Method and device for controlling food cooking process

Abstract

The invention relates to a method (100) for controlling a food cooking process. The method comprises a step of detecting (S101) a change in weight of a first vaporizable component in the food during a first period of time. The method further comprises the step of determining (S102) an initial state of the food based at least in part on the detected change in weight of the first vaporizable component in the food. The method further comprises a step of controlling (S103) the cooking process based at least in part on the determined initial state of the food. The invention also relates to a corresponding apparatus and a computer program product.

Description

[0001] This application is a divisional application of the international application date of March 3, 2015, which entered the Chinese national phase on September 9, 2016, with application number 201580013070.3 and invention name “Method and device for controlling food cooking process”. Technical Field

[0002] Embodiments of the present invention relate to cooking process control, and more particularly, to a method, apparatus, and computer program product for controlling a cooking process based on detecting an initial state of food. Background Art

[0003] It should be understood that the initial state of certain types of food to be cooked may have some influence on the control of the cooking process. As used herein, "initial state" refers to the state of the food at the beginning of cooking or near the beginning of the cooking process. For example, the initial state may include whether the food is frozen or non-frozen, the frozen state or degree of freezing of the food, the amount of food, etc. In general, the cooking profile or parameters should be selected based at least in part on the initial state of the food. For example, different cooking times and / or temperatures may be selected depending on whether the food is frozen.

[0004] Traditionally, the initial state of food is determined by the user of the food, and the cooking process is controlled based on the cooking time, cooking temperature or possible other cooking parameters selected by the user. For example, the user can determine the initial state of the food he / she wants to cook based on some visual and / or tactile clues, and then select a cooking program by operating a button, knob or any other mechanism on the cooking device. However, users, especially ordinary consumers, often cannot accurately and quantitatively determine the initial state of various types of food. Therefore, human errors will affect the cooking process.

[0005] In order to achieve more precise control to automatically select cooking profiles, some invasive or non-invasive methods for detecting the frozen / non-frozen state of food have been proposed, for example, by sensing the initial temperature of the food. However, both invasive and non-invasive methods have defects that limit their practical application. For example, invasive methods generally require detection tools to contact food, which may cause the food to be damaged or contaminated. Non-invasive methods usually rely on sensing technologies such as infrared (IR), which can only detect the surface temperature of food. Therefore, it is difficult for non-invasive methods to predict whether food is volume frozen, partially frozen or completely frozen. In addition, due to shortcomings such as high cost, inconvenient maintenance and inaccuracy in harsh environments (e.g., cooking environments), existing solutions cannot meet the actual needs of consumer cooking equipment while providing sufficient robustness for cooking process control.

[0006] EP 0 238 022 A2 describes a heating device for cooking cakes, comprising a gas sensor and a weight sensor for determining the total heating time.

[0007] EP 0001396 Al describes a method of cooking meat in a microwave oven by determining the average internal temperature of the meat, which is indicative of the internal doneness of the meat, as a function of sensed and sampled time-varying "in situ" humidity and temperature ambient conditions.

[0008] US 2013 / 0092682 A1 describes an oven comprising multiple energy sources and a cooking controller capable of varying cooking parameters based on information received from an oven operator.

[0009] JP S5847934A discloses a method of cooking in a high frequency heater, comprising setting a weight reduction ratio based on the type and amount of a substance to be cooked, and stopping cooking when the actual weight reduction ratio reaches the set point.

[0010] In light of the foregoing, there exists a need in the art for a more accurate and cost-effective solution for cooking process control. Summary of the invention

[0011] In order to solve the above and other potential problems, the embodiments of the present invention provide a method, an apparatus and a computer program product for cooking process control.

[0012] The invention is defined by the independent claims. The dependent claims define preferred embodiments.

[0013] In one aspect, embodiments of the present invention provide a method for controlling a cooking process of food.

[0014] The method comprises the steps of: detecting a weight change of a first vaporizable component in a food during a first period of time; determining an initial state of the food based at least in part on the detected weight change of the first vaporizable component in the food; and controlling the cooking process based at least in part on the determined initial state of the food. Other embodiments in this regard include corresponding computer program products for cooking process control.

[0015] In another aspect, an embodiment of the present invention provides an apparatus for controlling a cooking process of food. The apparatus includes: a detection unit configured to detect a weight change of a first vaporizable component in the food during a first period of time, wherein the first vaporizable component includes water in the food; an initial state determination unit configured to determine an initial state of the food based at least in part on the detected weight change of the first vaporizable component in the food; and a cooking control unit configured to control the cooking process based at least in part on the determined initial state.

[0016] Implementation of embodiments of the present invention may achieve one or more of the following advantages. According to embodiments of the present invention, the initial state of food may be determined by detecting a change in the weight of an evaporable component (e.g., water) in the food. In this manner, the initial state of the food may be determined without contact with the food, thereby avoiding any damage or contamination. In addition, since the change in the weight of the evaporable component in the food may be accurately detected using reliable, low-cost equipment, the method may be able to determine the initial state of the food and control the cooking process with high accuracy while maintaining costs at a relatively low level. Furthermore, exemplary embodiments of the present invention require little or no user intervention and may be used in conjunction with a variety of cooking devices.

[0017] Other features and advantages of embodiments of the present invention will also be understood from the following description of exemplary embodiments when taken in conjunction with the accompanying drawings, which illustrate the spirit and principles of the present invention by way of example. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The following drawings and description describe the details of one or more embodiments of the present invention. Other features, aspects and advantages of the present invention will become apparent from the following description, drawings and claims, among which:

[0019] Figure 1 is a flowchart of a method for controlling a cooking process of food according to an exemplary embodiment of the present invention.

[0020] Figure 2A and Figure 2B are schematic diagrams showing thermogravimetric curves of French fries and meatballs according to exemplary embodiments of the present invention; and

[0021] Figure 3 is a block diagram illustrating an apparatus for controlling a cooking process of food according to an embodiment of the present invention.

[0022] Throughout the drawings, the same or similar reference numerals denote the same or similar elements. DETAILED DESCRIPTION

[0023] Generally, embodiments of the present invention provide a method, apparatus, and computer program product for cooking process control. A core inventive concept of the present invention is to determine the initial state of the food by detecting the weight change of the water or any other evaporable component in the food over a period of time. Since the weight change can be detected by various reliable and low-cost methods, embodiments of the present invention provide an accurate and cost-effective way to determine the initial state of the food (e.g., frozen / non-frozen, food quantity, etc.) and control the cooking process accordingly.

[0024] Reference now Figure 1 , in which a flow chart of a method 100 for controlling the cooking process according to an exemplary embodiment of the present invention is shown.

[0025] In step S101, a weight change of a vaporizable component in food during a first period of time is detected. As used herein, "vaporizable component" refers to any component that can evaporate from food under certain conditions. For example, in some embodiments, the vaporizable component can be water in food. As is known, for example, when heating food, water evaporates as the temperature rises. Alternatively or additionally, it is possible to detect a weight change of any other suitable vaporizable component in food, such as vaporizable fat, etc. For illustrative purposes only, in the following discussion, some exemplary embodiments will be described with respect to water. However, it should be noted that the scope of the present invention is not limited thereto.

[0026] In some embodiments, the weight change of the first vaporizable component in the food can be detected as a separate procedure from the cooking process. That is, in such an embodiment, the weight change of the first vaporizable component in the food and thus the initial state of the food are detected before the cooking process begins. In this way, the entire cooking process can be controlled based on the detected initial state of the food, so that the food can be cooked well.

[0027] Alternatively, in some other embodiments, detecting the weight change of the first vaporizable component in the food and determining the initial state of the food can be performed as part of the cooking process. More specifically, in such an embodiment, the first stage in which the weight change of the first vaporizable component in the food is detected can be the initial stage of the cooking time of the cooking process. As an example, the user can first select a cooking profile or cooking program, for example, randomly or based on personal experience or some visual / tactile clues. Then, in the initial stage of the cooking time (such as a few minutes), the weight change of the first vaporizable component is detected, so that the initial state of the food can be determined to control the rest of the cooking process. This is very beneficial for the cooking time because no additional time is required.

[0028] In some embodiments, in order to facilitate the detection of the weight change of the first vaporizable component in the food, the food may be placed in an environment with a predetermined configuration. For example, the food may be placed in an oven or any other suitable cooking device with a predetermined humidity, temperature, etc. Specifically, in some embodiments, the food may be preheated to accelerate the evaporation rate of the first vaporizable component.

[0029] According to an embodiment of the present invention, in step S101, the weight change of the first vaporizable component in the food can be detected in various ways. For example, assuming that the evaporation of the first vaporizable component in the first time period is the only reason for the weight change of the food. According to the law of conservation of mass, the weight loss of the food is equal to the weight of the first vaporizable component evaporated from the food. Therefore, in some exemplary embodiments, the weight change of the first vaporizable component in the food can be measured by detecting the weight change of the food itself during the first time period.

[0030] According to embodiments of the present invention, the weight change of food during the first period can be measured by various low-cost and accurate methods. For example, in some embodiments, the initial weight of the food is measured and recorded. The weight of the food can then be sampled over time. For example, the weight of the food can be sampled periodically (e.g., every one or two minutes). Alternatively, sampling can be performed continuously until enough data has been collected to determine the initial state. For example, the weight of the food can be sampled using a weight sensor or an electronic balance supporting the cooking device. Based on the sampling of the weight of the food and the initial weight, a set of values ​​of the change in the weight of the food can be calculated.

[0031] Additionally or alternatively, in some embodiments, one or more other features related to the change in weight of the food may be measured. As an example, in some embodiments, the time for the weight of the food to change by at least one predetermined amount may be measured. As another example, based on a set of values ​​of the change in weight of the food, a thermogravimetric (TG) curve can be established that characterizes the change in weight of the food over a first period of time. For example, the TG curve may be embodied as a description of the change in weight of the food over time, which will be referred to below. Figure 2A and Figure 2B Discussion. In some embodiments, the TG curve may be normalized, denoised or otherwise processed, for example. At least one morphological feature is then extracted from the TG curve based on a prediction model for identifying an initial state. Examples of morphological features include, but are not limited to, derivatives of various orders, slopes, gradients, and the like.

[0032] It should be noted that while detecting a change in weight of food is an effective method for detecting a change in weight of the first evaporable component in the food, the scope of the present invention is not limited thereto. For example, in those embodiments where the first evaporable component in the food is water, in step S101, the change in weight of the first evaporable component in the food can be measured by detecting a change in an environmental parameter during the first period of time. Examples of environmental parameters include, but are not limited to, humidity. It should be understood that in a closed environment such as an oven, the humidity of the surrounding air will increase as the water in the food evaporates. Therefore, by detecting a change in the ambient humidity, the weight change of the water can be derived. Any suitable humidity sensor, whether currently known or developed in the future, can be used to detect humidity, and the scope of the present invention is not limited thereto.

[0033] As another example, in step S101, the weight change of the first evaporable component in the food can be detected by directly measuring the amount of the first evaporable component that has evaporated from the food in the first period of time. For example, it is well known that when water evaporates into the air, the water molecules rotate with the alternating electromagnetic field and convert their energy into heat energy. Therefore, the amount of evaporated water can be directly detected using radio frequency radiation with a suitable frequency. Based on the detected amount of evaporated water, the weight change of the water in the food can be derived.

[0034] It should be noted that, according to embodiments of the present invention, different techniques for detecting the weight change of the first vaporizable component in the food may be used alone. Or alternatively, two or more of them may be combined in any suitable manner. In addition, the scope of the present invention is not limited to the examples described above. Instead, any other suitable technique, whether currently known or developed in the future, may be used to detect or assess the weight change of the first vaporizable component in the food.

[0035] Continue to refer to Figure 1 The method 100 then proceeds to step S102 where an initial state of the food is determined based at least in part on the detected weight change of the first vaporizable component in the food.

[0036] As discussed above, the "initial state" refers to the state of the food at or near the beginning of the cooking process. For example, the initial state may include whether the food is frozen or non-frozen, the freezing state or degree of the food, the amount of food, etc. As an example, the freezing state may be divided into a plurality of levels, each of which corresponds to a range of food temperature.

[0037] According to an embodiment of the present invention, the correlation between the weight change of the first vaporizable component in the food (or, in some embodiments, the weight of the food) and the initial state of the food can be predetermined. For example, in some embodiments, the weight change of the first vaporizable component in the food may be simply compared with a predetermined threshold and then the initial state may be determined based on the comparison. As an example, there may be two initial states to be selected, frozen and non-frozen. If the weight change of the first vaporizable component in the food within the first time period is higher than the predetermined threshold, it can be determined that the initial state of the food is a frozen state. On the contrary, if this weight change is lower than the predetermined threshold, it can be determined that the initial state of the food is a non-frozen state.

[0038] In order to more accurately control the cooking process, in some embodiments, the correlation between the weight change of the first vaporizable component in the food and the initial state of the food can be characterized by a prediction model. In general, the prediction model can be regarded as a classifier for identifying the initial state of the food based on one or more features related to the weight change of the first vaporizable component in the food (which may include, for example, one or more features representing the weight change of the food). As discussed above, the required features are collected in step S101 and may include, but are not limited to, the weight change value or change rate of the first vaporizable component in the food at multiple time points, the time it takes to reach a predetermined amount of weight change, or any other features extracted from the TG curve created during training. These features can be used as input to the prediction model in step S102 to obtain the predicted initial state of the food.

[0039] In some exemplary embodiments, the prediction model may predict the initial temperature of the food based on one or more features of the input. The frozen state of the food may then be determined based on the predicted temperature and a specific freezing level may be predicted. Alternatively, in some embodiments, the prediction model may directly map the extracted features to the initial state of the food.

[0040] According to embodiments of the present invention, any suitable prediction model can be used to determine the initial state of the food. Examples of prediction models include, but are not limited to, hidden Markov models (HMM), support vector machines (SVM), artificial neural networks, or any other suitable prediction models. The prediction model can be trained in advance and, in some embodiments, can be refined during use.

[0041] In particular, in some embodiments, prediction models may be established or trained for individual food types. That is, different prediction models are used for different types of food. Since it is known that the volatility of different foods may be different, this helps to improve the accuracy of the initial state prediction. Therefore, in some embodiments, determining the initial state of the food may include obtaining the type of the food. In some embodiments, the type of food may be specified by the user. For example, the user may select or specify the type of food using a mechanism on a cooking device. Alternatively, the type of food may be automatically identified using suitable sensors, machine vision, or pattern recognition technology. As an example, in some embodiments, one or more images of the food may be acquired and analyzed to identify the shape or other features of the food, thereby determining the type of food.

[0042] In those embodiments where the type of food is obtained, the initial state of the food can be determined by a prediction model based on the weight change of the first vaporizable component in the food detected in step S101 and the obtained type of food. More specifically, a prediction model designed for the type of food selected can be selected. One or more features related to the weight change of the first vaporizable component in the food are then input into the selected prediction model to determine the initial state.

[0043] It should be noted that, although it is beneficial to obtain and utilize the type of food in some embodiments, this is not necessarily performed. For example, for those dedicated cooking devices designed to cook similar types of food, a single prediction model is sufficient and there is no need to obtain the type of food. Therefore, in some embodiments, the step of obtaining the type of food can be omitted.

[0044] like Figure 1 As shown, in step S103, the cooking process is controlled based at least in part on the determined initial state of the food. Generally, the cooking profile or one or more parameters thereof for the cooking process can be adjusted according to the determined initial state. For example, the cooking time, temperature and / or any other relevant parameters or settings can be adjusted. In some embodiments, the cooking profile for each initial state of the food can be predicted. For illustrative purposes only, the following table shows an example.

[0045] Initial state Cooking Profiles freezing 16min, 200℃ Non-frozen 12min, 200℃

[0046] As discussed above, in some embodiments, determining the initial state may be performed prior to the cooking procedure. Therefore, in these embodiments, the cooking process may be controlled from the very beginning to utilize a cooking profile corresponding to the determined initial state. Alternatively, the initial state may also be determined during the cooking process. That is, the first time period used for initial state determination is the initial stage of the cooking time, such as the first few minutes. In these embodiments, if it is found that the initial cooking profile is not suitable for the determined initial state, the cooking profile or parameters used for the remaining cooking steps may be adjusted in step S103. On the other hand, if the initial cooking profile selected by the user happens to be one corresponding to the determined initial state, the remaining cooking time period does not need to be adjusted. In other words, according to an embodiment of the present invention, control of the cooking process includes protecting the cooking profile from being changed.

[0047] In addition, in some embodiments, controlling the cooking process in step S103 further includes automatically monitoring the doneness of the food or the time to complete the cooking of the food. To this end, the weight change of the second evaporable component in the food can be detected in the second time period of the cooking process. According to an embodiment of the present invention, the second evaporable component may or may not be the same as the first evaporable component. For example, in some embodiments, the second evaporable component may also be water in the food, and one or more of the following characteristics may be detected at at least one time point in the second time period: water loss, water loss rate, change in water loss rate, etc. The weight change of the second evaporable component in the food can be measured in a manner similar to the above discussion on the first evaporable component, so it will not be repeated.

[0048] Based on the detected weight change of the second evaporable component in the food and the initial state determined in step S102, the degree of maturity of the food and the time to complete the cooking of the food can be determined. For example, for a certain type of food in a given initial state, when the water loss reaches a predetermined value, the food can be determined to be fully cooked. In addition, in some embodiments, the user is allowed to select the degree of doneness he / she needs (e.g., lightly cooked, medium cooked, well cooked). A model can be used to characterize the correlation between each possible degree of doneness and the weight change of the second evaporable component in the food (or the weight change of the food in the same embodiment). Then, based on the weight change of the second evaporable component in the food detected during the second period, the cooking process can be controlled to reach the degree of doneness required by the user.

[0049] For illustration purposes only, an example will now be discussed. In this example, the food to be cooked includes French fries and meatballs. Before frying, the weight of the food is measured using an electronic balance and the initial temperature of the food is measured using a thermometer. While the food is placed in the food basket, the initial weight is recorded. During the frying process, the weight of the food is detected and recorded. The conditions for this example (for both French fries and meatballs) are listed below:

[0050] Initial state: Frozen, Unfrozen

[0051] Initial weight: 300g, 300g, 500g

[0052] Frying temperature: 200℃

[0053] Total frying time: about 20 minutes

[0054] Figure 2A TG curves 201 and 202 were established when heating frozen and non-frozen French fries in an air fryer. Specifically, Figure 2A In FIG. 2 , curve 201 represents the TG curve of French fries in a frozen state, and curve 202 represents the TG curve of French fries in a non-frozen state. As described above, the TG curve describes the weight change of food over time. Similarly, Figure 2B In the figure, curve 203 represents the TG curve of the meatballs in a frozen state, and curve 204 represents the TG curve of the meatballs in a non-frozen state. Figure 2A and 2B , the vertical axis represents the normalized weight in arbitrary units, and the horizontal axis represents the frying time (in seconds).

[0055] During training, the TG curve in the form of a weight change curve is normalized, denoised and smoothed. It can be seen that foods in different initial states (frozen / non-frozen) have different TG curves. Therefore, the initial state (frozen or non-frozen) can be determined in combination with the initial weight of the food using the features in the TG curve. More specifically, in this example, the normalized remaining weight of the food at 180 seconds of frying (labeled as RW) will be used to determine the initial state. The initial food weight (labeled as M) is also considered as an independent predictor variable. In this example, the prediction model represents the correlation between the initial temperature of the food (labeled as T) and the two independent variables RW and M, as follows:

[0056] T=a*RW+b*M+c*RW*M+d

[0057] Where a, b, c and d represent parameters. The parameter values ​​are derived by training the prediction model using linear regression based on the collected training data:

[0058] parameter fries meatball a -1.1316E+03 -2.2060E+03 b -1.18219E-01 1.8667E+00 c 2.1701E-01 -1.8249E+00 d 1.1110E+03 2.1518E+03

[0059] When detecting the initial state, the values ​​of variables M and RW are detected and input into the prediction model to obtain the predicted initial temperature T. Then, the initial state of the food is classified according to the preset temperature interval of the food. For example, if the T value is lower than or equal to the threshold value of 0°C, the initial state of the food is determined to be a frozen state. If the estimated value of T is higher than 0°C, the initial state of the food is determined to be a non-frozen state. The experimental results show that the initial state of the food can be accurately identified.

[0060] Figure 3 A block diagram of a device for controlling a cooking process of food according to an embodiment of the present invention is shown. As shown in the figure, the device 300 includes: a first detection unit 301, configured to detect a weight change of a first evaporable component in the food during a first period of time, wherein the first evaporable component includes water in the food; an initial state determination unit 302, configured to determine an initial state of the food based at least in part on the detected weight change of the first evaporable component; and a cooking control unit 303, configured to control a cooking process based at least in part on the determined initial state of the food.

[0061] In some embodiments, the first detection unit 301 may include at least one of the following: a food weight detection unit, configured to detect a change in weight of food during a first time period; an environmental parameter detection unit, configured to detect a change in an environmental parameter during the first time period, the environmental parameter including humidity; and a component weight detection unit, configured to detect an evaporation amount of a first evaporable component evaporated from the food during the first time period.

[0062] In some embodiments, the food weight detection unit may include at least one of the following: a weight sampling unit configured to sample the weight change of the food at at least one time point within a first time period; a time determination unit configured to determine the time elapsed for the weight change of the food to reach at least one predetermined amount; and a feature extraction unit configured to extract at least one morphological feature from a thermogravimetric curve characterizing the weight change of the food during the first time period.

[0063] In some embodiments, the first period may be an initial stage of a cooking time of the cooking process. In these embodiments, the cooking control unit 303 may be configured to adjust the cooking process during the remaining stage of the cooking time based at least in part on the determined initial state of the food.

[0064] In some embodiments, the food may be placed in an environment having a predetermined configuration to facilitate detecting a change in weight of the first vaporizable component.

[0065] In some embodiments, the apparatus 300 may further include a food type acquisition unit configured to acquire the type of food. In these embodiments, the initial state determination unit 301 may be configured to determine the initial state of the food based on a predetermined prediction model and the acquired food type based on the detected weight change of the first vaporizable component in the food.

[0066] In some embodiments, the apparatus 300 may further include: a second detection unit configured to detect a weight change of a second vaporizable component in the food during a second period of the cooking process; and a doneness determination unit configured to determine the doneness of the food based on the detected weight change of the second vaporizable component of the food.

[0067] It should be noted that the device 300 can be implemented as hardware, software / firmware or a combination thereof. In some embodiments, one or more units in the device 300 can be implemented as software modules. For example, an embodiment of the present invention can be embodied as a computer program product that is tangibly stored in a non-transitory computer-readable medium. The computer program product includes machine-executable commands that, when executed, cause the machine to perform the steps of method 100. Alternatively or additionally, all or part of the units in the device 300 can be implemented using hardware modules, such as integrated circuits (ICs), application-specific integrated circuits (ASICs), system integrated chips (SOCs), field programmable gate arrays, and the like. In addition, in some embodiments, the device 300 can be integrated into a cooking device. Alternatively, the device 300 can be operated as a separate device.

[0068] In general, various exemplary embodiments may be implemented in hardware or dedicated circuits, software, logic, or a combination thereof. Certain aspects may be implemented in hardware, but other aspects may be implemented in firmware or software, which may be executed by a controller, microprocessor, or other computing device. Although various aspects of the exemplary embodiments of the present invention are illustrated and described as block diagrams, flow charts, or using other graphical representations, it should be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general-purpose hardware or controllers, and other computing devices, or a combination thereof, as non-limiting examples.

[0069] In the context of the present invention, a machine-readable medium may be any tangible medium that may contain or store a program used by or connected to an instruction execution system, device, or apparatus. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical fiber, electromagnetic field, infrared, or semiconductor system, device, or device, or any suitable combination thereof. More specific examples of machine-readable storage media may include an electronic connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0070] The computer program code for executing the method of the present invention may be written in any combination of one or more programming languages. These computer program codes may be provided to a general-purpose computer processor, a special-purpose computer or other programmable data program device, so that when the computer processor or other programmable data program device executes the code, the functions / operations specified in the flowchart and / or block diagram are executed. The program code may be executed entirely on a computer, partially on a computer, as an independent software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server.

[0071] The above-described embodiments are merely illustrative and are not intended to limit the technical methods of the present invention. Although the present invention is described in detail with reference to preferred embodiments, it should be understood by those skilled in the art that the technical methods of the present invention may be modified or replaced equally without departing from the spirit and scope of the technical solutions of the present invention, and they also fall within the scope of protection of the claims of the present invention. In the claims, the word "comprising" does not exclude other elements or steps, and the word "one" or "an" does not exclude multiple. Any figure mark in the claims should not be understood as limiting the scope of protection.

Claims

1. A method (100) for controlling a cooking process of food, the method comprising the steps of: - detecting (S101) a weight change of the food caused by evaporation of a first vaporizable component in the food within a first period of time; - determining (S102) the initial state of the food according to the trained prediction model and based on the detected weight change of the food, wherein the initial state refers to a state in which the food is in or is about to start a cooking process, wherein the correlation between the weight change of the food caused by the evaporation of the first vaporizable component in the food during the first period of time and the initial state of the food is characterized by the trained prediction model; - controlling (S103) the cooking process at least partly based on the determined initial state of the food.

2. The method according to claim 1, wherein the step of detecting (S101) the weight change of the food comprises at least one of the following steps: - detecting a change in weight of the food based on an initial weight of the food and another weight of the food sampled during the first period of time; - detecting a change in an environmental parameter during said first period, said environmental parameter comprising humidity; and - detecting the amount of said first vaporizable component vaporized from said food during said first period of time.

3. The method according to claim 2, wherein the step of detecting the weight change of the food comprises at least one of the following steps: - sampling the weight change of the food at at least one time point within the first time period; - determining the time elapsed for the weight of the food to change by at least one predetermined amount; as well as - extracting at least one morphological feature from a thermogravimetric curve characterizing a change in weight of said food during said first period of time.

4. A method according to any one of claims 1 to 3, wherein the first time period is an initial stage of a cooking time of the cooking process, and wherein the step of controlling (S103) the cooking process includes the step of adjusting the cooking process in a remaining time period of the cooking time based at least in part on the determined initial state of the food.

5. The method according to any one of claims 1 to 3, wherein the food is placed in an environment having a predetermined configuration for the step of detecting (S101) a weight change.

6. The method according to any one of claims 1 to 3, wherein the step of determining (S102) the initial state of the food comprises the steps of: - obtaining the type of said food; and - based on the detected weight change of the first vaporizable component in the food, determining the initial state of the food according to the trained prediction model and the acquired type of the food.

7. The method according to any one of claims 1 to 3, wherein the step of controlling (S103) the cooking process comprises the steps of: - detecting another weight change of the food due to evaporation of a second vaporizable component in the food during a second period of time during the cooking process; and - Determining the doneness of the food based on the detected further weight change of the food.

8. The method according to any one of claims 1 to 3, wherein the initial state of the food includes whether the food is frozen or non-frozen, and the freezing state or degree of the food.

9. A device (300) for controlling a cooking process of food, the device comprising: - a first detection unit (301) configured to detect a weight change of the food caused by evaporation of a first vaporizable component in the food within a first period of time; - an initial state determination unit (302), configured to determine the initial state of the food according to a trained prediction model and based on the detected weight change of the food, wherein the initial state refers to a state in which the food is in or is about to start a cooking process, wherein the correlation between the weight change of the food caused by the evaporation of the first vaporizable component in the food within the first time period and the initial state of the food is characterized by the trained prediction model; and - a cooking control unit (303) configured to control the cooking process based at least in part on the determined initial state of the food.

10. The device according to claim 9, wherein the first detection unit (301) comprises at least one of the following: - a food weight detection unit configured to detect a weight change of the food during a first period; - an environmental parameter detection unit configured to detect a change in an environmental parameter during a first period of time, the environmental parameter comprising humidity; and - a component weight detection unit configured to detect the amount of said first vaporizable component vaporized from said food during said first period of time.

11. The device according to claim 10, wherein the food weight detection unit comprises at least one of the following: - a weight sampling unit, configured to sample the weight change of the food at at least one time within the first time period; - a time determination unit configured to determine the time elapsed when the weight change of the food reaches at least one predetermined amount; - a feature extraction unit configured to extract at least one morphological feature from a thermogravimetric curve representing a weight change of the food within a first period of time.

12. An apparatus according to any one of claims 9 to 11, wherein the first time period is an initial stage of a cooking time of the cooking process, and wherein the cooking control unit (303) is configured to adjust the cooking process in a remaining time period of the cooking time based at least in part on the determined initial state of the food.

13. Apparatus according to any one of claims 9 to 11, wherein the food is placed in an environment having a predetermined configuration for detection.

14. The device according to any one of claims 9 to 11, further comprising: - a food type obtaining unit, configured to obtain the type of the food, The initial state determination unit (302) is configured to determine the initial state of the food based on the detected weight change of the first vaporizable component in the food, according to the trained prediction model and the acquired type of the food.

15. The device according to any one of claims 9 to 11, further comprising: - a second detection unit configured to detect another weight change of the food due to evaporation of a second vaporizable component in the food during a second period of the cooking process; as well as A doneness determination unit configured to determine the doneness of the food based on the detected further weight change of the food.

16. Apparatus according to any one of claims 9 to 11, wherein the first vaporisable component is water.

17. The apparatus according to any one of claims 9 to 11, wherein the initial state of the food comprises whether the food is frozen or non-frozen, and the freezing state or degree of the food.

18. A computer program product for controlling a cooking process of food, the computer program product being tangibly stored on a non-transitory computer-readable medium and comprising machine-executable instructions which, when executed, cause the machine to perform the steps of the method (100) according to any one of claims 1 to 8.

Images