Determining a variation of mass per unit length of a food product
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- MAJA MASCHINENFABRIK HERMANN SCHILL GMBH & CO KG
- Filing Date
- 2025-12-16
- Publication Date
- 2026-06-25
Smart Images

Figure EP2025087448_25062026_PF_FP_ABST
Abstract
Description
[0001] Determining a variation of mass per unit length of a food product
[0002] FIELD OF THE INVENTION
[0003] This disclosure relates to a computer-implemented method for determining a mass per unit of length variation of a food product, in particular to such method involving the determination of weights of food items in a group of food items that comprises food items from different food products. This disclosure also relates to a computer, cutting system and computer program for performing such method.
[0004] BACKGROUND
[0005] US2008 / 0190303 A1 discloses a device for slicing a food bar which has a certain mass per unit length variation over its length, into food portions, e.g. food slices, that are to have a predefined weight. The device can calculate, based on historical information, a prediction of the mass per unit length variation of an unsliced food bar.
[0006] Predicting a mass per unit of length variation of an unsliced food bar can get complicated quite fast, especially if there are no measurements available of individual slices of previously sliced food bars. This may for example be the case if several slices are packed together in a group and are only weighed after packing.
[0007] In light of the above, there is a need in the art for a method for determining a mass per unit length variation of a food product that obviates the need for measuring individual slices.
[0008] SUMMARY
[0009] Therefore, one aspect of this disclosure relates to a computer-implemented method for determining a mass per unit of length variation of a food product. The method comprises obtaining, e.g. receiving, weight data acquired by a weighing system. The weight data are indicative of one or more respective weights of one or more groups of food items and of a weight of a first group of food items. Each group out of the one or more groups of food items is a group of food items that have been separated from, e.g. cut off from, a first food product. Further, the first group of food items comprises a first sub-group of one or more food items that have been separated from, e.g. cut off from, the first food product and a second sub-group of one or more food items that have been separated from, e.g. cut off from, a second food product. The first food product and second food product are a same type of food product, for example a beef loin primal cut. The method also comprises obtaining position data indicating, for each group of food items for which the weight data indicate the weight and for the first sub-group of the first group, a position in the first food product. Then, the mass per unit of length variation of the food product is determined, which comprises steps (i) and (ii). Step (i) is estimating a weight of the first sub-group of the first group and determining, based on the estimated weight and based on the position indicated by the position data for the first sub-group of the first group, a mass per unit of length value for the first sub-group of the first group. Step (ii) is determining, for each of the one or more groups of food items, based on the weight of the group of food items in question and based on the position indicated by the position data for the group of food items in question, a mass per unit of length value.
[0010] The different values for mass per unit of length for the different groups of food items indicate a variation of the mass per unit of length.
[0011] As known, the mass per unit of length typically varies along a dimension of a food product. Not only because the density (grams I m3) within the food product varies along such dimension, but also because a size of a cross-section that is perpendicular to such dimension varies. Even if for example the food product is pressed into a cylinder, as happens in the industry with primal pieces of beef, then still the piece’s cross section perpendicular to the length axis of the cylinder varies because there will always be some void spaces in the cylinder that are not filled with the beef. The mass per unit of length variation is a valuable parameter to determine, because it allows to determine how thick a food item should be when the food item is to have a certain weight. To illustrate, if X(x) indicates the mass per unit length at position x, then the weight, w(xi), of a food item that is cut off from the food product at position xi is approximately given by w(xx) = r,) * d, wherein d indicates the thickness of the food item that is cut off. Herein, X(x) may be given by X(x) = <5(x) * A(x), wherein 8(x) indicates the density [g / m3] of the food product at position x, and A(x) indicates the cross section [m2] of the food product at position x. It should be appreciated that some parameter value “at position x” may be understood as an average parameter value of a range near and / or around position x. More precisely, if the food item that is cut off from the food product “at position xi" extends between position XA and XB, then the weight of the food items is given by wix^) = A x fXB8 (x)dx for A constant along x and by when A varies along x.
[0012] As used herein, thickness of a (sub-)group or food item may be understood as the dimension of the (sub-)group or food item that extends in the same direction as the dimension along which the mass per unit of length variation is known. As used herein, the length of a positional range of a (subgroup or food item may correspond to the thickness of the (sub-)group or food item. Further, it should be appreciated that when for example a variation of the density within the food product in three dimensions is estimated, 8 x,y,z), and a cross section of the food product along at least one of these dimensions is estimated, then effectively a mass per unit of length variation along that at least one dimension is determined as referred to herein.
[0013] The disclosed method is advantageous as it allows to determine a mass per unit of length variation even when weight data for individual food items are not available, but only weight data indicating the weight per group of food items, and even when there are groups that contain food items coming from different food products. For example, it may be that slices are cut off from primal pieces of meat and that the slices are to packaged in groups of 5 slices. Then such a group of 5 slices may contain 3 slices from one primal piece and 2 slices from another primal piece. The method disclosed herein namely enables to determine the weight of each food item in such a mixed group based on the total number of food items in such mixed group and on a total weigh of this mixed group. One way to do this would be to determine the average weight of the food items in the mixed group. The inventor realized this enables to more accurately determine the mass per unit of length variation than would be the case when such mixed groups would not be considered.
[0014] The position data for a single group of food items may indicate multiple positions, for example one position in one food product for one sub-group in that group of food items, and another position in another food product for another sub-group in that group of food items. Additionally or alternatively, an indicated position for a single group of food items would typically be indicative of a range within the original food product in which range the food items were present before the original food product was cut. Further, the indicated positions may be absolute positions, e.g. 12 cm from the front of a primal piece, or may be relative positions, e.g. at position 10% where 0% indicates the front of a primal piece and 100% indicates the end of the primal piece. A relative position may also be indicated by a relative order number, e.g. the 5thgroup originating from the food product.
[0015] Irrespective of the above, preferably, the position data indicate, for each food item, a position in the food product from which the food item in question originates, e.g. a range in the food product from the food item in question originates.
[0016] A mass per unit length variation referred to herein may be understood to indicate respective mass per unit length values for a plurality of positions in a food product. Each (sub-) group of food items referred to herein is associated with a position in the first food product, e.g. the position as indicated by the position data. Note that this associated position is in principle also indicative of a positional range in the first food product, namely the range from which the (sub-)group of food items in question originates. Further, for each of the one or more groups of food items, the weight is known. A (sub-)group’s mass per unit of length value for the position and / or range indicated for that group, may be determined by dividing the weight of the group in question by a length of the positional range.
[0017] Preferably, a food item referred to herein is a slice. Further, preferably each group of food items is or will be packaged together.
[0018] Further, it should be noted that estimating some parameter value is one way of determining that parameter value.
[0019] In an embodiment, the weight of the first sub-group of the first group is estimated based on a total number of food items in the first group of food items and based on the weight of the first group of food items and based on a number of food items in the first sub-group of the first group.
[0020] For example, the ratio between number of food items in the first sub-group of the first group and the total number of food items in the first group may be multiplied by the weight of the first group to estimate the weight of the first sub-group of the first group.
[0021] When the position data indicate a position in the second food product for the second sub-group of the first group, the weigh may additionally or alternatively be estimated based on the weight of the first group of food items and based on the position of the first sub-group of the first group in the first food product and based on the position of the second sub-group of the first group in the second food product.
[0022] The position of the first sub-group of the first group in the first food product may have certain dimension. The first sub-group may for example have had a certain total thickness in the first food product. Likewise, the position of the second sub-group of the first group in the second product may have certain dimensions as well. The second sub-group may for example have had a certain total thickness in the second food product. For example, the ratio between the total thickness of the first sub-group and the sum of the total thicknesses of the first and, resp. second sub-group may be multiplied by the weight of the first group to estimate the weight of the first sub-group.
[0023] In an embodiment, determining the mass per unit of length value for the first sub-group of the first group comprises determining an average weight of the food items in the first group of food items based on the total number of food items in the first group and based on the weight of the first group of food items.
[0024] The above steps for estimating the weight of the sub-group of the first group may be performed for any sub-group referred to herein for estimating the weight thereof.
[0025] For example, the average weight of food items in a group may be given by the total weight of the group divided by the total number of food items in that group. The weight of each food item in the first sub-group may then be taken as equal to this average weight. If for the weight of each food item in the first sub-group is known, then the weight of the first sub-group can be easily calculated by multiplying this value with the number of food items in the first sub-group.
[0026] The average weight may also be a weighted average. A weighted average may for example be used if it is known that the first sub-group contains heavier slices than the second sub-group, for example because the first sub-group originates from a rear end of the first food product and the second sub-group originates from a front end of the second food product wherein typically the front rear end part of that type of food item has a higher density and / or larger cross section than the front end part of that type of food item.
[0027] In an embodiment, the weight data are indicative of a weight of a second group of food items. Herein, the second group of food items comprises a first sub-group of one or more food items that have been separated from, e.g. cut off from, the first food product and a second sub-group of one or more food items that have been separated from, e.g. cut off from, a third food product. The first, second and third food product are the same type of food product. In this embodiment, the position data indicate a position for the first sub-group of the second group. Further, determining the mass per unit of length variation comprises estimating a weight of the first sub-group of the second group and determining, based on the estimated weight and based on the position indicated by the position data for the first sub-group of the second group, a mass per unit of length value for the first sub-group of the second group.
[0028] This embodiment enables to accurately determine the mass per unit of length variation even if food items at one end are grouped together with food items of the second food product and food items at the other end are grouped together with food items of the third food product.
[0029] In an embodiment, the method comprises determining, for each food product out of a plurality of food products, a mass per unit length variation. The plurality of food products being of the same type as the first and second food product and the plurality of food products comprising the first and second food product. Herein, determining, for each food product out of a plurality of food products, the mass per unit of length variation, for each food product out of the plurality of food products: (a) receiving weight data acquired by the weighing system, the weight data being indicative of one or more respective weights of one or more groups of food items, wherein each group out of the one or more groups of food items is a group of food items that have been separated from, e.g. cut off from, the food product in question, and
[0030] (b) receiving position data indicating, for each group of food items for which the weight data indicate the weight, a position of the group of food items in question in the food product in question, and
[0031] (c) for each group of the one or more groups of food items, determining, based on the weight of the group in question and based on the position indicated by the position data, a mass per unit of length value for the group of food items in question. In this embodiment, the method comprises determining a reference mass per unit length variation for said type of food product based on the respectively determined mass per unit length variations of the plurality of food products.
[0032] This embodiment enables to accurately determine a reference mass per unit length variation which may be assumed correct for any food product of that type of food product. Since the reference mass per unit of length variation is based on a plurality of mass per unit of length variations as determined for a plurality of food products, it is quite accurate.
[0033] The plurality of food products also comprises the third food product, if the weight data are indicative of the weight of the second group of food items.
[0034] In an embodiment, the plurality of food products comprises a subset of multiple food products. Further, in this embodiment, for each food product out of the multiple food products, the weight data are indicative of a weight of a particular group of food items. The particular group of food items comprises a first sub-group of one or more food items that have been separated from, e.g. cut off from, the food product in question and a second sub-group of one or more food items that have been separated from, e.g. cut off from, another food product. In this embodiment, determining the mass per unit of length variation comprises, for each food product out of the subset of multiple food products, estimating a weight of the first sub-group of the particular group and determining, based on the estimated weight of the first sub-group of the particular group and based on a position as indicated by the position data for the firs sub-group of the particular group, a mass per unit of length value for the first sub-group of the particular group.
[0035] The weight of the first sub-group of the particular group may be estimated based on a total number of food items in the particular group of food items and based on the weight of the particular group of food items and based on a number of food items in the first sub-group of the particular group.
[0036] For example, the ratio between number of food items in the first sub-group of the particular group and the total number of food items in the particular group may be multiplied by the weight of the particular group to estimate the weight of the first sub-group of the particular group.
[0037] When the position data indicate a position in the second food product for the second sub-group of the particular group, the weight may additionally or alternatively be estimated based on the weight of the particular group of food items and based on the position of the first sub-group of the particular group in the first food product and based on the position of the second sub-group of the particular group in the second food product. The position of the first sub-group of the particular group in the first food product may have certain dimensions. The first sub-group may for example have had a certain total thickness in the first food product. Likewise, the position of the second sub-group of the particular group in the second product may have certain dimensions as well. The second sub-group may for example have had a certain total thickness in the second food product. For example, the ratio between the total thickness of the first sub-group and the sum of the total thicknesses of the first and second sub-group may be multiplied by the weight of the particular group to estimate the weight of the first sub-group.
[0038] Thus, the subset of multiple food products are the food products of which food items are eventually grouped with food items from other food products.
[0039] The multiple food products may comprise at least two food products, for example.
[0040] Of course, each food product can have overlap with two food products, in the sense that one or more of its food items are grouped together with food items from a first other food product and that one or more of its food items are grouped together with food items from a second other food product. If this is the case, then for such food product, the weight data are indicate of a weight of a further particular group of food items. This further particular group of food items comprises a first subgroup of one or more food items that have been separated from the food product in question and a second subgroup of one or more food times that have been separated from another food product. For such food product, a weight of each food items in the first sub-group of the further particular group is determined based on a total number of food items in the further particular group and based on the weight of the further particular group of food items. Then, step (c) is performed based also on the determined weights for the one or more food items in the first sub-group of the further particular group.
[0041] In an embodiment, each mass per unit length variation determined for each food product out of the plurality of food products, is a mass per unit length variation along a first direction. In this embodiment, determining the reference mass per unit length variation comprises standardizing the mass per unit length variations determined for the plurality of food products so that each mass per unit length variation indicates mass per unit length for a same plurality of relative positions along the first direction.
[0042] The distance over which each food product extends in the first direction may vary per food product. To illustrate, if each mass per unit length variation is a mass per unit length variation along a length of the food product, then each food product may have a different length. Without standardization, it would be quite challenging to arrive at a sufficiently accurate reference mass per unit of length variation. The standardization for example involves compressing or extending each mass per unit of length variation such that each covers the same distance. Alternatively, one could express each mass per unit of length of variation for relative positions, such that each mass per unit of length variation extends from 0% of the length to 100% of the length.
[0043] In an embodiment, each respective mass per unit length variation determined for a food product is represented by an array K of length N with N being a positive integer number, K =
[0044] {fc-L, fc2, fc3, ... , kN-ltkN}, wherein N has some value for one food product out of the plurality of food products and a different value for another food product out of the plurality of food products. In this embodiment, standardizing the mass per unit length variations comprises determining, for each array K, based on the array K in question, an array R of length M, M being a positive integer number, R =
[0045] {m1,m2,m3, wherein M has the same value for each array K. For every element in
[0046] R applies that determining the reference mass per unit length variation based on the respectively determined arrays R.
[0047] This embodiment provides for a standardization that has been found to work well. N would typically be the number of food items that are separated from the food product in question, e.g. the number of slices that are cut off from the food product in question.
[0048] In an embodiment, determining the reference mass per unit length variation comprises
[0049] - determining for a particular food product out of the plurality of food products, a particular array Rpof length M, M being a positive integer number, Rp= {mp l, mp 2,mp 3, ... , mp M-1, mp M}, array Rprepresenting an, optionally standardized, mass per unit length variation of the particular food product, wherein an array Rcurrentof length M, Rcurrent=
[0050] {Recurrent, 1' ^current, 2' ^current, 3' - .^ urrcnt.M- ^ urrcnt.M}. represents a previously determined reference mass per unit length variation, and
[0051] - updating array Rcurrent, this step comprising updating, for each i from 1 to M, mcurrent ibased on a difference between mp iand mcurrent i.
[0052] The updated Rcurrentmay be understood as the reference mass per unit of length variation. This embodiment allows to update the reference mass per unit of length variation each time that a mass per unit of length variation has been determined for some food product. Updating the array Rcurrentbased on a difference between the Rcurrentand Rprather than just taking Rpas the new reference mas per unit of length variation, is beneficial as it prevents that an outlier mass per unit of length variation will be used as a reference mass per unit of length variation.
[0053] In an embodiment, array Rcurrentrepresents a current reference mass per unit length variation. In this embodiment, the method comprises, after determining each mass per unit length variation represented by an array / ? = determining, for each i from 1 to M, a difference between and mcurrent iand then updating mcurrent ibased on this difference, herewith updating array Rcurrent-
[0054] Herein, the reference mass per unit of length variation is indeed updated after each determination of an actual mass per unit of length variation.
[0055] In an embodiment, the reference mass per unit length variation indicates a particular value of mass per unit length for a particular relative position in the type of food product. In this embodiment, the method further comprises determining a difference between the particular value and a local average of values that are indicated by the reference mass per unit length variation for respective relative positions near the particular relative position. This embodiment also comprises, based on the determined difference, updating the particular value so that it is closer to the local average of values herewith determining an updated reference mass per unit length variation.
[0056] This embodiment prevents that errors grow larger and larger in the reference mass per unit of length variation. If such correction is not present, then the reference mass per unit of length variation may end up having a very high value next to a very low value. This is incorrect, but does not necessarily yield incorrect slicing of the food product. After all, these extreme values may average out to normal values if the reference mass per unit of length variation is resampled so that it can be used for determining how to slice an actual food product. However, in some circumstances the incorrect reference mass per unit of length can indeed produce wrong results if food items fall between these equalizing errors. Hence, such errors in the reference mass per unit of length variation are preferably prevented.
[0057] If the reference mass per unit of length variation is represented by an array of elements, wherein each element indicates a mass per unit of length value for a relative range in the food product, then, for some element, the local average value forthat element may be the average of the respective values of the two elements neighboring that element and of that element itself.
[0058] In an embodiment, the method comprises receiving target data indicating a target weight of a food item, such as a slice, that is to be separated from, e.g. cut off from, a further food product of the type of food product. This embodiment also comprises receiving dimension data indicating at least one dimension of the further food product, and controlling, based on the target weight, and on the at least one dimension, and on the, optionally updated, reference mass per unit length variation, controlling a cutting device to cut off the food item from the further food product.
[0059] In this embodiment, the reference mass per unit of length variation may for example be used to determine the slice thickness. If the reference mass per unit of length variation is accurate enough then the food item that is cut off will indeed have a weight that is equal to the target weight or that is at least within some acceptable range from the target weight.
[0060] The mass per unit of length variation is for example a variation in a first direction meaning that for a plurality of positions along the first direction respective mass per unit of length values are indicated. The dimension of the further food product is preferably a dimension that extends along the first direction. To illustrate, if the mass per unit of length variation indicates a variation of the mass per unit of length of the further food product along a length of the food product, then the dimension data preferably indicate a length of the further food product. To this end, the length of the food products may be measured somehow.
[0061] The target weight of a slice may vary per food product, or even per slice.
[0062] In an embodiment, the food item is a first or last slice that is to be separated from, e.g. cut off from, the further food product. In this embodiment, the method comprises determining the mass per unit length variation of a particular food product of the type of food product, and, based on a difference between the reference mass per unit length variation for said type of food product and the determined mass per unit length variation of the particular food product, adjusting the target weight of the food item. This embodiment further comprises controlling, based on the adjusted target weight, the cutting device cut off the food item from the further food product.
[0063] This embodiment allows to hand the first and last slice of a food product differently than intermediate slices. This is beneficial because the first and last slice of a food product are special in that they comprise only one cut surface. By treating these slices differently, the first and last slice will have weights that are closer to a desired value.
[0064] The particular food product would typically be the food product that has been cut before the further food product. Also, the reference mass per unit length variation referred to in this embodiment has preferably not yet been updated based on the determined mass per unit length variation of the particular food product.
[0065] One aspect of this disclosure relates to a non-transitory computer-readable storage medium storing at least one software code portion, the software code portion, when executed or processed by a computer, is configured to perform any of the computer-implemented methods disclosed herein.
[0066] One aspect of this disclosure relates to a computer readable storage medium having computer readable program code embodied therewith, and a processor, preferably a microprocessor, coupled to the computer readable storage medium, wherein responsive to executing the computer readable program code, the processor is configured to perform any of the methods disclosed herein.
[0067] One aspect of this disclosure relates to a cutting system comprising any of the cutting devices referred to herein, and any of the computers referred to herein, wherein the processor is configured to perform any of the methods disclosed herein.
[0068] Preferably, such cutting system also comprises a weighing system that is configured to measure respective weights of the groups of food items.
[0069] One aspect of this disclosure relates to a computer program or suite of computer programs comprising at least one software code portion or a computer program product storing at least one software code portion, the software code portion, when run on a computer system, being configured to configured to perform any of the methods disclosed herein.
[0070] One aspect of this disclosure relates to a computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out any of the computer- implemented methods described herein.
[0071] One aspect of this disclosure relates to a computer-readable data carrier having stored thereon any of the computer programs described herein.
[0072] The computer-readable data carrier may be hard disk, for example, or a signal.
[0073] One aspect of this disclosure relates to a computer readable storage medium having computer readable program code embodied therewith, and a processor, preferably a microprocessor, coupled to the computer readable storage medium, wherein responsive to executing the computer readable program code, the processor is configured to perform any of the computer-implemented methods described herein.
[0074] One aspect of this disclosure relates to a computer program or suite of computer programs comprising at least one software code portion or a computer program product storing at least one software code portion, the software code portion, when run on a computer system, being configured for executing any of the computer-implemented methods described herein.
[0075] One aspect of this disclosure relates to a non-transitory computer-readable storage medium storing at least one software code portion, the software code portion, when executed or processed by a computer, is configured to perform any of the computer-implemented methods described herein.
[0076] One aspect of this disclosure relates to a data carrier signal carrying any of the computer programs described herein.
[0077] Elements and aspects discussed for or in relation with a particular embodiment may be suitably combined with elements and aspects of other embodiments, unless explicitly stated otherwise. Embodiments of the present invention will be further illustrated with reference to the attached drawings, which schematically will show embodiments according to the invention. It will be understood that the present invention is not in any way restricted to these specific embodiments.
[0078] BRIEF DESCRIPTION OF THE DRAWINGS
[0079] Aspects of the invention will be explained in greater detail by reference to exemplary embodiments shown in the drawings, in which:
[0080] FIG. 1 illustrates a system for performing a method according to an embodiment;
[0081] FIG. 2 illustrates how food items originating from different food products may be grouped together according to an embodiment;
[0082] FIG. 3 indicates different positions of respective food items in a food product according to an embodiment;
[0083] FIG. 4 indicates different positions of respective food items in a compressed food product according to an embodiment;
[0084] FIG. 5 is a mass per unit of length variation that may be obtained by performing a method for determining mass per unit of length variation according to an embodiment;
[0085] FIG. 6 is a reference mass per unit of length variation according to an embodiment;
[0086] FIG. 7 is a flow chart illustrating a method for separating food items from food products according to an embodiment;
[0087] FIGs. 8A and 8B illustrate updating of a reference mass per unit of length variation according to an embodiment in more detail;
[0088] FIG. 9 illustrates a computer according to an embodiment.
[0089] DETAILED DESCRIPTION OF THE DRAWINGS
[0090] In the figures, identical reference numbers indicate identical or similar elements.
[0091] Figure 1 illustrates a system 2 according to an embodiment for performing a method for determining a mass per unit of length variation of a food product 4a, 4b. In figure 1 , the system 2 comprises a cutting device 6 for separating, preferably cutting, food items 8a, 8b, 8c, 8d (only four indicated with a reference number for clarity) from the food products that enter the cutting device 6. These food items 8a, 8b, 8c, 8d would typically be slices of meat. The food items are grouped and thus form groups of food items 10a, 10b, 10c, 10d. This may be because these food items are going to be packaged together later in the process. The system 2 as depicted in figure 1 also comprises a weighing system 12 that is configured to measure the weight of each group 10a, 10b, 10c, 10d and to output weight data indicative of the respective weight of the groups 10a, 10b, 10c, 10d. It should be appreciated that the weighing system 12 does not measure the individual weight of each food item 8a, 8b, 8c, 8d.
[0092] Typically, the weight of each group of food items 10 should be within some predetermined weight range. Such predetermined weight range may be specified by an order. For example, a supermarket may have put in an order for a number of packages, wherein each package contains five slices of meat and weight somewhere between 350 and 360 grams. However, it is quite challenging to achieve that each group of food items indeed has a weight as desired, not only because each food product has a certain mass per unit length variation along at least one its dimension, such as along its length L, which has to be considered when cutting off the food items, but also because the food products 4a, 4b that are input into the cutting device 6 have different dimensions. The mass per unit of length varies along a dimension of a food product because the cross section perpendicular to this dimension varies along the dimension and because the density of the food product is not constant throughout. Some tissue of the food product may be denser than other tissue of the food product.
[0093] In order to achieve that food items have a desired weight, preferably each food item would be measured individually to learn whether the settings of the cutting device were appropriate or not and to for example adapt the settings for a next food product for example by providing some sort of feedback loop between the weighing system and the cutting device 6. However, it is not always possible or desired to weigh each individual food item. The system as shown in figure 1 , for example, in particular its weighing system 12, only weighs the total weight of each group 10 that passes by. Of course, the feedback on group level has a lower resolution than feedback on the individual food item level which makes it difficult to control the cutting device 6 such that it outputs food items and groups of food items having weights as desired.
[0094] The fact that the weight of the groups 10 is measured rather than the individual food items 8 comes with another complication in that the groups may contain food items originating from different food products 4. This makes it even more challenging to use the weight data as output by the weighing system 12 as feedback. Figure 2 illustrates by way of example four groups of food items 10b, 10c, 10d, 10e. Group 10e only contains food items that originate from food product 4d. Group 10d comprises a sub-group of food items 14a originating from food product 4e and a sub-group of food items 14b originating from food product 4d. Group 10c only contains food items that originate from food product 4e. Group 10b comprises sub-group of food items 14c originating from food product 4e and a sub-group of food items 14d originating from food product 4f.
[0095] In the system 2 as shown in figure 1 , the computer 100 receives the weight data from the weighing system. The computer 100 also receives position data, from the cutting device 6. The position data indicate a position in the food product. To illustrate, figure 3 shows food product 4d that is also visible in figure 1 . Figure 3 shows that food item 8e has a thickness, for example a slice thickness, equal to (x1 - xO), food item 8f has a thickness equal to (x2 - x1), et cetera. As shown in figure 1 , food items 8e and 8f end up in group 10d and food items 8g - 8k end up in group 10e. In this case, the position data may then indicate for groupl Od the range xO to x2 in food product 4d, and for group 10e the range x2 to x7 in food product 4d. It should be appreciated that the position data may also indicate a further range for group 10d, namely the range in food product 4e from which the other food items in group 10d originate.
[0096] The cutting device 6 may be configured to store and / or output, e.g. to the computer 100, where in a currently processed food product it makes a cut for each food item. As such, the cutting device 6 is configured to determine the position data and send it to the computer 100. Alternatively, the computer 100 has previously instructed the cutting device 6 where to make different cuts in the food product, for example based on weighing data received from another food product. If this is the case, then the computer 100 has already obtained the position data for the food product before the food product is actually cut by the cutting device.
[0097] Figure 4 illustrates how, according to an embodiment, a food product 4d may be given a more uniform shape, namely by pressing the food product 4d into a cylinder 14, preferably a cylinder having circular base, but the cylinder may also have an oval shape or some odd shape. A piston-like element 16 is used to press the food product 4d into the cylinder. As a result, the food product 4d will at least have a more constant cross section along its length. Therefore, the mass per unit of length will vary less which aids to cut food items, such as slices, that have a weight as desired.
[0098] Referring again to figure 1 , the computer will at some point thus have obtained, by means of the weight data, the respective weights of all groups containing food items originating from a particular food product. Also, by means of the position data, the computer will at some point have obtained a position and / or position range of each group containing food items originating from that particular food product. To illustrate, at some point, the computer 100 will have obtained for food product 4d the respective weight of all groups containing food items originating from food product 4d including groups 10d and group 10e. Also, the computer 100 will have obtained at some point in time the position, for example the position range, of food items 8g, 8h, 8i, 8j, 8k (which are in group 10e) in food product 4d, for example the range x2 to x7 indicated in figure 3 or figure 4, the position, for example the position range, of food items 8e and 8f (which are in group 10d) in food product 4d, for example the range xO to x2 indicated in figure 3 or figure 4. The computer may then determine the value of weight per unit of length for the range x2 to x7, X(x2-> x7), as
[0099] X(x2x7) = wWe / d = wWe / x7- x2), wherein w10eindicates the weight of group 10e, and (x7- x2) indicates the position range spanned by group 10e, which is the combined thickness of all food items in group 10e.
[0100] Further, the computer 100 may determine the value of weight per unit of length for the range xO wherein w14fcindicates the weight of subgroup 14b, and (x2- x0) indicates the position range spanned subgroup 14b, which is the combined thickness of all food items in subgroup 14b, namely of food items 8e and 8f (see figure 1). Further, w14fcmay be determined based on the total number of food items in group 10d, which is 5, and based on the weight of group 10d, w10d, and based on the number of food items in sub-group 14b, which is 2, as w14fc=2 / s *wiod’ ^us giving the mass per unit of length variation for the range xO to x2 as
[0101] X(x0-> x2) = 2 * w10d / (5(x2- x0)). In this calculation, the average weight of the food items in group 10d (w10d / 5) may be considered as being determined.
[0102] Figure 5 indicates a mass per unit of length variation for food product 4d. Herein, Xr= X(x0-> x2), and X2= X(x2-> x7) as given above. The ultimately determined mass per unit of length variation for food product 4d thus indicates for a plurality of positions, in this case for a plurality of ranges, respective mass per unit of length values.
[0103] Preferably, a mass per unit of length variation is determined for each food product, thus also for food products 4a, 4b, 4e and 4f shown in figure 1 . This namely allows to determine a reference mass per unit of length variation for the type of food product in question. Such reference mass per unit of length variation is for example an average mass per unit of length variation of all determined mass per unit of length variations. Of course, for each food product, determining the mass per unit of length variation may potentially involve determining a mass per unit of length variation for a sub-group, which can be performed as described above.
[0104] The mass per unit of length variations referred to herein would typically be mass per unit of length variations along a length of the food product. Of course, the length differs per food product, which complicates the determination of a reference mass per unit of length variation. Therefore, it has been found advantageous to standardize the determined mass per unit of length variations that are determined for the respective food products such that each mass per unit of length variation indicates respective mass per unit of length values for a same plurality of relative positions along the first direction.
[0105] Figure 6 shows an example of a standardized mass per unit of length variation of some food product. This standardized mass per unit of length variation is represented by an array of length 10, wherein each element in the array indicates a density (in [g / dm3]) for a range within the food product, for example 1020 g / dm3for range 70% to 80% of the total length of the food product. Since the size of the cross-section of the cut food product parallel to the cut surface is either known, for example because it is pressed into a known shape (as for example in figure 4) or is measured before cutting, determining the density variation in [g / dm3] is effectively the same as determining the mass per unit of length variation.
[0106] Figures 6 is a flow chart illustrating a method according to an embodiment. In step 20, the dimensions of some food product that is going to be cut are measured. In an example, a primal piece of beef is pressed into a cylinder as shown in figure 4. The system may comprise a position sensor for measuring the position of the piston 16. The position sensor may be a position sensor of a servomotor driving the piston 16 that is configured to measure the position, e.g. the angular position, of the servomotor. Since the position of the servomotor corresponds to the position of the piston, effectively, the position of the piston is measured by measuring the position of the servomotor. The position of the piston in the fully compressed state may be used as an indication for the length of the food product.
[0107] Step 22 comprises, determining, based on a reference mass per unit of length variation for the type of food product to which the food product belongs, and based on a target weight of the one or more pieces that are going to be cut from the food product, and based on the dimensions as measured in step 20, the positions of the cuts that need to be made in the food product. Herewith, effectively position data are obtained since the positions of the cuts effectively determine the positions of the food items (in the food product) resulting from those cuts.
[0108] In step 24, the food items are separated from, e.g. cut off from, the food product.
[0109] In step 26, each group of food items is weighed to obtain the weight data as referred to herein.
[0110] In step 28, the mass per unit of length variation of the food product is determined. If some of the food items have ended up in a group with food items from another food product, then the mass per unit of length variation is determined in accordance with the methods described herein which involve estimating the weight of a sub-group within a group, for example based on a ratio between number of food items in the sub-group and number of food items in the group multiplied by the weight of that group.
[0111] In step 30, the determined mass per unit of length variation is standardized in order to make it comparable with other mass per unit of length variations. This may be performed as described in the summary section.
[0112] In step 32, the reference mass per unit of length variation is updated based on the mass per unit of length variation that was just determined in step 30. Especially if there is a large difference between reference mass per unit of length variation and the mass per unit of length variation resulting from step 30, then the reference mass per unit of length variation may need to be updated to obtain food items of desired weight.
[0113] As shown, the updated reference mass per unit of length variation is used for a subsequent food product that is going to be cut.
[0114] Figures 7A and 7B illustrate an embodiment wherein proportional-integral controllers, PI controllers, are used for updating the reference mass per unit of length variation. Figure 8A shows an initial reference mass per unit of length variation Rref,i as an array of M elements. Herein, each element indicates a mass per unit of length value for some relative range within a food product. The reference mass per unit of length variation Rref,i is used in step 22 for determining the cuts for food product 4d as indicated. Thereafter, steps 24, 26 and 28 are performed which have been described with reference to figure 7 as well. Ki is the obtained mass per unit of length variation for food product 4d. It has N elements. Standardization step 30 converts this mass per unit of length variation to a standardized mass per unit of length variation Ri for food product 4d, which has M elements. It thus conveniently has the same number of elements as the reference mass per unit of length. Thereafter, the reference mass per unit of length variation is updated in step 32 based on Ri.
[0115] In this embodiment, M number of PI controllers are fed an error signal “e”. Each error signal is determined based on a difference between an element in Rref.i and a corresponding element in Ri. PI controllers are well known in the art and are quite easily implemented. Each PI controller outputs a new value for an element in a new reference mass per unit of length variation Rref,2.
[0116] Figure 8B shows that Rref,2 is subsequently used for determining the cuts for food product 4e. Again, the reference mass per unit of length variation is updated similarly as in figure 8A, using the same PI controllers, and yet another reference mass per unit of length variation Rref,3 is determined that may be used for a subsequent food product. Figure 9 schematically illustrates a data processing 100, also referred to as a computer 100, according to an embodiment. Additionally or alternatively, the data processing system 100 can be implemented, for example, as a consumer device such as a smartphone, other mobile phone, tablet computer, wearable computing device (for example, a smart watch, eyeglasses, or a head wearable display), desktop computer, laptop computer, Programmable Logical Controller (PLC), or implemented with distributed computing devices.
[0117] In data processing system 100, a system bus 102 connects the different components of the data processing system 100. In particular, the system bus 102 depicted in figure 9 connects the Central Processing Unit (CPU) 104, memory elements 106, input devices 108, output devices 110 and communication devices 112 with each other so that they can exchange information. The system bus 102 may be understood to serve both as data bus, address bus and control bus known in the art.
[0118] The CPU 104 is configured to perform steps as per the instructions comprised in a computer program. To illustrate, based on such instructions, the CPU may perform any of the computer- implemented methods described herein. Typically, the CPU 104 is embodied as a microprocessor, which can be implemented on a single metal-oxide-semiconductor integrated circuit chip. The CPU 104 comprises a control unit 114, an arithmetic logical unit (ALU) 116 and a plurality of registers 118.
[0119] The control unit 114 is configured to retrieve instructions from a main memory 120. Typically, the control unit 114 comprises a binary decoder to convert the retrieved instructions into timing and control signals that direct the operation of for example the ALU 116. ALU 116 is configured to perform logical operations, such as additions, subtraction, multiplication, division and Boolean operations, that are required for carrying out the instructions. The registers 118 are small memory elements that can be read and written at relatively high speed. A register may for example store an instruction, a storage address, or any other kind of data. In addition, the CPU may contain hardware caches known in the art (not shown). Preferably the CPU has different levels of caches. These hardware caches may be understood as an intermediate state between the faster registers 119 and the slower main memory 120.
[0120] Memory elements 106 comprise a main memory 120. The main memory 120, also referred to as primary storage in the art, has stored data that is directly accessible to the CPU 104. The CPU 104 may continuously read instructions, i.e. read computer programs, stored in the main memory 120 and execute these instructions. The main memory 120 is typically a random access memory (RAM).
[0121] Memory elements 106 further comprise so-called secondary storage 122, which may be embodied as one or more hard disk drives and / or as one or more solid state drives. Typically, these secondary storage is non-volatile. Further, the memory elements may comprise other storage devices 124, such as removable storage devices, e.g. CD, DVD, USB flash drives, floppy disks, et cetera.
[0122] Input devices 108 may be understood as devices that are used to provide information to the computer 100, in particular to the CPU 104. In turn, the computer can interpret this information as indicative of particular user requests or information. Non-limiting examples of input devices are a keyboard, a microphone, a joystick, a touch sensitive screen, a keyboard, a touch pad, a touch screen, a mouse or other pointing device, a scroll wheel, a click wheel, a dial, a button, a switch, a keypad, a sensor (for example, a motion sensor or an eye tracking sensor), a weighing system 12 described herein, et cetera.
[0123] Output devices 110 may be understood as devices that output information out of the computer and / or as devices that are controlled by the computer. Non-limiting examples of output devices 110 are a printer, headphones, loudspeaker, a motor-generator referred to herein, a cutting device referred to herein, et cetera. Another example of an output device is a display to display images generated by or delivered to the computer. The display can incorporate various image generation technologies, for example, a liquid crystal display (LCD), a light-emitting diode (LED), such as an organic light-emitting diode (OLED), a projection system, a cathode ray tube (CRT), or the like, together with supporting electronics (for example, digital-to-analog or analog-to-digital converters, or signal processors). A device such as a touch screen that functions as both input and output device can be used. User output devices can be provided in addition to or instead of a display. Examples include indicator lights, speakers, tactile “display” devices, printers, and so on.
[0124] Communication devices 112 may be understood as devices that allow the computer system to communicate with other computers, such as with a server computer, client computer, or any other type of remote device. Communication devices 112 are for example configured to provide a connection to a wide area network (for example, the Internet) to which a WAN interface of a remote server system is also connected. Communication devices 112 can include a wired interface (for example, ethernet) and / or a wireless interface implementing various RF data communication standards, such as Wi-Fi, Bluetooth, or cellular data network standards (for example, 3G, 4G, 5G, 60 GHz, or LTE). Non-limiting examples of communication devices 112 include modems, cable modems, ethernet cards, Bluetooth modules, et cetera.
[0125] Many of the features described in this specification can be implemented as processes that are specified as a set of program instructions encoded on a computer readable storage medium. When these program instructions are executed by one or more processors, they cause the processors to perform various operations indicated in the program instructions. Examples of program instructions or computer code include machine code, such as is produced by a compiler, and files including higher- level code that are executed by a computer, an electronic component, or a microprocessor using an interpreter. Through suitable programming, processor 104 can provide various functionality for computer 100, including any of the functionality described herein as being performed by a server or client, or other functionality associated with message management services.
[0126] It will be appreciated that computer 100 is illustrative and that variations and modifications are possible. Computer systems used in connection with the present disclosure can have other capabilities not specifically described here. Further, while computer 100 is described with reference to particular blocks, it is to be understood that these blocks are defined for convenience of description and are not intended to imply a particular physical arrangement of component parts. For instance, different blocks can be located in the same facility, in the same server rack, or on the same motherboard. Further, the blocks need not correspond to physically distinct components. Blocks can be configured to perform various operations, for example, by programming a processor or providing appropriate control circuitry, and various blocks might or might not be reconfigurable depending on how the initial configuration is obtained. Implementations of the present disclosure can be realized in a variety of apparatus, including electronic devices implemented using any combination of circuitry and software.
[0127] While the invention has been illustrated and described in detail in the drawings and foregoing description, such illustration and description are to be considered illustrative or exemplary and not restrictive. The invention is not limited to the disclosed embodiments.
[0128] Other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims.
[0129] In the claims, the word “comprising” does not exclude other elements or steps, and the indefinite article “a” or “an” does not exclude a plurality.
[0130] A single processor or other unit may fulfill the functions of several items recited in the claims.
[0131] The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to obtain an advantage.
[0132] 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 the Internet or other wired or wireless telecommunication systems.
[0133] Any reference signs in the claims should not be construed as limiting the scope.
Claims
CLAIMS1 . A computer-implemented method for determining a variation along a first direction of a food product’s parameter, the parameter being mass per unit of length, the variation indicating respective values of the parameter for a plurality of positions along the first direction, the method comprising obtaining weight data acquired by a weighing system, the weight data being indicative of one or more respective weights of one or more groups of food items and of a weight of a first group of food items, wherein each group out of the one or more groups of food items is a group of food items that have been separated from, e.g. cut off from, a first food product, and wherein the first group of food items comprises a first sub-group of one or more food items that have been separated from, e.g. cut off from, the first food product and a second sub-group of one or more food items that have been separated from, e.g. cut off from, a second food product, wherein the first food product and second food product are a same type of food product, for example a beef loin primal cut, the method comprising obtaining position data indicating, for each group of food items for which the weight data indicate the weight and for the first sub-group of the first group, a position in the first food product along the first direction, the position being indicative of a positional range in the first food product, and determining the variation of the food product’s parameter along the first direction, this step comprising estimating a weight of the first sub-group of the first group and determining, based on the estimated weight and based on the position indicated by the position data for the first subgroup of the first group, a value of mass per unit of length for the first sub-group of the first group, preferably by dividing the estimated weight by a length of the positional range associated with the position indicated by the position data for the first sub-group of the first group, and determining, for each of the one or more groups of food items, based on the weight of the group of food items in question and based on the position indicated by the position data for the group of food items in question, a value of mass per unit of length, preferably by dividing the weight of the group of food items in question by a length of the positional range associated with the position indicated by the position data for the group of food items in question.
2. The method according to claim 1 , wherein the weight of the first sub-group of the first group is estimated based on a total number of food items in the first group of food items and based on the weight of the first group of food items and based on a number of food items in the first sub-group of the first group, and / or wherein the position data indicate, for the second sub-group of the first group, a position in the second food product along the first direction, the position being indicative of a positional range in the second food product, wherein the weight of the first sub-group of the first group is estimated based on theweight of the first group of food items and based on the position of the first sub-group of the first group in the first food product and based on the position of the second sub-group of the first group in the second food product.
3. The method according to claim 1 or 2, wherein the weight data are indicative of a weight of a second group of food items, wherein the second group of food items comprises a first sub-group of one or more food items that have been separated from, e.g. cut off from, the first food product and a second sub-group of one or more food items that have been separated from, e.g. cut off from, a third food product, wherein the first, second and third food product are the same type of food product, wherein the position data indicate a position along the first direction for the first sub-group of the second group, determining the variation of the food product’s parameter along the first direction comprises estimating a weight of the first sub-group of the second group and determining, based on the estimated weight and based on the position indicated by the position data for the first sub-group of the second group, a value of mass per unit of length for the first sub-group of the second group, preferably by dividing the estimated weight of the first sub-group of the second group by a length of the positional range associated with the position indicated by the position data for the first sub-group of the second group.
4. The method according to any of the preceding claims, comprising determining, for each food product out of a plurality of food products, a mass per unit length variation, the plurality of food products being of the same type as the first and second food product and the plurality of food products comprising the first and second food product, this step comprising, for each food product out of the plurality of food products,(a) receiving weight data acquired by the weighing system, the weight data being indicative of one or more respective weights of one or more groups of food items, wherein each group out of the one or more groups of food items is a group of food items that have been separated from, e.g. cut off from, the food product in question, and(b) receiving position data indicating, for each group of food items for which the weight data indicate the weight, a position of the group of food items in question in the food product in question, the position being indicative of a positional range in the food product in question, and(c) for each group of the one or more groups of food items, determining, based on the weight of the group in question and based on the position indicated by the position data, a mass per unit of length value for the group of food items in question, preferably by dividing the weight of the group in question by a length of the positional range associated with the position indicated by the position data for the group of food items in question, the method comprising determining a reference variation of mass per unit length for said type of food product based on the respectively determined variations of mass per unit length of the plurality of food products.
5. The method according to claim 4, wherein the plurality of food products comprises a subset of multiple food products, wherein for each food product out of the multiple food products, the weight data are indicative of a weight of a particular group of food items, wherein the particular group of food items comprises a first sub-group of one or more food items that have been separated from, e.g. cut off from, the food product in question and a second sub-group of one or more food items that have been separated from, e.g. cut off from, another food product, wherein for each food product out of the subset of multiple food products, determining the mass per unit of length variation comprises estimating a weight of the first sub-group of the particular group and determining, based on the estimated weight of the first sub-group of the particular group and based on a position as indicated by the position data for the first sub-group of the particular group, a mass per unit of length value for the first sub-group of the particular group, preferably by dividing the estimated weight of the first-sub-group of the particular group by a length of the positional range associated with the position indicated by the position data for the first sub-group of the particular group.
6. The method according to claim 4 or 5, wherein each variation of mass per unit length determined for each food product out of the plurality of food products, is a variation of mass per unit length along the first direction, such as along a length of the food product in question, wherein determining the reference variation of mass per unit length comprises standardizing the variations of mass per unit length determined for the plurality of food products so that each variation of mass per unit of length indicates respective values of mass per unit of length for a same plurality of relative positions along the first direction, such as along the length of the food product in question.
7. The method according to claim 6, wherein each respective variation of mass per unit length determined for a food product is represented by an array K of length N with N being a positive integer number, K = {kltk2, k3, ... , kN-, kN}, wherein N has some value for one food product out of the plurality of food products and a different value for another food product out of the plurality of food products, wherein standardizing the variations of mass per unit length comprises determining, for each array K, based on the array K in question, an array R of length M, M being a positive integer number, R = , mM-1, mM}, wherein M has the same value for each array K, wherein for every element in R applies that21 the method comprisingdetermining the reference variation of mass per unit length based on the respectively determined arrays R.
8. The method according to any of the preceding claims 4-7, wherein determining the reference variation of mass per unit length comprises- determining for a particular food product out of the plurality of food products, a particular array Rpof length M, M being a positive integer number, Rp= {mp l, mp 2,mp 3, , mp M-1, mp M}, array Rprepresenting an, optionally standardized, mass per unit length variation of the particular food product, wherein an array Rcurrentof length M, Rcurrent=reference mass per unit length variation, and- updating array Rcurrent, this step comprising updating, for each i from 1 to M, mcurrent ibased on a difference between mp iand mcurrent i.
9. The method according to claim 7 and 8, wherein array Rcurrentrepresents a current reference variation of mass per unit length, the method comprising after determining each variation of mass per unit length represented by an array R = {77 / ^77 / 2,77 / 3,determining, for each i from 1 to M, a difference betweenand mcurrent iand then updating mcurrent ibased on this difference, herewith updating array Rcurrent.
10. The method according to any of the preceding claims 4-9, wherein the reference variation of mass per unit of length indicates a particular value of mass per unit length for a particular relative position in the type of food product, the method further comprising determining a difference between the particular value and a local average of values that are indicated by the reference variation of mass per unit length for respective relative positions near the particular relative position, and based on the determined difference, updating the particular value so that it is closer to the local average of values herewith determining an updated reference variation of mass per unit length.
11. The method according to any of the preceding claims 4-10, further comprising receiving target data indicating a target weight of a food item, such as a slice, that is to be separated from, e.g. cut off from, a further food product of the type of food product, and receiving dimension data indicating at least one dimension of the further food product, and22 based on the target weight, and on the at least one dimension, and on the, optionally updated, reference variation of mass per unit length, controlling a cutting device to cut off the food item from the further food product.
12. The method according to claim 11 , wherein the food item is a first or last slice that is to be separated from, e.g. cut off from, the further food product, and determining the variation of mass per unit length of a particular food product of the type of food product, and based on a difference between the reference variation of mass per unit length for said type of food product and the determined variation of mass per unit length of the particular food product, adjusting the target weight of the food item, and based on the adjusted target weight, controlling the cutting device cut off the food item from the further food product.
13. A computer comprising a a computer readable storage medium having computer readable program code embodied therewith, and a processor, preferably a microprocessor, coupled to the computer readable storage medium, wherein responsive to executing the computer readable program code, the processor is configured to perform the method according to any of the preceding claims 1-12.
14. A cutting system comprising a cutting device referred to in claim 11 , and a computer according to claim 13, wherein the processor is configured to perform the method according to claim 11 .
15. A computer program or suite of computer programs comprising at least one software code portion or a computer program product storing at least one software code portion, the software code portion, when run on a computer system, being configured for executing the method according to any of claims 1-12.