Intelligent cooking heating control method and system based on multi-dimensional user evaluation driving

Abstract

The invention relates to the field of cooking heating control, and discloses an intelligent cooking heating control method and system based on multi-dimensional user evaluation driving, and the method comprises the steps: obtaining a plurality of cooking heating parameters corresponding to each control dimension of target cooking equipment, obtaining a priority control dimension and a non-priority control dimension determined by the user in the plurality of control dimensions, and obtaining user historical feedback data corresponding to each control dimension; determining a plurality of optimized cooking heating parameters corresponding to the priority control dimension of the target cooking equipment according to user historical feedback data corresponding to the priority control dimension and the plurality of cooking heating parameters corresponding to the priority control dimension; and determining a plurality of adjusted cooking heating parameters corresponding to the non-priority control dimension according to user historical feedback data corresponding to the non-priority control dimension, the plurality of optimized cooking heating parameters and the plurality of cooking heating parameters corresponding to the non-priority control dimension. According to the invention, deep parameter optimization can be carried out for the cooking effect index most concerned by the user.

Description

Technical Field

[0001] The present application relates to the technical field of cooking heating control, and more specifically, to an intelligent cooking heating control method and system driven by multi-dimensional user evaluation. Background Art

[0002] The current heating control technology of smart cooking equipment mostly uses temperature control strategies based on preset programs or shallow parameter feedback mechanisms to optimize cooking, which makes it difficult to deeply optimize according to the core needs of users. Taking Chinese stir-fry as an example, the existing system generally monitors the temperature of the pot through thermocouples and uses PID algorithms to maintain constant firepower, but it is unable to establish a dynamic mapping relationship between the oil temperature fluctuation curve and core indicators such as the degree of Maillard reaction of ingredients and nutrient retention rate, nor can it optimize the heating process of cooking. In addition, when the device receives dual-target instructions of "shortening cooking time" and "reducing oil fume emissions" at the same time, the optimization algorithm will make a homogenized trade-off between time cost and energy efficiency, resulting in a decrease in the browning degree of the dish compared to single-target optimization, and the fluctuation range of vitamin C retention rate is too high, exposing the defect of insufficient optimization depth of key indicators.

[0003] The traditional multi-objective optimization framework has the problem of misaligned objective function coupling in cooking and heating scenarios. In particular, when the user preference index and the physical parameters of the equipment are nonlinearly related, the resource allocation strategy is prone to systematic deviations. Taking the stir-frying of Kung Pao Chicken as an example, the existing system decomposes the heat control into multiple parallel optimization dimensions such as temperature stability, gas consumption, and oil smoke concentration, and uses fixed weight coefficients for joint solution. When user feedback requires optimization of the crispness and tenderness of the taste of the dish, the existing multi-objective optimization algorithm causes a large amount of computing resources to be consumed on secondary indicators with low user perception, while the crispness and tenderness indicator related to the taste of the dish receives a lower optimization weight, which ultimately causes the multi-objective Pareto frontier to converge to the suboptimal solution domain, failing to meet the user's extreme demand for core quality indicators. Summary of the Invention

[0004] The purpose of this application is to provide an intelligent cooking heating control method and system driven by multi-dimensional user evaluation, which solves the technical problem of not being able to perform deep parameter optimization for the cooking effect indicators that users are most concerned about, and achieves the technical effect of deep parameter optimization for the cooking effect indicators that users are most concerned about.

[0005] An embodiment of the present application provides an intelligent cooking and heating control method based on multi-dimensional user evaluation, the method comprising: obtaining multiple cooking heating parameters corresponding to each control dimension of a target cooking device, obtaining priority control dimensions and non-priority control dimensions determined by a user in the multiple control dimensions, and obtaining user historical feedback data corresponding to each control dimension; wherein the multiple cooking heating parameters include heat source distribution parameters, food moisture, heating power, heating temperature and heating time of each cooking heating section, the multiple control dimensions include a health dimension and a taste dimension, and the number of priority control dimensions is 1; through a cooking heating optimization unit, based on the user historical feedback data corresponding to the priority control dimension and the multiple cooking heating parameters corresponding to the priority control dimension, multiple optimized cooking heating parameters corresponding to the priority control dimension of the target cooking device are determined; through a cooking heating adjustment unit, based on the user historical feedback data corresponding to the non-priority control dimension, the multiple optimized cooking heating parameters and the multiple cooking heating parameters corresponding to the non-priority control dimension, multiple adjusted cooking heating parameters corresponding to the non-priority control dimension of the target cooking device are determined.

[0006] In one possible implementation, the method also includes: obtaining user historical time-series feedback data corresponding to each control dimension; determining, through a user preference migration identification unit, multiple cooking heating parameter update weights corresponding to each control dimension based on the user historical time-series feedback data corresponding to each control dimension; wherein the user historical time-series feedback data corresponding to each control dimension includes the rating value of the user corresponding to each control dimension in chronological order; determining, through a cooking heating optimization unit, multiple optimized cooking heating parameters corresponding to the priority control dimension of the target cooking device based on the user historical time-series feedback data corresponding to the priority control dimension, multiple cooking heating parameters corresponding to the priority control dimension, and multiple cooking heating parameter update weights; determining, through a cooking heating adjustment unit, multiple adjusted cooking heating parameters corresponding to the non-priority control dimension of the target cooking device based on the user historical feedback data corresponding to the non-priority control dimension, multiple optimized cooking heating parameters, multiple cooking heating parameters corresponding to the non-priority control dimension, and cooking heating parameter update weights.

[0007] In another possible implementation, a user preference migration identification unit is used to determine multiple cooking heating parameter update weights corresponding to each control dimension based on the user historical time series feedback data corresponding to each control dimension, including: a feedback optimization unit based on a cooking knowledge graph is used to determine multiple conflicting historical time series feedback data groups based on the user historical time series feedback data corresponding to each control dimension, each conflicting historical time series feedback data group including two groups of conflicting user historical time series feedback data corresponding to the multiple control dimensions; the cooking heating parameter update weight corresponding to the non-priority control dimension in each conflicting historical time series feedback data group is multiplied by a preset update weight adjustment ratio value to adjust the cooking heating parameter update weight corresponding to the non-priority control dimension.

[0008] In another possible implementation, the method further includes: determining a plurality of first cooking heating parameters and a plurality of second cooking heating parameters among a plurality of cooking heating parameters corresponding to a priority control dimension, the plurality of first cooking heating parameters being the cooking heating parameters that are prioritized for optimization among the plurality of cooking heating parameters corresponding to the priority control dimension, and the plurality of second cooking heating parameters being the cooking heating parameters that are not prioritized for optimization among the plurality of cooking heating parameters corresponding to the priority control dimension; through a cooking heating optimization unit, updating weights based on historical time series feedback data of users corresponding to the priority control dimension, the plurality of first cooking heating parameters, and the plurality of cooking heating parameters, determining a plurality of optimized first cooking heating parameters corresponding to the plurality of first cooking heating parameters, and obtaining the target cooking equipment's subsequent optimization through the plurality of optimization parameters. the first feedback data of the user when cooking with the first cooking heating parameter is optimized; when the first feedback data is positive feedback, the cooking heating optimization unit updates the weights according to the user's historical time series feedback data corresponding to the priority control dimension, the multiple first cooking heating parameters, and the cooking heating parameters corresponding to the multiple first cooking heating parameters, to determine the multiple optimized second cooking heating parameters corresponding to the multiple second cooking heating parameters of the target cooking device; when the first feedback data is negative feedback, the cooking heating optimization unit updates the weights according to the first feedback data, the multiple first cooking heating parameters, and the cooking heating parameters corresponding to the multiple first cooking heating parameters, to re-determine the multiple optimized first cooking heating parameters corresponding to the multiple first cooking heating parameters of the target cooking device.

[0009] In another possible implementation, the method further includes: obtaining the number of negative feedbacks corresponding to the negative feedback when the first feedback data is negative feedback; when the number of negative feedbacks is greater than or equal to the preset number of negative feedbacks, obtaining correlation coefficients between the multiple second cooking heating parameters and the multiple first cooking heating parameters, the correlation coefficients representing the degree of influence of the first cooking heating parameters on the second cooking heating parameters when they are adjusted; determining a preset number of multiple target second cooking heating parameters from the multiple second cooking heating parameters in descending order of the correlation coefficients; and determining, through the cooking heating optimization unit, multiple optimized first cooking heating parameters corresponding to the multiple first cooking heating parameters and the multiple target second cooking heating parameters according to the first feedback data, the multiple first cooking heating parameters, the cooking heating parameter update weights corresponding to the multiple first cooking heating parameters, the multiple target second cooking heating parameters and the cooking heating parameter update weights corresponding to the multiple target second cooking heating parameters.

[0010] In another possible implementation, a cooking heating optimization unit re-determines a plurality of optimized first cooking heating parameters corresponding to the plurality of first cooking heating parameters based on the first feedback data, the adjusted plurality of first cooking heating parameters, and the plurality of cooking heating parameter update weights corresponding to the plurality of first cooking heating parameters, including: determining a preset number of target second cooking heating parameters from the plurality of second cooking heating parameters as the first cooking heating parameters, and obtaining parameter adjustment thresholds corresponding to the plurality of target second cooking heating parameters; determining, within a range of the parameter adjustment thresholds corresponding to the plurality of target second cooking heating parameters, the cooking heating optimization unit determines, based on the first feedback data, the plurality of first cooking heating parameters, the cooking heating parameter update weights corresponding to the plurality of first cooking heating parameters, the plurality of target second cooking heating parameters, and the cooking heating parameter update weights corresponding to the plurality of target second cooking heating parameters; and obtaining first feedback data from the user when the target cooking device subsequently performs cooking using the plurality of optimized first cooking heating parameters and the plurality of optimized target second cooking heating parameters.

[0011] In another possible implementation, a cooking heating adjustment unit is used to determine a plurality of adjusted cooking heating parameters corresponding to the non-priority control dimension based on historical user feedback data corresponding to the non-priority control dimension, a plurality of optimized cooking heating parameters, and a plurality of cooking heating parameters corresponding to the non-priority control dimension, including: obtaining the lower limit values ​​of the plurality of cooking heating parameters corresponding to the non-priority control dimension of the target cooking device; and a cooking heating adjustment unit is used to determine a plurality of adjusted cooking heating parameters corresponding to the non-priority control dimension with the lowest energy consumption of the target cooking device based on historical user feedback data corresponding to the non-priority control dimension, a plurality of optimized cooking heating parameters, a plurality of cooking heating parameters corresponding to the non-priority control dimension, and a lower limit value of the plurality of cooking heating parameters corresponding to the non-priority control dimension.

[0012] In another possible implementation, the method also includes: obtaining an associated cooking device that has a similar relationship with the target cooking device, and obtaining a cooking heating parameter mapping relationship between the associated cooking device and the target cooking device; determining multiple mapped cooking heating parameters of the associated cooking device based on multiple optimized cooking heating parameters and cooking heating parameter mapping relationships; and determining the remaining cooking heating parameters of the associated cooking device based on the multiple mapped cooking heating parameters of the associated cooking device through a cooking parameter adjustment model of the associated cooking device.

[0013] In another possible implementation, the method further includes: obtaining mapped cooking feedback data of a user when the associated cooking device cooks using multiple mapped cooking heating parameters; when the mapped cooking feedback data is positive feedback, determining the remaining cooking parameters of the associated cooking device according to the multiple mapped cooking heating parameters of the associated cooking device through a cooking parameter adjustment model of the associated cooking device; when the mapped cooking feedback data is negative feedback, determining a negative score value of the mapped cooking feedback data; when the negative score value of the mapped cooking feedback data is greater than or equal to a preset negative score value, reverting the multiple mapped cooking heating parameters of the associated cooking device to the cooking heating parameters before optimization; when the negative score value of the mapped cooking feedback data is less than the preset negative score value, obtaining parameter sensitivities corresponding to the multiple mapped cooking heating parameters of the associated cooking device; determining a preset number of multiple suppressed mapped cooking heating parameters among the multiple mapped cooking heating parameters in descending order of parameter sensitivity; and multiplying the multiple suppressed mapped cooking heating parameters by a preset attenuation coefficient to weaken the multiple suppressed mapped cooking heating parameters.

[0014] An embodiment of the present application also provides an intelligent cooking and heating control system driven by multi-dimensional user evaluation, including a unit for executing any of the methods described above.

[0015] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0016] An embodiment of the present application provides an intelligent cooking and heating control method driven by multi-dimensional user evaluation, the method comprising: obtaining multiple cooking heating parameters corresponding to each control dimension of a target cooking device, obtaining priority control dimensions and non-priority control dimensions determined by a user in the multiple control dimensions, and obtaining user historical feedback data corresponding to each control dimension; wherein the multiple cooking heating parameters include heat source distribution parameters, food moisture, heating power, heating temperature and heating time of each cooking heating section, the multiple control dimensions include a health dimension and a taste dimension, and the number of priority control dimensions is 1; through a cooking heating optimization unit, based on the user historical feedback data corresponding to the priority control dimension and the multiple cooking heating parameters corresponding to the priority control dimension, multiple optimized cooking heating parameters corresponding to the priority control dimension of the target cooking device are determined; through a cooking heating adjustment unit, based on the user historical feedback data corresponding to the non-priority control dimension, the multiple optimized cooking heating parameters and the multiple cooking heating parameters corresponding to the non-priority control dimension, multiple adjusted cooking heating parameters corresponding to the non-priority control dimension of the target cooking device are determined. The method in the embodiment of the present application can perform in-depth parameter optimization for the cooking effect indicators that users are most concerned about, avoid the problem of resource dispersion in the multi-objective optimization process, and at the same time perform secondary adjustments based on the feedback data of non-priority dimensions. It can achieve balanced improvement of multi-dimensional indicators while ensuring core needs, thereby improving the optimization effect of the cooking heating process. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 A flowchart of the first intelligent cooking and heating control method driven by multi-dimensional user evaluation provided in an embodiment of the present application;

[0019] Figure 2 A schematic diagram of the workflow of the first intelligent cooking and heating control method driven by multi-dimensional user evaluation provided in an embodiment of the present application;

[0020] Figure 3 A flowchart of a second intelligent cooking and heating control method driven by multi-dimensional user evaluation provided in an embodiment of the present application;

[0021] Figure 4 A flowchart of a third intelligent cooking and heating control method driven by multi-dimensional user evaluation provided in an embodiment of the present application;

[0022] Figure 5 A schematic diagram of the logical structure of an intelligent cooking and heating control system driven by multi-dimensional user evaluations provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0024] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0025] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0026] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0027] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in 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 "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0028] Existing automatic cooking equipment generally achieves basic cooking functions through a preset temperature-time curve. The health of the dishes is simply limited by the amount of oil (<5mL) and the maximum temperature (≤180℃), while the taste of the dishes is solidified by increasing the heat to above 220℃. As a result, the contradiction between nutrient loss and taste deterioration is difficult to reconcile. It is unable to dynamically balance the conflicting thresholds of vitamin retention rate (requiring low-temperature slow cooking) and Maillard reaction (requiring instantaneous high temperature), and it is also incompatible with user personalized needs and real-time environmental variables.

[0029] Based on the above reasons, an embodiment of the present application provides an intelligent cooking and heating control method driven by multi-dimensional user evaluation, which includes: obtaining multiple cooking heating parameters corresponding to each control dimension of the target cooking device, obtaining the priority control dimension and non-priority control dimension determined by the user in the multiple control dimensions, and obtaining user historical feedback data corresponding to each control dimension; wherein the multiple cooking heating parameters include the heat source distribution parameters, food humidity, heating power, heating temperature and heating time of each cooking heating section, the multiple control dimensions include a health dimension and a taste dimension, and the number of priority control dimensions is 1; through a cooking heating optimization unit, based on the user historical feedback data corresponding to the priority control dimension and the multiple cooking heating parameters corresponding to the priority control dimension, determine the multiple optimized cooking heating parameters corresponding to the priority control dimension of the target cooking device; through a cooking heating adjustment unit, based on the user historical feedback data corresponding to the non-priority control dimension, the multiple optimized cooking heating parameters and the multiple cooking heating parameters corresponding to the non-priority control dimension, determine the multiple adjusted cooking heating parameters corresponding to the non-priority control dimension of the target cooking device. The method in the embodiment of the present application can perform in-depth parameter optimization for the cooking effect indicators that users are most concerned about, avoid the problem of resource dispersion in the multi-objective optimization process, and at the same time perform secondary adjustments based on the feedback data of non-priority dimensions. It can achieve balanced improvement of multi-dimensional indicators while ensuring core needs, thereby improving the optimization effect of the cooking heating process.

[0030] In some scenarios, an intelligent cooking heating control method based on multi-dimensional user evaluation driven by an embodiment of the present application can be applied to the parameter optimization of the stir-fry cooking system, which can improve the parameter optimization effect of the stir-fry cooking system and improve the effect of deep parameter optimization of the cooking effect indicators that users are most concerned about.

[0031] The following is a detailed description of an intelligent cooking and heating control method based on multi-dimensional user evaluation provided in an embodiment of the present application with reference to specific examples.

[0032] Figure 1 The flowchart of the first intelligent cooking heating control method based on multi-dimensional user evaluation driven by the embodiment of the present application is as follows: Figure 1As shown, the intelligent cooking and heating control method driven by multi-dimensional user evaluation in the embodiment of the present application includes S110 to S120, and S110 to S120 are described in detail below.

[0033] S110: Obtain multiple cooking and heating parameters corresponding to each control dimension of the target cooking device, obtain the priority and non-priority control dimensions determined by the user within the multiple control dimensions, and obtain historical user feedback data corresponding to each control dimension. The multiple cooking and heating parameters include heat source distribution parameters, ingredient moisture, heating power, heating temperature, and heating time for each cooking and heating section. The multiple control dimensions include a health dimension and a taste dimension. The number of priority control dimensions is one.

[0034] In this implementation method, in order to achieve intelligent control and optimization of cooking heating parameters, multiple cooking heating parameters corresponding to each control dimension can be obtained through the target cooking equipment. The multiple cooking heating parameters corresponding to each control dimension can be different from each other. These parameters can cover detailed control factors in different heating stages. These control factors can specifically include the heat source distribution parameters, food humidity, heating power, heating temperature and heating time of each cooking heating section.

[0035] When performing cooking control, the heat source distribution parameters of each cooking heating section can describe the energy output configuration mode of the heating element in space, the food humidity parameters can reflect the moisture content of the food monitored by the real-time humidity sensor, and the heating power and temperature parameters correspond to the operating parameter settings of the executive elements of the cooking equipment.

[0036] Exemplarily, the multiple cooking heating parameters corresponding to each control dimension may be preset according to the characteristics of the cooking equipment.

[0037] Exemplarily, each control dimension may be preset, and the multiple control dimensions may include a health dimension and a taste dimension, wherein the health dimension represents the health status dimension of the dish, and the taste dimension represents the taste status dimension of the dish.

[0038] During actual operation, users can select a unique priority control dimension from multiple preset control dimensions such as health dimension and taste dimension through the device interaction interface. At the same time, the cooking optimization system can synchronously obtain the historical evaluation data corresponding to each dimension as the basis for optimization.

[0039] For example, when performing cooking optimization, the user's historical feedback data on each control dimension can be collected, and the user's historical feedback data corresponding to each control dimension can be stored to facilitate subsequent optimization based on the user's historical feedback data corresponding to each control dimension in the historical data.

[0040] For example, the health dimension might include evaluation metrics like nutrient retention and harmful substance production, while the taste dimension might include sensory indicators like crispness and tenderness. When a user selects health as the priority control dimension, the system can retrieve the user's past ratings of dish indicators like vitamin content and burnt residue. This historical feedback data can be stored locally on the device or in a cloud database and associated with a specific recipe using a timestamp.

[0041] S120. The cooking and heating optimization unit determines, based on the historical user feedback data corresponding to the priority control dimension and the multiple cooking and heating parameters corresponding to the priority control dimension, multiple optimized cooking and heating parameters corresponding to the priority control dimension for the target cooking device. The cooking and heating adjustment unit determines, based on the historical user feedback data corresponding to the non-priority control dimension, the multiple optimized cooking and heating parameters, and the multiple cooking and heating parameters corresponding to the non-priority control dimension, multiple adjusted cooking and heating parameters corresponding to the non-priority control dimension for the target cooking device.

[0042] Figure 2 The first method of intelligent cooking and heating control based on multi-dimensional user evaluation driven by the embodiment of the present application is shown in the following figure: Figure 2 As shown, when performing cooking optimization, the cooking heating optimization unit can perform an in-depth analysis of the heating parameters related to the priority control dimension. The cooking heating optimization unit can specifically be a neural network model based on deep learning, which can determine the multiple optimized cooking heating parameters corresponding to the priority control dimension of the target cooking equipment based on the user historical feedback data corresponding to the priority control dimension and the multiple cooking heating parameters corresponding to the priority control dimension.

[0043] When performing cooking optimization, the cooking heating optimization unit can dynamically adjust the combination of parameters such as heat source distribution parameters, food humidity, heating power, heating temperature and heating time to generate an optimized parameter set that meets the priority control dimension requirements and conforms to the physical constraints of the equipment, thereby obtaining multiple optimized cooking heating parameters corresponding to the priority control dimensions of the target cooking equipment.

[0044] For example, when performing cooking optimization through the cooking heating optimization unit, when the priority control dimension is the health dimension, the duration of the high-temperature heating segment can be shortened accordingly, while increasing the uniform heat source coverage in the medium-temperature stage.

[0045] like Figure 2As shown, after completing the parameter optimization of the priority control dimension, the cooking heating adjustment unit can coordinately adjust the parameters of the non-priority control dimension. The cooking heating adjustment unit can optimize the multiple cooking heating parameters corresponding to the non-priority control dimension of the target cooking device based on the optimized multiple optimized cooking heating parameters, while introducing the user historical feedback data corresponding to the non-priority dimension and the multiple cooking heating parameters corresponding to the non-priority control dimension, to obtain the multiple adjusted cooking heating parameters corresponding to the non-priority control dimension of the target cooking device.

[0046] For example, after optimizing multiple cooking and heating parameters in the health dimension, the user feedback data in the taste dimension can be used to fine-tune multiple cooking and heating parameters corresponding to the non-priority control dimension of the target cooking equipment, so that the adjusted parameters can improve the crispness of the skin while maintaining the level of nutrient retention. This phased optimization mechanism can ensure that the control requirements of different dimensions receive differentiated processing priorities.

[0047] The beneficial effect of the above implementation method is that by setting up a screening mechanism for a single priority control dimension, we can focus on the cooking effect indicators that users are most concerned about for in-depth parameter optimization, avoid the problem of resource dispersion in the multi-objective optimization process, and at the same time combine the feedback data of non-priority dimensions for secondary adjustments. It can achieve balanced improvement of multi-dimensional indicators while ensuring core needs, thereby improving the optimization effect of the cooking heating process.

[0048] The beneficial effect of the above implementation method is that, by establishing a dynamic correlation model between historical feedback data and heating parameters, personalized parameter adaptation can be performed based on the preference characteristics formed by users over a long period of use; at the same time, the phased optimization-adjustment mechanism not only maintains the clarity of the main optimization direction, but also takes into account the collaborative optimization space of secondary parameters, forming an intelligent control solution with adaptability to user characteristics, further improving the optimization effect of the cooking heating process.

[0049] In some implementations, the above method further includes S130 to S140, which are described in detail below.

[0050] S130: Obtain historical user time-series feedback data corresponding to each control dimension. The user preference migration identification unit determines, based on the historical user time-series feedback data corresponding to each control dimension, multiple cooking and heating parameter update weights corresponding to each control dimension. The historical user time-series feedback data corresponding to each control dimension includes the rating values ​​provided by users over time for each control dimension.

[0051] In this implementation, the user's historical time series feedback data arranged in chronological order for different control dimensions during the historical cooking process can also be obtained. The user's historical time series feedback data corresponding to each control dimension records the evolution trajectory of the user's score for specific cooking effect indicators in different time periods, such as the dynamic score sequence given by the user when using the health dimension indicator of the automatic cooking equipment for five consecutive times, and then the cooking is optimized according to the user's historical time series feedback data corresponding to each control dimension.

[0052] For example, the user's historical time-series feedback data can be structuredly stored in a storage module built into the cooking device or in a cloud database, and the correspondence between the timestamp and the rating value of the user's feedback in time sequence corresponding to each control dimension can be retained.

[0053] After obtaining the user historical time series feedback data corresponding to each control dimension, the user preference migration identification unit can be used to analyze the fluctuation characteristics and trend directions of the score sequences of different control dimensions. According to the user historical time series feedback data corresponding to each control dimension, the multiple cooking heating parameter update weights corresponding to each control dimension can be determined, and then the cooking parameters can be optimized according to the multiple cooking heating parameter update weights corresponding to each control dimension.

[0054] For example, for the crispness dimension, when it is detected that the user's three most recent feedback scores are continuously lower than the historical average, the parameter update weight coefficient of this dimension can be automatically increased. This weight distribution mechanism can capture the migration pattern of user preferences caused by seasonal changes or taste adjustments. For example, in winter, users may be more inclined to increase the weight configuration of moisture retention.

[0055] S140. The cooking and heating optimization unit determines, based on the historical user feedback data corresponding to the priority control dimension, the multiple cooking and heating parameters corresponding to the priority control dimension, and the multiple cooking and heating parameter update weights, the multiple optimized cooking and heating parameters corresponding to the priority control dimension for the target cooking device. The cooking and heating adjustment unit determines, based on the historical user feedback data corresponding to the non-priority control dimension, the multiple optimized cooking and heating parameters, the multiple cooking and heating parameters corresponding to the non-priority control dimension, and the cooking and heating parameter update weights, the multiple adjusted cooking and heating parameters corresponding to the non-priority control dimension for the target cooking device.

[0056] After obtaining the updated weights of multiple cooking heating parameters, the cooking heating optimization unit can determine the multiple optimized cooking heating parameters corresponding to the priority control dimension of the target cooking device based on the user historical time series feedback data corresponding to the priority control dimension, the multiple cooking heating parameters corresponding to the priority control dimension, and the multiple cooking heating parameter update weights, so as to optimize the multiple cooking heating parameters corresponding to the priority control dimension.

[0057] For example, when the priority control dimension is the health dimension, the duration parameter of the high-temperature stage can be adjusted, and the weights can be updated by referring to multiple cooking heating parameters corresponding to the user to generate a parameter configuration plan that can not only improve the target dimension score but also meet the equipment safety threshold.

[0058] After obtaining multiple optimized cooking heating parameters corresponding to the priority control dimension of the target cooking device, the cooking heating adjustment unit can determine multiple adjusted cooking heating parameters corresponding to the non-priority control dimension of the target cooking device based on user historical feedback data corresponding to the non-priority control dimension, multiple optimized cooking heating parameters, multiple cooking heating parameters corresponding to the non-priority control dimension, and cooking heating parameter update weights, thereby optimizing the multiple cooking heating parameters corresponding to the non-priority control dimension.

[0059] In this implementation, through the cooking heating adjustment unit, after the priority dimension parameters are determined, supplementary adjustments can be made based on the historical feedback data of the non-priority dimensions. This phased optimization mechanism can ensure that the parameter adjustment of the non-priority dimensions will not affect the optimized core indicators, thereby ensuring the optimization effect of the cooking parameters.

[0060] The beneficial effect of the above implementation method is that, by establishing a dynamic weight allocation mechanism through time series data analysis, it can accurately identify the migration patterns of user preferences and ensure that the parameter optimization process always adapts to the user's latest focus; by adopting a hierarchical optimization strategy, on the basis of ensuring that the priority control dimension achieves the optimal parameter configuration, multi-indicator collaborative optimization is achieved through compensatory adjustments of non-priority dimensions, avoiding the degradation of other indicators caused by single-dimensional optimization.

[0061] The beneficial effect of the above implementation method is that, through the combined application of historical data and real-time feedback, it not only maintains the continuity of personalized tuning, but also provides sufficient historical reference basis for equipment parameter adjustment.

[0062] In some implementations, in the above-mentioned S130, the user preference migration identification unit is used to determine the update weights of multiple cooking heating parameters corresponding to each control dimension based on the user historical time series feedback data corresponding to each control dimension, including S131 to S132. S131 to S132 are described in detail below.

[0063] S131. Determine, through a feedback optimization unit based on the cooking knowledge graph, a plurality of conflicting historical time series feedback data groups according to the user historical time series feedback data corresponding to each control dimension. Each conflicting historical time series feedback data group includes two groups of user historical time series feedback data that conflict with each other among the user historical time series feedback data corresponding to the plurality of control dimensions.

[0064] When users provide feedback, there is often conflicting feedback information. In this implementation, in order to improve the accuracy of calculating the update weights of multiple cooking heating parameters corresponding to each control dimension, a feedback optimization unit can be constructed based on the cooking knowledge graph to perform conflict relationship analysis on the user's historical time series feedback data. By analyzing the user's historical time series feedback data of different control dimensions, feedback data combinations with negative correlation and contradictory relationships can be identified.

[0065] For example, in an automatic cooking system, when users' crispness scores for stir-fried pork slices with green peppers show an upward trend, if there is also associated data showing a decrease in moisture retention scores, the system can determine that the feedback data of these two dimensions constitute a conflicting historical time series feedback data group. The identification of this conflict relationship can be used to analyze the two conflicting groups of user historical time series feedback data.

[0066] S132. Multiply the cooking and heating parameter update weight corresponding to the non-priority control dimension in each conflict history time series feedback data group by a preset update weight adjustment ratio value to adjust the cooking and heating parameter update weight corresponding to the non-priority control dimension.

[0067] After obtaining the conflict history time series feedback data set, the parameter update weights of non-priority control dimensions can be dynamically adjusted through the feedback optimization unit. For example, in the temperature control dimension optimization of an automatic frying pan, if the system identifies a scoring conflict between the taste dimension (priority dimension) and the health dimension (non-priority dimension), the parameter update weight of the health dimension is multiplied by a proportional coefficient of 0.6. This weight adjustment mechanism can effectively alleviate the parameter confrontation problem in the multi-objective optimization process. At the same time, the conflict handling method based on domain knowledge enables the parameter weight adjustment to be consistent with the cooking principles of specific ingredients. For example, when processing fish ingredients, the system will automatically strengthen the correlation analysis weight between the moisture retention dimension and the fishy smell control dimension.

[0068] For example, while maintaining the optimization of the core firepower parameters of the stir-fry mode, the constraint strength on the temperature uniformity index of the pot body is moderately relaxed.

[0069] The beneficial effect of the above implementation method is that, through the intelligent identification of conflicting data groups and dynamic weight adjustment, it can effectively solve the parameter conflict problem between multi-dimensional optimization goals and ensure that the core needs of the priority dimensions are fully met; combining the domain knowledge of the cooking knowledge graph to adjust the weight, so that the parameter optimization process not only meets the user's personalized needs, but also follows scientific cooking principles.

[0070] The beneficial effect of the above implementation method is that, through the proportional attenuation mechanism of the non-priority dimension weights, a reasonable optimization space is reserved for parameter adjustment of the non-priority dimension while maintaining the stability of the main optimization direction.

[0071] Figure 3 The flowchart of the second intelligent cooking heating control method based on multi-dimensional user evaluation driven by the embodiment of the present application is as follows: Figure 3 As shown, the above method further includes S210 to S230, and S210 to S230 are described in detail below.

[0072] S210. Determine multiple first cooking heating parameters and multiple second cooking heating parameters among the multiple cooking heating parameters corresponding to the priority control dimension, where the multiple first cooking heating parameters are the cooking heating parameters that are prioritized for optimization among the multiple cooking heating parameters corresponding to the priority control dimension, and the multiple second cooking heating parameters are the cooking heating parameters that are not prioritized for optimization among the multiple cooking heating parameters corresponding to the priority control dimension.

[0073] In this implementation, when optimizing the cooking heating parameters of the priority control dimension, the multiple cooking heating parameters corresponding to the priority control dimension can be divided into multiple first cooking heating parameters that need to be optimized first and multiple second cooking heating parameters that are not optimized first.

[0074] For example, when processing the stir-fry mode in an automatic cooking system, the priority control dimension is the fire intensity. The system can divide the gas valve opening and flame distribution uniformity into the first cooking heating parameter group, and divide the stir-fry frequency and pot tilt angle into the second cooking heating parameter group. This parameter grading mechanism can ensure the rapid optimization of the core cooking effect. For example, when the user pursues a high-fire stir-fry effect, the gas supply parameters are adjusted first to achieve instantaneous high-temperature output.

[0075] S220. Through the cooking heating optimization unit, based on the user's historical time series feedback data corresponding to the priority control dimension, multiple first cooking heating parameters and multiple cooking heating parameter update weights, determine multiple optimized first cooking heating parameters corresponding to the multiple first cooking heating parameters, and obtain the user's first feedback data when the target cooking device subsequently cooks using the multiple optimized first cooking heating parameters.

[0076] After obtaining multiple first cooking heating parameters and multiple second cooking heating parameters, multiple optimized first cooking heating parameters corresponding to the multiple first cooking heating parameters are determined based on the user's historical time series feedback data corresponding to the priority control dimension, the multiple first cooking heating parameters and the multiple cooking heating parameter update weights, so as to realize the first round of optimization of the multiple first cooking heating parameters based on the user's historical feedback data.

[0077] It should be noted that the multiple cooking heating parameter update weights include the cooking heating parameter update weights corresponding to the multiple first cooking heating parameters.

[0078] For example, when an automatic frying pan is processing the Kung Pao Chicken cooking task, the system prioritizes adjusting the heating power parameters and preheating time parameters of the high-temperature section based on the user's five consecutive scoring trends on the dry aroma index. The optimized parameter combination can be immediately applied to the subsequent cooking process, and the first feedback data is obtained through the user's instant scoring of the burnt aroma of the dish, and the first feedback data is evaluated to determine whether the first feedback data is positive feedback or negative feedback.

[0079] Exemplarily, when determining whether the first feedback data is positive feedback or negative feedback, after obtaining multiple optimized first cooking heating parameters, the dry aroma score can be obtained after optimizing the multiple optimized first cooking heating parameters. When the dry aroma score is improved by 2 levels, it can be determined as positive feedback, and when the dry aroma score is reduced, it can be determined as negative feedback.

[0080] S230. When the first feedback data is positive feedback, the cooking heating optimization unit determines, based on the user's historical time-series feedback data corresponding to the priority control dimension, the plurality of first cooking heating parameters, and the cooking heating parameter update weights corresponding to the plurality of first cooking heating parameters, a plurality of optimized second cooking heating parameters corresponding to the plurality of second cooking heating parameters of the target cooking device. When the first feedback data is negative feedback, the cooking heating optimization unit re-determines, based on the first feedback data, the plurality of first cooking heating parameters, and the cooking heating parameter update weights corresponding to the plurality of first cooking heating parameters, a plurality of optimized first cooking heating parameters corresponding to the plurality of first cooking heating parameters of the target cooking device.

[0081] When positive feedback is received, the optimization process for the second cooking and heating parameters can be initiated. After the automatic cooking system successfully optimizes the core heat parameters, the second cooking and heating parameters can be optimized based on the user's historical rating data on the completeness of the dish. For example, the motion trajectory parameters of the stir-fry mechanism and the feeding timing parameters in the second cooking and heating parameters can be optimized. This phased optimization strategy can effectively reduce the risk of parameter coupling. For example, while ensuring that the fire intensity meets the standard, the stir-fry angle parameters can be adjusted to ensure more even heating of the ingredients.

[0082] It should be noted that the multiple cooking heating parameter update weights include the cooking heating parameter update weights corresponding to the multiple second cooking heating parameters.

[0083] When negative feedback is detected, the re-optimization mechanism of the first cooking heating parameters can be automatically triggered. For example, after the automatic frying pan adjusts the stir-fry temperature parameters, the weights can be updated based on the first feedback data, multiple first cooking heating parameters and the cooking heating parameters corresponding to the multiple first cooking heating parameters, and the multiple optimized first cooking heating parameters corresponding to the multiple first cooking heating parameters of the target cooking device can be re-determined. This closed-loop optimization mechanism can realize dynamic calibration of parameters.

[0084] For example, if the user reports that the local coking score of the food has decreased, the matching relationship between the thermal conductivity coefficient and the temperature gradient parameter can be recalculated, and multiple optimized first cooking heating parameters corresponding to multiple first cooking heating parameters of the target cooking device can be re-determined.

[0085] The beneficial effect of the above implementation method is that, through the intelligent division of parameter optimization priorities and the step-by-step verification mechanism, the auxiliary parameter configuration can be gradually improved on the basis of ensuring the stable improvement of the core cooking effect; by establishing a feedback-driven iterative optimization process, the parameter adjustment process has the ability to self-correct, effectively avoiding the decline in user experience caused by a single optimization error.

[0086] The beneficial effect of the above implementation is that the modular optimization strategy of the parameter group is adopted, which not only maintains the flexibility of system adjustment but also ensures the coordinated operation relationship between different parameter groups.

[0087] In some implementations, the above method further includes S240 to S250, and S240 to S250 are described in detail below.

[0088] S240: Obtain a number of negative feedbacks corresponding to when the first feedback data is negative feedback. When the number of negative feedbacks is greater than or equal to a preset number of negative feedbacks, obtain correlation coefficients between the plurality of second cooking and heating parameters and the plurality of first cooking and heating parameters, respectively. The correlation coefficients represent the degree of influence of adjustment of the first cooking and heating parameters on the second cooking and heating parameters.

[0089] In this implementation, the number of negative feedbacks generated during the optimization process of the priority control dimension can be continuously tracked to further optimize the cooking parameters corresponding to the priority control dimension. For example, when the automatic stir-fry cooking system optimizes the stir-fry heat parameters, when the system receives three consecutive negative user ratings of the degree of burnt ingredients, the associated parameter analysis mechanism will be triggered, and the cooking parameters will be optimized through the associated parameter analysis mechanism. This feedback threshold setting can effectively identify stubborn problems that require systematic adjustment. For example, when the user's crispness rating of dry pot cauliflower is lower than the expected threshold five times in a row, the deep optimization process will be initiated.

[0090] When performing cooking optimization, when the number of negative feedbacks is greater than or equal to the preset number of negative feedbacks, the parameter correlation coefficient calculation module can be used to analyze the interaction relationship between different heating parameters, and obtain the correlation coefficients of multiple second cooking heating parameters and multiple first cooking heating parameters respectively. The correlation coefficient represents the degree of influence of the adjustment of the first cooking heating parameter on the second cooking heating parameter. Subsequently, the parameters can be optimized through the correlation coefficients of multiple second cooking heating parameters and multiple first cooking heating parameters respectively.

[0091] For example, in an automatic cooking pot, by analyzing historical optimization data, it was found that the stir-fry frequency parameter and the oil temperature control parameter have a high correlation coefficient of 0.85, which means that the motion parameters of the stir-fry mechanism need to be considered simultaneously when adjusting the oil temperature parameters.

[0092] S250: Determine a preset number of target second cooking heating parameters from the plurality of second cooking heating parameters in descending order of correlation coefficients. Determine, by a cooking heating optimization unit, a plurality of optimized first cooking heating parameters corresponding to the plurality of first cooking heating parameters and the plurality of target second cooking heating parameters, respectively, based on the first feedback data, the plurality of first cooking heating parameters, the cooking heating parameter update weights corresponding to the plurality of first cooking heating parameters, and the cooking heating parameter update weights corresponding to the plurality of target second cooking heating parameters.

[0093] When optimizing cooking parameters, priority can be sorted according to parameter impact strength, a preset number of target second cooking heating parameters can be determined from multiple second cooking heating parameters, and then cooking parameters can be optimized in order of parameter impact strength from high to low.

[0094] For example, when the automatic cooking system processes the Kung Pao Chicken cooking task, when it detects that the pot temperature parameter (the first cooking heating parameter) and the feeding timing parameter (the second cooking heating parameter) have a correlation coefficient of 0.92, the feeding timing parameter can be included in the current optimization batch. This correlation-driven parameter selection mechanism can effectively solve the collaborative optimization problem of the coupled parameter group, such as synchronously adjusting the stirring blade speed parameter to balance the heat conduction efficiency when optimizing the heating power parameter.

[0095] After obtaining a preset number of multiple target second cooking heating parameters, the cooking heating optimization unit can determine multiple optimized first cooking heating parameters corresponding to the multiple first cooking heating parameters and the multiple target second cooking heating parameters based on the first feedback data, the multiple first cooking heating parameters, the cooking heating parameter update weights corresponding to the multiple first cooking heating parameters, the multiple target second cooking heating parameters and the cooking heating parameter update weights corresponding to the multiple target second cooking heating parameters, thereby achieving synchronous optimization of the multiple optimized first cooking heating parameters.

[0096] For example, in the cooking scenario of fish-flavored shredded pork in an automatic frying pan, when the fire intensity parameter (first cooking heating parameter) and the stir-fry trajectory parameter (target second cooking heating parameter) need to be jointly optimized, the cooking heating optimization unit can be used to find a parameter combination that can improve the stir-frying effect and avoid the breakage of ingredients.

[0097] The beneficial effect of the above implementation method is that, through the associated parameter identification and joint optimization mechanism, it can effectively solve the parameter coupling problem in complex cooking scenarios and improve the overall efficiency of system optimization; the trigger mechanism based on the number of feedback times enables the deep optimization process to be started only when necessary, which not only ensures the efficiency of conventional optimization but also retains the ability to deal with complex problems.

[0098] The beneficial effect of the above-mentioned implementation method is that the above-mentioned comprehensive optimization method can break through the limitations of simple single-step optimization of the parameters of the priority control dimension, realize partial synchronous optimization of the cooking parameters of the priority control dimension and the cooking parameters of the non-priority control dimension, and improve the optimization effect of the cooking parameters.

[0099] In some implementations, in the above-mentioned S230, the cooking heating optimization unit updates the weights according to the first feedback data, the adjusted multiple first cooking heating parameters, and the multiple cooking heating parameters corresponding to the multiple first cooking heating parameters, and re-determines the multiple optimized first cooking heating parameters corresponding to the multiple first cooking heating parameters, including S231 to S232. S231 to S232 are described in detail below.

[0100] S231: Determine a preset number of target second cooking heating parameters from a plurality of second cooking heating parameters as first cooking heating parameters, and obtain parameter adjustment thresholds corresponding to the plurality of target second cooking heating parameters.

[0101] In the above-mentioned S230, when the first feedback data is negative feedback, it is necessary to re-determine the multiple optimized first cooking heating parameters corresponding to the multiple first cooking heating parameters of the target cooking equipment. During the parameter optimization process, the multiple second cooking heating parameters can be repositioned through dynamic reorganization of parameter groups and threshold constraints, and the cooking parameter optimization effect can be improved by synchronously adjusting the multiple first cooking heating parameters and the multiple second cooking heating parameters.

[0102] For example, when the automatic stir-fry cooking system processes the task of stir-frying green beans, after the stir-fry mechanism speed parameter (the second cooking heating parameter) is selected as the target second cooking heating parameter, the speed adjustment range can be automatically set to 800-1200 rpm (parameter adjustment threshold) according to the equipment performance specifications. The setting of this parameter threshold can ensure the safe operation of the equipment, such as preventing mechanical failures caused by motor overheating, and at the same time provide a feasible parameter search space for the optimization algorithm.

[0103] Exemplarily, the preset number of the plurality of target second cooking heating parameters may be a number preset based on empirical values.

[0104] In this implementation, key auxiliary parameters can be included in the priority optimization sequence through the parameter group reorganization mechanism. For example, when an automatic frying pan optimizes the cooking process of Kung Pao Chicken, when it is detected that the pot temperature uniformity parameter (the second cooking heating parameter) and the fire intensity parameter (the first cooking heating parameter) are highly correlated, the temperature uniformity parameter can be temporarily promoted to the first cooking heating parameter. This dynamic parameter reorganization strategy can break through the limitations of traditional parameter classification. For example, when processing stir-fried dishes that require precise temperature control, the temperature stability parameter and the fire intensity parameter can be optimized simultaneously.

[0105] S232: Within a parameter adjustment threshold range corresponding to the multiple target second cooking heating parameters, the cooking heating optimization unit determines, based on the first feedback data, the multiple first cooking heating parameters, the cooking heating parameter update weights corresponding to the multiple first cooking heating parameters, the multiple target second cooking heating parameters, and the cooking heating parameter update weights corresponding to the multiple target second cooking heating parameters, multiple optimized first cooking heating parameters corresponding to the multiple first cooking heating parameters, and multiple optimized target second cooking heating parameters corresponding to the multiple target second cooking heating parameters. The cooking heating optimization unit also obtains first user feedback data when the target cooking device subsequently performs cooking using the multiple optimized first cooking heating parameters and the multiple optimized target second cooking heating parameters.

[0106] During the joint optimization process of cooking parameters, the cooking heating optimization unit can determine multiple optimized first cooking heating parameters corresponding to the multiple first cooking heating parameters and multiple optimized target second cooking heating parameters corresponding to the multiple target second cooking heating parameters based on the first feedback data, multiple first cooking heating parameters, cooking heating parameter update weights corresponding to the multiple first cooking heating parameters, multiple target second cooking heating parameters and cooking heating parameter update weights corresponding to the multiple target second cooking heating parameters.

[0107] For example, through the cooking heating optimization unit, the automatic cooking system can simultaneously optimize the induction cooker power parameters (first cooking heating parameters) and the feeding interval parameters (second cooking heating parameters), and find a cooking parameter combination that can ensure the stir-frying firepower and achieve precise feeding.

[0108] During cooking, the user's first feedback data can be obtained when the target cooking device subsequently cooks through multiple optimized first cooking heating parameters and multiple optimized target second cooking heating parameters, and the cooking parameters can be subsequently optimized through the methods in S240 to S250.

[0109] The beneficial effect of the above implementation method is that, through the dynamic reorganization of parameter groups and the threshold constraint mechanism, it can break through the limitations of traditional parameter classification and achieve precise control of key influencing parameters; the use of a multi-dimensional collaborative optimization model can effectively solve the multi-parameter coupling problem in complex cooking scenarios, thereby improving the overall optimization efficiency of the system.

[0110] In some implementations, in the above-mentioned S120, the cooking heating adjustment unit determines multiple adjusted cooking heating parameters corresponding to the non-priority control dimension based on the user historical feedback data corresponding to the non-priority control dimension, multiple optimized cooking heating parameters and multiple cooking heating parameters corresponding to the non-priority control dimension, including S121 to S122. S121 to S122 are described in detail below.

[0111] S121. Obtain lower limit values ​​of multiple cooking heating parameters corresponding to non-priority control dimensions of the target cooking device.

[0112] In this implementation, an energy consumption optimization mechanism can be introduced when adjusting parameters of non-priority control dimensions. For example, when an automatic cooking system optimizes the oil temperature control parameters of the stir-fry mode, the minimum safety threshold of the hot oil temperature can be obtained as 160°C. The setting of this lower limit value can not only ensure the basic requirements of the cooking process, such as preventing the desizing of water starch in ingredients due to insufficient oil temperature, but also provide a benchmark constraint for energy consumption optimization.

[0113] S122. Through the cooking heating adjustment unit, based on the user historical feedback data corresponding to the non-priority control dimension, multiple optimized cooking heating parameters, multiple cooking heating parameters corresponding to the non-priority control dimension and the lower limit values ​​of the multiple cooking heating parameters corresponding to the non-priority control dimension, determine the multiple adjusted cooking heating parameters corresponding to the non-priority control dimension with the lowest energy consumption for the target cooking device.

[0114] When performing parameter optimization through the cooking heating adjustment unit, multi-objective calculations can be performed based on historical feedback data and equipment energy consumption characteristics to achieve the purpose of determining multiple adjustment cooking heating parameters corresponding to the non-priority control dimensions with the lowest energy consumption for the target cooking equipment.

[0115] For example, when an automatic cooking pot is preparing dry-fried shredded beef, it can optimize the hot oil holding time from 90 seconds to 75 seconds based on historical user ratings of the dish's dryness and aroma, while ensuring the oil temperature does not drop below 180°C. This cooking parameter optimization approach incorporates user preferences and the device's energy efficiency profile. If historical data analysis reveals a high user acceptance of a slight reduction in the oiliness, the duration of high-energy consumption phases will be automatically shortened.

[0116] For example, when determining adjustment parameters, a cooking and heating adjustment unit based on an energy consumption-performance balance algorithm can be used to optimize the parameters. For example, when optimizing the power parameters of the stir-fry mechanism in an automatic cooking system, the lower limit of the motor speed parameter can be set to 800 rpm based on the average user rating of the completeness of the ingredients.

[0117] In this implementation, by establishing a speed-energy consumption-integrity cooking heating adjustment unit, we find a speed parameter combination that can maintain the integrity of the food shape while minimizing energy consumption. For example, the Pareto optimality of energy consumption and effect is achieved at 850 rpm, thereby improving the optimization effect of cooking parameters.

[0118] The beneficial effect of the above implementation method is that, by setting the constraint of the lower limit value of the parameter, the energy-saving potential of the equipment can be maximized while ensuring the basic cooking effect; energy consumption optimization is carried out by combining historical feedback data, so that the parameter adjustment is in line with the implicit preferences formed by users over a long period of use, and the economic goal of improving energy efficiency is achieved.

[0119] Figure 4 The flowchart of the third intelligent cooking heating control method based on multi-dimensional user evaluation driven by the embodiment of the present application is as follows: Figure 4 As shown, the above method further includes S310 to S320, and S310 to S320 are described in detail below.

[0120] S310: Acquire associated cooking devices that have a similar relationship with the target cooking device, and acquire a cooking heating parameter mapping relationship between the associated cooking devices and the target cooking device.

[0121] In this implementation method, associated cooking devices that have a similar relationship with the target cooking device can be obtained, and the cooking heating parameter mapping relationship between the associated cooking devices and the target cooking device can be obtained. The parameters between multiple devices can be migrated through the cooking heating parameter mapping relationship to achieve cooking optimization of multiple cooking devices.

[0122] For example, in an automatic cooking system, once a user optimizes the heat parameters of a built-in wok (target device), the system can automatically identify a tabletop wok (associated device) with the same heating module as a similar device. This device association can be established through empirical analysis, such as by analyzing the maximum power difference and heat transfer efficiency differences between the two devices to establish a mapping benchmark.

[0123] S320: Determine a plurality of mapped cooking heating parameters for the associated cooking device based on the plurality of optimized cooking heating parameters and the cooking heating parameter mapping relationship. Determine remaining cooking heating parameters for the associated cooking device based on the plurality of mapped cooking heating parameters for the associated cooking device using a cooking parameter adjustment model for the associated cooking device.

[0124] When optimizing cooking parameters, multiple mapped cooking heating parameters of associated cooking devices can be determined based on multiple optimized cooking heating parameters and cooking heating parameter mapping relationships, thereby optimizing multiple mapped cooking heating parameters based on the cooking heating parameter mapping relationships.

[0125] For example, when the optimization parameters of the built-in wok (target cooking device) include "preheating stage power parameter 65%", the mapping parameters can be automatically adjusted to "preheating stage power parameter 75%" based on the characteristic that the rated power of the desktop wok (associated cooking device) is 15% lower.

[0126] When optimizing cooking parameters, the cooking parameter adjustment model of the associated cooking device can be further used to determine the remaining cooking heating parameters of the associated cooking device based on multiple mapped cooking heating parameters of the associated cooking device, thereby optimizing the remaining cooking heating parameters of the cooking parameters.

[0127] For example, after the tabletop wok (associated cooking equipment) completes the mapping adaptation of the core firepower parameters, the system automatically calculates the air supply interval parameters and the fan speed parameters according to the unique hot air circulation structural characteristics of the cooking equipment.

[0128] The beneficial effect of the above implementation method is that through device parameter mapping and supplementary optimization mechanism, personalized cooking plans can be quickly migrated across devices, greatly improving the user convenience in multi-device scenarios; using device-specific parameter adjustment models for supplementary optimization effectively solves the parameter adaptation distortion problem caused by hardware differences, ensuring the consistency of optimization effects among different devices.

[0129] In some implementations, the above method further includes S330 to S350, and S330 to S350 are described in detail below.

[0130] S330: Obtaining mapped cooking feedback data from a user when the associated cooking device cooks using a plurality of mapped cooking heating parameters.

[0131] In this implementation method, dynamic calibration of parameter migration can be further achieved by establishing a cross-device feedback verification mechanism. Specifically, the user's mapped cooking feedback data can be obtained when the associated cooking device cooks through multiple mapped cooking heating parameters, and then the cooking optimization effect can be evaluated based on the mapped cooking feedback data.

[0132] For example, in an automatic stir-fry cooking system, after the optimized stir-frying firepower parameters of an embedded wok are migrated to a desktop wok, the system continuously collects user rating data on the dryness and aroma of cooking with the new equipment. This feedback data can be synchronized to the cloud analysis platform in real time through the device networking module. For example, after the user completes cooking Kung Pao Chicken three times, an evaluation data set containing 12 sets of rating data is formed.

[0133] S340: When the mapped cooking feedback data is positive feedback, determining the remaining cooking and heating parameters of the associated cooking device based on the plurality of mapped cooking and heating parameters of the associated cooking device using a cooking parameter adjustment model for the associated cooking device. When the mapped cooking feedback data is negative feedback, determining a negative score value for the mapped cooking feedback data.

[0134] After obtaining the mapped cooking feedback data, differentiated parameter adjustment strategies can be implemented through the positive and negative feedback classification mechanism. When the mapped cooking feedback data is positive feedback, the cooking parameter adjustment model of the associated cooking device is used to determine the remaining cooking heating parameters of the associated cooking device based on multiple mapped cooking heating parameters of the associated cooking device, thereby achieving targeted optimization of the cooking parameters.

[0135] For example, if a user of a tabletop wok (associated cooking device) gives positive reviews for the migrated parameters five or more times in a row, the system automatically triggers the optimization process for the remaining parameters. For example, based on the device's preheating time, the temperature compensation parameters during the feeding window are optimized. This positive feedback-driven mechanism can accelerate parameter coordination between devices.

[0136] After obtaining the mapped cooking feedback data, when the mapped cooking feedback data is negative feedback, a negative score value of the mapped cooking feedback data may be determined, and the cooking parameters may be quantitatively optimized according to the negative score value.

[0137] S350: When the negative score value of the mapped cooking feedback data is greater than or equal to a preset negative score value, reverting the multiple mapped cooking and heating parameters of the associated cooking device to the pre-optimized cooking and heating parameters. When the negative score value of the mapped cooking feedback data is less than the preset negative score value, obtaining parameter sensitivities corresponding to the multiple mapped cooking and heating parameters of the associated cooking device. Determining a preset number of suppressed mapped cooking and heating parameters from the multiple mapped cooking and heating parameters in descending order of parameter sensitivity. Multiplying the multiple suppressed mapped cooking and heating parameters by a preset attenuation coefficient to weaken the multiple suppressed mapped cooking and heating parameters.

[0138] When responding to negative feedback, when the negative score value of the mapped cooking feedback data is greater than or equal to the preset negative score value, it means that the user's negative feedback level is too large. At this time, the multiple mapped cooking heating parameters of the associated cooking equipment can be rolled back to the cooking heating parameters before optimization to re-optimize the cooking process and thereby ensure the cooking optimization effect.

[0139] When performing cooking optimization, when the negative score value of the mapped cooking feedback data is less than the preset negative score value, it means that the user's negative feedback level is small. The parameter sensitivities corresponding to multiple mapped cooking heating parameters of the associated cooking equipment can be obtained, and then the cooking process can be optimized according to the parameter sensitivity.

[0140] For example, when it is detected that the user of a desktop wok has given a food coking score below the threshold three times in a row, the system can identify the heat conduction efficiency parameter (sensitivity 0.88) as the key influencing factor through the parameter influencing factor analysis module.

[0141] After obtaining the parameter sensitivity, a preset number of multiple suppression mapping cooking heating parameters can be determined among the multiple mapping cooking heating parameters in order of parameter sensitivity from high to low, and then the cooking process can be fine-tuned through the multiple suppression mapping cooking heating parameters. The multiple suppression mapping cooking heating parameters can be multiplied by the preset attenuation coefficient to weaken the multiple suppression mapping cooking heating parameters, thereby improving the cooking optimization effect.

[0142] For example, when optimizing mapping parameters for a tabletop wok, if the oil temperature fluctuation parameter is detected as the most sensitive, the system applies a 0.7 dampening factor to that parameter. This dynamic adjustment strategy effectively prevents over-optimization, for example, by reducing the parameter adjustment range while maintaining the core optimization direction, thus avoiding volatile cooking results caused by aggressive adjustments to a single parameter.

[0143] The beneficial effect of the above implementation method is that, by establishing a cross-device feedback closed-loop verification mechanism, it can realize the intelligent migration and dynamic calibration of personalized parameters, ensuring the reliable reproduction of optimization effects between different devices; adopting a parameter sensitivity-driven attenuation adjustment strategy, when responding to negative feedback, it can not only correct obvious deviations but also avoid completely negating existing optimization results.

[0144] The beneficial effect of the above-mentioned implementation method is that when the negative score value of the mapped cooking feedback data is greater than or equal to the preset negative score value, the multiple mapped cooking heating parameters of the associated cooking equipment are rolled back to the cooking heating parameters before optimization; when the negative score value of the mapped cooking feedback data is less than the preset negative score value, a graded response strategy is established through a preset threshold mechanism, so that the parameter adjustment process has both flexibility and stability.

[0145] An embodiment of the present application also provides an intelligent cooking and heating control system driven by multi-dimensional user evaluation, including a unit for executing any of the methods described above.

[0146] Figure 5 A logical structure diagram of an intelligent cooking and heating control system driven by multi-dimensional user evaluation provided in an embodiment of the present application is shown in FIG. Figure 5As 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 method. The beneficial effects of the embodiment of the present application have been described in the above method and will not be repeated here.

[0147] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0148] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by 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 embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0149] 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, the present application implements all or part of the process of the above-mentioned method embodiment by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can at least include: any entity or device capable of carrying computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, mobile hard drive, magnetic disk, or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0150] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0151] Those skilled in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel 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.

[0152] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0153] The units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0154] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. An intelligent cooking and heating control method based on multi-dimensional user evaluation, characterized in that: The method comprises: Obtain multiple cooking heating parameters corresponding to each control dimension of the target cooking device, obtain the priority control dimension and non-priority control dimension determined by the user in the multiple control dimensions, and obtain historical user feedback data corresponding to each control dimension; wherein the multiple cooking heating parameters include heat source distribution parameters, food moisture, heating power, heating temperature, and heating time for each cooking heating section; the multiple control dimensions include a health dimension and a taste dimension; and the number of priority control dimensions is one; Through the cooking heating optimization unit, based on the user historical feedback data corresponding to the priority control dimension and the multiple cooking heating parameters corresponding to the priority control dimension, the multiple optimized cooking heating parameters corresponding to the priority control dimension of the target cooking device are determined; through the cooking heating adjustment unit, based on the user historical feedback data corresponding to the non-priority control dimension, the multiple optimized cooking heating parameters and the multiple cooking heating parameters corresponding to the non-priority control dimension, the multiple adjusted cooking heating parameters corresponding to the non-priority control dimension of the target cooking device are determined.

2. The method according to claim 1, wherein The method further comprises: Obtaining historical user time-series feedback data corresponding to each control dimension; determining, through a user preference migration identification unit, the update weights of multiple cooking and heating parameters corresponding to each control dimension based on the historical user time-series feedback data corresponding to each control dimension; wherein the historical user time-series feedback data corresponding to each control dimension includes the rating values ​​of users corresponding to each control dimension in chronological order; Through the cooking heating optimization unit, based on the user's historical time-series feedback data corresponding to the priority control dimension, the multiple cooking heating parameters corresponding to the priority control dimension, and the multiple cooking heating parameter update weights, the multiple optimized cooking heating parameters corresponding to the priority control dimension of the target cooking device are determined; through the cooking heating adjustment unit, based on the user's historical feedback data corresponding to the non-priority control dimension, the multiple optimized cooking heating parameters, the multiple cooking heating parameters corresponding to the non-priority control dimension, and the cooking heating parameter update weights, the multiple adjusted cooking heating parameters corresponding to the non-priority control dimension of the target cooking device are determined.

3. The method according to claim 2, wherein The user preference migration identification unit determines the update weights of multiple cooking and heating parameters corresponding to each control dimension based on the user's historical time series feedback data corresponding to each control dimension, including: A feedback optimization unit based on the cooking knowledge graph determines multiple conflicting historical time series feedback data groups based on the user historical time series feedback data corresponding to each control dimension. Each conflicting historical time series feedback data group includes two conflicting groups of user historical time series feedback data corresponding to the multiple control dimensions. The cooking heating parameter update weight corresponding to the non-priority control dimension in each conflict history time series feedback data group is multiplied by a preset update weight adjustment ratio value to adjust the cooking heating parameter update weight corresponding to the non-priority control dimension.

4. The method according to claim 3, wherein The method further comprises: determining a plurality of first cooking heating parameters and a plurality of second cooking heating parameters among the plurality of cooking heating parameters corresponding to the priority control dimension, wherein the plurality of first cooking heating parameters are priority-optimized cooking heating parameters among the plurality of cooking heating parameters corresponding to the priority control dimension, and the plurality of second cooking heating parameters are non-priority-optimized cooking heating parameters among the plurality of cooking heating parameters corresponding to the priority control dimension; The cooking heating optimization unit determines, based on the user's historical time-series feedback data corresponding to the priority control dimension, the plurality of first cooking heating parameters, and the plurality of cooking heating parameter update weights, a plurality of optimized first cooking heating parameters corresponding to the plurality of first cooking heating parameters, and obtains first feedback data from the user when the target cooking device subsequently cooks using the plurality of optimized first cooking heating parameters; When the first feedback data is positive feedback, the cooking heating optimization unit updates the weights based on the user's historical time series feedback data corresponding to the priority control dimension, multiple first cooking heating parameters, and the cooking heating parameters corresponding to the multiple first cooking heating parameters, to determine the multiple optimized second cooking heating parameters corresponding to the multiple second cooking heating parameters of the target cooking device; when the first feedback data is negative feedback, the cooking heating optimization unit updates the weights based on the first feedback data, multiple first cooking heating parameters, and the cooking heating parameters corresponding to the multiple first cooking heating parameters, to re-determine the multiple optimized first cooking heating parameters corresponding to the multiple first cooking heating parameters of the target cooking device.

5. The method according to claim 4, wherein The method further comprises: Obtaining a number of negative feedbacks corresponding to when the first feedback data is negative feedback; when the number of negative feedbacks is greater than or equal to a preset number of negative feedbacks, obtaining correlation coefficients between the plurality of second cooking and heating parameters and the plurality of first cooking and heating parameters, the correlation coefficients representing a degree of influence of adjustment of the first cooking and heating parameters on the second cooking and heating parameters; A preset number of target second cooking heating parameters are determined from the multiple second cooking heating parameters in descending order of correlation coefficients; through the cooking heating optimization unit, based on the first feedback data, the multiple first cooking heating parameters, the cooking heating parameter update weights corresponding to the multiple first cooking heating parameters, the multiple target second cooking heating parameters and the cooking heating parameter update weights corresponding to the multiple target second cooking heating parameters, a plurality of optimized first cooking heating parameters corresponding to the multiple first cooking heating parameters and the multiple target second cooking heating parameters are determined.

6. The method according to claim 5, wherein The cooking heating optimization unit updates weights based on the first feedback data, the adjusted plurality of first cooking heating parameters, and the plurality of cooking heating parameters corresponding to the plurality of first cooking heating parameters, and re-determines the plurality of optimized first cooking heating parameters corresponding to the plurality of first cooking heating parameters, including: determining a preset number of target second cooking heating parameters from the plurality of second cooking heating parameters as first cooking heating parameters, and obtaining parameter adjustment thresholds corresponding to the plurality of target second cooking heating parameters; Within the parameter adjustment threshold range corresponding to multiple target second cooking heating parameters, the cooking heating optimization unit determines multiple optimized first cooking heating parameters corresponding to the multiple first cooking heating parameters and multiple optimized target second cooking heating parameters corresponding to the multiple target second cooking heating parameters based on the first feedback data, multiple first cooking heating parameters, cooking heating parameter update weights corresponding to the multiple first cooking heating parameters, and cooking heating parameter update weights corresponding to the multiple target second cooking heating parameters; and obtains the first feedback data of the user when the target cooking device subsequently cooks using the multiple optimized first cooking heating parameters and the multiple optimized target second cooking heating parameters.

7. The method according to claim 6, wherein The cooking heating adjustment unit determines, based on user historical feedback data corresponding to the non-priority control dimension, the multiple optimized cooking heating parameters, and the multiple cooking heating parameters corresponding to the non-priority control dimension, the multiple adjusted cooking heating parameters corresponding to the non-priority control dimension, including: Obtaining lower limit values ​​of multiple cooking heating parameters corresponding to non-priority control dimensions of the target cooking device; Through the cooking heating adjustment unit, based on the user historical feedback data corresponding to the non-priority control dimension, multiple optimized cooking heating parameters, multiple cooking heating parameters corresponding to the non-priority control dimension and the lower limit values ​​of the multiple cooking heating parameters corresponding to the non-priority control dimension, multiple adjusted cooking heating parameters corresponding to the non-priority control dimension with the lowest energy consumption of the target cooking equipment are determined.

8. The method according to claim 7, wherein The method further comprises: Acquire associated cooking devices that have a similar relationship with the target cooking device, and acquire a cooking heating parameter mapping relationship between the associated cooking devices and the target cooking device; Based on multiple optimized cooking heating parameters and cooking heating parameter mapping relationships, multiple mapped cooking heating parameters of the associated cooking device are determined; through the cooking parameter adjustment model of the associated cooking device, based on the multiple mapped cooking heating parameters of the associated cooking device, the remaining cooking heating parameters of the associated cooking device are determined.

9. The method according to claim 8, wherein The method further comprises: obtaining mapped cooking feedback data from a user when the associated cooking device cooks using a plurality of mapped cooking heating parameters; When the mapped cooking feedback data is positive feedback, determining the remaining cooking heating parameters of the associated cooking device according to the plurality of mapped cooking heating parameters of the associated cooking device through a cooking parameter adjustment model of the associated cooking device; when the mapped cooking feedback data is negative feedback, determining a negative score value of the mapped cooking feedback data; When the negative score value of the mapped cooking feedback data is greater than or equal to a preset negative score value, the multiple mapped cooking heating parameters of the associated cooking device are rolled back to the cooking heating parameters before optimization; when the negative score value of the mapped cooking feedback data is less than the preset negative score value, the parameter sensitivities corresponding to the multiple mapped cooking heating parameters of the associated cooking device are obtained; among the multiple mapped cooking heating parameters, a preset number of multiple suppressed mapped cooking heating parameters are determined in descending order of parameter sensitivity; and the multiple suppressed mapped cooking heating parameters are multiplied by a preset attenuation coefficient to weaken the multiple suppressed mapped cooking heating parameters.

10. An intelligent cooking and heating control system driven by multi-dimensional user evaluation, characterized in that: Comprising means for performing the method according to any one of claims 1 to 9.

Images