Integrated intelligent cooking platform control method and system based on internet of things

Abstract

This application relates to the field of cooking control and discloses a control method and system for an integrated intelligent cooking platform based on the Internet of Things (IoT). The method includes: acquiring the current cooking recipe of the integrated intelligent cooking platform, and acquiring multiple cooking modules and cooking parameters corresponding to the current cooking recipe; determining the corrected cooking parameters of multiple cooking modules based on the current cooking recipe and the cooking parameters of the multiple cooking modules using a cooking recipe optimization model; determining the collaborative control matrix of multiple cooking modules based on the current cooking recipe using a cooking recipe parsing unit, whereby the collaborative control matrix characterizes the cross-module coupling influence characteristics of the multiple cooking modules; and determining the corrected cooking parameters of multiple cooking modules based on the current cooking recipe, the cooking parameters of the multiple cooking modules, and the collaborative control matrix using the cooking recipe optimization model. This application can simplify the cooking process of the integrated intelligent cooking platform and optimize the overall cooking process of the integrated intelligent cooking platform.

Description

Technical Field

[0001] This application relates to the field of cooking control technology, and more specifically, to an integrated intelligent cooking platform control method and system based on the Internet of Things. Background Technology

[0002] Existing integrated smart cooking platforms typically integrate multiple cooking function modules to achieve unified cooking operations. These modules include, but are not limited to: frying modules for pan-frying and grilling; baking modules for high-temperature baking and braising; steaming modules for steam generation and heating; and boiling modules for boiling, stewing, and blanching. Through the combination or independent operation of these modules, the platform can theoretically complete a variety of basic cooking tasks such as frying eggs, roasting meat, steaming fish, boiling noodles, making soup, baking pastries, and air frying, aiming to meet users' diverse kitchen needs.

[0003] However, current control methods for these integrated intelligent cooking platforms have significant limitations during operation. The mainstream operating mode of these platforms relies on users manually starting, stopping, and setting parameters (such as time, temperature, and heat) for different cooking modules. This modular, discrete control method has obvious drawbacks: firstly, for users, controlling the cooking process is complex and cumbersome, requiring monitoring and adjusting the working status of each module separately. This is especially problematic when cooking complex recipes that require multiple modules to work together, resulting in a poor user experience and a high risk of errors. Secondly, there is a lack of organic, recipe-specific parameter linkage and optimization between different cooking modules. The preset or user-defined parameters of integrated intelligent cooking platforms are often independent of each module, failing to achieve optimal parameter ratios and dynamic adjustments across modules based on the overall cooking logic of a specific recipe. This makes it difficult for the platform to achieve the best flavor and texture when executing complex recipes, resulting in insufficient optimization of the recipe during cooking. Summary of the Invention

[0004] The purpose of this application is to provide an integrated intelligent cooking platform control method and system based on the Internet of Things, which solves the technical problems of complex and cumbersome cooking process control and the inability to optimize cooking according to the overall cooking logic of a specific recipe, and achieves the technical effect of simplifying the cooking process and optimizing the cooking process of the integrated intelligent cooking platform as a whole.

[0005] This application provides an integrated intelligent cooking platform control method based on the Internet of Things. The method includes: acquiring the current cooking recipe of the integrated intelligent cooking platform, and acquiring multiple cooking modules and cooking parameters corresponding to the current cooking recipe; wherein, the multiple cooking modules include a steaming module, a boiling module, a stir-frying module, a pan-frying module, and a baking module; and determining the corrected cooking parameters of the multiple cooking modules based on the current cooking recipe and the cooking parameters of the multiple cooking modules through a cooking recipe optimization model; wherein, the cooking recipe optimization model is trained based on sample cooking recipes and the cooking parameters of the sample cooking recipes.

[0006] In one possible implementation, a cooking recipe optimization model is used to determine modified cooking parameters for multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. This includes: determining a collaborative control matrix for multiple cooking modules based on the current cooking recipe using a cooking recipe parsing unit, where the collaborative control matrix characterizes the cross-module coupling influence features of the multiple cooking modules; and determining modified cooking parameters for multiple cooking modules based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control matrix using the cooking recipe optimization model.

[0007] In another possible implementation, a cooking recipe optimization model is used to determine the corrected cooking parameters for multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. This also includes: using a cooking recipe adjustment unit to determine the crispness influence coefficient of the steaming module on the frying module, the humidity influence coefficient of the stir-frying module on the baking module, and the doneness influence coefficient of the boiling module on the stir-frying module, based on the current cooking recipe. The crispness influence coefficient, humidity influence coefficient, and doneness influence coefficient are then fused with a collaborative control matrix to obtain a collaborative control adjustment matrix. The cooking recipe adjustment unit is trained using the current sample cooking recipe, the sample crispness influence coefficient of the steaming module on the frying module, the sample humidity influence coefficient of the stir-frying module on the baking module, and the sample doneness influence coefficient of the boiling module on the stir-frying module. The cooking recipe optimization model determines the corrected cooking parameters for multiple cooking modules based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control adjustment matrix.

[0008] In another possible implementation, a cooking recipe optimization model is used to determine modified cooking parameters for multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. This also includes: obtaining flavor substance delivery constraints for different ingredients in the current cooking recipe from a cooking recipe database; applying threshold correction to the collaborative control adjustment matrix based on the flavor substance delivery constraints to obtain a collaborative control constraint matrix; wherein the flavor substance delivery constraints characterize the retention characteristics of flavor substances in ingredients when cooking conditions change, and include flavor substance cooking time constraints, flavor substance concentration constraints, flavor substance formation rate constraints, and flavor substance weight constraints; and determining modified cooking parameters for multiple cooking modules based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control constraint matrix using the cooking recipe optimization model.

[0009] In another possible implementation, a cooking recipe optimization model is used to determine the corrected cooking parameters for multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. This also includes: acquiring the cooking parameters and timing feedback parameters corresponding to each of the multiple cooking modules; determining the collaborative control feedback matrix corresponding to multiple cooking modules using a cooking module parsing unit for each cooking module, based on the cooking parameters and timing feedback parameters for each cooking module; wherein the timing feedback parameters include timing temperature parameters, timing humidity parameters, and timing pressure parameters; and determining the corrected cooking parameters for multiple cooking modules using the cooking recipe optimization model based on the current cooking recipe, the cooking parameters of multiple cooking modules, the collaborative control constraint matrix, and the collaborative control feedback matrix.

[0010] In another possible implementation, a cooking recipe optimization model is used to determine the corrected cooking parameters for multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. This also includes: obtaining the recipe adjustment priority weights corresponding to the current cooking recipe from a cooking recipe database; fusing the collaborative control feedback matrix and collaborative control constraint matrix corresponding to multiple cooking modules according to the recipe adjustment priority weights to obtain a collaborative control fusion matrix; wherein the recipe adjustment priority weights represent the priority weights of the multiple cooking modules when adjusting them separately; and determining the corrected cooking parameters for multiple cooking modules based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control fusion matrix using the cooking recipe optimization model.

[0011] In another possible implementation, a cooking recipe optimization model is used to determine the corrected cooking parameters for multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. This also includes: obtaining the main dish cooking priority weight corresponding to the current cooking recipe input by the user; determining the cooking priority weights of other dishes in the current cooking recipe based on the main dish cooking priority weight using a cooking recipe planning unit; fusing the collaborative control feedback matrix and collaborative control constraint matrix corresponding to multiple cooking modules according to the main dish cooking priority weight and the cooking priority weights of other dishes in the current cooking recipe to obtain a collaborative control fusion matrix; wherein, the main dish cooking priority weight represents the priority weight of the dish with higher importance corresponding to the current cooking recipe; and determining the corrected cooking parameters for multiple cooking modules based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control fusion matrix using the cooking recipe optimization model.

[0012] In another possible implementation, a cooking recipe optimization model is used to determine the corrected cooking parameters for multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. This also includes: obtaining cooking feedback information corresponding to the current cooking recipe from user feedback; determining the recipe adjustment priority correction weight corresponding to the current cooking recipe based on the cooking feedback information and recipe adjustment priority weights using a cooking recipe planning unit; and fusing the collaborative control feedback matrix and collaborative control constraint matrix corresponding to each cooking module according to the recipe adjustment priority correction weights for each cooking module to obtain a collaborative control fusion matrix. The cooking recipe optimization model determines the corrected cooking parameters for multiple cooking modules based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control fusion matrix.

[0013] In another possible implementation, a cooking recipe optimization model is used to determine the modified cooking parameters of multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. This also includes: determining the difference eigenvalues ​​corresponding to multiple collaborative control fusion matrices in historical data, and determining multiple target collaborative control fusion matrices whose difference eigenvalues ​​are less than preset difference eigenvalues; determining the mean matrix of the multiple target collaborative control fusion matrices as the target collaborative control matrix; and using the cooking recipe optimization model, the modified cooking parameters of multiple cooking modules are determined based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the target collaborative control matrix.

[0014] This application also provides an integrated intelligent cooking platform control system based on the Internet of Things, including a unit for performing the method described in any of the preceding embodiments.

[0015] The beneficial effects of the embodiments in this application compared with the prior art are:

[0016] This application provides a control method for an integrated intelligent cooking platform based on the Internet of Things (IoT). The method includes: acquiring the current cooking recipe of the integrated intelligent cooking platform, and acquiring multiple cooking modules and corresponding cooking parameters for the current cooking recipe; wherein the multiple cooking modules include a steaming module, a boiling module, a stir-frying module, a pan-frying module, and a baking module; and determining corrected cooking parameters for the multiple cooking modules based on the current cooking recipe and the cooking parameters of the multiple cooking modules using a cooking recipe optimization model; wherein the cooking recipe optimization model is trained based on sample cooking recipes and their cooking parameters. The method in this application can monitor and adjust the working status of each module separately, and can perform optimal parameter allocation and dynamic adjustment across modules according to the overall cooking logic of a specific recipe. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating the first IoT-based integrated intelligent cooking platform control method provided in this application embodiment;

[0019] Figure 2 A schematic diagram illustrating the workflow of the first IoT-based integrated intelligent cooking platform control method provided in this application embodiment;

[0020] Figure 3 A schematic flowchart illustrating the second IoT-based integrated intelligent cooking platform control method provided in this application embodiment;

[0021] Figure 4 A schematic diagram illustrating the workflow of a second IoT-based integrated smart cooking platform control method provided in this application embodiment;

[0022] Figure 5 A flowchart illustrating the third IoT-based integrated intelligent cooking platform control method provided in this application embodiment;

[0023] Figure 6 This is a schematic diagram of the logical structure of an integrated intelligent cooking platform control system based on the Internet of Things, provided as an embodiment of this application. Detailed Implementation

[0024] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0025] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0026] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrases "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0027] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0028] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0029] The current cooking process control is complex and cumbersome, requiring the monitoring and adjustment of the working status of each module separately. This is especially true when cooking complex recipes that require the cooperation of multiple modules, resulting in a poor user experience and a high risk of errors. At the same time, there is a lack of parameter linkage and optimization between different cooking modules based on specific recipes and in an organic and coordinated manner.

[0030] Based on the above reasons, this application provides an integrated intelligent cooking platform control method based on the Internet of Things. This method includes: acquiring the current cooking recipe of the integrated intelligent cooking platform, and acquiring multiple cooking modules and corresponding cooking parameters for the current cooking recipe; wherein the multiple cooking modules include a steaming module, a boiling module, a stir-frying module, a pan-frying module, and a baking module; and determining corrected cooking parameters for the multiple cooking modules based on the current cooking recipe and the cooking parameters of the multiple cooking modules using a cooking recipe optimization model; wherein the cooking recipe optimization model is trained based on sample cooking recipes and their cooking parameters. The method in this application can monitor and adjust the working status of each module separately, and can perform optimal parameter allocation and dynamic adjustment across modules according to the overall cooking logic of a specific recipe.

[0031] In some scenarios, the IoT-based integrated intelligent cooking platform control method of this application embodiment can be applied to the control of an integrated intelligent cooking platform including a steaming module, a boiling module, a stir-frying module, a pan-frying module, and a baking module. It can centrally control and optimize the cooking of the integrated intelligent cooking platform according to the recipe, thereby improving the effectiveness of the integrated intelligent cooking platform.

[0032] The following describes in detail, with specific examples, an integrated intelligent cooking platform control method based on the Internet of Things provided in the embodiments of this application.

[0033] Figure 1 A flowchart illustrating the first IoT-based integrated intelligent cooking platform control method provided in this application embodiment is shown below. Figure 1 As shown, the control method of this IoT-based integrated intelligent cooking platform includes S110 to S120, and S110 to S120 will be described in detail below.

[0034] S110. Obtain the current cooking recipe from the integrated intelligent cooking platform, and obtain multiple cooking modules and the corresponding cooking parameters for the current cooking recipe. The multiple cooking modules include steaming, boiling, stir-frying, pan-frying, and baking modules.

[0035] Figure 2 A schematic diagram of the workflow of the first IoT-based integrated intelligent cooking platform control method provided in this application embodiment is shown below. Figure 2 As shown, the current cooking recipe of the integrated intelligent cooking platform can be obtained, as well as multiple cooking modules and the cooking parameters corresponding to the current cooking recipe. The multiple cooking modules include steaming, boiling, stir-frying, pan-frying and baking modules. These cooking modules can perform different cooking functions for different ingredients to complete the cooking process of complex recipes.

[0036] For example, the current cooking recipe can contain complex recipes with multiple cooking modules working together. For instance, a braised pork dish may require blanching in the boiling module first, then caramelizing the sugar in the stir-fry module, and finally simmering in the boiling module. By obtaining the cooking parameters corresponding to each module, it can be ensured that each module executes precisely according to the recipe requirements.

[0037] For example, the current cooking recipe can contain a complex recipe in which multiple cooking modules work together. For instance, multiple dishes may include a first dish cooked by stir-frying, a second dish cooked by boiling, and a third dish cooked by baking. By obtaining the cooking parameters corresponding to each module, it can be ensured that each module accurately executes the cooking process of the first, second, and third dishes according to the recipe requirements.

[0038] S120. Using a cooking recipe optimization model, based on the current cooking recipe and the cooking parameters of multiple cooking modules, determine the corrected cooking parameters for multiple cooking modules. The cooking recipe optimization model is trained based on sample cooking recipes and their cooking parameters.

[0039] like Figure 2 As shown, after obtaining the cooking parameters of multiple cooking modules, the cooking recipe optimization model can be used to determine the corrected cooking parameters of multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. Subsequently, cooking can be carried out using the corrected cooking parameters of multiple cooking modules.

[0040] For example, the cooking recipe optimization model can be a deep learning model based on neural networks. The cooking recipe optimization model can be trained based on sample cooking recipes, the cooking parameters of sample cooking recipes, and the sample cooking parameters of multiple cooking modules. The cooking recipe optimization model can learn the mapping relationship between different recipes and the best cooking parameters. The model can output the optimal parameter adjustment scheme for each cooking module based on the current recipe and environmental conditions.

[0041] For example, the current cooking recipe of the integrated smart cooking platform can be obtained through a database deployed in the cloud. The cooking recipe optimization model can be deployed in the cloud. The current cooking recipe and the cooking parameters of multiple cooking modules can be processed in the cloud to obtain the corrected cooking parameters of multiple cooking modules. The corrected cooking parameters of multiple cooking modules can be sent to the integrated smart cooking platform through the Internet of Things.

[0042] The beneficial effects of the above implementation method are that it obtains cooking parameters corresponding to multiple cooking modules and the current cooking recipe, so that when cooking complex recipes that require the cooperation of multiple modules, the working status of each module can be monitored and adjusted separately, which improves the user experience, increases the fault tolerance of the system, and improves the cooking effect of the integrated intelligent cooking platform.

[0043] The beneficial effect of the above implementation method is that it can perform optimal parameter matching and dynamic adjustment across modules according to the overall cooking logic of a specific recipe, so that the cooking platform can achieve the best flavor and taste effect when executing complex recipes, and improve the optimization of recipe cooking.

[0044] Figure 3 A flowchart illustrating the second IoT-based integrated intelligent cooking platform control method provided in this application embodiment is shown below. Figure 3 As shown, in S120 above, the cooking recipe optimization model determines the modified cooking parameters of multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules, including S121 to S122. S121 to S122 will be explained in detail below.

[0045] S121. Through the cooking recipe parsing unit, determine the collaborative control matrix of multiple cooking modules based on the current cooking recipe. The collaborative control matrix characterizes the cross-module coupling influence characteristics of multiple cooking modules.

[0046] Figure 4 A schematic diagram of the workflow of the second IoT-based integrated smart cooking platform control method provided in this application embodiment is shown below. Figure 4 As shown, in this implementation, the cooking recipe parsing unit can determine the collaborative control matrix of multiple cooking modules based on the current cooking recipe. The collaborative control matrix can quantitatively characterize the interaction and cross-module coupling effects between different cooking modules on the recipe, such as the correlation between the dynamic effects of the steaming module and the boiling module on the recipe. The collaborative control matrix can collaboratively optimize the cooking process of different dishes.

[0047] For example, when the integrated intelligent cooking platform executes the stewing function of the first dish, the cooking recipe analysis unit can analyze parameters such as heating power and heating time in the current recipe, and then predict indicators such as the tenderness of the first dish. Through the collaborative control matrix that reflects the mutual influence of these modules, the collaborative control matrix can guide the cooking of the second dish, such as the doneness and crispness. Then, based on the tenderness of the first dish, the doneness and crispness of the second dish can be adjusted, thereby improving the texture and difference of multiple dishes in the recipe and improving the cooking effect of the recipe.

[0048] For example, the cooking recipe parsing unit can be a deep learning model based on neural networks, which can be trained by sample cooking recipes and sample collaborative control matrices of multiple cooking modules.

[0049] S122. Using the cooking recipe optimization model, determine the corrected cooking parameters for multiple cooking modules based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control matrix.

[0050] like Figure 4 As shown, after obtaining the collaborative control matrix, the cooking recipe optimization model can be used to determine the modified cooking parameters of multiple cooking modules based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control matrix. Then, the cooking process can be optimized based on the modified cooking parameters of multiple cooking modules.

[0051] For example, in the process of an integrated intelligent cooking platform performing the stewing function of the first dish and the stir-frying function of the second dish, after obtaining the collaborative control matrix, the corrected stewing parameters of the first dish and the corrected stir-frying parameters of the second dish can be determined based on the current cooking recipe, the stewing parameters of the first dish, the stir-frying parameters of the second dish among the cooking parameters of multiple cooking modules, and the collaborative control matrix.

[0052] For example, the cooking recipe optimization model can be a reinforcement learning-based intelligent decision-making model. The cooking recipe optimization model can be trained with a large amount of historical cooking data and can learn the optimal combination of parameters between different modules.

[0053] The beneficial effect of the above implementation method is that by obtaining the collaborative control matrix of multiple cooking modules corresponding to the current cooking recipe and equipment, the collaborative control matrix represents the cross-module coupling effect of multiple cooking modules, and the recipe is subsequently optimized through the collaborative control matrix, ensuring the scientificity and rationality of the recipe optimization.

[0054] The beneficial effect of the above implementation method is that it optimizes the current cooking recipe based on the current cooking recipe, the cooking parameters of multiple cooking modules and the collaborative control matrix, thereby improving the cooking effect of the integrated intelligent cooking platform in the current cooking recipe.

[0055] In some implementations, S120 above involves determining the corrected cooking parameters of multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules through a cooking recipe optimization model. It also includes S123 to S124, which will be explained in detail below.

[0056] S123. Using the cooking recipe adjustment unit, based on the current cooking recipe, determine the crispness influence coefficient of the steaming module on the frying module, the humidity influence coefficient of the stir-frying module on the baking module, and the cooking influence coefficient of the boiling module on the stir-frying module. Then, fuse the crispness influence coefficient, humidity influence coefficient, cooking influence coefficient, and collaborative control matrix to obtain the collaborative control adjustment matrix. The cooking recipe adjustment unit is trained using the current sample cooking recipe, the sample crispness influence coefficient of the steaming module on the frying module, the sample humidity influence coefficient of the stir-frying module on the baking module, and the sample cooking influence coefficient of the boiling module on the stir-frying module.

[0057] In this implementation, the cooking recipe adjustment unit can determine the influence coefficients of the steaming module on the crispness of the frying module, the influence coefficients of the stir-frying module on the humidity of the baking module, and the influence coefficients of the boiling module on the doneness of the stir-frying module, based on the current cooking recipe. These influence coefficients reflect the interaction between different cooking modules.

[0058] For example, the cooking recipe adjustment unit can be a deep learning model based on neural networks. The cooking recipe adjustment unit can be trained by the current sample cooking recipe, the sample crispness influence coefficient of the steaming module on the frying module, the sample moisture influence coefficient of the stir-frying module on the baking module, and the sample doneness influence coefficient of the boiling module on the stir-frying module. During the training process, the cooking recipe adjustment unit can learn the complex correlation patterns between different cooking modules.

[0059] For example, the influence coefficient of the steaming module on the crispness of the frying module can characterize the extent to which the crispness of the frying module is increased when the tenderness of the steaming module is greater, so as to improve the difference between the tenderness of steaming and the crispness of frying in the recipe, thereby improving the richness of the cooking texture of the recipe.

[0060] For example, the humidity influence coefficient of the stir-fry module on the baking module can characterize the reduction in humidity of the baking module when the crispness of the ingredients is high in the stir-fry module, so as to increase the difference between stir-fry crispness and baking humidity in the recipe, thereby improving the richness of the cooking taste of the recipe.

[0061] For example, the influence coefficient of the cooking module on the cooking module can characterize the range of cooking module cooking degree when the tenderness in the cooking module is high, so as to increase the difference between the tenderness in the cooking module and the cooking degree in the cooking module, thereby improving the richness of the cooking taste of the recipe.

[0062] After determining the brittleness influence coefficient, moisture influence coefficient, and ripeness influence coefficient, these influence coefficients can be fused with the collaborative control matrix to obtain the collaborative control adjustment matrix.

[0063] For example, when integrating the brittleness influence coefficient, humidity influence coefficient, and maturity influence coefficient with the collaborative control matrix, the coefficient diagonal matrix corresponding to the influence coefficient can be constructed first. The coefficient diagonal matrix can be assigned weight matrices W1 and W2 with the original matrix. Subsequently, the collaborative control adjustment matrix can be obtained by weighted summation of the coefficient diagonal matrix and the collaborative control matrix according to the Hadamard product (⊙).

[0064] S124. Using the cooking recipe optimization model, determine the corrected cooking parameters for multiple cooking modules based on the current cooking recipe, cooking parameters of multiple cooking modules, and collaborative control adjustment matrix.

[0065] After obtaining the collaborative control adjustment matrix, the cooking recipe optimization model can determine the corrected cooking parameters of multiple cooking modules based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control adjustment matrix. The cooking recipe optimization model can combine the collaborative control adjustment matrix of the mutual influence between the parameters of each module to obtain the corrected cooking parameters of multiple cooking modules.

[0066] The beneficial effect of the above implementation method is that, based on the cooking characteristics in the current cooking recipe, the influence coefficient of the steaming module on the crispness of the frying module, the influence coefficient of the stir-frying module on the humidity of the baking module, and the influence coefficient of the boiling module on the doneness of the stir-frying module are determined. Then, the cooking process is comprehensively optimized based on the influence coefficients of crispness, humidity, and doneness, which improves the overall richness of the taste and the diversity of the cooking characteristics of each dish in the recipe, and improves the cooking effect of each dish in the recipe.

[0067] The beneficial effect of the above implementation method is that it integrates the crispness influence coefficient, humidity influence coefficient, ripeness influence coefficient and collaborative control matrix to obtain a collaborative control adjustment matrix, and optimizes the cooking process according to the collaborative control adjustment matrix, which facilitates the convenience of optimizing the cooking of the integrated intelligent cooking platform in the current cooking recipe.

[0068] In some implementations, S120 above involves determining the corrected cooking parameters of multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules using a cooking recipe optimization model. It also includes S125 to S126, which will be explained in detail below.

[0069] S125. Obtain the flavor substance transfer constraints corresponding to different ingredients in the current cooking recipe from the cooking recipe database. Based on the flavor substance transfer constraints, perform threshold correction on the cooperative control adjustment matrix to obtain the cooperative control constraint matrix. The flavor substance transfer constraints characterize the retention features of flavor substances in the ingredients when cooking conditions change. These constraints include flavor substance cooking time constraints, flavor substance concentration constraints, flavor substance formation rate constraints, and flavor substance weight constraints.

[0070] In this implementation, the flavor substance transfer constraints corresponding to different ingredients in the current cooking recipe can be obtained through the cooking recipe database. The flavor substance transfer constraints can characterize the retention characteristics of flavor substances in ingredients when cooking conditions change, providing a scientific basis for subsequent parameter optimization.

[0071] It should be noted that the constraints on flavor substance delivery include cooking time constraints, concentration constraints, formation rate constraints, and weight constraints. These constraints together constitute a complete index system for flavor substance retention.

[0072] In this implementation, the collaborative control adjustment matrix can be threshold-corrected according to the flavor substance transfer constraints to obtain the collaborative control constraint matrix. This process can transform the flavor substance retention requirements into specific cooking control constraints, providing clear boundary conditions for subsequent parameter optimization. As a result, the collaborative control constraint matrix can effectively coordinate the parameter adjustment relationships between different cooking modules, ensuring that the optimization process meets the various requirements for flavor substance retention.

[0073] For example, when performing threshold correction on the cooperative control adjustment matrix based on flavor substance delivery constraints, the corresponding parameters in the cooperative control adjustment matrix can be directly adjusted to the parameters corresponding to the flavor substance delivery constraints.

[0074] S126. Using the cooking recipe optimization model, determine the modified cooking parameters of multiple cooking modules based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control constraint matrix.

[0075] After obtaining the collaborative control constraint matrix, the cooking recipe optimization model can determine the modified cooking parameters of multiple cooking modules based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control constraint matrix. The cooking recipe optimization model can comprehensively consider recipe characteristics, existing cooking parameters, and flavor retention constraints, and output the modified cooking parameters of multiple cooking modules.

[0076] For example, a cooking recipe optimization model can be obtained by using a reinforcement learning-based intelligent algorithm trained on a large amount of historical cooking data, and can adapt to different combinations of ingredients and cooking scenarios.

[0077] For example, when controlling the cooking of braised pork using an integrated intelligent cooking platform, the temperature curve of the pressure cooking module and the time parameters of the braising module can be automatically adjusted according to the constraints of flavor substance transfer in pork to ensure the best retention of flavor substances. At the same time, the heat parameters of the stir-frying module can be coordinated to achieve a perfect balance of taste and flavor.

[0078] The beneficial effect of the above implementation method is that it obtains the flavor substance transfer constraints corresponding to different ingredients in the current cooking recipe, and optimizes the retention of flavor substances in the cooking process according to the flavor substance transfer constraints. This avoids the loss of flavor substances in the ingredients due to over-optimization when optimizing the cooking parameters of the recipe, and improves the intelligent optimization of the cooking process.

[0079] The beneficial effects of the above implementation method are that, based on the flavor substance delivery constraint conditions, the threshold correction of the cooperative control adjustment matrix is ​​performed to obtain the cooperative control constraint matrix. Based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the cooperative control constraint matrix, the modified cooking parameters of multiple cooking modules are determined, which improves the convenience of optimizing the modified cooking parameters of multiple cooking modules and improves the efficiency of optimizing the modified cooking parameters.

[0080] In some implementations, S120 above involves determining the corrected cooking parameters of multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules through a cooking recipe optimization model. It also includes S127 to S128, which will be explained in detail below.

[0081] S127. Obtain the cooking parameters and timing feedback parameters corresponding to multiple cooking modules. Using the cooking module parsing unit for each cooking module, determine the collaborative control feedback matrix corresponding to the multiple cooking modules based on the cooking parameters and timing feedback parameters for each module. The timing feedback parameters include timing temperature parameters, timing humidity parameters, and timing pressure parameters.

[0082] During the operation of the integrated intelligent cooking platform, cooking parameters and timing feedback parameters corresponding to multiple cooking modules can be acquired. The cooking parameters of each cooking module can include preset control target parameters such as temperature setpoint, humidity setpoint, and pressure setpoint. The timing feedback parameters reflect the dynamic changes of each module in actual operation, including real-time monitoring data such as timing temperature parameters, timing humidity parameters, and timing pressure parameters.

[0083] In this implementation, each cooking module can be configured with a corresponding cooking module parsing unit. These parsing units can calculate the collaborative control feedback matrix between multiple cooking modules based on the cooking parameters and timing feedback parameters corresponding to their respective modules. The collaborative control feedback matrix can quantitatively reflect the differences in the operating states and the degree of mutual influence between different cooking modules, providing data support for subsequent collaborative optimization.

[0084] S128. Using the cooking recipe optimization model, determine the corrected cooking parameters for multiple cooking modules based on the current cooking recipe, cooking parameters of multiple cooking modules, collaborative control matrix, and collaborative control feedback matrix.

[0085] In this implementation, a cooking recipe optimization model can be used to determine the corrected cooking parameters for multiple cooking modules based on the current cooking recipe, cooking parameters of multiple cooking modules, collaborative control matrix, and collaborative control feedback matrix. Then, cooking optimization can be achieved by combining the feedback parameters of the cooking modules with the corrected cooking parameters.

[0086] For example, the cooking recipe optimization model can adopt a deep learning-based neural network model. The cooking recipe optimization model can be trained by sample cooking recipes, sample cooking parameters of multiple cooking modules, sample collaborative control matrix, and sample collaborative control feedback matrix. It can comprehensively analyze multi-dimensional information such as the current cooking recipe, cooking parameters of multiple cooking modules, collaborative control matrix, and collaborative control feedback matrix. During the training process, the cooking recipe optimization model can learn the correlation rules between parameters of different cooking modules and how to adjust the operating parameters of each module according to real-time feedback.

[0087] For example, when cooking different dishes in a recipe using the steaming module and the frying module respectively, the cooking recipe optimization model can determine more reasonable corrected cooking parameters by adjusting the steaming tenderness and frying crispness, based on the time-series temperature parameters of the steaming module, the steaming time, the time-series temperature parameters of the frying module, the frying time, and the collaborative control feedback matrix of the two modules.

[0088] The beneficial effects of the above implementation method are that it obtains the cooking parameters and timing feedback parameters corresponding to multiple cooking modules, determines the collaborative control feedback matrix, and determines the corrected cooking parameters of multiple cooking modules based on the collaborative control feedback matrix. This realizes the cooking optimization of multiple cooking modules based on the feedback parameters, improves the working stability of multiple cooking modules during the cooking process, and ensures the cooking effect of multiple cooking modules.

[0089] Figure 5 A flowchart illustrating the third IoT-based integrated intelligent cooking platform control method provided in this application embodiment is shown below. Figure 5 As shown, in the above-mentioned S120, the cooking recipe optimization model determines the modified cooking parameters of multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. It also includes S210 to S220, which are explained in detail below.

[0090] S210. Obtain the recipe adjustment priority weights corresponding to the current cooking recipe from the cooking recipe database. Based on these priority weights, fuse the collaborative control feedback matrices and collaborative control constraint matrices corresponding to multiple cooking modules to obtain a collaborative control fusion matrix. The recipe adjustment priority weights represent the priority weights of the multiple cooking modules when adjusting them individually for the current cooking recipe.

[0091] In this implementation, the priority weight of the current cooking recipe can be obtained from the cooking recipe database. The priority weight of the recipe can reflect the order of importance of each cooking module during the adjustment process. For example, in a recipe that includes stewed and roasted dishes, the control priority of the stewing module may be higher than that of the roasting module, while in a recipe that includes fried and stir-fried dishes, the opposite is true. These weights can be derived from the statistical analysis of historical cooking data, or they can be preset by cooking experts based on experience.

[0092] After obtaining the recipe adjustment priority weights, the collaborative control feedback matrices and collaborative control constraint matrices corresponding to multiple cooking modules can be fused according to the recipe adjustment priority weights to obtain a collaborative control fusion matrix. The collaborative control feedback matrix records the feedback parameters in the cooking of each module, while the collaborative control constraint matrix contains the operating constraints of each module. By fusing them through priority weights, the collaborative relationship between the parameter adjustments of important modules and other cooking modules can be ensured.

[0093] For example, when fusing the collaborative control feedback matrix and collaborative control constraint matrix corresponding to multiple cooking modules according to the recipe priority weight, the collaborative control feedback matrix and collaborative control constraint matrix can be added together according to the recipe priority weight to obtain the collaborative control fusion matrix.

[0094] S220. Through the cooking recipe optimization model, based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control fusion matrix, determine the corrected cooking parameters of multiple cooking modules.

[0095] After obtaining the collaborative control fusion matrix, the cooking recipe optimization model can be used to determine the corrected cooking parameters for multiple cooking modules based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control fusion matrix.

[0096] For example, the cooking recipe optimization model can be an intelligent decision-making model based on reinforcement learning. The cooking recipe optimization model can analyze the collaborative relationship and priority weights between modules and output the optimal parameter adjustment scheme.

[0097] For example, in a recipe that includes both stewed and roasted dishes, the stewing module may have a higher control priority than the roasting module. The cooking parameters of the stewing module can be optimized first, and the parameters of the roasting module can be adaptively adjusted based on the optimized cooking parameters of the stewing module to improve the flavor richness of different dishes in the recipe.

[0098] The beneficial effect of the above implementation method is that it obtains the priority weight of the recipe adjustment when adjusting the priority weight of the multiple cooking modules corresponding to the current cooking recipe, and then optimizes the cooking process by adjusting the priority weight of the recipe adjustment, which ensures the priority order of the optimization of each cooking module during the cooking process and improves the coordination effect of multiple cooking modules.

[0099] The beneficial effects of the above implementation method are that, by adjusting the priority weights according to the recipe, the collaborative control feedback matrix and collaborative control constraint matrix corresponding to multiple cooking modules are fused to obtain a collaborative control fusion matrix, and the cooking process is optimized based on the collaborative control fusion matrix, which improves the convenience of optimizing the cooking parameters of multiple cooking modules and improves the efficiency of optimizing the cooking parameters.

[0100] In some implementations, S120 above involves determining the corrected cooking parameters of multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules through a cooking recipe optimization model. It also includes S230 to S240, which will be explained in detail below.

[0101] S230. Obtain the main dish cooking priority weight corresponding to the current cooking recipe input by the user. Through the cooking recipe planning unit, determine the cooking priority weights of other dishes in the current cooking recipe based on the main dish cooking priority weight. Based on the main dish cooking priority weight and the cooking priority weights of other dishes in the current cooking recipe, fuse the collaborative control feedback matrix and collaborative control constraint matrix corresponding to multiple cooking modules to obtain the collaborative control fusion matrix. The main dish cooking priority weight represents the priority weight of the dish with higher importance corresponding to the current cooking recipe.

[0102] In this implementation, the cooking priority weight of the main dish corresponding to the current cooking recipe input by the user can also be obtained. The cooking priority weight of the main dish reflects the user's assessment of the importance of the core dish in the current cooking recipe. The cooking priority weight of the main dish can be manually set by the user on the intelligent cooking platform interface or input through voice interaction. By clarifying the priority of the main dish, optimization direction can be provided for the subsequent collaborative cooking of multiple dishes.

[0103] After obtaining the cooking priority weight of the main dish, the cooking recipe planning unit can determine the cooking priority weights of other dishes in the current recipe based on the main dish's cooking priority weight. The cooking recipe planning unit can use rule-based or machine learning-based weight allocation algorithms to ensure that the priority of side dishes and accompaniments maintains a reasonable ratio with that of the main dish. For example, when the main dish has a higher priority, the system will automatically reduce the priority weight of the side dishes.

[0104] After obtaining the cooking priority weights of the main dish and other dishes in the current cooking recipe, the collaborative control feedback matrix and collaborative control constraint matrix corresponding to multiple cooking modules can be fused to obtain a collaborative control fusion matrix. The collaborative control feedback matrix records the interaction and influence relationships between each cooking module, while the collaborative control constraint matrix includes cooking constraints such as temperature and time. By using a priority-weighted matrix fusion method, the importance of parameters related to the main dish can be highlighted.

[0105] S240. Through the cooking recipe optimization model, based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control fusion matrix, determine the corrected cooking parameters of multiple cooking modules.

[0106] After obtaining the collaborative control fusion matrix, the cooking recipe optimization model can be used to determine the corrected cooking parameters for multiple cooking modules based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control fusion matrix.

[0107] For example, a cooking recipe optimization model can be an intelligent decision-making system based on reinforcement learning. By analyzing historical cooking data and real-time sensor information, it outputs the optimal parameter combination for each module. For instance, when grilling steak as the main dish, the model will prioritize ensuring the temperature control of the oven module while fine-tuning the cooking parameters of other cooking modules to improve the texture and flavor of the dish, such as enhancing the crispness and tenderness of stir-fried dishes.

[0108] The beneficial effect of the above implementation method is that it obtains the cooking priority weight of the main dish corresponding to the current cooking recipe input by the user, and determines the cooking priority weight of other dishes in the current cooking recipe based on the cooking priority weight of the main dish. Subsequently, it optimizes the cooking process based on the cooking priority weight of the main dish and the cooking priority weight, ensuring that the cooking recipe is cooked according to the dishes with higher importance, and improving the optimization stability of the overall cooking process.

[0109] The beneficial effect of the above implementation method is that, according to the cooking priority weight of the main dish and the cooking priority weight of other dishes in the current cooking recipe, the collaborative control feedback matrix and collaborative control constraint matrix corresponding to multiple cooking modules are fused to obtain a collaborative control fusion matrix. Subsequently, the corrected cooking parameters of multiple cooking modules are determined through the collaborative control fusion matrix, which facilitates efficient parameter optimization of multiple cooking modules and improves the cooking effect.

[0110] In some implementations, S120 above involves determining the corrected cooking parameters of multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules using a cooking recipe optimization model. It also includes S250 to S260, which will be explained in detail below.

[0111] S250. Obtain cooking feedback information corresponding to the current cooking recipe from user feedback. Through the cooking recipe planning unit, determine the recipe adjustment priority correction weight corresponding to the current cooking recipe based on the cooking feedback information and the recipe adjustment priority weight. According to the recipe adjustment priority correction weight corresponding to each cooking module, fuse the collaborative control feedback matrix and collaborative control constraint matrix corresponding to each cooking module to obtain the collaborative control fusion matrix.

[0112] In this implementation, the first step is to obtain the cooking feedback information corresponding to the current cooking recipe from the user. This feedback information can include subjective data such as the user's satisfaction rating of the cooking result, taste evaluation, or suggestions for improvement. This data reflects the user's actual experience with the current cooking recipe.

[0113] After obtaining the cooking feedback information corresponding to the current cooking recipe, the cooking recipe planning unit can determine the recipe adjustment priority correction weight corresponding to the current cooking recipe based on the cooking feedback information and the recipe adjustment priority weight. The recipe adjustment priority weight can reflect the relative importance of different cooking modules in the overall recipe optimization. By combining user feedback information for dynamic adjustment, the optimization process can better meet the personalized needs of users.

[0114] For example, the cooking recipe planning unit can be a deep learning model based on a neural network. The cooking recipe planning unit can be trained using sample cooking feedback information, sample recipe adjustment priority weights, and sample recipe adjustment priority correction weights.

[0115] After obtaining the recipe adjustment priority correction weight, the recipe adjustment priority correction weight can be adjusted according to the recipe adjustment priority corresponding to each cooking module. The collaborative control feedback matrix and collaborative control constraint matrix corresponding to each cooking module are then fused to obtain the collaborative control fusion matrix. The collaborative control constraint matrix can represent the mutual influence relationship between different cooking modules that combine the cooking feedback information corresponding to the current cooking recipe with user feedback.

[0116] S260. Through the cooking recipe optimization model, based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control fusion matrix, determine the corrected cooking parameters of multiple cooking modules.

[0117] After obtaining the collaborative control fusion matrix, the cooking recipe optimization model can be used to determine the corrected cooking parameters for multiple cooking modules based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control fusion matrix.

[0118] For example, in an integrated intelligent cooking platform, when a user reports that the braised pork is too tough, the system can adjust the temperature and time parameters of the stewing module for cooking the braised pork based on this feedback. At the same time, it can coordinate and control the heat parameters of the stir-frying modules for other dishes to ensure that the textures of each dish complement each other, resulting in a recipe with a rich and distinctive flavor.

[0119] For example, the cooking recipe optimization model can be an intelligent optimization model based on reinforcement learning. The cooking recipe optimization model can be trained by sample cooking recipes, sample cooking parameters of multiple cooking modules, sample collaborative control fusion matrix, and sample modified cooking parameters of multiple cooking modules, and can comprehensively consider multiple factors to adjust parameters.

[0120] The beneficial effect of the above implementation method is that it obtains cooking feedback information corresponding to the current cooking recipe from the user, and optimizes the cooking based on the user's cooking feedback information, thereby improving the personalization of the cooking process and enhancing the optimization effect of the recipe.

[0121] The beneficial effects of the above implementation method are that, according to the collaborative control feedback matrix and recipe adjustment priority correction weight corresponding to each cooking module, the collaborative control feedback matrix and collaborative control constraint matrix corresponding to each cooking module are fused to obtain the collaborative control fusion matrix. Based on the collaborative control fusion matrix, the corrected cooking parameters of multiple cooking modules are determined, which facilitates centralized optimization of multiple cooking modules and improves the optimization efficiency and convenience of the cooking process.

[0122] In some implementations, S120 above involves determining the corrected cooking parameters of multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules through a cooking recipe optimization model. It also includes S270 to S280, which will be explained in detail below.

[0123] S270. Determine the difference eigenvalues ​​corresponding to multiple collaborative control fusion matrices in historical data, and determine multiple target collaborative control fusion matrices whose difference eigenvalues ​​are less than preset difference eigenvalues. Determine the mean matrix of the multiple target collaborative control fusion matrices as the target collaborative control matrix.

[0124] In this implementation, the difference feature values ​​corresponding to multiple collaborative control fusion matrices in historical data can be determined, and multiple target collaborative control fusion matrices with difference feature values ​​less than preset difference feature values ​​can be determined. The collaborative control fusion matrix can reflect the collaborative relationship of control parameters between different cooking modules, and the difference feature value is used to measure the stability of the collaborative control fusion matrix.

[0125] During the operation of the intelligent cooking platform, the collaborative control fusion matrix in historical cooking data can be continuously collected. The aforementioned difference feature values ​​can be calculated by matrix feature value decomposition method and used to evaluate the fluctuation degree of the collaborative control fusion matrix. The preset difference feature values ​​can be set according to the statistical analysis of historical cooking data. By screening the target collaborative control fusion matrix with smaller difference feature values, a more stable collaborative control scheme in historical data can be selected.

[0126] After determining multiple target collaborative control fusion matrices, the mean matrix of these matrices can be calculated as the target collaborative control matrix. The mean matrix can be calculated using an element-wise averaging method to retain the common characteristics of each target collaborative control fusion matrix. The target collaborative control matrix integrates the advantages of multiple stable collaborative control schemes, providing a benchmark reference for subsequent optimization of cooking parameters.

[0127] For example, in an integrated intelligent cooking platform, when the stir-frying module and the baking module are controlled simultaneously, the optimal synergistic relationship between the stir-frying temperature and the baking temperature can be obtained by calculating the average of multiple stable synergistic control fusion matrices. This synergistic relationship can avoid the overall cooking effect from being reduced by adjusting the parameters of a single module alone.

[0128] S280. Using the cooking recipe optimization model, determine the corrected cooking parameters for multiple cooking modules based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the target collaborative control matrix.

[0129] In this implementation, the cooking recipe optimization model can be further used to determine the modified cooking parameters of multiple cooking modules based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the target collaborative control matrix.

[0130] For example, the cooking recipe optimization model can be a neural network-based prediction model. The cooking recipe optimization model can be trained based on sample cooking recipes, sample cooking parameters of multiple cooking modules, sample target collaborative control matrix, and sample modified cooking parameters of multiple cooking modules. The cooking recipe optimization model can generate corresponding parameter adjustment schemes by combining the current cooking state and the target collaborative control matrix.

[0131] The beneficial effect of the above implementation method is that it determines multiple target collaborative control fusion matrices with difference feature values ​​less than preset difference feature values, and then optimizes the cooking process in a concentrated manner through multiple target collaborative control fusion matrices. This achieves the purpose of optimizing cooking based on relatively stable cooking control parameters in historical data, and improves the control effect of the cooking process.

[0132] This application also provides an integrated intelligent cooking platform control system based on the Internet of Things, including a unit for performing the method described in any of the preceding embodiments.

[0133] Figure 6 A schematic diagram of the logical structure of an integrated intelligent cooking platform control system based on the Internet of Things provided in this application embodiment is shown below. Figure 6 As shown, the system 1 of this embodiment includes a processing unit 11, a storage unit 12, and a transceiver unit 13. The processing unit 11 is used to process data, the storage unit 12 is used to store data, and the transceiver unit 13 is used to send and receive data. The processing unit 11, the storage unit 12, and the transceiver unit 13 cooperate with each other to implement the above-described method. The beneficial effects of the embodiments of this application have been described in the above-described method and will not be repeated here.

[0134] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0135] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0136] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0137] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0138] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0139] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0140] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0141] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A control method for an integrated intelligent cooking platform based on the Internet of Things, characterized in that, The method includes: Obtain the current cooking recipe from the integrated intelligent cooking platform, and obtain multiple cooking modules and the corresponding cooking parameters for the current cooking recipe; among them, the multiple cooking modules include steaming, boiling, stir-frying, pan-frying, and baking modules; The cooking recipe optimization model determines the corrected cooking parameters for multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules; the cooking recipe optimization model is trained based on sample cooking recipes and the cooking parameters of sample cooking recipes. By optimizing the cooking recipe model, based on the current cooking recipe and the cooking parameters of multiple cooking modules, the corrected cooking parameters for multiple cooking modules are determined, including: The cooking recipe parsing unit determines the collaborative control matrix of multiple cooking modules based on the current cooking recipe. The collaborative control matrix characterizes the cross-module coupling influence of multiple cooking modules. By optimizing the cooking recipe model, the corrected cooking parameters of multiple cooking modules are determined based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control matrix. The cooking recipe optimization model determines corrected cooking parameters for multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. This also includes: The cooking recipe adjustment unit determines the crispness influence coefficient of the steaming module on the frying module, the humidity influence coefficient of the stir-frying module on the baking module, and the cooking influence coefficient of the boiling module on the stir-frying module based on the current cooking recipe. These crispness, humidity, and cooking influence coefficients are then fused with the collaborative control matrix to obtain the collaborative control adjustment matrix. The cooking recipe adjustment unit is trained using the current sample cooking recipe, the sample crispness influence coefficient of the steaming module on the frying module, the sample humidity influence coefficient of the stir-frying module on the baking module, and the sample cooking influence coefficient of the boiling module on the stir-frying module. By using a cooking recipe optimization model, the corrected cooking parameters for multiple cooking modules are determined based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control adjustment matrix.

2. The method as described in claim 1, characterized in that, The cooking recipe optimization model determines corrected cooking parameters for multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. This also includes: By using a cooking recipe database, the flavor substance transfer constraints corresponding to different ingredients in the current cooking recipe are obtained. Based on the flavor substance transfer constraints, the collaborative control adjustment matrix is ​​threshold-corrected to obtain the collaborative control constraint matrix. Among them, the flavor substance transfer constraints characterize the retention characteristics of flavor substances in ingredients when cooking conditions change. The flavor substance transfer constraints include flavor substance cooking time constraints, flavor substance concentration constraints, flavor substance formation rate constraints, and flavor substance weight constraints. By using a cooking recipe optimization model, the modified cooking parameters of multiple cooking modules are determined based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control constraint matrix.

3. The method as described in claim 2, characterized in that, The cooking recipe optimization model determines corrected cooking parameters for multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. This also includes: The cooking parameters and timing feedback parameters corresponding to multiple cooking modules are obtained respectively; the collaborative control feedback matrix corresponding to multiple cooking modules is determined by the cooking module parsing unit corresponding to each cooking module based on the cooking parameters and timing feedback parameters corresponding to each cooking module; wherein, the timing feedback parameters include timing temperature parameters, timing humidity parameters, and timing pressure parameters; By using a cooking recipe optimization model, the modified cooking parameters of multiple cooking modules are determined based on the current cooking recipe, the cooking parameters of multiple cooking modules, the collaborative control constraint matrix, and the collaborative control feedback matrix.

4. The method as described in claim 3, characterized in that, The cooking recipe optimization model determines corrected cooking parameters for multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. This also includes: The recipe adjustment priority weights corresponding to the current cooking recipe are obtained from the cooking recipe database. According to the recipe adjustment priority weights, the collaborative control feedback matrices and collaborative control constraint matrices corresponding to multiple cooking modules are fused to obtain the collaborative control fusion matrix. Among them, the recipe adjustment priority weights represent the priority weights of multiple cooking modules when the multiple cooking modules corresponding to the current cooking recipe are adjusted respectively. By using a cooking recipe optimization model, the corrected cooking parameters for multiple cooking modules are determined based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control fusion matrix.

5. The method as described in claim 3, characterized in that, The cooking recipe optimization model determines corrected cooking parameters for multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. This also includes: The system obtains the cooking priority weight of the main dish corresponding to the current cooking recipe input by the user; through the cooking recipe planning unit, it determines the cooking priority weight of other dishes in the current cooking recipe based on the cooking priority weight of the main dish; according to the cooking priority weight of the main dish and the cooking priority weight of other dishes in the current cooking recipe, it fuses the collaborative control feedback matrix and collaborative control constraint matrix corresponding to multiple cooking modules to obtain the collaborative control fusion matrix; where the cooking priority weight of the main dish represents the priority weight of the dish with higher importance corresponding to the current cooking recipe; By using a cooking recipe optimization model, the corrected cooking parameters for multiple cooking modules are determined based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control fusion matrix.

6. The method as described in claim 3, characterized in that, The cooking recipe optimization model determines corrected cooking parameters for multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. This also includes: Obtain cooking feedback information corresponding to the current cooking recipe from user feedback; through the cooking recipe planning unit, determine the recipe adjustment priority correction weight corresponding to the current cooking recipe based on the cooking feedback information and recipe adjustment priority weight; according to the recipe adjustment priority correction weight corresponding to each cooking module, fuse the collaborative control feedback matrix and collaborative control constraint matrix corresponding to each cooking module to obtain the collaborative control fusion matrix; By using a cooking recipe optimization model, the corrected cooking parameters for multiple cooking modules are determined based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the collaborative control fusion matrix.

7. The method as described in claim 6, characterized in that, The cooking recipe optimization model determines corrected cooking parameters for multiple cooking modules based on the current cooking recipe and the cooking parameters of multiple cooking modules. This also includes: Determine the difference eigenvalues ​​corresponding to multiple collaborative control fusion matrices in historical data, and determine multiple target collaborative control fusion matrices whose difference eigenvalues ​​are less than preset difference eigenvalues; determine the mean matrix of multiple target collaborative control fusion matrices as the target collaborative control matrix; By using a cooking recipe optimization model, the corrected cooking parameters for multiple cooking modules are determined based on the current cooking recipe, the cooking parameters of multiple cooking modules, and the target collaborative control matrix.

8. An integrated intelligent cooking platform control system based on the Internet of Things, characterized in that, Includes a unit for performing the method according to any one of claims 1 to 7.

Images