SENSOR BOARD AND METHOD FOR DETERMINING THE TYPE OF BEVERAGE IN A CONTAINER AND HEATING AND / OR FOAMING DEVICE HAVING SUCH A SENSOR BOARD - Patent application

Abstract

The present invention relates to a sensor board for determining the type of beverage in a container, comprising a processing unit, at least one light source for emitting light, and at least one spectral sensor for collecting reflected light from the at least one light source, wherein the at least one light source has a spectrum with a peak between 780 nm and 950 nm, and the at least one spectral sensor has a spectral response with a peak between 760 nm and 970 nm, the peak of the spectral response of the at least one spectral sensor being shifted by 20 nm or less from the peak of the at least one light source. The present invention also relates to a heating and / or frothing device for heating and / or frothing a beverage, and to a method for determining the type of beverage in a container.

Description

[Technical Field]

[0001] The present invention relates to a sensor board for determining the type of beverage in a container, more particularly to a sensor board for a heating and / or frothing device for heating and / or frothing a beverage. The present invention also relates to a method for determining the type of beverage in a container. [Background technology]

[0002] When preparing beverages, more specifically, when preparing beverages that are heated or frothed using a steam pipe, it is important to strictly follow a specific recipe when heating and / or frothing, depending on the type of beverage being heated or frothed, e.g., milk or a plant-based alternative. In standard heating and / or frothing devices, the type of beverage is determined visually, for example, by the bar staff operating the device. This is not always possible for certain types of beverages by sight alone. Furthermore, bar staff may rely on the aroma and taste of the beverage. It can be unpleasant or even unacceptable for customers to see bar staff smelling or tasting the beverage while preparing it. Therefore, it is necessary to have the packaging nearby to determine the type of beverage. When preparing multiple beverages quickly, when multiple containers of different but similar beverages are prepared, errors are likely to occur, resulting in inaccurate heating or frothing of the beverages and suboptimal beverage preparation. In such cases, the heated or frothed beverage is often discarded and remade, resulting in product loss. Therefore, it is desirable to be able to automatically determine the type of beverage in a container.

[0003] Patent document 1 describes a method for printing on beverages. The beverage is, for example, a coffee cup or beer glass that is placed under a printer after preparation or tapping. Text and / or images are then printed on the surface of the printer. Depending on the type of beverage, coffee-based or hop-based inks are used. Patent document 1 describes that spectral information, more specifically, the absorption of light having a wavelength of 430 nm, can be used to determine the color of the beer and to use ink of the appropriate color.

[0004] The method of US 2007 / 0129999 has the disadvantage that it is not suitable for identifying beverages that are typically heated and / or frothed in a steam pipe, such as milk, plant-based milk alternatives, chocolate milk, etc. Similarly, the method of US 2007 / 01299999 has the disadvantage that it is only intended for use with glasses or cups that are almost completely filled, and is not suitable for use with containers that contain only a small amount of beverage for heating or frothing (which makes automatic recognition of the beverage more difficult). Therefore, the method of US 2007 / 0129999999 is only suitable for use with already prepared beverages.

[0005] Patent document 2 describes a monitoring system for a beverage production machine. The monitoring system comprises a sensor board with a light source and a spectral sensor for collecting reflected light from the light source. Patent document 2 has the disadvantage that it is mainly suitable for recognizing coffee types.

[0006] Patent document 3 relates to a semi-automatic device for preparing beverages, which is suitable for recognizing packaging of ingredients for preparing the beverage, but not for recognizing the beverage itself.

[0007] Patent Document 4 relates to an automatic detection system for a beverage vending machine, the detection being primarily aimed at determining the presence or absence or correct placement of a beverage supply container. [Prior art documents] [Patent documents]

[0008] [Patent Document 1] European Patent Application Publication No. 3928994 [Patent Document 2] U.S. Patent Application Publication No. 2021 / 022547 [Patent Document 3] US Patent Application Publication No. 2005 / 022674 [Patent Document 4] US Patent Application Publication No. 2015 / 0136991 Summary of the Invention [Problem to be solved by the invention]

[0009] The present invention aims to solve at least some of the above problems or drawbacks. [Means for solving the problem]

[0010] In a first aspect, the invention relates to a sensor board for determining the type of beverage in a container, such as milk, plant-based milk substitute, juice, espuma or soup, according to claim 1.

[0011] The sensor board is advantageous for automatically determining the type of beverage in a container based on the presence of at least one light source having a spectrum with a peak between 780 nm and 950 nm. The type of beverage in a container can be determined by measuring and processing the spectral values ​​of light from the at least one light source reflected by the beverage in the container onto a spectral sensor. The applicant surprisingly discovered that a light source with such a peak in its spectrum is highly advantageous for identifying beverages used in beverage preparation, particularly for identifying, for example, milk and plant-based alternatives. Using a spectral sensor with a spectral response having a peak that is shifted by up to 20 nm from the peak of the at least one light source is advantageous for determining spectral values ​​from reflected light because the spectral sensor has high sensitivity near the peak of the at least one light source. Automatically determining the type of beverage in a container is highly advantageous when preparing a beverage, particularly when heating and / or frothing the beverage, in order to automatically adjust the recipe for preparing the beverage to achieve optimal preparation. Furthermore, certain hygiene standards can also be monitored, for example, to monitor product freshness. The sensor board can also help determine whether a beverage contains ingredients listed on an allergen list or ingredients that may cause an intolerance reaction. Milk and plant-based milk alternatives are not always easily distinguishable visually. Visually distinguishing between different types of milk or different plant-based alternatives is even more complicated. It is nearly impossible to visually distinguish whether a drink has already undergone pre-treatment, such as pasteurization or skimming. Thanks to the sensor board, bar staff no longer need to smell or taste the drink to determine its type. They also no longer need to have the drink's packaging on hand to prevent mistakes. During busy times, having multiple containers of similar but different drinks on hand can speed up drink preparation without introducing errors.

[0012] Preferred embodiments of the sensor board are shown in claims 2 to 8.

[0013] A particularly preferred embodiment relates to a sensor board according to claim 2.

[0014] This preferred embodiment is advantageous in avoiding deviations in the results when determining the type of beverage in a container due to reflections of light emitted by the at least one light source on the side walls of the container. When preparing a beverage, the container is filled with only a small amount of beverage or, conversely, a large amount of beverage depending on the beverage being prepared. This also means that there is more or less reflection of the emitted light on the side walls of the container. These reflections affect the spectral values ​​measured by the at least one spectral sensor. By measuring the level of the beverage in the container or by measuring the volume of the beverage in the container (which allows the level to be calculated), the effect of reflections on the side walls of the container can be taken into account, allowing for a robust determination of the type of beverage in the container.

[0015] In a second aspect, the present invention relates to a heating and / or frothing device as defined in claim 9. The presence of a sensor board according to the first aspect makes this device highly advantageous for automatically adjusting and setting a recipe for preparing a beverage based on the type of beverage in the container, which is automatically determined using the sensor board. This prevents bar staff from making mistakes by visually determining the type of beverage when preparing a beverage. It also eliminates the need for the beverage container to be on hand to determine the beverage in the container. Furthermore, bar staff can work cooperatively during busy periods. For example, a first bar staff member or a cobot can prepare multiple containers containing similar but different beverages while a second bar staff member heats and / or frothes the beverage in the container, efficiently preparing the beverage. Because the type of beverage is automatically detected, the recipe is automatically adjusted to optimally heat and / or frothe the beverage in the container, even if the second bar staff member does not have prior knowledge of the type of beverage in the container.

[0016] A preferred embodiment relates to a heating and / or frothing device according to claim 10.

[0017] The actuator for varying the relative position between the platform for supporting the container and the sensor board advantageously obtains a first fixed predetermined distance between the at least one light source and the upper liquid level in the container, and a second fixed predetermined distance between the at least one spectral sensor and the upper liquid level. This is advantageous because, regardless of the amount of beverage in the container, reflection of the light emitted by the at least one light source on the side wall of the container always has a substantially similar effect on the spectral value measured by the spectral sensor. It is also advantageous that substantially the same amount of light emitted by the at least one light source always reaches the upper liquid level, which means that the resulting spectral value is less subject to fluctuations due to ambient light. This results in a robust determination of the type of beverage in the container.

[0018] In a third aspect, the present invention relates to a method according to claim 11.

[0019] This method is advantageous for automatically determining the type of beverage in a container by using at least one light source having a spectrum with a peak between 780 nm and 950 nm. The type of beverage in the container can be determined by determining and processing the spectral values ​​of light from the at least one light source reflected by the beverage in the container to a spectral sensor. A light source having a peak between 780 nm and 950 nm is highly advantageous for identifying beverages used in beverage preparation, and is particularly advantageous for distinguishing between milk and plant-based alternatives, for example. Using a spectral sensor having a spectral response with a peak that is shifted by up to 20 nm from the peak of the at least one light source is advantageous for determining spectral values ​​from the reflected light, since the spectral sensor has high sensitivity near the peak of the at least one light source. Being able to automatically determine the type of beverage in a container is highly advantageous when preparing beverages, particularly when heating and / or frothing the beverage, in order to automatically adjust the recipe for preparing the beverage to achieve optimal preparation while avoiding errors.

[0020] Preferred embodiments of the method are set out in the dependent claims 12-15.

[0021] In a fourth aspect, the present invention relates to a method for heating and / or frothing a beverage in a container, such as milk or a plant-based milk substitute, juice, espuma or soup, the method comprising the steps of determining the type of beverage in the container using a sensor board according to the first aspect, and subsequently heating and / or frothing the beverage in the container according to a predetermined recipe.

[0022] This method is advantageous because the beverage is optimally heated and / or frothed according to a recipe depending on the type of beverage in the container, thereby avoiding errors. DETAILED DESCRIPTION OF THE INVENTION

[0023] Unless otherwise defined, all terms used in the description of the present invention, including technical and scientific terms, have the meanings commonly understood by those skilled in the art to which the present invention pertains. In order to better understand the description of the present invention, the following terms are clearly explained.

[0024] As used herein, "a" and "the" refer to both the singular and the plural unless the context dictates otherwise. For example, "a segment" means one or more segments.

[0025] The terms "comprise", "comprising", "consist of", "consisting of", "provided with", "include", "including", "contain" and "containing" are synonyms and are inclusive or open terms indicating the presence of what follows and do not exclude or preclude the presence of other components, properties, elements, components or steps that are known from or disclosed in the prior art.

[0026] Recitation of a numerical interval by endpoints includes all integer, fractional and / or real numbers between, and including, those endpoints.

[0027] Moreover, terms such as "first," "second," "third," etc. are used in the specification and claims to distinguish between like elements and do not necessarily denote an order or chronological sequence unless otherwise stated. The terms so used are interchangeable under appropriate circumstances, and it will be understood that the embodiments of the invention described herein may operate in orders other than those described or illustrated herein.

[0028] In the context of this specification, "container" means a drinking vessel. Non-limiting examples of materials suitable for a container include ceramic, porcelain, metal, glass, plastic, paperboard, etc. The container is preferably a metal container. A non-limiting example of a container is a jug with a spout and preferably a handle. Another non-limiting example is a cup, preferably a paperboard or plastic cup that can be closed with a lid having a drinking spout.

[0029] In the context of this specification, an LED is a light emitting diode.

[0030] In the context of this specification, the spectral response of a spectral sensor means the response of the spectral sensor to light of equal power as a function of the wavelength of the light.

[0031] In the context of this specification, determining a beverage type means identifying and categorizing a beverage based on beverage characteristics. The beverage type corresponds to the category into which the beverage is classified. Non-limiting examples of beverage characteristics include fat content, color, composition, etc. Non-limiting examples of categories include milk and plant-based milk alternatives. These categories may also be more specifically defined, such as skim milk, low-fat milk, whole milk, almond milk, rice milk, soy milk, coconut milk, hazelnut milk, etc.

[0032] In a first aspect, the present invention relates to a sensor board for determining the type of beverage in a container, such as milk or plant-based milk substitute, juice, espuma or soup.

[0033] According to a preferred embodiment, the sensor board comprises a processing unit, at least one light source for emitting light, and at least one spectral sensor for collecting reflected light from the at least one light source.

[0034] The sensor board may include a rigid printed circuit board, a flexible printed circuit board, or a combination of both. The sensor board is preferably a single printed circuit board. Alternatively, the sensor board may be made up of multiple printed circuit boards connected to each other using connectors and / or cables.

[0035] The processing unit is a processor or a microcontroller. Preferably, the processing unit is a microcontroller. Non-limiting examples of suitable microcontrollers include an ARM Cortex M4 or an ARM Cortex M7. Preferably, the processing unit is communicatively coupled to at least one spectral sensor to configure the at least one spectral sensor and read spectral values ​​determined by the at least one spectral sensor. If the sensor board includes multiple spectral sensors, the processing unit is communicatively coupled to each spectral sensor. The processing unit is communicatively coupled directly or indirectly to at least one spectral sensor. Indirectly communicatively coupled means that the processing unit communicates with another chip, which is in turn communicatively coupled directly or indirectly to at least one spectral sensor. Preferably, the processing unit is communicatively coupled via a UART or I / O. 2 C, is directly communicatively coupled to at least one spectral sensor via a series connection.

[0036] Preferably, at least one light source is an LED. If the sensor board comprises multiple light sources, each light source is preferably an LED. Preferably, the LED has an output power of at least 0.50 W, more preferably at least 0.75 W, even more preferably at least 1.00 W, and even more preferably at least 1.25 W. Preferably, the LED has an output power of up to 3.50 W, more preferably up to 3.00 W, even more preferably up to 2.50 W, and even more preferably up to 2.00 W. Alternatively, the light source is a laser. Preferably, the laser has an output power equivalent to the output power of the aforementioned LED. Preferably, at least one light source comprises a lens for directing emitted light toward the beverage in the container. If the sensor board comprises multiple light sources, each light source preferably comprises a lens for directing emitted light toward the beverage in the container. At least one light source has a spectrum with a peak between 780 nm and 950 nm. A particularly advantageous value is 830 nm and 940 nm. Preferably, the spectral peak between 780 nm and 950 nm of at least one light source is the global maximum of the spectrum. When the sensor board includes multiple light sources, at least one of the light sources has a spectrum with a peak between 780 nm and 950 nm. The spectra of the multiple light sources may have peaks between 780 nm and 950 nm, and the peaks between 780 nm and 950 nm of the multiple light sources may be the same or different.

[0037] The at least one spectral sensor is preferably a sensor chip. This is advantageous because the space required for the sensor chip on the sensor board is limited, and the cost of the sensor chip is also limited. The at least one spectral sensor is suitable for capturing light emitted by the at least one light source and reflected by an upper liquid surface formed by the beverage in the container. If the sensor board includes multiple spectral sensors, the multiple spectral sensors are preferably part of a single chipset. Non-limiting examples of suitable spectral sensors include Osram AS7265 and AS7341. The at least one spectral sensor has a spectral response with a peak between 760 nm and 970 nm. The peak between 760 nm and 970 nm of the spectral response of the at least one spectral sensor is offset by at most 20 nm, preferably at most 18 nm, more preferably at most 16 nm, even more preferably at most 14 nm, and even more preferably at most 12 nm from the peak between 780 nm and 950 nm in the spectrum of the at least one light source. Preferably, the peak in the spectral response between 760 nm and 970 nm of at least one spectral sensor is a global maximum in the spectral response. When the sensor board includes multiple spectral sensors, at least one spectral sensor has a spectral response with a peak between 760 nm and 970 nm. The multiple spectral sensors may have peak spectral responses between 760 nm and 970 nm, and the peaks between 760 nm and 970 nm of the multiple spectral sensors may be the same or different.

[0038] The sensor board is advantageous for automatically determining the type of beverage in a container. Each beverage has a spectral response. When light shines on a beverage, it transmits some of the light, reflects some, and absorbs some. This depends on the wavelength of the light. A beverage's "spectral response" refers to the proportion of light that is reflected. A beverage's spectral response also depends on its ingredients. Therefore, it is possible to distinguish specific beverages from one another based on their spectral response. Beverage identification can be done in a single step or multiple steps, first determining the beverage's main category and then one or more subcategories. For example, measuring the spectral response of a beverage across the entire range from 400 nm to 970 nm, i.e., across visible light and near-infrared, can only be achieved with an expensive spectrometer and a light source with a very broad spectrum. This requires specialized, expensive equipment and is time-consuming. This makes it impractical for automatically determining the type of beverage in a container as it is prepared. The applicant surprisingly discovered that a light source having a spectrum peaking between 780 nm and 950 nm is highly advantageous for identifying beverages used in beverage preparation, and is particularly advantageous for distinguishing between, for example, milk and plant-based alternatives. This is particularly advantageous because measuring the spectral response at a single point between 780 nm and 950 nm allows for rapid and automatic identification of numerous types of beverages using a simple sensor board. A light source having a spectrum peaking between 780 nm and 950 nm is advantageous for distinguishing between, for example, milk and plant-based alternatives, as well as for identifying milk at least in part based on its fat content. The use of a spectral sensor having a spectral response peak shifted by up to 20 nm from the peak of at least one light source is advantageous for determining spectral values ​​from reflected light because the spectral sensor has high sensitivity near the peak of at least one light source. The ability to automatically determine the type of beverage in a container is highly advantageous for preparing beverages, particularly when heating and / or frothing the beverage, in order to automatically adjust the recipe for preparing the beverage to achieve optimal preparation.Additionally, certain hygiene standards can be monitored, for example, to monitor product freshness. The sensor board can also help determine whether a beverage contains ingredients listed on an allergen list or that may cause an intolerance reaction. Milk and plant-based milk alternatives are not always easily distinguishable visually. Visually distinguishing different types of milk or different plant-based alternatives is even more complicated. Visually determining the fat content of milk is far from easy. It is nearly impossible to visually distinguish whether a beverage has undergone pretreatment, such as pasteurization or skimming. Thanks to the sensor board, bar staff no longer need to smell or taste the beverage to determine its type. It also eliminates the need to keep the beverage packaging on hand to prevent mistakes. During busy times, multiple containers containing similar but different beverages can be kept on hand to speed up beverage preparation without introducing errors.

[0039] According to a preferred embodiment, the sensor board comprises a measurement sensor for measuring the level and / or volume of the beverage in the container. The measurement sensor is, for example, a ToF (Time of Flight) sensor that measures the distance between the ToF sensor and the upper liquid level formed by the beverage in the container. The measurement sensor is, for example, a sensor that is immersed in the beverage in the container. Preferably, the measurement sensor is a ToF sensor. This is advantageous because there is no contact between the measurement sensor and the beverage in the container. The processing unit is preferably communicatively coupled to the measurement sensor directly or indirectly. Preferably, the processing unit is communicatively coupled to the measurement sensor via a UART or I / O. 2 C, etc. are communicatively coupled directly to the measurement sensors via a serial connection.

[0040] Other non-limiting examples of suitable measurement sensors for measuring the level and / or volume of a beverage in a container include lasers and cameras. A laser is suitable for measuring the distance between the level of the beverage in the container and the sensor board. A camera is suitable for estimating the level and / or volume of a beverage in a known container. Using a known container, it is possible to estimate, based on the camera image, how far the beverage is from the top edge of the known container or another reference point within the known container, from which the level and / or volume of the beverage in the known container can be determined.

[0041] This embodiment is advantageous in that it avoids deviations in the results when determining the type of beverage in a container due to reflections of the light emitted by the at least one light source on the side walls of the container. When preparing a beverage, depending on the beverage to be prepared, the container may be filled with only a small amount of beverage or, conversely, with a much larger amount. This also means that the side walls of the container reflect more or less of the emitted light. These reflections affect the spectral values ​​measured by the at least one spectral sensor. The reflections on the side walls of the container do not represent the beverage in the container. By measuring the level of the beverage in the container or by measuring the volume of the beverage in the container, the level can be calculated, taking into account the effect of reflections on the side walls of the container, allowing for a robust determination of the type of beverage in the container.

[0042] According to a preferred embodiment, the sensor board comprises a temperature sensor for measuring the temperature of the beverage in the container. The temperature sensor is, for example, a temperature sensor that is immersed in the beverage in the container. The temperature sensor is, for example, a thermometer that measures the temperature of the container. The temperature of the container is a measure of the temperature of the beverage in the container. Preferably, the temperature sensor is an optical sensor based on infrared measurement. This is advantageous because, as a result, there is no contact between the temperature sensor and the beverage in the container, and the temperature of the beverage is measured directly rather than indirectly. The processing unit is preferably communicatively coupled to the temperature sensor, either directly or indirectly. Preferably, the processing unit is communicatively coupled to the temperature sensor via a UART or I / O. 2 C, etc. are communicatively coupled directly to the temperature sensor via a series connection.

[0043] This embodiment is advantageous in avoiding deviations in results when determining the type of beverage in a container based on the temperature of the beverage in the container. The characteristics of the beverage in the container may depend on the temperature of the beverage. For example, when a beverage is heated, it expands, which may reduce the specific gravity of the beverage. This may affect the spectral response of the beverage in the container. By measuring the temperature of the beverage in the container, the effect of the beverage temperature on the spectral response can be taken into account, allowing for a robust determination of the type of beverage in the container.

[0044] This embodiment is further advantageous when the sensor board is used in a heating and / or frothing device according to the second aspect. Depending on the type of beverage, it may not be possible to heat the beverage to the same temperature without the beverage breaking down and losing its flavor or quality, or without the foam collapsing during frothing. In this case, the temperature sensor is advantageous not only for accurately determining the beverage, but also for simultaneously determining whether the beverage is at the right temperature.

[0045] According to a preferred embodiment, the sensor board comprises at least two light sources. The first light source has a spectrum with a peak between 780 nm and 849 nm. A particularly advantageous value is 830 nm. Preferably, the peak of the spectrum of the first light source between 780 nm and 849 nm is the global maximum of the spectrum. A particularly advantageous value is 830 nm. The second light source has a spectrum with a peak between 850 nm and 950 nm. A particularly advantageous value is 940 nm. Preferably, the peak of the spectrum of the first light source between 850 nm and 950 nm is the global maximum of the spectrum. One or more spectral sensors have a spectral response with a first peak. The first peak is shifted by 20 nm or less from the peak of the spectrum of the first light source between 780 nm and 849 nm. One or more spectral sensors have a spectral response with a second peak. The second peak is offset by 20 nm or less from the peak between 850 nm and 950 nm of the spectrum of the second light source. When the sensor board includes only one spectral sensor, it is clear that the single spectral sensor has a spectral response with a first peak and a second peak. When the sensor board includes multiple spectral sensors, the first spectral sensor may have a spectral response with a first peak and the second spectral sensor may have a spectral response with a second peak, or the single spectral sensor may have a spectral response with a first peak and a second peak. Similarly, it is possible for multiple spectral sensors to have spectral responses with a first peak, a second peak, or a first peak and a second peak.

[0046] This embodiment is advantageous for more accurately determining the type of beverage in the container. Applicant surprisingly found that this embodiment improves the ability to distinguish between different types of milk having different compositions, such as fat content, between milk and plant-based alternatives, and between plant-based alternatives. A deviation of 20 nm or less between the first peak and the peak between 780 nm and 849 nm in the spectrum of the first light source and between the second peak and the peak between 850 nm and 950 nm in the spectrum of the second light source is advantageous when determining spectral values ​​from reflected light because one or more spectral sensors located near the first peak and the second peak have high sensitivity.

[0047] According to a preferred embodiment, at least one light source is current-controlled. If the sensor board includes multiple light sources, preferably all light sources are current-controlled. The current intensity of the at least one light source is adjustable from the processing unit. For example, the current intensity is adjustable because the processing unit is communicatively coupled, directly or indirectly, to a driver of the at least one light source. If the sensor board includes multiple light sources, preferably the processing unit is communicatively coupled, directly or indirectly, to each driver of each light source.

[0048] Preferably, the current is at least 200 mA, more preferably at least 250 mA, even more preferably at least 300 mA, and even more preferably at least 350 mA.

[0049] Preferably, the current is at most 850mA, more preferably at most 800mA, even more preferably at most 750mA, and even more preferably at most 700mA.

[0050] This embodiment is particularly advantageous for calibrating the sensor board. Calibrating the sensor board ensures that similar spectral values ​​are obtained by the spectral sensor for similar beverages, thereby enabling robust determination of the type of beverage in the container. The spectral sensor typically has an adjustable gain for the spectral response. This adjustable gain is typically the same for each peak of the spectral response. The spectral response of each peak of the spectral response can be indirectly affected by adjusting the current intensity of each light source separately. This embodiment is particularly advantageous when the sensor board includes multiple light sources. This embodiment is also advantageous for obtaining similar spectral values ​​over the lifetime of the sensor board. Light sources emit less light over time. By increasing the current intensity based on the light source's operating time, i.e., the number of hours the light source has emitted light, a consistent light output from the light source can be obtained over the lifetime of the sensor board. This embodiment is also particularly advantageous for automatically increasing or decreasing the light source. If the current intensity is too low, the spectral value may be minimized at a particular wavelength depending on the type of beverage in the container. If the current intensity is too high, the spectral value may be maximized at a particular wavelength depending on the type of beverage in the container. In either case, information is lost and the spectral value may not be discriminatory enough to accurately determine the type of beverage in the container. By automatically amplifying or attenuating the current intensity, it is possible to obtain a spectral value that is not at a minimum or maximum value but still provides sufficient discrimination.

[0051] According to a preferred embodiment, the sensor board comprises a first additional light source, which has a spectrum with a peak between 410 nm and 480 nm. A particularly advantageous value is 420 nm. Preferably, the peak of the spectrum of the first additional light source between 410 nm and 480 nm is the global maximum of the spectrum. The spectral response of the one or more spectral sensors has a peak between 400 nm and 500 nm. Said peak between 400 nm and 500 nm is shifted by a maximum of 20 nm from the peak of the first additional light source.

[0052] This embodiment is advantageous for more accurately determining the type of beverage in the container. The applicant surprisingly found that this embodiment can be used to achieve improved discrimination between different types of milk from different manufacturers, plant-based alternatives such as coconut milk, soy milk, and hazelnut milk, and between similar plant-based alternatives from different manufacturers, even if they have similar compositions, such as similar fat content. This embodiment is also advantageous for distinguishing beverages with small color differences. A maximum 20 nm shift between the peak of the first additional light source and the peak between 400 nm and 500 nm is advantageous for determining spectral values ​​from reflected light because one or more spectral sensors positioned near the peak of the first additional light source are highly sensitive.

[0053] According to a preferred embodiment, the sensor board comprises a second additional light source, which has a spectrum with a peak between 720 nm and 760 nm. A particularly advantageous value is 760 nm. Preferably, the peak of the spectrum of the second additional light source between 720 nm and 760 nm is the global maximum of the spectrum. The spectral response of the one or more spectral sensors has a peak between 700 nm and 800 nm. The aforementioned peak between 700 nm and 800 nm is shifted by a maximum of 20 nm from the peak of the second additional light source.

[0054] This embodiment is advantageous for more accurately determining the type of beverage in the container. The applicant has surprisingly found that this embodiment not only improves the ability to distinguish between the fat contents of different beverages, but also between milk and plant-based alternatives, and between plant-based alternatives and each other. This embodiment is particularly advantageous in combination with the previous embodiment in which the sensor board comprises a first light source and a second light source. A maximum 20 nm shift between the peak of the second additional light source and the peak between 700 nm and 800 nm is advantageous for determining spectral values ​​from reflected light, because one or more spectral sensors positioned near the peak of the second additional light source have high sensitivity.

[0055] According to a preferred embodiment, the sensor board includes a third additional light source. The third additional light source emits white light. The third additional light source is preferably a white LED. The third additional light source preferably has a spectrum from 500 nm to 700 nm, and emits light at wavelengths of 500 nm and 700 nm at at least 5% of the maximum intensity of light between 500 nm and 700 nm. The joint spectral response of all spectral sensors has at least eight peaks between 400 nm and 700 nm. The joint spectral response is the sum of the spectral responses of the individual spectral sensors. If the sensor board includes only one spectral sensor, the joint spectral response is the spectral response of at least one spectral sensor. Between 400 nm and 700 nm, the spectral distance between two adjacent peaks of the joint response is at most 50 nm, preferably at most 45 nm, and even more preferably at most 40 nm. This embodiment is advantageous for improving the overall discrimination ability based on spectral values ​​using white light. This embodiment is particularly advantageous when the ability to distinguish between two beverages based on any of the previous embodiments is insufficient, resulting in an inability to determine the type of beverage in the container with sufficient accuracy. A joint spectral response with at least eight peaks between 400 and 700 nm and a spectral distance of up to 50 nm is sufficient to adequately measure the spectral response of the beverages and determine the type of beverage in the container.

[0056] In a second aspect, the present invention relates to a heating and / or frothing device for heating and / or frothing a beverage.

[0057] According to one embodiment, the heating and / or frothing device comprises a frame, a platform for supporting a container, and a sensor board according to the first aspect for determining the type of beverage in the container. The heating and / or frothing device further comprises heating means for heating the beverage in the container and / or frothing means for frothing the beverage in the container. Non-limiting examples of heating means include electric heating elements. Non-limiting examples of frothing means include rotary beaters, which are preferably magnetically driven. Alternatively, the rotary beaters may be mechanically driven using a shaft. Preferably, the heating means and frothing means are combined, for example, as a steam pipe.

[0058] The at least one light source and the at least one spectral sensor of the sensor board face the platform. Preferably, the optical axis of the at least one light source and the optical axis of the at least one spectral sensor are arranged laterally relative to the platform. As a result, the optical axis of the at least one light source and the optical axis of the at least one spectral sensor are automatically arranged laterally relative to an upper liquid level formed by the beverage in the container.

[0059] This embodiment is highly advantageous for automatically adjusting and setting the recipe for preparing the beverage based on the type of beverage in the container.

[0060] According to a further embodiment, the heating and / or frothing device comprises a display and a rotary beater. The rotary beater is interchangeable. The display is communicatively coupled directly or indirectly to the processing unit of the sensor board. For example, the display is indirectly coupled to the processing unit of the sensor board via a main processing unit of the heating and / or frothing device. The display is configured to indicate the type of rotary beater used to froth the beverage.

[0061] This embodiment is advantageous for optimal frothing of the beverage. For example, depending on the type of beverage, such as whole milk or low-fat milk, a particular type of rotary beater may or may not be successful in frothing the beverage. Using the sensor board, the type of beverage in the container can be automatically determined, and then the display will automatically indicate the specified type of rotary beater for optimally frothing the beverage.

[0062] According to a preferred embodiment, the heating and / or frothing device comprises a frame, a platform for supporting the container, and a steam pipe. The frame is a support structure for the heating and / or frothing device. Preferably, the heating and / or frothing device comprises a housing mounted around the frame. The platform is mounted to the frame. The steam pipe is mounted to the frame. The steam pipe comprises a nozzle for injecting steam or compressed gas into the beverage in the container to heat and / or froth the beverage. The heating and / or frothing device comprises a sensor board according to the first aspect for determining the type of beverage in the container.

[0063] The at least one light source and the at least one spectral sensor of the sensor board face the platform. Preferably, the optical axis of the at least one light source and the optical axis of the at least one spectral sensor are arranged laterally relative to the platform. As a result, the optical axis of the at least one light source and the optical axis of the at least one spectral sensor are automatically arranged laterally relative to an upper liquid level formed by the beverage in the container.

[0064] This embodiment is highly advantageous for automatically adjusting and setting a recipe for preparing a beverage based on the type of beverage in the container. The type of beverage in the container is automatically determined using the sensor board. This prevents bar staff from visually misjudging the type of beverage when preparing the beverage. It also eliminates the need for the beverage container to be on hand to identify the beverage in the container. Furthermore, bar staff can work collaboratively when they are very busy. For example, a first bar staff member or a cobot can prepare multiple containers containing similar but different beverages, while a second bar staff member heats and / or froths the beverage in the container to efficiently prepare the beverage. Because the type of beverage is automatically detected, the recipe is automatically adjusted, allowing the second bar staff member to optimally heat and / or froth the beverage in the container, even without prior knowledge of the type of beverage in the container. Because the heating and / or frothing device can fully automatically heat and / or froth the beverage in the container based on the recipe, the second bar staff member can even perform other tasks while heating and / or frothing.

[0065] According to a preferred embodiment, the heating and / or whipping device comprises an actuator for changing the mutual position between the platform and the sensor board. The actuator is communicatively coupled to a processing unit of the sensor board. The actuator is communicatively coupled to the processing unit of the sensor board directly or indirectly. For example, the actuator is indirectly coupled to the processing unit of the sensor board via a main processing unit of the heating and / or whipping device.

[0066] The actuator advantageously acquires a first fixed predetermined distance between the at least one light source and the upper liquid level formed by the beverage in the container, and a second fixed predetermined distance between the at least one spectral sensor and the upper liquid level. This is advantageous because, as a result, regardless of the amount of beverage in the container, reflection of the light emitted by the at least one light source on the side wall of the container always has a substantially similar effect on the spectral value measured by the spectral sensor. Another advantage is that, since substantially the same amount of light emitted by the at least one light source always reaches the upper liquid level, fluctuations due to ambient light are reduced. This allows for a robust determination of the type of beverage in the container. When the sensor board includes multiple light sources and / or multiple spectral sensors, these multiple light sources and / or multiple spectral sensors preferably have fixed positions relative to each other, so it is clear that the aforementioned advantages are also maintained in these cases.

[0067] According to one embodiment, the heating and / or frothing device includes a network connection. The network connection can be either a wired or wireless network connection, such as an Ethernet connection or a WiFi connection. The network connection is advantageous for remotely updating software running on the processing unit of the sensor board. This is particularly advantageous when the sensor board needs to recognize new types of beverages, such as new plant-based milk substitutes or new manufacturers of a certain type of beverage. The network connection is also advantageous for automatically receiving orders, for example, from a cash register system, so that the correct recipe for the beverage can be automatically selected and the sensor board can be used to confirm whether the correct beverage is heated and / or frothed. The network connection is also advantageous for transmitting spectral values ​​of the beverage to a server, for example, if the beverage is not automatically recognized. The transmitted spectral values ​​can then be used as a training example for a classification algorithm, as described below.

[0068] According to one embodiment, the heating and / or frothing device comprises input means for inputting data. The input means may be, for example, a touch display, a keyboard, or other suitable means. The input means is advantageous for inputting the type of beverage when the type of beverage cannot be automatically determined using the sensor board. This embodiment, like the previous embodiment, is particularly advantageous when combined with a network connection. This allows the input type of beverage to be transmitted to a server together with the spectral values ​​of the beverage, so that the spectral values ​​can be used as an annotated training example for a classification algorithm. This embodiment is also advantageous for using the spectral values ​​of the beverage together with the input type of beverage to train a classification algorithm on the processing unit of the heating and / or frothing device, as will be explained in the next aspect. The input means is also particularly advantageous for inputting a recipe for heating and / or frothing the beverage. This is particularly advantageous when the type of beverage cannot be automatically determined using the sensor board. This usually means that a recipe for heating and / or frothing this type of beverage is not available. By inputting a recipe via the input means, unknown types of beverages can be heated and / or frothed using the heating and / or frothing device, and since the input recipe is associated with the input type, beverages of this type can later be heated and / or frothed automatically.

[0069] In a third aspect, the present invention relates to a method for determining the type of beverage in a container, such as milk or plant-based milk substitute, juice, espuma or soup.

[0070] According to a preferred embodiment, the method comprises: - illuminating the beverage in the container with light from at least one light source; - capturing light reflected by the beverage from at least one light source using at least one spectral sensor; - processing the spectral values ​​of the reflected light determined by the at least one spectral sensor using a processing unit for determining the type of beverage in the container; Includes.

[0071] The at least one light source has a spectrum with a peak between 780 nm and 950 nm. The at least one spectral sensor has a spectral response with a peak between 760 nm and 970 nm. The peak of the spectral response of the at least one spectral sensor is offset from the peak of the at least one light source by a maximum of 20 nm. The at least one light source and the at least one spectral sensor are directed toward the beverage in the container. Preferably, the optical axis of the at least one light source and the optical axis of the at least one spectral sensor are positioned transversely to the upper liquid level formed by the beverage in the container. Preferably, the at least one light source irradiates the beverage for at least 50 milliseconds, more preferably at least 75 milliseconds, and even more preferably at least 90 milliseconds. This is advantageous because it means that the beverage is irradiated for a period of time long enough for the at least one spectral sensor to measure stable spectral values. Preferably, the at least one light source irradiates the beverage for a maximum of 2.0 seconds, more preferably at a maximum of 1.5 seconds, and even more preferably at a maximum of 1.2 seconds. This is advantageous for automatically determining the type of beverage in the container as quickly as possible. When multiple light sources are used in carrying out the method, different light sources can sequentially and simultaneously illuminate the beverage in the container, preferably containing at least 100 mL of beverage, which is advantageous in order to avoid light reflections from the bottom of the container that could interfere with determining the spectral response of the beverage.

[0072] Determining the type of beverage can be done in a single step or multiple steps, where the primary category of beverage is determined first, and then one or more subcategories are determined.

[0073] This method is advantageous for automatically determining the type of beverage in a container by using at least one light source having a spectrum with a peak between 780 nm and 950 nm. The type of beverage in the container can be determined by determining and processing the spectral values ​​of light from the at least one light source reflected by the beverage in the container onto a spectral sensor. A light source having a peak between 780 nm and 950 nm is highly advantageous for identifying beverages used in beverage preparation, particularly for distinguishing between, for example, milk and plant-based alternatives. The use of a spectral sensor having a spectral response with a peak that is shifted by up to 20 nm from the peak of the at least one light source is advantageous for determining the spectral values ​​from the reflected light, since the at least one spectral sensor has high sensitivity near the peak of the at least one light source. The ability to automatically determine the type of beverage in a container is highly advantageous when preparing beverages, particularly when heating and / or frothing the beverage, in order to automatically adjust the recipe for preparing the beverage to achieve optimal preparation while avoiding errors.

[0074] According to a preferred embodiment, before illuminating the beverage in the container with light from the at least one light source, the method includes a first additional step of measuring the level and / or volume of the beverage in the container using a measurement sensor. The beverage in the container forms an upper liquid level. The first additional step is followed by a second additional step. In the second additional step, the at least one light source and the upper liquid level are positioned at a predetermined first distance from each other. In the second additional step, the at least one spectral sensor and the upper liquid level are positioned at a predetermined second distance from each other. The first distance and the second distance are measured transversely to the upper liquid level.

[0075] It will be apparent that if the at least one light source and the at least one spectral sensor have fixed positions relative to each other, positioning the at least one light source and the upper liquid level at a first predetermined distance relative to each other will also position the at least one spectral sensor and the upper liquid level at a second predetermined distance relative to each other. This embodiment also applies mutatis mutandis when multiple light sources and multiple spectral sensors are used in performing the method.

[0076] This embodiment is advantageous because, regardless of the amount of beverage in the container, the reflection of the light emitted by the at least one light source on the sidewall of the container always has a substantially similar effect on the spectral value measured by the spectral sensor. This also has the advantage that substantially the same amount of light emitted by the at least one light source always reaches the upper liquid level, resulting in less fluctuation due to ambient light. This results in a robust determination of the type of beverage in the container.

[0077] For example, this embodiment of the method is carried out using the heating and / or frothing device according to the second aspect, where the heating and / or frothing device includes an actuator for changing the relative position between the platform and the sensor board, similar to the previously described embodiment of the heating and / or frothing device. In a second additional step, the platform is moved toward the sensor board until the at least one light source and the upper liquid level are positioned at a first predetermined distance and the at least one spectral sensor and the upper liquid level are positioned at a second predetermined distance from each other. For example, the platform is moved toward the sensor board until the nozzle of the steam pipe contacts the upper liquid level.

[0078] Preferably, the second additional step is only performed if the level and / or volume of the beverage in the container, measured using the measurement sensor, is above a first predetermined value and below a second predetermined value. This is advantageous because there should not be too much or too little beverage in the container in order to heat and / or froth the beverage. This is further advantageous because if there is too little beverage in the container, the type of beverage in the container may be incorrectly determined, for example because the bottom of the container is too visible and interferes with the expected light reflection.

[0079] According to a preferred embodiment, before processing the spectral values ​​of the reflected light determined by the at least one spectral sensor using the processing unit, the method comprises a third additional step of measuring the temperature of the beverage in the container using a temperature sensor. This embodiment can be advantageously, but need not be, combined with the previously described embodiments.

[0080] This embodiment is advantageous in avoiding deviations in results when determining the type of beverage in a container based on the temperature of the beverage in the container. The characteristics of the beverage in the container may depend on the temperature of the beverage. For example, when the beverage is heated, it expands, which may reduce the specific gravity of the beverage. This may affect the spectral response of the beverage in the container. By measuring the temperature of the beverage in the container, the effect of the beverage temperature on the spectral response can be taken into account, allowing for a robust determination of the type of beverage in the container.

[0081] According to a preferred embodiment, a classification algorithm is executed in the processing unit when processing the spectral values ​​of the reflected light determined by the at least one spectral sensor. If multiple spectral sensors are used when performing the method, it is preferred that all spectral values ​​determined by all spectral sensors are processed by the classification algorithm in the processing unit.

[0082] The classification algorithm was trained using training examples of multiple beverages. Non-limiting examples of the training examples include skim milk, low-fat milk, whole milk, soy milk, coconut milk, hazelnut milk, etc. For each training example, spectral values ​​are obtained by illuminating the training example with light from at least one light source and collecting reflected light from the training example using at least one spectral sensor. When multiple spectral sensors and / or multiple light sources are used in implementing the method, it is preferred that the spectral values ​​of the training examples be obtained using all of the spectral sensors and / or all of the light sources. Non-limiting examples of suitable classification algorithms include support vector machines (SVM) and random forests. Preferably, the classification algorithm is an SVM algorithm. Preferably, the classification algorithm is trained on a server or computer. Alternatively, the classification algorithm is trained on a processing unit, where the processing unit is included in the heating and / or frothing device according to the second aspect.

[0083] This embodiment is advantageous because it uses training examples to provide a classification algorithm that robustly determines the type of beverage in the container and is easily extensible to new types of beverages by adding additional training examples.

[0084] According to a further embodiment, each training example is in the same container during acquisition of the spectral values ​​as during determination of the beverage type.

[0085] This embodiment is particularly advantageous because the spectral values ​​of the training examples can be determined in the same container used to determine the type of beverage when performing the method, thereby automatically taking into account the shape and material of the container and therefore reflections on the container's side walls. This embodiment is particularly advantageous when combined with the previous embodiment, in which at least one light source is positioned at a first predetermined distance from the upper liquid level and at least one spectral sensor is positioned at a second predetermined distance from the upper liquid level.

[0086] According to one embodiment, the plurality of training examples comprises a set of identical beverages at different temperatures. This embodiment is advantageous because it automatically takes into account the possibility of different spectral responses of beverages at different temperatures. This embodiment is particularly advantageous when combined with the previously described embodiment in which the temperature of the beverage in the container is measured in order to process the spectral values.

[0087] According to one embodiment, spectral values ​​of a plurality of training examples are obtained at different light intensities of at least one light source. When LEDs are used, this is done, for example, by using different current intensities to control the LEDs. This is advantageous for automatically taking into account possible differences in the spectral response of the beverage at different light intensities. This is particularly advantageous for automatically increasing or decreasing the light source, for example, as described above for the sensor board.

[0088] According to one embodiment, the at least one light source and the at least one spectral sensor are calibrated. The at least one light source and the at least one spectral sensor are calibrated using an empty beverage container. This embodiment of the method can be implemented using both the heating and / or frothing device according to the second aspect and the sensor board according to the first aspect. When implementing the method using the heating and / or frothing device according to the second aspect, an empty beverage container is used with the heating and / or frothing device. The empty container is preferably positioned so that it shields the at least one light source and the at least one spectral sensor from external light. For example, when using the heating and / or frothing device according to the second aspect, the heating and / or frothing device includes an actuator for changing the relative position between the platform and the sensor board. As with the previously described embodiment of the heating and / or frothing device, the platform is moved toward the sensor board until the empty container is positioned relative to the sensor board or is in close proximity to the sensor board.

[0089] This embodiment is advantageous in absorbing differences due to manufacturing margins between light sources and between spectral sensors. If the measurement results deviate from the expected measurement results, for example, a different current intensity can be set for the light source, as described above when calibrating the sensor board according to the first aspect. Alternatively, if the measurement results deviate, a scaling factor for the measurement results can be determined. This allows the same training example to be used for all sensor boards. The calibration is preferably performed before commissioning the sensor board according to the first aspect or the heating and / or frothing device according to the second aspect. The calibration can be repeated during use of the sensor board according to the first aspect or the heating and / or frothing device according to the second aspect, for example, to compensate for changes over time in the at least one light source and / or the at least one spectral sensor.

[0090] In a fourth aspect, the present invention relates to a method for heating and / or frothing a beverage in a container, such as milk or a plant-based milk substitute, juice, espuma or soup.

[0091] According to a preferred embodiment, the method comprises the steps of determining the type of beverage in the container, followed by heating and / or frothing the beverage in the container according to a predetermined recipe.

[0092] The determination of the type of beverage in the container is performed using a sensor board according to the first aspect. The determination of the type of beverage in the container is preferably performed by performing a method according to the third aspect.

[0093] The heating and / or frothing of the beverage is preferably started automatically after the type of beverage in the container has been determined. A predetermined recipe is automatically selected from a collection of recipes depending on the type of beverage in the container. This means, for example, that if whole milk is determined as the type of beverage in the container and the beverage is to be frothed, a recipe for frothing whole milk is selected from the collection of recipes. The heating and / or frothing of the beverage is preferably performed using a heating and / or frothing device according to the second aspect.

[0094] This method is advantageous because the beverage is optimally heated and / or frothed according to a recipe depending on the type of beverage in the container, thus avoiding errors.

[0095] Those skilled in the art will appreciate that the method according to the third aspect is preferably carried out using a sensor board according to the first aspect or a heating and / or whipping device according to the second aspect, and that the sensor board according to the first aspect or the heating and / or whipping device according to the second aspect is preferably configured to carry out the method according to the third aspect. Accordingly, each of the features described herein above and below may relate to any of the four aspects of the invention.

Claims

1. 1. A sensor board for determining the type of beverage in a container, such as milk or a plant-based milk substitute, juice, espuma or soup, comprising: a processing unit; at least one light source for emitting light; and at least one spectral sensor for collecting reflected light from said at least one light source, wherein said at least one light source has a spectrum with a peak between 780 nm and 950 nm, and said at least one spectral sensor has a spectral response with a peak between 760 nm and 970 nm, and wherein the peak of the spectral response of said at least one spectral sensor is shifted from the peak of said at least one light source by 20 nm or less.

2. 2. A sensor board according to claim 1, characterized in that the sensor board comprises a measurement sensor for measuring the level and / or volume of the beverage in the container.

3. 3. A sensor board according to claim 1 or 2, characterized in that the sensor board comprises a temperature sensor for measuring the temperature of the beverage in the container.

4. 4. The sensor board of claim 1, wherein the sensor board comprises at least two light sources, a first light source having a spectrum with a peak between 780 nm and 849 nm, a second light source having a spectrum with a peak between 850 nm and 950 nm, one or more spectral sensors having a spectral response with a first peak that is shifted from the peak of the first light source by a maximum of 20 nm, and one or more spectral sensors having a spectral response with a second peak that is shifted from the peak of the second light source by a maximum of 20 nm.

5. The sensor board according to any one of claims 1 to 4, characterized in that the at least one light source is current controlled, the current intensity of the at least one light source being adjustable from the processing unit.

6. 6. The sensor board according to claim 1, further comprising a first additional light source, the first additional light source having a spectrum with a peak between 410 nm and 480 nm, the spectral response of one or more spectral sensors having a peak between 400 nm and 500 nm, the peak between 400 nm and 500 nm being shifted by a maximum of 20 nm from the peak of the first additional light source.

7. 7. The sensor board of claim 1, further comprising a second additional light source, the second additional light source having a spectrum with a peak between 720 nm and 780 nm, the spectral response of one or more spectral sensors having a peak between 700 nm and 800 nm, the peak between 700 nm and 800 nm being shifted from the peak of the second additional light source by a maximum of 20 nm.

8. 8. The sensor board according to claim 1, wherein the sensor board comprises a third additional light source, the third additional light source emitting white light, the joint spectral response of all spectral sensors having at least 12 peaks between 400 nm and 700 nm, and the spectral distance between two adjacent peaks of the joint spectral response between 400 nm and 700 nm is at most 50 nm.

9. 9. A heating and / or frothing apparatus for heating and / or frothing a beverage, comprising: a frame; a platform attached to the frame for supporting a container; and a steam pipe attached to the frame, the steam pipe comprising a nozzle for injecting steam or compressed gas into the beverage in the container to heat and / or froth the beverage; and a sensor board according to any one of claims 1 to 8 for the heating and / or frothing apparatus to determine the type of beverage in the container.

10. The heating and / or frothing device according to claim 9, characterized in that the heating and / or frothing device comprises an actuator for changing the relative position between the platform and the sensor board, the actuator being communicatively coupled to the processing unit of the sensor board.

11. 1. A method for determining the type of beverage in a container, such as milk or plant-based milk substitute, juice, espuma or soup, comprising: - illuminating said beverage in said container with light from at least one light source; - capturing light reflected by said beverage from said at least one light source using at least one spectral sensor; - processing the spectral values ​​of the reflected light determined by the at least one spectral sensor using a processing unit for determining the type of beverage in the container; wherein the at least one light source has a spectrum with a peak between 780 nm and 950 nm, and the at least one spectral sensor has a spectral response with a peak between 760 nm and 970 nm, and the peak of the spectral response of the at least one spectral sensor is shifted from the peak of the at least one light source by 20 nm or less.

12. 12. The method of claim 11, further comprising a first additional step of measuring the level and / or volume of the beverage in the container using a measurement sensor before irradiating the beverage in the container with light from the at least one light source, the beverage in the container forming an upper liquid level, the first additional step being followed by a second additional step, in which the at least one light source and the upper liquid level are positioned at a predetermined first distance from each other, and in which the at least one spectral sensor and the upper liquid level are positioned at a predetermined second distance from each other.

13. 13. The method of claim 11 or 12, characterized in that the method comprises a third additional step of measuring the temperature of the beverage in the container using a temperature sensor before processing the spectral values ​​of the reflected light determined by the at least one spectral sensor using the processing unit.

14. 14. The method of claim 11, wherein when processing the spectral values ​​of the reflected light determined by the at least one spectral sensor, a classification algorithm is executed on the processing unit, the classification algorithm being trained using a plurality of training examples of beverages, and obtaining spectral values ​​for each of the training examples by illuminating each of the training examples with light from the at least one light source and collecting light reflected by each of the training examples using the at least one spectral sensor, and each of the training examples being in the same container during obtaining the spectral values ​​as during determining the type of the beverage.

15. 15. The method of claim 14, wherein the plurality of training examples includes a set of the same beverage at different temperatures.

Images