Method for non-invasive determination of microbial population reduction within food products

Abstract

The present invention relates to a computer-implemented method and a device for non- invasively determining a reduction of a microbial population within food products being treated into a facility during a transformation process, wherein said facility comprises at least one temperature sensor configured to acquire a temperature representative of said transformation process without being in contact with the food products.

Description

METHOD FOR NON-INVASIVE DETERMINATION OF MICROBIALPOPULATION REDUCTION WITHIN FOOD PRODUCTSFIELD OF INVENTION

[0001] The present invention relates to the field of food products proces sing, and notably to the field of food safety for preventing contamination of the food supply. More in details, the present invention relates to a method and a device for non-invasively determining a reduction of a microbial population within food products being treated into a facility during a transformation process.BACKGROUND OF INVENTION

[0002] In industrial facilities, the quality of food products is verified through various methods, including regular monitoring and control processes. Temperature checks, especially for perishable products like ham, are crucial for ensuring food safety and quality. Temperature control is a critical factor in preventing the growth of harmful microorganisms.

[0003] Industrial facilities must comply with food safety regulations and standards set by regulatory bodies. These regulations often include specific temperature requirements for different types of food products. Regular inspections may be conducted to ensure compliance.

[0004] For certain food products, such as ham, thermal processing methods such as cooking and smoking are employed. These processes are designed to achieve specific temperature profiles to ensure both safety and desired product characteristics. Monitoring devices are used to verify that the internal temperature of the product reaches the required level. Continuous monitoring throughout the production process is essential.

[0005] In the case where multiple food products (i.e., a lot of food products) undergo a same transformation process in one predefined facility, such as ham in a smokehouse, a periodic temperature measurement inside at least one of the food products must be conducted. Currently, in most of the facilities, technicians have to enter the facility, one or more times, to manually perform said temperature measurements in order to monitor the temperature inside, preferably at the core, of food products undergoing a transformation process. During this regular procedure a food thermometer must be inserted into the food product, and often through a packaging (i.e., a plastic film) which is generally destructuring the food product and compromises the integrity of the packaging. As consequence, these group food products of the lot that are used to monitor the temperature during the transformation process must be discarded.

[0006] In this context, the invention herein described proposes a non-invasive solution allowing to perform continuous monitoring of core temperature of a lot of food products being transformed into a facility without causing damages to any food product of the lot.SUMMARY

[0007] This invention thus relates to a computer-implemented method for non- invasively determining a reduction of a microbial population within food products being treated into a facility during a transformation process, wherein said facility comprises at least one temperature sensor configured to acquire a temperature representative of said transformation process without being in contact with the food products, said method comprising: receiving at least one temperature inside said facility as a function of time acquired during said transformation process with said at least one temperature sensor; accessing a temperature prediction model, said temperature prediction model being configured to receive as input said at least one temperature as a function of time acquired by said at least one temperature sensor and to provide as output predictions of a volumetric temperature distribution (i.e. temperaturedistribution), as a function of time, inside at least one of said food products during the transformation process inside said facility; providing as input to said temperature prediction model said received at least one temperature, so to obtain said volumetric temperature distribution as a function of time inside at least one of said food products; calculating a lowest temperature inside said at least one of said food products using said volumetric temperature distribution as a function of time inside the food product; using at least said volumetric temperature distribution inside at least one of said food products, calculating a log reduction value associated with said at least one of said food products with respect to one microorganism species of concern among the endogenous microbial population; classifying, based at least in part on the log reduction value, the food products at least as compliant or non-compliant with respect to said microorganism species of concern among the microbial population; providing as output at least said lowest temperature of the at least one of the food products and said class of the food products.

[0008] According to one embodiment, the computer-implemented method for non- invasively determining a reduction of a microbial population within food products being treated into a facility during a transformation process, wherein said facility comprises at least one temperature sensor configured to acquire a temperature representative of said transformation process, comprises: receiving at least one temperature as a function of time acquired during said transformation process with said at least one temperature sensor; accessing a temperature prediction model, said temperature prediction model being configured to receive as input at least one temperature as a function of time acquired by said at least one temperature sensor and to provide as output predictions of a temperature distribution, as a function of time, inside at least one of said food products during the transformation process;providing as input to said temperature prediction model said received at least one temperature, so to obtain a temperature distribution as a function of time inside at least one of said food products; calculating a lowest temperature inside said food product using said temperature distribution as a function of time inside the food product; using at least said temperature distribution inside at least one of said food products, calculating a log reduction value associated with the at least one of said food products with respect to one microorganism species of concern among the endogenous microbial population; classifying, based at least in part on the log reduction value, the food products at least as compliant or non-compliant with respect to said microorganism species of concern among the microbial population; providing as output at least said lowest temperature of the at least one of the food products and said class of the food products.

[0009] According to other advantageous aspects of the invention, the computer- implemented method comprises one or more of the features described in the following embodiments, taken alone or in any possible combination.

[0010] In one embodiment, said temperature prediction model is configured to model heat penetration in one food product and is defined by model parameters, and at least one of said model parameters is selected on the base of food product characteristics.

[0011] In one embodiment, the food product characteristics comprises at least volumetric mass density, geometry, apparent heat capacity and apparent thermal conductivity.

[0012] In one embodiment wherein the food product during treatment is at least partially enveloped by at least one container, such as a mold and / or a packaging, said temperature prediction model is configured to further model heat penetration in the food product and said at least one container, so that said at least one model parameter is further selected based on characteristics of said at least one container.

[0013] In one embodiment, the at least one container characteristics comprise at least one volumetric mass density, geometry, thermal convection coefficient and apparent thermal conductivity.

[0014] In one embodiment, the facility during transformation process of the food products is characterized by a non-uniform temperature distribution, and said method for non-invasively determining a reduction of a microbial population within food products being treated into a facility during a transformation process further comprises a preliminary phase comprising:• receiving measurements of temperatures as a function of time, measured at a plurality of locations within the facility where the food products are being treated, and during transformation process of the food products;• generating a thermal map of said facility, using said measured temperatures;• by means of said thermal map, identifying a low temperature area within the facility corresponding to the lowest measured temperature (i.e. identifying, based on said generated thermal map, a low temperature area within the facility corresponding to the lowest measured temperature);• calculating a position for at least one temperature sensor within said low temperature area; wherein the at least one temperature sensor in the facility is placed in said calculated position.

[0015] In one embodiment, the classification of the food products comprises comparing the log reduction value to a predefined threshold, so that whenever the log reduction value is superior to said predefined threshold the food products are associated to class of compliant, while whenever the log reduction value is inferior to said predefined threshold the food products are associated to class of non-compliant.

[0016] In one embodiment, the classification of the food products comprises using a decision tree model.

[0017] In one embodiment, multiple log reduction values are stored in a database and are used to evaluate the transformation process of the food product to adjust at least one process parameter of the transformation process.

[0018] In one embodiment, the present method further comprises receiving at least one additional process data, acquired with an additional sensor during the transformation process, and further comprising using the temperature distribution and said at least one additional process data for calculating said log reduction value.

[0019] The present invention further relates to an loT platform, which is configured to carry out the steps of the method for non-invasively determining a reduction of a microbial population within food products according to any one of embodiments described herein above.

[0020] In addition, the disclosure relates to a computer program comprising software code adapted to perform a method for non-invasively determining a reduction of a microbial population within food products compliant with any of the above execution modes when the program is executed by a processor.

[0021] The present disclosure further pertains to a non-transitory program storage device, readable by a computer, tangibly embodying a program of instructions executable by the computer to perform a method for non-invasively determining a reduction of a microbial population within food products, compliant with the present disclosure.

[0022] Such a non-transitory program storage device can be, without limitation, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor device, or any suitable combination of the foregoing. It is to be appreciated that the following, while providing more specific examples, is merely an illustrative and not exhaustive listing as readily appreciated by one of ordinary skill in the art: a portable computer diskette, a hard disk, a ROM, an EPROM (Erasable Programmable ROM) or a Flash memory, a portable CD-ROM (Compact-Disc ROM).

[0023] This invention thus relates to a device for non-invasively determining a reduction of a microbial population within food products being treated into a facility during atransformation process, wherein said facility comprises at least one temperature sensor configured to acquire a temperature representative of said transformation process without being in contact with the food products, said method comprising: at least one input configured to receive:• at least one temperature inside said facility as a function of time acquired during said transformation process with said at least one temperature sensor;• a temperature prediction model, said temperature prediction model being configured to receive as input said at least one temperature as a function of time acquired by said at least one temperature sensor and to provide as output predictions of a volumetric temperature distribution, as a function of time, inside at least one of said food products during the transformation process inside said facility; at least one processor configured to:• provide as input to said temperature prediction model said received at least one temperature, so to obtain said volumetric temperature distribution as a function of time inside at least one of said food products;• calculate a lowest temperature inside said food product using said volumetric temperature distribution as a function of time inside the food product;• use at least said volumetric temperature distribution inside at least one of said food products, calculating a log reduction value associated with the at least one of said food products with respect to one microorganism species of concern among the endogenous microbial population;• classify, based at least in part on the log reduction value, the food products at least as compliant or non-compliant with respect to said microorganism species of concern among the microbial population; provide as output at least said lowest temperature of the at least one of the food products and said class of the food products.

[0024] According to one embodiment, this invention relates to a device for non- invasively determining a reduction of a microbial population within food products being treated into a facility during a transformation process, wherein said facility comprises atleast one temperature sensor configured to acquire a temperature representative of said transformation process, said method comprising: at least one input configured to receive:• at least one temperature as a function of time acquired during said transformation process with said at least one temperature sensor;• a temperature prediction model, said temperature prediction model being configured to receive as input at least one temperature as a function of time acquired by said at least one temperature sensor and to provide as output predictions of a temperature distribution, as a function of time, inside at least one of said food products during the transformation process; at least one processor configured to:• provide as input to said temperature prediction model said received at least one temperature, so to obtain a temperature distribution as a function of time inside at least one of said food products;• calculate a lowest temperature inside said food product using said temperature distribution as a function of time inside the food product;• use at least said temperature distribution inside at least one of said food products, calculating a log reduction value associated with the at least one of said food products with respect to one microorganism species of concern among the endogenous microbial population;• classify, based at least in part on the log reduction value, the food products at least as compliant or non-compliant with respect to said microorganism species of concern among the microbial population; provide as output at least said lowest temperature of the at least one of the food products and said class of the food products.

[0025] According to various embodiments, the device of the present invention is configured to carry out the steps of the method of the present invention.

[0026] The present invention further relates to a process for calibrating the method of the present invention in the case when, during transformation process of the foodproducts, the temperature distribution inside the facility is non-uniform, said process comprising: receiving measurements of temperatures as a function of time, measured at a plurality of locations within the facility where the food products is being treated, and during transformation process of the food products; generating a thermal map of said facility, using said measurements of temperatures; by means of said thermal map, identifying a low temperature area within the facility corresponding to the lowest measured temperature; calculating a position for at least one temperature sensor within said low temperature area; placing the at least one temperature sensor within said low temperature area in the facility.DEFINITIONS

[0027] In the present invention, the following terms have the following meanings:

[0028] The terms “adapted” and “configured” are used in the present disclosure as broadly encompassing initial configuration, later adaptation or complementation of the present device, or any combination thereof alike, whether effected through material or software means (including firmware).

[0029] The term “processor” should not be construed to be restricted to hardware capable of executing software, and refers in a general way to a processing device, which can for example include a computer, a microprocessor, an integrated circuit, or a programmable logic device (PLD). The processor may also encompass one or more Graphics Processing Units (GPU), whether exploited for computer graphics and image processing or other functions. Additionally, the instructions and / or data enabling to perform associated and / or resulting functionalities may be stored on any processor- readable medium such as, e.g., an integrated circuit, a hard disk, a CD (Compact Disc), an optical disc such as a DVD (Digital Versatile Disc), a RAM (Random- AccessMemory) or a ROM (Read-Only Memory). Instructions may be notably stored in hardware, software, firmware or in any combination thereof.

[0030] “Machine learning (ML)” designates in a traditional way computer algorithms improving automatically through experience, on the ground of training data enabling to adjust parameters of computer models through gap reductions between expected outputs extracted from the training data and evaluated outputs computed by the computer models.

[0031] “Datasets” are collections of data used to build an ML mathematical model, so as to make data-driven predictions or decisions. In “supervised learning” (i.e. inferring functions from known input-output examples in the form of labelled training data), three types of ML datasets (also designated as ML sets) are typically dedicated to three respective kinds of tasks: “training”, i.e. fitting the parameters, “validation”, i.e. tuning ML hyperparameters (which are parameters used to control the learning process), and “testing”, i.e. checking independently of a training dataset exploited for building a mathematical model that the latter model provides satisfying results.

[0032] A “neural network (NN)” designates a category of ML comprising nodes (called “neurons”), and connections between neurons modeled by “weights”. For each neuron, an output is given in function of an input or a set of inputs by an “activation function”. Neurons are generally organized into multiple “layers”, so that neurons of one layer connect only to neurons of the immediately preceding and immediately following layers.

[0033] The above ML definitions are compliant with their usual meaning, and can be completed with numerous associated features and properties, and definitions of related numerical objects, well known to a person skilled in the ML field. Additional terms will be defined, specified or commented wherever useful throughout the following description.BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The present disclosure will be better understood, and other specific features and advantages will emerge upon reading the following description of particular andnon-restrictive illustrative embodiments, the description making reference to the annexed drawings wherein:

[0035] Figure 1 is a block diagram representing schematically a particular mode of a system for non-invasively determining a reduction of a microbial population within food products being treated into a facility during a transformation process, compliant with the present disclosure;

[0036] Figure 2 a schematic representation of a facility according to one particular embodiment of the invention;

[0037] Figure 3 is a flow chart showing successive steps executed with the device for predicting of figure 1;

[0038] Figure 4 diagrammatically shows an apparatus integrating the functions of the device for determining a reduction of a microbial population of figure 1.

[0039] On the figures, the drawings are not to scale, and identical or similar elements are designated by the same references.ILLUSTRATIVE EMBODIMENTS

[0040] The present description illustrates the principles of the present disclosure. It will thus be appreciated that those skilled in the art will be able to devise various arrangements that, although not explicitly described or shown herein, embody the principles of the disclosure and are included within its scope.

[0041] All examples and conditional language recited herein are intended for educational purposes to aid the reader in understanding the principles of the disclosure and the concepts contributed by the inventor to furthering the art, and are to be construed as being without limitation to such specifically recited examples and conditions.

[0042] Moreover, all statements herein reciting principles, aspects, and embodiments of the disclosure, as well as specific examples thereof, are intended to encompass bothstructural and functional equivalents thereof. Additionally, it is intended that such equivalents include both currently known equivalents as well as equivalents developed in the future, i.e., any elements developed that perform the same function, regardless of structure.

[0043] Thus, for example, it will be appreciated by those skilled in the art that the block diagrams presented herein may represent conceptual views of illustrative circuitry embodying the principles of the disclosure. Similarly, it will be appreciated that any flow charts, flow diagrams, and the like represent various processes which may be substantially represented in computer readable media and so executed by a computer or processor, whether or not such computer or processor is explicitly shown.

[0044] The functions of the various elements shown in the figures may be provided through the use of dedicated hardware as well as hardware capable of executing software in association with appropriate software. When provided by a processor, the functions may be provided by a single dedicated processor, a single shared processor, or a plurality of individual processors, some of which may be shared.

[0045] It should be understood that the elements shown in the figures may be implemented in various forms of hardware, software or combinations thereof. Preferably, these elements are implemented in a combination of hardware and software on one or more appropriately programmed general-purpose devices, which may include a processor, memory and input / output interfaces.

[0046] The present disclosure will be described in reference to a particular functional embodiment of a device 1 for non-invasively determining a reduction of a microbial population within food products, as illustrated on Figure 1. In other words, the present device 1 is configured to determine the compliancy, and therefore indirectly the safety of an ingestible food products p, with respect to a microorganism of concern among the microbial population (i.e., a contaminant) as the ingestible product is being processed. The food product refers to food that is ingestible and result of the transformation process performed into the facility. The types of food products p that are processed within the facility F may vary, and it is to be appreciated that the food product p processed within the food processing facility F can be any suitable type of food product, transformed ornot-transformed product, such as a meat product, a vegetable product, a fruit product, a dairy product, a beverage product, a grain-based food product (e.g., cereal, snack bars, etc.), a dessert product, a food ingredient (e.g., flour, sugar, cocoa, etc.), or the like. It is also to be appreciated that a food product may be in solid form, liquid form, including powders, flours, or any other suitable form. As such, the term “food product” can mean beverages or drinks, in some examples.

[0047] The food products p may be at risk of contamination from one or more microorganism species of concern among the microbial population (i.e., contaminant(s)), either before the food product p is processed within the facility F (e.g., after harvesting, while in a holding facility, and / or during transport to the facility), or during processing of the food product within the facility F. An example of a contaminant is a microorganism species of concern among the microbial population. The microorganism species of concern may be a pathogen. As such, the microorganism species of concern may also be a nonpathogen contaminants, such as spoilage microorganisms, yeast, molds, etc. Salmonella is also discussed as an example pathogen herein, but it is to be appreciated that other pathogens may contaminate a food product p. Example pathogens include Salmonella, Clostridium perfringens, Campylobacter, Staphylococcus aureus, Escherichia coli, Listeria monocytogenes, Norovirus, Toxoplasma gondii, or any other known or heretofore undiscovered pathogen.

[0048] The device 1 of the present invention is advantageously designed to be implemented in the case where multiple food products p, each being a separate entity, are transformed during a same transformation process taking place into the facility F. As disclosed above, the food products p may be in solid or in liquid form, including powders, flours, etc. in which case the food products p are either conditioned into a packaging and / or at least partially enveloped by at least one container, such as a mold, allowing to contain the food products p in multiple separate units. The plurality of individual food products p may be displaced in the facility F into ranks, for example by being installed onto shelves.

[0049] In one example, the food products p may be hams, made of a mix of ingredients in a liquid form, conditioned into a plastic film as packaging and disposed into a mold, to be processed into a smokehouse (see fig. 2). Therefore, the food products p of the presentinvention do not encompass the case of a food product, for example in a liquid form, processed as a unique mass, for example into one tank, where the temperature may be assumed to be uniform in all the food product p and may be measured by one sensor inside the tank and in contact with the food product itself.

[0050] The present method provides a solution for the specific context, wherein it is not possible to access the temperature inside the food products p, and notably not at the core of the food products p, where the temperature is the lowest, without compromising the food product itself. Indeed, as presented in the background of the invention, current method implies the insertion of a thermal probe (i.e., a temperature sensor) inside one of the food products p. This action causes the creation of a hole in the food product itself and, if it is conditioned into a closed packaging causes as well an opening in the packaging, and potentially a leakage of the food product p. In some case, the food product p used to test the temperature cannot be commercialized anymore. Furthermore, said manual testing of the temperature must be performed multiple times during the transformation process which oblige one subject to enter the facility multiple times, and withstand high temperature (i.e., superior to 50°C). The present invention advantageously allows to avoid all these inconvenient.

[0051] The term “facility” in the present disclosure refers to a specialized appliance designed for the large-scale processing of food products p. Such a facility F may notably be an equipment, enclosing a volume, wherein the food products p are placed in other to be processed, i.e., exposed to a predefined transformation process comprising application of a predefined temperature, humidity, or other process parameters during predefined time periods. Some examples of facility are presented in the following list (which is not restrictive): smokehouse, drying chamber, industrial sous- vide cooker, industrial vacuum cooker, industrial hot water bath (hot water shower), industrial oven, industrial fryer, industrial steam cooker and the like. The facility may F be a transformation equipment with at least one entry point, or an entry point and an exit point, these entry and exit points may be sealed or not during the transformation process. The transformation process may be a batch process or a continuous process.

[0052] The device 1 is adapted to provide information fundamental for food safety and quality assurance in industrial food production. The device 1 is notably adapted to providea prediction of the lowest temperature among the plurality of the food products p present in the facility during the transformation process. Indeed, as explained above temperature control is a fundamental aspect of food safety and quality assurance in industrial food production. It plays a vital role in protecting consumers, complying with regulations, and delivering food products that meet both safety and quality standards. In this context, the control of the lowest temperature in the processed food products allow to ensure that even the coldest region(s), usually inside on or more of the food products p (i.e., worst case scenario) receives enough heat to guarantee the compliance to predefined standards.

[0053] The device 1 is also adapted to provide as output a prediction on the compliance of the food products p with respect to said microorganisms of concern among the microbial population. This compliance with microbial standards is vital for safeguarding public health, ensuring food safety, meeting regulatory requirements, and maintaining the integrity of the food industry.

[0054] The input data may be derived from the process parameters, notably the temperature, inside the facility F where the food products p are undergoing the transformation process.

[0055] Though the presently described device 1 is versatile and provided with several functions that can be carried out alternatively or in any cumulative way, other implementations within the scope of the present disclosure include devices having only parts of the present functionalities.

[0056] The device 1 is advantageously an apparatus, or a physical part of an apparatus, designed, configured and / or adapted for performing the mentioned functions and produce the mentioned effects or results. In alternative implementations, the device 1 is embodied as a set of apparatus or physical parts of apparatus, whether grouped in a same machine or in different, possibly remote, machines. The device 1 may e.g. have functions distributed over a cloud infrastructure and be available to users as a cloud-based service, or have remote functions accessible through an API.

[0057] In what follows, the modules are to be understood as functional entities rather than material, physically distinct, components. They can consequently be embodied either as grouped together in a same tangible and concrete component, or distributed into severalsuch components. Also, each of those modules is possibly itself shared between at least two physical components. In addition, the modules are implemented in hardware, software, firmware, or any mixed form thereof as well. They are preferably embodied within at least one processor of the device 1.

[0058] The device 1 comprises a module 11 for receiving the temperature as a function of time. The module 11 may also receive at least one additional process data, such as, but not limited to the humidity of the facility F as a function of time, the pressure of the facility F as a function of time, etc.

[0059] The measurements of the temperature as a function of time T(t) 21 may be transmitted, for example wirelessly, from at least one temperature sensor S positioned inside the facility F (i.e., but not into contact with any food product) and be received by module 11. In the same way, the facility F may be equipped with pressure sensors, humidity sensors, and the like, configured to transfer the measurements to module 11. These collected data, concerning the transformation process ongoing in the facility F, may take the form of a table comprising temperatures or the additional process data, associated with the time of collection. These collected data may be transferred continuously, after each acquisition, on in batches.

[0060] According to one embodiment, the temperature sensor S is placed in a predefined location inside the facility F corresponding to the area of the facility F experiencing the lowest temperature. This embodiment is particularly important in facilities where the distribution of temperature is not uniform in the whole volume, which may be the case in an oven or a smokehouse. Placing the temperature sensor S in the coldest spot of the facility F advantageously allows to consider monitor the most unfavorable area of the facility F during the transformation process.

[0061] The module 11 may as well receive the temperature prediction model 22, as well as its model parameters, stored in one or more local or remote database(s) 10. The latter can take the form of storage resources available from any kind of appropriate storage means, which can be notably a RAM or an EEPROM (Electrically-Erasable Programmable Read-Only Memory) such as a Flash memory, possibly within an SSD (Solid-State Disk). The temperature model is configured to provide predictions of avolumetric temperature distribution, as a function of time, inside at least one of said food products p during the transformation process. The temperature distribution (i.e. volumetric temperature distribution) be calculated as the temperature as a function of time at the nodes of a predefined grid defined inside one food product. The nodes on the grid may be equally spaced and their distance may variate from approximately a millimeter to few centimeters. An interpolation function may be implemented to obtain a continuous temperature distribution.

[0062] The temperature model takes as input the process parameter(s). In one example, the temperature model takes as input the temperatures as a function of time T(t) acquired by said at least one temperature sensor S. As previously described, the at least one sensor may be placed in a predefined location inside the facility F (without being in contact with any food product), therefore acquiring the temperature in the facility in proximity of at this predefined location.

[0063] The temperature prediction model may be configured to model heat penetration in one food product. Among its model parameters, at least one or more model parameter is (are) selected on the base of food product characteristics. In one example, the food product characteristics taken as model parameters are at least volumetric mass density, geometry, apparent heat capacity and apparent thermal conductivity. As the nature of the main ingredient (e.g., pork meats being replaced by turkey meat) and the proportion between the different ingredients strongly influence the temperature calculation, other food product characteristics that may be taken into account such as water activity, moisture content, proteins content, fat content, carbohydrates content, salt content, and the like.

[0064] During the treatment process, the food products may p be at least partially enveloped by at least one container, such as a mold and / or a packaging. In this configuration, said temperature prediction model is advantageously adapted to take into account these new elements for the simulation of the heat penetration. Therefore, at least one model parameter of the temperature prediction model is selected based on characteristics of said at least one container. The at least one container characteristics may be, but not limited to, one of the following: volumetric mass density, geometry, thermal convection coefficient and apparent thermal conductivity. The geometry takes intoaccount the shape of the container, its thickness, etc. The global geometry of the food product and the containers may be approximated by simplified geometrical shapes such as a parallelepiped, a cylinder, a cone and the like (i.e., any other tridimensional shape).

[0065] The temperature distribution model provides a prediction of the temperature distribution for a specific food product and to do so may as well advantageously take into consideration the type of transformation process and the facility configuration. More precisely, said temperature distribution model is a volumetric temperature distribution model which provides a prediction of the temperature in the different zone of a specific food product. This advantageously allows to access to more precise information such as the lower and higher temperatures inside the food product, instead of a simple global mean temperature. The knowledge of the facility configuration and type of transformation process allows to simulate the correct physical phenomenon transferring the heat from the facility environment to the food products p in it. Notably the knowledge of these facility configuration and type of transformation process allows to calibrate the temperature distribution model (i.e., adapt it) to each specific facility F and transformation process. Therefore, additional model parameters may be selected based on the configuration chosen for the facility F during the transformation process, such as the loading rate of the facility F (i.e., the volume occupied by the food products p with respect to the total volume of the facility F), the distribution of the food products p inside the facility F and air flow speed inside the facility F, which may be approximately constant during the transformation process.

[0066] In one example, the database 10 may comprise a plurality of temperature distribution model associated with a specific transformation process, facility F and food product(s) p. In this case, a user may provide as further information to the module I l a selection of transformation process, facility F and food product p in order to access the desired temperature distribution model.

[0067] Different types of heat propagation algorithms / methods may be used such as Finite difference methods, which discretizes the spatial domain into a grid and approximate the heat equation by calculating temperature changes at discrete points or finite element methods which divides the system into smaller, simpler elements and where the heat equation is then solved for each element, and the results are combined tomodel heat propagation across the entire system. Other methods are also known by the person skilled in the art such as the meshfree methods, lattice Boltzmann method, Monte Carlo methods and the like.

[0068] The device 1 further comprises a module 12 for calculation of the volumetric temperature distribution inside at least one food product p as a function of time by providing as input to the temperature prediction model the temperature as a function of time T(t). The calculation of the volumetric temperature distribution may be performed only for one food product p as all food products p in the facility F are assumed to have the same characteristics and be conditioned in a same way.

[0069] Alternatively, if two different types of food products p are processed at the same time inside the facility F (see fig. 2), it is possible to monitor both type of food by calculating the volumetric temperature distribution inside each type of food product p. Therefore, module 12 will provide a first temperature distribution for the first (type) food product and a second temperature distribution for the second (type) food product. In this way multiple food products p may be monitored at the same time using the present invention.

[0070] The device 1 may further comprise a module 13 for extracting a temperature data from the volumetric temperature distribution obtained from module 12. Indeed, module 14 may calculate the lowest temperature as function of time Tmin(t) inside the food product p based on the estimated volumetric temperature distribution as a function of time. Alternatively, or in addition, module 13 may be configured to calculate the temperature at the core of the food product p. In this case, as volume for the core may be refined in the volume associated to the volumetric temperature distribution and the core temperature may be calculated as the mean temperature in the core volume. If two or more types of food product p are being produced the operation(s) will be repeated for all food product types.

[0071] The device 1 further comprises a module 14 for calculating (e.g., estimate) a metric, such as a log reduction value, used to quantify the effectiveness of a transformation process in reducing the concentration of microorganisms. The log reduction value indicates the order of magnitude by which the microbial population hasbeen reduced. Achieving a complete eradication of microorganisms is often challenging, and log reduction values provide a practical way to express the level of microbial reduction achieved through a specific treatment or process. The estimation of the log reduction value associated with one type of food product p and with respect to one microorganism species of concern among the endogen microbial population may be done using a model.

[0072] In general, the extracted temperature data (i.e., lowest temperature in the food product or the temperature at the core of the food product p), and optionally the additional process data, can be used with (e.g., provided as input to) a model(s) to determine (e.g., estimate) the log reduction value, associated with the food product p with respect to a microorganism species. That is, the database 10 may store one or more models that are usable to estimate a log reduction value of a microorganism species in a food product that is being processed within the facility. The log reduction value may be calculated using the following model (i.e., formula):

[0074] wherein Tref is the reference temperature used when establishing D-value and z- value,T is the temperature measured (i.e., the lowest temperature or the temperature at the core), t is the time in minutes associated to the T measured,D-value indicates time in minutes at a constant temperature, that is necessary to destroy 1 log of the microorganism present at a given reference temperature, and z (i.e., z-value) is the temperature increase required to reduce the D-value by a factor of 10; it is the number of degrees between a 10-fold change (or log cycle) in a microorganism’s heat resistance.

[0075] Each (log reduction value) model may be specific to a food product p and to a microorganism species. For example, a model may be specific to ham and to Salmonella in order to estimate a log reduction value of Salmonella in ham that is being processed within the smokehouse.

[0076] Thus, using the process data (i.e., extracted temperature data and additional process data) and the model, the module 14 may repeatedly determine log reductionvalues associated with the food product p with respect to a microorganism species of concern, and these log reduction values may be determined at any suitable frequency (e.g., every 10 seconds, every 30 seconds, every minute, etc.) and / or in response to events (e.g., in response to receipt of data relating to the completion of a particular stage of the treatment of the food product) as the food product p is being processed (e.g., treated) within the facility F. As log reduction values are determined by the module 14, the log reduction values can be stored as food safety data in the database 10. In addition, the raw data (temperature from the sensor and the additional process data) received from the module 11 may be stored as the food safety data.

[0077] The device 1 may comprise a module 15 for classification. In this module, the log reduction values determined by the module 14 can be used to classify the food product p as one of multiple class labels indicative of a compliance of the food product p with respect to said microorganism species of concern among the microbial population and these class label may be stored as the food safety data.

[0078] In one example, the classification may be binary. A binary “compliant” or “not compliant” classification of a food product p may be based on whether the log reduction value satisfies a predefined threshold (e.g., a threshold of 5-Log). “Satisfying” a predefined threshold, as used herein can mean meeting or exceeding the predefined threshold, or strictly exceeding the predefined threshold. Notably, whenever the log reduction value is superior to said predefined threshold the food products p are associated to class of compliant while whenever the log reduction value is inferior to said predefined threshold the food products p are associated to class of non-compliant. For example, a threshold of 5-Log may be satisfied by a determined log reduction value of 5-Log, because 5-Log is equal to the threshold in this example. Additionally, or alternatively, a threshold of 5-Log may be satisfied by a determined log reduction value of 6-Log. In general, the threshold or any criterion used to classify the log reduction values, and therefore the food products p, is evaluated according to country’s food safety regulations as compliance to these regulations is mandatory for food producers. The term “compliant” refers therefore to the compliancy of the food product p to one chosen country’s food safety regulation.

[0079] The module 15 for classification may, further to the “compliant” or “not compliant” classes, be configured to associate the food products p to other classes. For example, if the log reduction value is out of a known range of values, the class selected may be an “error” class representing the fact that something went wrong during the calculation process leading to the calculation of the log reduction value. Another class that can be selected by module 15 may be an “at risk” class representing the fact that attention should be taken for the batch of food products p under monitoring. A rule may be used to select this class consisting in comparing the log reduction value to a range of values around the predefined threshold, notably the range of values may be defined as approximately the predefined threshold value plus or minus the estimation of the measurement error on the calculation of the log reduction value.

[0080] The module 15 for classification may be further configured to evaluate the quality of the transformation process with respect to the compliancy policy to be applied. In this example, module 15 may use as input for the classification the log reduction value during all the transformation process or at least part, notably the final part, of the transformation process, plus the temperature profiles (i.e., lower temperature or core temperature during the transformation process). Based on this input, module 15 may associate the transformation process to a first class “compliant over processing”. The first class “compliant over processing” be selected for example when the log reduction value exceeds the predefined threshold for compliancy and / or the temperature exceed a minimum safety temperature threshold a predefined period of time before the ending of the transformation process. Indeed, if for example the Log reduction value and temperature are compliant (i.e., satisfies the predefined rules) 1 hour before the end of the transformation process, the class “compliant over processing” will be selected. This is a useful information for the user that now know that transformation process may still be improved by reducing the processing time (e.g., heating, cooking) so to gain efficiency, reduce energetic dependence, and gain in weight of the final food process (as less water will evaporate in the transformation process) and still be compliant to the chosen policy.

[0081] Alternatively to the use of a threshold, module 15 may classify the food products p using a machine learning model, such as a decision tree model. A decision tree model represents a decision-making process in which each internal node of the tree correspondsto a decision based on the value of a particular feature, and each leaf node represents the outcome or the final decision. Advantageously, decision trees are valuable tools for decision-making and prediction due to their interpretability, transparency, and versatility.

[0082] Alternatively, machine learning models, such as the neural networks, may be trained using specific training datasets, notably specific to the microorganism species of concern among the microbial population, the transformation process, the type of food product p and the facility F.

[0083] Over time, it can be appreciated that a large amount of food safety data can be collected and / or generated as a food product p is processed within a facility F, and this food safety data is thereafter accessible to the device 1 and to authorized users associated with a food processing entity that operates the facility F. In some examples, the device 1 is further configured to generate reports (e.g., sometimes referred to herein as “food safety reports”), which may be sent to one or more users automatically and / or at the request of the user.

[0084] Advantageously, using the device 1 described herein, a food processing entity can readily confirm that their food products p are safe with respect to a microorganism species of concern of interest, and this can be done for the food processing entity’s entire inventory of the food products p. That is, log reduction values and / or reports can be generated per batch of the food product p to indicate the compliance (with respect to a microorganism species of concern) of each batch of the food product p that is processed within the facility F. This provides traceability for the food processing entity’s food production process, which allows the food processing entity to comply with food safety rules and / or regulations with minimal effort. In particular, the platform’s ability to monitor non-invasively the safety of a food product p as the food product p is being processed within the facility F is an improvement over traditional approaches of merely validating the safety of random samples of a food product.

[0085] The device 1 may further comprise a setting module configured to be used during a preliminary phase of set up of the sensors in the facility F. This module is particularly useful in the case of facilities characterized by a non-uniform temperature distribution during the transformation process of the food products p. This setting module isconfigured to receive a set of measurements of temperatures as a function of time, measured at a plurality of locations within the facility F where the food product is being treated (without being in contact with the food product(s)), and during transformation process of the food product p. Then the setting module uses said measured temperatures to generate a thermal map of said facility F. The low temperature area within the facility F corresponding to the lowest measured temperature from the analysis of this thermal map. A position for at least one temperature sensor S is then calculated (e.g., selected) within said low temperature area. The setting module therefore may provide this position for the temperature sensor as output so that the temperature sensor S in the facility F is placed in this calculated position. Advantageously, placing the temperature sensor S at the coldest spot inside the facility F allow to closely monitor the most unfavorable temperature in the facility F.

[0086] The device 1 is interacting with a user interface 16, via which information can be entered and retrieved by a user. The user interface 16 includes any means appropriate for entering or retrieving data, information or instructions, notably visual, tactile and / or audio capacities that can encompass any or several of the following means as well known by a person skilled in the art: a screen, a keyboard, a trackball, a touchpad, a touchscreen, a loudspeaker, a voice recognition system.

[0087] In its automatic actions, the device 1 may for example execute the following process (Figure 3):- receiving the temperature as a function of time 21, the temperature prediction model 22 and optionally additional process data (step 41),- obtaining a volumetric temperature distribution as a function of time inside at least one of said food products p using the temperature prediction model 22 and the temperature as a function of time 21 (step 42),- calculating a lowest temperature 31 inside said food product p (step 43),- calculating a log reduction value associated with the at least one of said food products p with respect to one microorganism species of concern among the endogenous microbial population (step 44),- classifying, based at least in part on the log reduction value, the food products p at least as compliant or non-compliant (step 45).

[0088] A particular apparatus 9, visible on Figure 4, is embodying the device 1 described above. It corresponds for example to a workstation, a laptop, a tablet, a smartphone, or a head- mounted display (HMD).

[0089] That apparatus 9 is suited to non-invasively determining a reduction of a microbial population within food products p. It comprises the following elements, connected to each other by a bus 95 of addresses and data that also transports a clock signal:- a microprocessor 91 (or CPU),- a graphics card 92 comprising several Graphical Processing Units (or GPUs) 920 and a Graphical Random Access Memory (GRAM) 921,- a non-volatile memory of ROM type 96,- a RAM 97,- one or several VO (Input / Output) devices 94 such as for example a keyboard, a mouse, a trackball, a webcam; other modes for introduction of commands such as for example vocal recognition are also possible;- a power source 98; and- a radiofrequency unit 99.

[0090] According to a variant, the power supply 98 is external to the apparatus 9.

[0091] The apparatus 9 also comprises a display device 93 of display screen type directly connected to the graphics card 92 to display synthesized images calculated and composed in the graphics card. The use of a dedicated bus to connect the display device 93 to the graphics card 92 offers the advantage of having much greater data transmission bitrates and thus reducing the latency time for the displaying of food product reports composed by the graphics card. According to a variant, a display device is external to apparatus 9 and is connected thereto by a cable or wirelessly for transmitting the display signals. The apparatus 9, for example through the graphics card 92, comprises an interface for transmission or connection adapted to transmit a display signal to an external display means such as for example an LCD or plasma screen or a video-projector. In this respect, the RF unit 99 can be used for wireless transmissions.

[0092] It is noted that the word "register" used hereinafter in the description of memories 97 and 921 can designate in each of the memories mentioned, a memory zone of low capacity (some binary data) as well as a memory zone of large capacity (enabling a whole program to be stored or all or part of the data representative of data calculated or to be displayed). Also, the registers represented for the RAM 97 and the GRAM 921 can be arranged and constituted in any manner, and each of them does not necessarily correspond to adjacent memory locations and can be distributed otherwise (which covers notably the situation in which one register includes several smaller registers).

[0093] When switched-on, the microprocessor 91 loads and executes the instructions of the program contained in the RAM 97.

[0094] As will be understood by a skilled person, the presence of the graphics card 92 is not mandatory, and can be replaced with entire CPU processing and / or simpler visualization implementations.

[0095] In variant modes, the apparatus 9 may include only the functionalities of the device 1. In addition, the device 1 may be implemented differently than a standalone software, and an apparatus or set of apparatus comprising only parts of the apparatus 9 may be exploited through an API call or via a cloud interface.

[0096] The present invention further relates to an loT platform, which is configured to carry out the steps of the method for non-invasively determining a reduction of a microbial population within food products p. For loT (Internet of Things) platform is referred in the present invention to a comprehensive software ecosystem designed to streamline the development, deployment, and management of connected devices (i.e., temperature sensor and additional sensors) and applications. At its core, an loT platform encompasses a range of technical components that collectively enable seamless connectivity, data collection, storage, analytics, and device management. These components include robust device management functionalities for onboarding, monitoring, and updating loT devices, connectivity management to handle diverse communication protocols, secure data ingestion and storage mechanisms, analytics tools for processing and deriving insights from the collected data, visualization capabilities through dashboards, security measures such as encryption and authentication, integrationcapabilities for interfacing with existing enterprise systems, and scalability features to accommodate the growing number of connected devices. The platform's technical architecture allows to create custom applications, ensuring adaptability and efficiency in implementing loT solutions tailored to specific business requirements.

Claims

CLAIMS1. A computer-implemented method for non-invasively determining a reduction of a microbial population within food products (p) being treated into a facility (F) during a transformation process, wherein said facility (F) comprises at least one temperature sensor (S) configured to acquire a temperature representative of said transformation process without being in contact with the food products (p), said method comprising: receiving at least one temperature inside said facility (F) as a function of time (21) acquired during said transformation process with said at least one temperature sensor (S); accessing a temperature prediction model (22), said temperature prediction model being configured to receive as input said at least one temperature as a function of time (21) acquired by said at least one temperature sensor (S) and to provide as output predictions of a volumetric temperature distribution, as a function of time, inside at least one of said food products (p) during the transformation process inside said facility (F); providing as input to said temperature prediction model said received at least one temperature, so to obtain said volumetric temperature distribution as a function of time inside at least one of said food products (p); calculating a lowest temperature (31) inside said at least one of said food products (p) using said volumetric temperature distribution as a function of time inside the food product (p); using at least said volumetric temperature distribution inside at least one of said food products (p), calculating a log reduction value associated with said at least one of said food products (p) with respect to one microorganism species of concern among the endogenous microbial population; classifying, based at least in part on the log reduction value, the food products (p) at least as compliant or non-compliant with respect to said microorganism species of concern among the microbial population;providing as output at least said lowest temperature (31) of the at least one of the food products (p) and said class (32) of the food products (p).

2. The method according to claim 1, wherein said temperature prediction model is configured to model heat penetration in one food product (p) and is defined by model parameters, and wherein at least one of said model parameters is selected on the base of food product characteristics.

3. The method according to claim 2, wherein the food product characteristics comprise at least volumetric mass density, geometry, apparent heat capacity and apparent thermal conductivity.

4. The method according to either one of claims 2 to 3, wherein the food product (p) during treatment is at least partially enveloped by at least one container, such as a mold and / or a packaging, and said temperature prediction model is configured to further model heat penetration in the food product (p) and said at least one container, so that said at least one model parameter is further selected based on characteristics of said at least one container.

5. The method according to claim 4, wherein the at least one container characteristics comprise at least one volumetric mass density, geometry, thermal convection coefficient and apparent thermal conductivity.

6. The method according to any one of claims 1 to 5, wherein the facility (F) during transformation process of the food products (p) is characterized by a non-uniform temperature distribution, further comprises a preliminary phase comprising: o receiving measurements of temperatures as a function of time, measured at a plurality of locations within the facility (F) where the food products (p) are being treated, and during transformation process of the food products (p); o generating a thermal map of said facility (F), using said measured temperatures; o identifying, based on said generated thermal map, a low temperature area within the facility (F) corresponding to the lowest measured temperature;o calculating a position for at least one temperature sensor (S) within said low temperature area; wherein the at least one temperature sensor (S) in the facility (F) is placed in said calculated position.

7. The method according to any one of claims 1 to 6, wherein classifying said food products (p) comprises comparing the log reduction value to a predefined threshold, so that whenever the log reduction value is superior to said predefined threshold the food products (p) are associated to class of compliant, while whenever the log reduction value is inferior to said predefined threshold the food products (p) are associated to class of non-compliant.

8. The method according to any one of claims 1 to 6, wherein classifying said food products (p) comprises using a decision tree model.

9. The method according to any one of claims 1 to 8, wherein multiple log reduction values are stored in a database and are used to evaluate the transformation process of the food product (p) to adjust at least one process parameter of the transformation process.

10. The method according to any one of claims 1 to 9, comprising further receiving at least one additional process data, acquired with an additional sensor during the transformation process, and further comprising using the volumetric temperature distribution and said at least one additional process data for calculating said log reduction value.

11. An loT platform, which is configured to carry out the steps of the method according to any one of claims 1 to 10.

12. A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method according to any one of claims 1 to 10.

13. A computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out the method according to any one of claims 1 to 10.

Images