the cell count threshold limit. By alerting the farmer, he/ she becomes aware of the situation and is enabled to make a visual inspection of the animal, for determining additional measures, if required.

Optionally, the controller may be communicatively connected to the cell count device. The controller may also be configured to deactivate the milk diverting mechanism and/ or the cell count device, when a second time limit counted from the triggering milking session is reached without detection of any cell count measurement of any future milking session performed after the first time limit, but before the second time limit, exceeding the cell count threshold limit. The second time limit is longer than the first time limit. Both time limits are counted from the triggering milking session.

The somatic cell count is measured during every milk session occurring after the first time limit from the triggering milking session. However, in case no increased somatic cell count is found when the second time limit is reached, the reason is probably that the animal does not have mastitis. It is then no reason to continue making additional somatic cell count measurements. Thereby unnecessary somatic cell count measurements are avoided, or at least reduced.

Optionally, the second time limit may be set between 3-6 days from the triggering milking session.

The teat specific milk secretion rate decrease of the animal suffering from mastitis occurs about two days before an increased somatic cell count could be measured. By continue to perform the somatic cell count measurements during this critical period after the triggering milking session, possibly with some margin, it could be ruled out that the tested animal has- mastitis risk or not. The decreased teat specific milk secretion rate having triggered the somatic cell count measurements could then be concluded to have been caused by an infec- tion/mastitis risk or another matter, such as for example a misreading, technical failure of the milk extracting arrangement, excessive short/ long time between milk sessions for the animal, random fluctuations in milk secretion rate of the animal, for example.

Optionally, the day threshold limit for the determined days in lactation may be set to a value between 10 and 90 days, preferable 30-60 days.

At the beginning of the lactation cycle, the milk secretion of animals is irregular and the teat specific milk secretion rate of the animal is consequently irregular and fluctuating. To calculate the rolling milk secretion rate deviation limit based on these irregular measurements is likely to result in too many false positive teat specific milk secretion rates.

Optionally, the milk diverting mechanism may comprise a pump.

By using a pump for diverting the milk, a more precise amount of milk could be extracted to be used for the milk sample to be provided to the somatic cell count device, in comparison with using valves. A pump is also superior from an operational point of view, in comparison with using a valve, which require more frequent maintenance.

Optionally, the controller may be configured to determine a time value at a first milking session of a lactation period of the individual animal and store the time value, associated with the identity of the individual animal in the database, and determine days in lactation of the identified individual animal based on the stored time value.

Additional specifications are thereby provided for successfully performing the described concept.

Other advantages and additional novel features will become apparent from the subsequent detailed description.

FIGURES

Embodiments of the invention will now be described in further detail with reference to the accompanying figures, in which:

Figure 1 illustrates an example of a milk system at a farm, according to an embodiment of the invention;

Figure 2 illustrates a timeline with examples of milk sessions, milk permissions and activation time periods of an animal;

Figure 3A illustrates examples of a milking data in form of teat specific milk secretion rate of an animal at different milk sessions;

Figure 3B illustrates examples of a milking data in form of teat specific milk secretion rate of an animal at different milk sessions;

Figure 3C illustrates examples of a milking data in form of teat specific milk secretion rate of an animal at different milk sessions;

Figure 4 illustrates an example of a milk system and a user equipment, according to an embodiment of the invention. DETAILED DESCRIPTION

Embodiments of the invention described herein are defined as a milk system, which may be put into practice in the embodiments described below. These embodiments may, however, be exemplified and realised in many different forms and are not to be limited to the examples set forth herein; rather, these illustrative examples of embodiments are provided so that this disclosure will be thorough and complete.

Still other objects and features may become apparent from the following detailed description, considered in conjunction with the accompanying drawings. It is to be understood, however, that the drawings are designed solely for purposes of illustration and not as a definition of the limits of the herein disclosed embodiments, for which reference is to be made to the appended claims. Further, the drawings are not necessarily drawn to scale and, unless otherwise indicated, they are merely intended to conceptually illustrate the structures and procedures described herein.

Figure 1 illustrates a scenario with a milk system 100 for milking a herd of individual animals 101 , which may be comprised at a dairy farm.

“Animal” may be any arbitrary type of domesticated, milk producing female mammal, such as for example cow, goat, sheep, camel, dairy buffalo, yak, etc., although the discussed examples and figures primarily are envisioned with cows in mind.

The milk system 100 and the dairy farm may comprise an automatic milk extracting arrangement 110, which also sometimes may be referred to as a milking robot or rotating milking parlour. However, the milk extracting arrangement 110 may in some embodiments comprise other automatic milking equipment based on automatic/ autonomous attachment of teat cups 111a, 111 b, 111c, 111 d to the animal teats.

In the illustrated embodiment, the milk extracting arrangement 110 is a based on a walkthrough principle as indicated by the arrows in the image. An advantage therewith is that pass-through rate or circulation of animals through the milk extracting arrangement 110 is increased, allowing more animals to be served by one milk extracting arrangement 110, thereby increasing the total milk yield at the farm.

The animal 101 may visit the automatic milk extracting arrangement 110 voluntarily for being milked, tempted by palatable nutrition offered at the automatic milking equipment (sometimes referred to as free animal traffic). Alternatively, the animal 101 may be selected by a selection gate, leading the animal 101 to the automatic milk extracting arrangement 110 when passing between different sections of the farm, for example a resting area and a fodder area (sometimes referred to as forced animal traffic).

When the animal 101 is approaching a selection gate 118 to the milk extracting arrangement 110, an animal identifier device 116 is determining identity of the animal 101 to be milked.

The animal identifier device 116 may for example recognise the animal 101 by identifying a tag emitting wireless signals, for example a transponder, an RFID tag or Bluetooth tag with a unique encoding identity which is associated with the animal 101.

The tag may be attached to one or both ears of the animal 101 , arranged in a necklace around the neck of the animal 101 , under the hide of the head of the animal 101 , around a horn of the animal 101 , in a headwear, belt or other similar arrangement unequivocally associating the tag, and thereby also the unique encoding identity, with the animal 101.

However, the animal identifier device 116 may alternatively comprise a camera, and the animal 101 may be identified by image recognition, as animals e.g., cows typically have distinctive colour signs/ patterns on the hide, in combination with size and other differences in body constitution. Also, or alternatively an identification number encoded in a graphic encoding such as e.g., barcode, European Article Number (EAN) code, data matrix, Quick Response (QR) code may be printed on the tag or directly on the hide of the animal 101 , possibly in form of a tattoo. Any other convenient method for animal identification may be utilised in some embodiments.

The animal identifier device 116 may be communicatively connected to a controller 120. The controller 120 may comprise one or several digital computer or processing circuitry that controls one or more electrical systems, or electrical sub systems, of the farm, based on e.g., information read from the animal identifier device 116 and other sensors of the farm. The controller 120 is communicatively connected with a database 130. The communication may be made over a wired or wireless communication interface in different embodiments. The controller 120 may also be communicatively connected (wired or wireless) with various other entities of the milk system 100 such e.g., the milk extracting arrangement 110, the animal identifier device 116, the milk meters 112a, 112b, 112c, 112d, the time measurement device 119, the milk diverting mechanism 115, and/ or the cell count device 113. The wireless communication interface may comprise, or at least be inspired by wireless communication technology such as Wi-Fi, Wireless Local Area Network (WLAN), Ultra Mobile Broadband (UMB), Bluetooth (BT) to name but a few possible examples of wireless communications in some embodiments. Alternatively, radio access technologies may be applied, such as e.g., 5^th Generation wireless system; 4^th Generation wireless system; 3^rd Generation wireless system, etc.

The obtain identification of the animal 101 may be checked with the database 130 for checking whether the animal 101 has a milk permission.

For avoiding that any animal visits the milk extracting arrangement 110 too frequently, animals are prohibited to enter the milk extracting arrangement 110 without a milk permission granted to the individual animal. The milk permission is granted when a certain time period (such as e.g., 6-8 hours) has passed since the last milking event of the individual animal 101.

In case the animal 101 has a milk permission, the controller 120 may send a command to the selection gate 118 to open. The animal 101 is thereby allowed to enter the milk extracting arrangement 110. The selection gate 118 may immediately close again once the animal 101 has passed, thereby temporarily obstructing other animals from entering the milk extracting arrangement 110.

The animal 101 may then enter the milk extracting arrangement 110, possibly via a passage to a holding area or milking position where the milking equipment/ teat cups 111a, 111 b, 111c, 111 d may be attached onto the teats of the animal 101 , for example by a robotic arm 117, possibly after a cleaning process and/ or oxytocin stimulating treatment of the teats.

Milk may then be extracted from the teats via the teat cups 111a, 111 b, 111c, 111d and the extracted milk may be collected in a milk tank 122. An extracted amount of milk of each respective teat of the animal 101 , extracted during the milking session, may be measured by a set of milk meters 112a, 112b, 112c, 112d (this is sometimes referred to as quarter milking). This respective measurement may be stored in the database 130, associated with the identity of the animal 101 and an identity of the respective teat, i.e. , rear left, rear right, front left, front right (in case of an animal having four teats); and a time stamp or possibly some other identity of the milking session.

The granted milk permission usually does not mean that the animal 101 in question immediately rush to the milk extracting arrangement 110. She may be busy with other activities, there may be a queue of other animals to the milk extracting arrangement 110 and/ or she may be taking a power nap, be hanging out in social interaction areas of the farm, having a snack at the food table, making an excursion for fresh grass and a sunbathe in an outside recreation area, or enjoying a rotating cow brush, for example.

There may also be technical reasons for delay or variations between milking events for the animal 101 , for example an electricity cut, maintenance break, cleaning of the barn, etc., or even psychological reasons, such as a new employee at the farm, or a new machinery making unfamiliar noise may make the animals hesitant to approach the milk extracting arrangement 110.

For these and other similar reasons, the time period between two consecutive milking sessions will somewhat vary, also for a completely healthy animal, which in turn may cause milk secretion rate of the animal to vary, within an interval.

When the animal 101 is sick for example suffering from mastitis, it has been observed by the inventor that teat specific milk secretion rate/ quarter milk yield secreted per hour is reduced very early in the inflammation process. The teat specific milk secretion rate is reduced some days, such as about 2-3 days before a significant increase in somatic cell count is observed.

The reasons for this relation is found in biological and behavioural reactions and processes of the sick animal which per se are out of the scope of this invention, for example that pathogens attacks the epithelial tissue of sick animals in which the milk is synthesized and secreted, but also that the sick animal could be assumed to sleep/ rest more than the healthy animal (thereby extending the period between milking sessions), eat/ drink less than the healthy animal (thereby having less nutrition/ water to convert into milk), etc.

When the animal 101 returns to the milk extracting arrangement 110 for the next milking session, the above-described procedure is repeated, provided that the animal 101 has a granted milk permission. The controller 120 may then measure, via a time measurement device 119, an inter-milking session time period between two consecutive milking sessions, without any milking session in between, of the individual animal 101. This inter-milking session time period is then stored in the database 130, associated with the identity of the individual animal 101 and the time stamps of at least one of the two consecutive milking sessions.

The controller 120 then determines days in lactation of the identified individual animal 101 to be milked and compares this value with a day threshold limit. The day threshold limit may be set to a value between 10 and 90 days, preferable 30-60 days.

The reason is that the (teat specific) milk secretion rate during commencement of the days in lactation may be irregular, but also that several measurements are required in order to establish a “normal” variation of milk secretion rates of the healthy animal, to be used as a reference for later made measurements, as will be explained.

When the animal 101 is determined to have days in lactation exceeding the threshold limit, the controller 120 then calculate a teat specific milk secretion rate by dividing the amount of extracted milk of each teat during the latest milking session, with the associated inter-milking session time period.

This calculated teat specific milk secretion rate is then stored at least temporarily, associated with the identity of the individual animal 101 and the identity or time stamp of the latest milking session. The calculated teat specific milk secretion rate and the associated values may be stored in the database 130 and later retrieved for calculating a rolling milk secretion rate deviation limit.

The controller 120 then calculate a rolling milk secretion rate deviation limit, which is animal specific, teat specific and updated at each milking session, based on stored teat specific milk secretion rates, obtained from the database 130, from a number of previous milking sessions, within a rolling time period, closest in time to the latest milking session.

The teat specific milk secretion rates of the animal 101 of the latest milking session are then compared by the controller 120 with the teat specific rolling milk secretion rate deviation limit. Also, the controller 120 is configured to determine whether any one of the compared teat specific milk secretion rates of the animal 101 during the latest milking session is lower than the teat specific rolling milk secretion rate deviation limit, based on the made comparison.

The controller 120 is also configured to trigger activation of the milk diverting mechanism 115 during at least one future milking session of the individual animal 101 after a first time limit from the latest milking session, to divert the milk sample from the milk forwarding entity 114 and forward the milk sample or the sub sample of the milk sample to the cell count device 113. A cell count measurement of the number of somatic cells in the milk extracted from the individual animal 101 by the cell count device 113 is thereby enabled, when any one of the compared teat specific milk secretion rates of the latest milking session is lower than the teat specific rolling milk secretion rate deviation limit.

Hereby, cell counting is enabled by the cell count device 113, only when a decreased/ low teat specific milk secretion rate has previously been made within a certain time period for example within about 1-6 days before. The number of somatic cell counting sessions is radically reduced in comparison with general somatic cell counting based on milk extracted during every milking session. Less chemicals are used/ wasted in this process, saving money for the farmer.

By reducing the number of somatic cell counting sessions, time is saved at the milk extracting arrangement 110, leading to increased throughput of animals, i.e. increased milk yield per time unit at the farm. By using the milk extracting arrangement 110 more efficiently, the total milk yield at the farm is increased, without having to make investments in additional milk extracting arrangements 110/ milking robots.

At the same time, the risks of not detecting a mastitis animal at the farm is not reduced, in comparison with making somatic cell counting at every milking session of every animal.

Figure 2 graphically illustrates a timeline on which relations between milk permissions 210a, 210b of the animal 101 ; milking sessions 220a, 220b of the animal 101 ; inter-milking session time period 230, i.e., a time period between two consecutive milking sessions 220a, 220b of the animal 101 , without any intermediate other milking session in between.

The placement of the animal 101 on the illustrated timeline represents the “current” time, i.e., the milking session 220a is the latest milking session 220a of the animal 101 at the moment illustrated in Figure 2.

A teat specific milk secretion rate is calculated by dividing the amount of extracted milk of each teat during the latest milking session 220a, with the associated inter-milking session time period 230. The associated inter-milking session time period 230 is the time period between the latest milking session 220a and the penultima milking session 220b, without any milking sessions of the same animal 101 between those two consecutive milking sessions 220a, 220b.

The calculated teat specific milk secretion rate is compared with a rolling milk secretion rate deviation limit, which is calculated based on stored teat specific milk secretion rates, obtained from the database 130, from a number of previous milking sessions 220a, 220b, during a rolling time period as schematically illustrated and explained in Figures 3A-3C.

In case at least one of the calculated teat specific milk secretion rates is lower than the rolling milk secretion rate deviation limit, the milk diverting mechanism 115 is triggered to divert a milk sample from the milk forwarding entity 114 and forward the milk sample to the cell count device 113 after a first time limit 241 from the latest milking session 220a/ triggering milking session, in the future. Thereby, a cell count measurement of the number of somatic cells in milk extracted from the individual animal 101 is enabled in a future milking session 220x, 220y, occurring after the first time limit 241 .

The first time limit 241 may be set to about 1-2 days after the triggering milking session, i.e., the latest milking session 220a that has triggered the activation of the milk diverting mechanism 115 due to detection of at least one teat specific milk secretion rate of that milking session 220a being lower than the rolling teat specific milk secretion rate deviation limit.

Increased somatic cell count measurements could be expected after about 1-2 days after an observation has been made of decreased teat specific milk secretion rate of an animal with infection/ mastitis; and in any case within a second time limit 242, which is within about between 3-6 days from the latest milking session 220a.

During a first future milking session 220x occurring after the first time limit 241 , a milk sample may be diverted to the cell count device 113. Somatic cell count may be performed, and a comparison may be made with a cell count threshold limit. The cell count threshold limit may for example be set to 400 000 cells per ml of milk, or some other appropriate configurable value such as 300 000 cells per ml of milk, etc., (non-limiting examples). This cell count threshold limit may be configurable by the farmer, for example, based on legal requirements and/ or quality ambitions.

In case the somatic cell count of the milk sample exceeds the cell count threshold limit, it could be concluded that the animal 101 has an infection/ mastitis risk. When this occurs, an alert may be generated to get the attention of the farmer to decide whether any particular additional measure would have to be made for the animal 101 , such as disallowing milk of the animal 101 to be forwarded to the common bulk tank 122, or otherwise be used for human consumption; by introducing medicine to the animal 101 , special diet, calling a veterinarian, etc.

Making additional somatic cell counts after having concluded that the animal 101 has infection/ mastitis risk due to increased somatic cell count does not add any information, besides merely confirming the infection/ mastitis risk.

When a cell count measurement of the future milking session 220x occurring after the first time limit 241 , exceeds a cell count threshold limit, the milk diverting mechanism 115 and/ or the cell count device 113 may be deactivated. Thereby, any later cell count measurement by the cell count device 113, for example during a second future milking session 220y, occurring later in time than the future milking session 220x of the cell count measurement exceeding the cell count threshold limit, may be disabled.

In case none of the cell count measurements of the future milking sessions 220x, 220y of the individual animal 101 performed within the limited activation time period 240, i.e., after the first time limit 241 , but before the second time limit 242, results in a cell count measurement exceeding the cell count threshold limit, the animal 101 could be assumed to not suffer from infection/ mastitis.

Future cell count measurement by the cell count device 113 may then be disabled when the second time limit 242 of the limited activation time period 240 has been reached, about 3-6 days, after the latest milking session 220a when the activation of the milk diverting mechanism 115 was triggered. The milk diverting mechanism 115 and/ or the cell count device 113 may thereby be deactivated.

Figure 3A illustrates milking data 300 of teat specific milk secretion rates of an animal 101 at different milking sessions 220a, 220b, 220c, 220d, which have been made at different moments in time.

The teat specific milk secretion rates of the animal 101 is calculated, during or in association with each respective milking session 220a, 220b, 220c, 220d.

The teat specific milk secretion rates are calculated by dividing the amount of extracted milk of each teat during the latest milking session 220a of the animal 101 , with the associated inter-milking session time period 230. These teat specific milk secretion rates are compared with a respective teat specific rolling milk secretion rate deviation limit 310a, 310b, 310c, 310d.

The teat specific rolling milk secretion rate deviation limit 310a, 310b, 310c, 31 Od is animal specific, i.e., unique for the individual animal 101 and teat specific, i.e., unique for each respective teat of the animal 101 , and updated at each milking session 220a, 220b, 220c, 220d. The teat specific rolling milk secretion rate deviation limit 310a, 310b, 310c, 31 Od is calculated based on the teat specific milk secretion rates from a number of previous milking sessions 220b, 220c, 220d within a rolling time period 320, closest in time to the latest milking session 220a, but not including the latest milking session 220a.

The teat specific rolling milk secretion rate deviation limit 310a, 310b, 310c, 31 Od may in some alternative embodiments be only one common teat specific rolling milk secretion rate deviation limit.

Incomplete or interrupted milking sessions 220a, 220b, 220c, 220d of the animal 101 occurring within the rolling time period 320, and/ or exceptional outlier values may be excluded from the calculation of the teat specific rolling milk secretion rate deviation limit 310a, 310b, 310c, 31 Od.

The rolling time period 320 may comprise the previous milking sessions 220b, 220c, 220d that have been performed during the latest 3-10 days, as counted from the triggering milking session. In some embodiments, the rolling time period 320 does not comprise the latest milking session 220a. A drop in teat specific milk secretion rate during the latest milking session 220a is thereby not allowed to influence the calculation of the teat specific rolling milk secretion rate deviation limit 310a, 310b, 310c, 31 Od, leading to less false positives. Thereby, unnecessary somatic cell count is avoided.

However, in some alternative embodiments, the rolling time period 320 may also comprise the latest milking session 220a, in addition to the previous milking sessions 220b, 220c, 220d.

In the illustrated scenario, one teat specific milk secretion rate of the latest milking session 220a is lower than the rolling milk secretion rate deviation limit 310a, 310b, 310c, 31 Od. Thereby, activation of the milk diverting mechanism 115 is triggered, for diverting a milk sample from the milk forwarding entity 114 and forward the milk sample or the sub sample of the milk sample to the cell count device 113, during a future milking session 220x, 220y occurring after the first time limit 241 as counted from the triggering milking session. Cell count measurement of milk extracted from the individual animal 101 during the future milking session 220x, 220y occurring after the first time limit 241 is thereby enabled.

The teat specific rolling milk secretion rate deviation limit 310a, 310b, 310c, 31 Od may be repeatedly updated and recalculated after each milking session 220a, 220b, 220c, 220d, based on the respective calculated teat specific milk secretion rates of the animal 101 of the milking sessions 220a, 220b, 220c, 220d, within the rolling time period 320.

The teat specific rolling milk secretion rate deviation limit 310a, 310b, 310c, 31 Od may be calculated to a value with a margin below an average value for the teat specific milk secretion rates of the number of the previous milking sessions 220b, 220c, 220d closest in time to the latest milking session 220a, in some embodiments.

The margin may for example be 10% - 20% of the spread of the teat specific milk secretion rates of the number of the previous milking sessions 220b, 220c, 220d closest in time to the latest milking session 220a, for example, or somewhere in between.

The teat specific rolling milk secretion rate deviation limit 310a, 310b, 310c, 31 Od may alternatively be calculated by multiplication of an inter percentile range 330 with a factor, as schematically illustrated in Figure 3B, illustrating the inter percentile range 330 of one teat specific rolling milk secretion rate deviation limit 310a.

The inter percentile range 330 may have a lower limit 331 and an upper limit 332, which may enclose a predetermined or configurable percentile of the calculated teat specific milk secretion rates of the previous milking sessions 220b, 220c, 220d within the rolling time period 320, such as for example 80%, or a percentage between for example in an interval between 60%-99%. Thereby, extreme values/ outliers are filtered out.

For example, the lower limit 331 of the inter percentile range 330 may be subtracted from the upper limit 332 of the inter percentile range 330, and the result may be multiplied with the factor, for example 1.5. Other factors may be selected, such as for example in an interval between 0.1 - 5, e.g., 1.5 - 3.5, etc. The result of this calculation may then be subtracted from the lower limit 331 of the inter percentile range 330.

Figure 3C also illustrates milking data 300 of teat specific milk secretion rates of an animal 101 at different milking sessions 220a, 220b, 220c, 220d, which have been made at different moments in time, for example about twice a day.

In the illustration in Figure 3C, it is shown an example wherein the teat specific rolling milk secretion rate deviation limit 310a is increasing over time, as the rolling time period 320 is advancing in time, due to an increase in teat specific milk secretion rates of the animal 101 at different milking sessions 220a, 220b, 220c, 220d, over time during the observed/ illustrated time period.

The level and level variations in milk secretion rate are different for different individual animals 101 at the farm depending on for example genetic conditions, days in milk, nutrition, why a fixed/ generic milk secretion rate deviation limit 310a applied for all animals at the farm cannot be used without having excessive amount of false positive results and/ or undetected drops in teat specific milk secretion rate.

Figure 4 illustrates a scenario according to an embodiment of a milk system 100. The controller 120, upon detection that the cell count measurement for the animal 101 exceeds the cell count threshold limit, may alert the farmer. The farmer thereby becomes aware of the situation concerning the animal 101 and is enabled to check the animal status, for determining whether a veterinarian is to be consulted, antibiotics to be provided, etc.

The alert may be output on an output device 410, for example embodied as a mobile telephone or computer of the farmer. However, other examples of output device 410 may be a display device/ screen, a sound generating device/ loudspeaker, a haptic device, etc., which may be arranged in/ at the barn, or at the home of the farmer, or be carried by the farmer.

The alert may comprise information concerning an identity of the animal 101 and information concerning the detected somatic cell count exceeding the threshold limit. Other information may also optionally be provided, for example current location of the animal 101 , milk yield data of the animal 101 , teat specific milk secretion rate, physical data of the animal 101 etc., data which may assist the farmer in determining level of seriousness/ priority of the alert.

The controller 120 may be connected to the output device 410 via a wired connection, or alternatively a wireless connection via a transceiver 125, for example based on any of the previously enumerated technologies.

The controller 120 may comprise a computer of hardware or hardware/ firmware device implemented using processing circuity such as, but not limited to, a processor, Central Processing Unit (CPU), a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a System-on-Chip (SoC), a programmable logic unit, a microprocessor, an application-specific integrated circuit, or any other device capable of electronically performing operations in a defined manner. Furthermore, the controller 120 may comprise a memory in some embodiments. The optional memory may comprise a physical device utilised to store data or programs, i.e., sequences of instructions, on a temporary or permanent basis. According to some embodiments, the memory may comprise integrated circuits comprising silicon-based transistors. The memory may comprise e.g., a memory card, a flash memory, a USB memory, a hard disc, or another similar volatile or non-volatile storage unit for storing data such as e.g., ROM (Read-Only Memory), PROM (Programmable Read-Only Memory), EPROM (Erasable PROM), EEPROM (Electrically Erasable PROM), etc. in different embodiments.

At least some of the above-described actions to be performed by the controller 120 may be implemented by a computer program. The computer program may be provided for instance in the form of a computer-readable medium, i.e. a such as a tangible electronic, magnetic, optical, infrared, electromagnetic, and/ or semiconductor system, apparatus, and/ or device data carrier carrying computer program code for performing at least some of the described method steps according to some embodiments when being loaded into the one or more processing circuits of the controller 120. The computer program may be provided as computer program code on a server and downloaded to the controller 120 remotely, e.g., over an Internet or an intranet connection.

The terminology used in the description of the embodiments as illustrated in the accompanying drawings is not intended to be limiting of the described milk system 100; the controller 120; the method; the computer program and/ or the computer-readable medium. Various changes, substitutions and/ or alterations may be made, without departing from invention embodiments as defined by the appended claims.

As used herein, the term “and/ or” comprises any and all combinations of one or more of the associated listed items. The term “or” as used herein, is to be interpreted as a mathematical OR, i.e., as an inclusive disjunction; not as a mathematical exclusive OR (XOR), unless expressly stated otherwise. In addition, the singular forms “a”, “an” and “the” are to be interpreted as “at least one”, thus also possibly comprising a plurality of entities of the same kind, unless expressly stated otherwise. It will be further understood that the terms “includes”, “comprises”, “including” and/ or “comprising”, specifies the presence of stated features, actions, integers, steps, operations, elements, and/ or components, but do not preclude the presence or addition of one or more other features, actions, integers, steps, operations, elements, components, and/ or groups thereof. A single unit such as e.g., a processor may fulfil the functions of several items recited in the claims. The mere fact that certain measures or features are recited in mutually different dependent claims, illustrated in different figures, or discussed in conjunction with different embodiments does not indicate that a combination of these measures or features cannot be used to advantage. A computer program may be stored/ distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware but may also be distributed in other forms such as via Internet or other wired or wireless communication system.

Claims

PATENT CLAIMS

1. A milk system (100) for milking a herd of individual animals (101), wherein the milk system (100) comprises: a milk extracting arrangement (110) configured to extract milk from each individual animal (101) during a milking session (220a, 220b, 220c, 220d) via teat cups (111a, 111 b, 111c, 111d), attached to teats of the individual animal (101), and configured to provide the extracted milk to a milk forwarding entity (114), which milk forwarding entity (114) is configured to temporarily store and/ or transport milk from one animal (101) at a time from the milk extracting arrangement (110) to a bulk tank (122); a cell count device (113), configured to receive a milk sample or a sub sample of the milk sample and measure a number of somatic cells in the milk sample; a milk diverting mechanism (115), connected to the milk forwarding entity (114) and to the cell count device (113), and configured to divert the milk sample from the milk forwarding entity (114) and forward the milk sample or the sub sample of the milk sample to the cell count device (113); an animal identifier device (116) configured to determine identity of the individual animal (101) to be milked; a database (130); a set of milk meters (112a, 112b, 112c, 112d), wherein each milk meter (112a, 112b, 112c, 112d) is arranged to measure an extracted amount of milk of each respective teat of the individual animal (101) during the milking session (220a, 220b, 220c, 220d); a time measurement device (119) configured to measure time; a controller (120) communicatively connected to the milk extracting arrangement (110), the animal identifier device (116), the milk meters (112a, 112b, 112c, 112d) , the time measurement device (119), the milk diverting mechanism (115) and the database (130); wherein the controller (120) is configured to, repeatedly for every milking session (220a, 220b, 220c, 220d): store the extracted amount of milk of each respective teat of the individual animal (101) in the database (130), associated with the identity of the individual animal (101), an identity of the teat, and a time stamp of the milking session (220a, 220b, 220c, 220d); determine, via the time measurement device (119), an inter-milking session time period (230) between two consecutive milking sessions (220a, 220b, 220c, 220d), without any milking session in between, of the individual animal (101); store the inter-milking session time period (230) at least temporarily, associated with the identity of the individual animal (101) and the time stamps of the two consecutive milking sessions (220a, 220b, 220c, 220d); determine days in lactation of the identified individual animal (101) to be milked; in case the determined days in lactation exceeds a day threshold limit: calculate a teat specific milk secretion rate by dividing the amount of extracted milk of each teat during the latest milking session (220a), with the associated inter-milking session time period (230); store the calculated teat specific milk secretion rate, associated with the identity of the individual animal (101) and the latest milking session (220a) in the database (130); calculate a rolling milk secretion rate deviation limit (310a, 310b, 310c, 31 Od), which is animal specific and teat specific and updated at each milking session (220a, 220b, 220c, 220d), based on stored teat specific milk secretion rates, obtained from the database (130), from a number of previous milking sessions (220b, 220c, 220d) within a rolling time period (320), closest in time to the latest milking session (220a); compare each teat specific milk secretion rate of the latest milking session (220a) with the corresponding teat specific rolling milk secretion rate deviation limit (310a, 310b, 310c, 310d); determine whether any one of the compared teat specific milk secretion rates is lower than the corresponding teat specific rolling milk secretion rate deviation limit (310a, 310b, 310c, 31 Od), based on the made comparison; and trigger activation of the milk diverting mechanism (115) during at least one future milking session (220x, 220y) of the individual animal (101) after a first time limit (241) from the latest milking session (220a), to divert the milk sample from the milk forwarding entity (114) and forward the milk sample or the sub sample of the milk sample to the cell count device (113), thereby enabling a cell count measurement of the number of somatic cells in the milk extracted from the individual animal (101), when any one of the compared teat specific milk secretion rates of the latest milking session (220a) is lower than the rolling milk secretion rate deviation limit (310a, 310b, 310c, 31 Od) for the specific teat, the latest milking session (220a) becomes the triggering milking session.

2. The milk system (100) according to claim 1 , wherein the rolling time period (320) comprises the previous milking sessions (220b, 220c, 220d) closest in time to the latest milking session (220a) that have been performed during the latest 3-10 days.

3. The milk system (100) according to any one of claims 1-2, wherein the controller (120) is configured to calculate an average for the teat specific milk secretion rates of the number of the previous milking sessions (220b, 220c, 220d) closest in time to the latest milking session (220a) leaving outliers out of the calculation, and set the rolling milk secretion rate deviation limit (310a, 310b, 310c, 31 Od) for the specific teat to a value with a margin below the calculated average.

4. The milk system (100) according to any one of claims 1-3, wherein the controller (120) is configured to calculate the inter percentile range (330) for the teat specific milk secretion rates of the number of the previous milking sessions (220b, 220c, 220d) closest in time to the latest milking session (220a), wherein the inter percentile range (330) has a lower limit value (331) and/ or an upper limit value (332); and recalculate the rolling milk secretion rate deviation limit (310a, 310b, 310c, 31 Od) for the respective teats based on multiplication of the inter percentile range (330) with a factor.

5. The milk system (100) according to any one of claims 1-4, wherein the first time limit (241) is set between 1-2 days from the triggering milking session.

6. The milk system (100) according to any one of claims 1-5, wherein the controller (120) is communicatively connected to the cell count device (113) and wherein the controller (120) is configured to detect when the cell count measurement of the future milking session (220x) occurring after the first time limit (241) from the triggering milking session exceeds a cell count threshold limit; and deactivate the milk diverting mechanism (115) and/ or the cell count device (113) upon the detection of the cell count measurement exceeding the cell count threshold limit.

7. The milk system (100) according to claim 6, wherein the controller (120) is configured to alert a farmer upon detection of the cell count measurement of the future milking session (220x), exceeding the cell count threshold limit.

8. The milk system (100) according to any one of claims 1-7, wherein the controller (120) is communicatively connected to the cell count device (113) and wherein the controller (120) is configured to deactivate the milk diverting mechanism (115) and/ or the cell count device (113), when a second time limit (242) counted from the triggering milking session is reached without detection of any cell count measurement of any future milking session (220x, 220y) performed after the first time limit (241), but before the second time limit (242), exceeding the cell count threshold limit.

9. The milk system (100) according to claim 8, wherein the second time limit (242) is set between 3-6 days from the triggering milking session.

10. The milk system (100) according to any one of claims 1-9, wherein the day threshold limit for the determined days in lactation is set to a value between 10 and 90 days, preferable 30-60 days.

11. The milk system (100) according to any one of claims 1-10, wherein the milk diverting mechanism (115) comprises a pump.

12. The milk system (100) according to any one of claims 1-11 , wherein the controller (120) is configured to determine a time value at a first milking session of a lactation period of the individual animal (101) and store the time value, associated with the identity of the individual animal (101) in the database (130), and determine days in lactation of the identified individual animal (101) based on the stored time value.