A control method and system of an intelligent cooker

Abstract

The present application relates to the technical field of data processing, in particular to a control method and system of an intelligent cooking machine, the method comprising: obtaining a plurality of historical temperature sequences collected recently, dividing to obtain a plurality of historical temperature subsequences and generating corresponding fitting curves; determining a temperature offset value based on the historical temperature of each peak point in the fitting curve and the corresponding target temperature, and then determining a typical temperature drift value; determining a mean offset coefficient based on each real-time temperature and the corresponding running power, determining a reference compensation power of the current cooking stage based on the mean offset coefficient and the typical temperature drift value; determining a cumulative offset value of the current cooking stage based on each real-time temperature and the corresponding target temperature, determining a correction power of the current moment based on the mean offset coefficient and the cumulative offset value, and adjusting the current running power based on the reference compensation power and the correction power; the present application can effectively reduce the temperature distortion in the cooking process, and realize intelligent and refined temperature control.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing and intelligent control, and in particular to a control method and system for an intelligent cooking machine. Background Art

[0002] Smart cooking machines in related technologies can be pre-programmed with a series of fixed cooking programs based on common recipes. These programs cover key parameters such as the heat level, stir-frying speed and frequency, and cooking time required for different dishes. To use the smart cooking machine, the user simply needs to select the program for the dish from the interface and press the start button. The machine will then automatically complete the cooking process according to the preset process. This method is simple and convenient, suitable for those with limited cooking experience.

[0003] Smart cooking machines are equipped with a variety of sensors to monitor key indicators during the cooking process. For example, temperature sensors can detect temperature fluctuations within the pot in real time, ensuring that ingredients are cooked within the appropriate temperature range. If the temperature is too high, the heat level is automatically adjusted. However, during cooking, the presence of oil and water evaporation can lead to errors in temperature detection. Consequently, existing smart cooking machines struggle to achieve optimal results when cooking complex dishes. Summary of the Invention

[0004] The object of the present invention is to provide a control method and system for an intelligent cooking machine, which can calibrate the error of real-time temperature, thereby adjusting cooking parameters and achieving more precise control.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] In one aspect, an embodiment of the present invention provides a method for controlling an intelligent cooking machine, the method comprising the following steps:

[0007] Acquire multiple historical temperature sequences collected recently, divide the historical temperatures in the historical temperature sequences into multiple historical temperature subsequences according to corresponding cooking stages, and generate fitting curves corresponding to the respective historical temperature subsequences;

[0008] determining a temperature offset value based on the historical temperature of each peak point in the fitting curve and the corresponding target temperature, and determining a typical temperature drift value of the fitting curve corresponding to the cooking stage based on the multiple temperature offset values ​​in the fitting curve;

[0009] Obtaining each real-time temperature and corresponding operating power in the current cooking stage, determining an average offset coefficient based on each real-time temperature and corresponding operating power, and determining a reference compensation power for the current cooking stage based on the average offset coefficient and a typical temperature drift value;

[0010] The cumulative offset value of the current cooking stage is determined based on each real-time temperature and the corresponding target temperature, the corrected power at the current moment is determined based on the offset coefficient mean and the cumulative offset value, and the current operating power is adjusted based on the benchmark compensation power and the corrected power.

[0011] Optionally, determining the temperature offset value based on the historical temperature of each peak point in the fitting curve and the corresponding target temperature, and determining the typical temperature drift value of the fitting curve corresponding to the cooking stage based on the multiple temperature offset values ​​in the fitting curve, includes:

[0012] Identify each peak point in the fitting curve and extract the corresponding historical temperature. Subtract the peak point historical temperature from the target temperature to obtain the initial temperature offset value.

[0013] If the initial temperature offset value is determined to be within the preset temperature tolerance range, several sampling points on both sides of the peak point are extracted, and the weight value of each sampling point is determined based on the time distance between the peak point and the sampling point and normalized. Based on the normalized weight value, the historical temperature of each sampling point is fused to obtain the characteristic temperature;

[0014] After replacing the historical temperature of the corresponding peak point with the characteristic temperature, a quadratic curve fitting is performed, and the temperature offset value of each peak point is determined based on the fitting curve obtained by the quadratic curve fitting;

[0015] Determine the time interval between adjacent peak points, determine the weight corresponding to the temperature offset value of each peak point based on the length of the time interval and the position in the fitting curve, and obtain the preliminary temperature drift value by taking the weighted average of each temperature offset value;

[0016] Determine the offset rate deviation between the preliminary temperature offset value and the historical temperature offset value. Process the offset rate deviation according to the number of times the cooking machine is run and the cumulative usage time to obtain a deviation correction factor. Based on the deviation correction factor, correct the preliminary temperature drift value to obtain a typical temperature drift value.

[0017] Optionally, determining a weight value of each sampling point based on the time distance between the peak point and the sampling point and performing normalization processing, and fusing the historical temperatures of each sampling point based on the normalized weight value to obtain a characteristic temperature, includes:

[0018] Determine the time distance between the peak point and each sampling point, perform index processing on the time distance, and obtain the weight value of each sampling point;

[0019] The weight values ​​of each sampling point are normalized, and the historical temperatures corresponding to each sampling point are weighted and fused based on the normalized weight values ​​to obtain the characteristic temperature.

[0020] Optionally, obtaining each real-time temperature and corresponding operating power in the current cooking stage, and determining a mean value of the offset coefficient based on each real-time temperature and corresponding operating power, includes:

[0021] Get each real-time temperature and corresponding operating power;

[0022] The ratio of each real-time temperature to the corresponding operating power is calculated to obtain the offset coefficient of each sampling point, and the average value of multiple offset coefficients is used as the mean offset coefficient.

[0023] Optionally, determining the reference compensation power of the current cooking stage based on the offset coefficient mean value and the typical temperature drift value includes:

[0024] Multiply the mean offset coefficient and the typical temperature drift value to obtain the reference compensation power.

[0025] Optionally, determining a reference offset value of the current cooking stage based on each real-time temperature and the corresponding target temperature, and determining a corrected power at the current moment based on the offset coefficient mean and the reference offset value, includes:

[0026] The real-time temperature and operating power are collected at equal intervals during the elapsed period of the current cooking stage to obtain multiple collection points;

[0027] Determine the temperature difference between the real-time temperature and the target temperature at each collection point to form a first temperature difference data set, and use Gaussian filtering to smooth the temperature difference at each collection point to obtain a second temperature difference data set;

[0028] Calculate the absolute residuals between the first and second temperature difference datasets. If the absolute residual of any sampling point is greater than or equal to the upper quintile of all absolute residuals, then record that sampling point as the reference point.

[0029] The reference power is determined based on the temperature difference value and the mean of the offset coefficient of the reference point. The two-tuple consisting of the temperature difference value and the reference power of each reference point is recorded as a power correction pair. The time period between any reference point and the first non-continuous reference point in the reverse time direction is recorded as a typical period.

[0030] The power correction pairs corresponding to the mean values ​​of the offset coefficients in each typical time period are obtained, and the reference powers of each power correction pair are averaged to obtain the corrected power.

[0031] On the other hand, an embodiment of the present invention provides a control system for an intelligent cooking machine, comprising:

[0032] at least one processor;

[0033] at least one memory for storing at least one program;

[0034] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0035] The beneficial effects of the present invention are as follows: the present invention discloses a control method and system for an intelligent cooking machine. The present invention effectively reduces temperature distortion during cooking by precisely regulating real-time temperature and operating power, thereby improving the intelligence level of the cooking machine, ensuring food taste and nutritional balance, and significantly improving cooking efficiency and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 This is a flow chart of a control method for an intelligent cooking machine according to an embodiment of the present invention;

[0038] Figure 2 The figure is a schematic structural diagram of a control system of an intelligent cooking machine according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects disclosed in the present invention, so as to fully understand the purpose, scheme and effect disclosed in the present invention. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other unless there is a conflict.

[0040] refer to Figure 1 ,like Figure 1 The figure shows a control method of an intelligent cooking machine provided by an embodiment of the present invention, the method comprising the following steps:

[0041] S100, obtaining a plurality of recently collected historical temperature sequences, dividing the historical temperatures in the historical temperature sequences into a plurality of historical temperature subsequences according to corresponding cooking stages, and generating fitting curves corresponding to the respective historical temperature subsequences;

[0042] Among them, the historical temperature sequence includes multiple historical temperatures uniformly sampled when the cooking machine is running according to the preset cooking program; specifically, a temperature sensor is set in the cooking appliance, and the real-time temperature is detected by a non-contact temperature sensor. After the cooking machine is started, the pot body begins to heat up, and the temperature gradually rises. When the set cooking temperature is reached, the temperature control device will trigger the cooking machine to automatically cover the pot and start cooking. During the cooking process, the temperature will fluctuate according to different cooking stages and food requirements. For example, when it is necessary to stir-fry with high heat, the temperature control device will automatically adjust the temperature in the pot according to the looseness of the vegetable. First, the temperature will be increased for stir-frying, so that the ingredients can be quickly heated and cooked to lock in nutrients and moisture. Then the temperature can be appropriately lowered to prevent the ingredients from burning. Before the end of cooking, in order to ensure that the food is evenly cooked, the temperature may be increased again or maintained for a certain period of time. For each cooking stage, the cooking program sets a corresponding temperature and duration, and the temperature control device controls the temperature according to the set cooking program. However, due to the influence of oil and water evaporation, there may be a deviation between the target temperature output by the temperature control device and the actual temperature in the pot. By obtaining multiple historical temperatures uniformly sampled during the cooking machine's recent multiple runs according to the preset cooking program, these multiple historical temperatures are divided according to the corresponding cooking stages to obtain historical temperature subsequences for each cooking stage, thereby determining the recent temperature changes of the cooking machine. In response to the nonlinear temperature changes that may occur during the cooking stages, a segmented fitting strategy is adopted to decompose the complex temperature curve into multiple sub-intervals and process them separately, thereby more accurately reflecting the actual temperature variation pattern. The segmented processing method can significantly improve the flexibility and accuracy of temperature calibration.

[0043] S200, determining a temperature offset value based on the historical temperature of each peak point in the fitting curve and the corresponding target temperature, and determining a typical temperature drift value of the fitting curve corresponding to the cooking stage based on the multiple temperature offset values ​​in the fitting curve;

[0044] Specifically, a corresponding fitting curve is generated by adopting polynomial fitting or spline interpolation methods; the difference between the actual temperature of each peak and the target temperature output by the temperature control device is calculated to obtain the temperature offset value of each peak point. For each cooking stage, the multiple temperature offset values ​​in the fitting curve corresponding to the cooking stage are processed to obtain the typical temperature drift value of the cooking stage.

[0045] S300, obtaining each real-time temperature and corresponding operating power in the current cooking stage, determining an average offset coefficient based on each real-time temperature and corresponding operating power, and determining a reference compensation power for the current cooking stage based on the average offset coefficient and a typical temperature drift value;

[0046] Specifically, during the current cooking phase, a dynamic analysis is performed based on real-time collected temperature and operating power data. First, the real-time temperature is compared to the corresponding operating power to determine the offset coefficient for each sampling point. These offset coefficients reflect the changing relationship between temperature and power under the current cooking state. Next, by averaging all offset coefficients, a more representative average is obtained, providing the basis for subsequent baseline compensation power calculations.

[0047] To further quantify the degree of temperature distortion, the typical temperature drift value determined in the previous step is combined with the currently calculated mean offset coefficient. These two metrics are weighted or nonlinearly mapped to obtain a baseline compensation power for each real-time temperature point. This not only reflects the degree to which the actual temperature deviates from the target temperature but also considers the impact of power regulation on temperature control, providing a more comprehensive assessment of temperature stability during the current cooking phase.

[0048] Furthermore, during the calculation process, abnormal data is screened and processed. For example, when the offset coefficient of certain sampling points deviates significantly from the overall mean, these outliers are automatically identified and corrected or eliminated to ensure the accuracy and reliability of the calculation results. This multi-level data processing approach effectively improves the intelligent cooking machine's adaptability to complex cooking scenarios and lays a solid foundation for precise temperature control.

[0049] S400, determine the cumulative offset value of the current cooking stage based on each real-time temperature and the corresponding target temperature, determine the corrected power at the current moment based on the offset coefficient mean and the cumulative offset value, and adjust the current operating power based on the benchmark compensation power and the corrected power.

[0050] Specifically, in the current cooking stage, the difference between each real-time temperature and the corresponding target temperature is first calculated, and these differences are accumulated to obtain a cumulative offset value. This cumulative offset value can reflect the degree to which the overall temperature deviates from the target temperature in the current stage. Next, combined with the reference compensation power calculated in the previous step, the cumulative offset value and the reference compensation power are comprehensively analyzed to generate the corrected temperature at the current moment. The obtained corrected temperature not only takes into account the deviation between the actual temperature and the target temperature, but also incorporates the impact of power regulation on temperature stability, thereby ensuring that it is closer to the actual cooking needs.

[0051] The cooking machine's operating power is adjusted based on the corrected temperature. By dynamically adjusting the heating module's output power, the pot's temperature gradually approaches the corrected temperature, ultimately achieving precise temperature control. In some embodiments, to improve response speed and stability, a feedback mechanism is introduced during the power adjustment process to monitor temperature changes in real time and make fine adjustments. Furthermore, to prevent frequent power fluctuations from negatively impacting cooking results, a certain adjustment threshold is set to ensure smooth and continuous power adjustment.

[0052] In steps S100 to S400, an embodiment of the present invention provides a temperature calibration system that dynamically adapts to the cooking needs of different dishes and effectively addresses interference with temperature detection caused by factors such as oil contamination and water evaporation, thereby significantly improving the temperature control accuracy of the intelligent cooking machine. In practical applications, a fitting curve is first generated based on the historical temperature subsequence. By comparing the historical temperature at the peak point with the target temperature, the typical temperature drift value for each cooking stage is accurately calculated. This not only considers the absolute temperature deviation but also incorporates the variation of the operating power, further improving calibration accuracy. Subsequently, dynamic monitoring of the real-time temperature and operating power allows for rapid identification and correction of abnormal data, ensuring the reliability of the calculation results. Finally, the current corrected power is determined based on the mean offset coefficient and the cumulative offset value. The current operating power is adjusted based on the baseline compensation power and the corrected power, providing a scientific basis for operating power adjustment and achieving intelligent and refined temperature control. The method provided by the present invention enables the cooking machine to exhibit greater stability and adaptability when processing complex dishes, providing users with a better cooking experience.

[0053] As an improvement to the above embodiment, determining the temperature offset value based on the historical temperature of each peak point in the fitting curve and the corresponding target temperature, and determining the typical temperature drift value of the fitting curve corresponding to the cooking stage based on the multiple temperature offset values ​​in the fitting curve, includes:

[0054] S210, identifying each peak point in the fitting curve and extracting the corresponding historical temperature, and subtracting the peak point historical temperature from the target temperature to obtain an initial temperature offset value;

[0055] The peak point reflects the key node of temperature change during the cooking process. The initial temperature offset value directly quantifies the deviation between the actual temperature and the target temperature at the peak point.

[0056] S220: If it is determined that the initial temperature offset value deviates from the preset temperature tolerance range, extract several sampling points on both sides of the peak point, determine a weight value for each sampling point based on the time distance between the peak point and the sampling point, perform normalization processing, and fuse the historical temperatures of each sampling point based on the normalized weight value to obtain a characteristic temperature;

[0057] It should be noted that the temperature tolerance range automatically adapts to the different needs of the cooking stage. For example, in the stir-fry stage, which requires rapid temperature rise, the temperature tolerance range is appropriately relaxed to allow for greater temperature fluctuations; while in the slow-cooking stage, which requires precise temperature control, the temperature tolerance range is strictly limited to ensure temperature stability. Through this adaptive mechanism, not only can the cooking needs of different dishes be better met, but it can also effectively reduce the misjudgment problem caused by fixed thresholds, thereby further improving the temperature control performance of the smart cooking machine. For example, in the stir-fry stage, due to the more drastic temperature changes, the temperature tolerance range can be appropriately expanded; while in the stewing stage, the temperature fluctuations are relatively gentle, and the temperature tolerance range can be reduced. The temperature tolerance range is set to ±2°C, which more accurately reflects the actual cooking needs.

[0058] By statistically analyzing the temperature offset values ​​of all peak points in the fitted curve and determining whether the temperature offset value deviates from the preset temperature tolerance range, the system selects several sampling points on both sides of the peak point and generates a corrected characteristic temperature through weighted fusion. This characteristic temperature replaces the historical temperature of the corresponding peak point and is then re-incorporated into the fitted curve. This not only effectively reduces errors caused by local anomalies but also improves the smoothness and accuracy of the fitted curve.

[0059] S230, performing quadratic curve fitting after replacing the historical temperature of the corresponding peak point with the characteristic temperature, and determining the temperature offset value of each peak point based on the fitting curve obtained by the quadratic curve fitting;

[0060] Specifically, by precisely correcting the peak points in the fitted curve, the calculated temperature offset value more closely reflects the temperature variations during the actual cooking process. During the quadratic curve fitting process, a local weighted regression method is employed to further optimize the smoothness and accuracy of the fitted curve. By analyzing the corrected fitted curve, the final temperature offset value for each peak point is extracted, and the tolerance range is dynamically adjusted based on the target temperature during the cooking phase, thereby enhancing the flexibility and accuracy of temperature calibration.

[0061] S240, determining a time interval between adjacent peak points, determining a weight corresponding to the temperature offset value of each peak point based on the length of the time interval and the position in the fitting curve, and performing a weighted average of each temperature offset value to obtain a preliminary temperature drift value;

[0062] Specifically, the time interval from the start time of the cooking time period to the first peak point is taken as the time interval corresponding to the first peak point, and the time interval between the first peak point and the second peak point is taken as the time interval corresponding to the second peak point, and so on. The closer each peak point is to the center of the fitting curve, the greater the importance of the time interval, the more it can reflect the temperature characteristics of the actual cooking process, and the higher the corresponding weight; the longer the time interval is, the more significant its impact on the typical temperature drift value, and the corresponding weight value also increases accordingly, ensuring that the weight of each peak point matches its actual impact in the cooking process, thereby more accurately reflecting the dynamic characteristics of temperature changes.

[0063] S250, determining the offset rate deviation between the preliminary temperature offset value and the historical temperature offset value, processing the offset rate deviation according to the number of times the cooking machine has been run and the cumulative usage time to obtain a deviation correction factor, and correcting the preliminary temperature drift value based on the deviation correction factor to obtain a typical temperature drift value.

[0064] It's important to note that as a cooking machine's frequency of operation and cumulative usage increase, the sensitivity of its temperature sensing element gradually decreases, leading to cumulative temperature deviations. The introduction of a deviation correction factor effectively offsets this cumulative effect, ensuring the long-term stability and accuracy of typical temperature drift values, further improving cooking reliability and user experience.

[0065] The specific processing process is as follows: by recording the preliminary temperature drift value of each cooking session and its corresponding number of cooking machine operations and usage time, a data model is established, the correlation between typical temperature drift values ​​and operating parameters is analyzed, and a deviation correction factor is generated. Combined with dynamic adjustment of the preliminary temperature drift value, the accuracy of the calibration result is ensured. The deviation correction factor is calculated as follows: Deviation correction factor = offset rate deviation value / (adjustment coefficient × number of operations × usage time). This formula comprehensively considers the impact of the number of operations and usage time on the sensitivity of the temperature sensing element. The value of the adjustment coefficient is determined based on actual test data to ensure that the correction factor reasonably reflects the change in temperature deviation. For example, the adjustment coefficient ranges from 0.1 to 0.5. Through multiple experimental verifications, the optimal value is selected to balance the correction effect and the actual deviation, ensuring the accuracy and applicability of the temperature drift value correction. By dynamically adjusting the preliminary temperature drift value, the long-term stability and accuracy of the calibration result are ensured, further improving the reliability of the cooking process. The corrected typical temperature drift value = preliminary temperature drift value × (1 + deviation correction factor). This formula effectively combines real-time data with historical cumulative effects to ensure precise control of cooking temperature every time and optimize the cooking experience.

[0066] The final typical temperature drift value not only reflects the degree to which the actual temperature deviates from the target temperature, but also comprehensively considers the influence of power regulation and external interference factors during the cooking process, providing a more accurate reference basis for subsequent benchmark compensation power calculations.

[0067] In this embodiment, the typical temperature drift calculation method effectively addresses the changing demands of complex cooking scenarios, demonstrating greater adaptability and stability, particularly when processing dishes that require frequent temperature adjustments. By dynamically adjusting weights and deviation correction factors, errors caused by device characteristics or external interference can be minimized, providing reliable assurance for precise temperature control in intelligent cooking machines.

[0068] As an improvement to the above embodiment, in S220, the weight value of each sampling point is determined based on the time distance between the peak point and the sampling point and normalized, and the historical temperature of each sampling point is fused based on the normalized weight value to obtain the characteristic temperature, including:

[0069] S221, determining the time distance between the peak point and each sampling point, performing exponential processing on the time distance, and obtaining a weight value of each sampling point;

[0070] S222 , normalizing the weight values ​​of the respective sampling points, and performing weighted fusion on the historical temperatures corresponding to the respective sampling points based on the normalized weight values ​​to obtain a characteristic temperature.

[0071] It's important to note that a dynamic weighting mechanism is introduced during the correction process, assigning different weights based on the temporal distance between the sampling point and the peak point. The weight is negatively correlated with the temporal distance; the greater the temporal distance, the smaller the weight. This ensures that the corrected data more closely reflects actual temperature trends. This further enhances the fitting curve's adaptability to complex cooking scenarios and provides more reliable data for subsequent calculations of typical temperature drift values.

[0072] As an improvement to the above embodiment, in S300, obtaining each real-time temperature and corresponding operating power in the current cooking stage, and determining the mean value of the offset coefficient based on each real-time temperature and corresponding operating power, includes:

[0073] S311, obtaining each real-time temperature and corresponding operating power;

[0074] S312 , calculating the ratio of each real-time temperature to the corresponding operating power to obtain an offset coefficient for each sampling point, and taking an average value of the multiple offset coefficients as an offset coefficient mean.

[0075] It should be noted that the relationship between temperature and power may vary across different cooking stages. The offset coefficient can capture this dynamic change, providing basic data for subsequent evaluation of temperature regulation through power during each cooking stage. For example, during a high-heat stir-fry, the power is high, and the real-time temperature is also relatively high, so a corresponding offset coefficient is calculated. Meanwhile, during a low-heat simmer, the power is low, and the real-time temperature is also low, so a corresponding offset coefficient is also calculated. By analyzing the offset coefficients for each cooking stage, we can better understand the operation of the smart cooking machine at different cooking stages, thereby further improving the accuracy of temperature control.

[0076] The offset coefficient of the current cooking stage can reflect the relationship between temperature and power in the current cooking state, thereby providing a real-time basis for power adjustment in subsequent cooking stages, ensuring that in different cooking stages, the smart cooking machine can accurately adjust the heating strategy according to the dynamic changes in real-time temperature and power, and further optimize the cooking effect.

[0077] As an improvement to the above embodiment, in S300, determining the reference compensation power for the current cooking stage based on the offset coefficient mean and the typical temperature drift value includes:

[0078] Multiply the mean offset coefficient and the typical temperature drift value to obtain the reference compensation power.

[0079] It should be noted that the benchmark compensation power is not a fixed value, but is dynamically adjusted according to the cooking stage and external environment to ensure that each cooking can be carried out within the ideal temperature range, effectively improving the taste and nutritional retention of dishes.

[0080] As an improvement to the above embodiment, in S400, determining the reference offset value of the current cooking stage based on each real-time temperature and the corresponding target temperature, and determining the corrected power at the current moment based on the offset coefficient mean and the reference offset value, includes:

[0081] S411, collecting real-time temperature and operating power at equal intervals during the elapsed period of the current cooking stage to obtain multiple collection points;

[0082] Specifically, starting from the current cooking stage, the real-time temperature and operating power are recorded every certain period of time (for example, 5 seconds), and the time scale of collecting the real-time temperature and operating power is recorded as a collection point, thereby obtaining the real-time temperature and operating power of a series of continuous collection points.

[0083] S412, determining the temperature difference between the real-time temperature and the target temperature at each collection point to form a first temperature difference data set, and smoothing the temperature difference at each collection point using a Gaussian filter to obtain a second temperature difference data set;

[0084] Specifically, the temperature difference between the real-time temperature and the target temperature at each collection point is calculated and recorded to construct a first temperature difference dataset. A Gaussian filter algorithm is applied to the first temperature difference dataset to smooth the temperature differences and form a second temperature difference dataset, effectively removing random fluctuations and ensuring data stability.

[0085] S413, calculating the absolute residuals between the first temperature difference dataset and the second temperature difference dataset, and if the absolute residual of any acquisition point is greater than or equal to the upper quintile of all absolute residuals, then recording the acquisition point as a reference point;

[0086] Specifically, we traverse all data points and calculate the absolute residual between the first and second temperature difference data sets at each point. We then find the upper quintile of all absolute residuals as a threshold. If the absolute residual for a data point is greater than or equal to the threshold, it is marked as a reference point for subsequent accurate calculation of the corrected power.

[0087] S414, determining a reference power based on the temperature difference values ​​and the mean of the offset coefficients at the reference points, recording a pair consisting of the temperature difference value and the reference power at each reference point as a power correction pair, and recording the time period between any reference point and the first non-consecutive reference point in the reverse time direction as a typical period;

[0088] Specifically, the product of the temperature difference and the mean offset coefficient at each reference point is calculated to obtain the reference power. The period between the reference point and the previous non-continuous reference point is defined as a typical period. The mean offset coefficient and corresponding power correction pair for each typical period are extracted, and the reference point in that period is marked as a typical point for precise adjustment of the operating power.

[0089] S415 , obtaining power correction pairs corresponding to the mean values ​​of the offset coefficients of each typical time period, and performing mean calculation on the reference powers of each power correction pair to obtain the corrected power.

[0090] Specifically, the power correction pairs at each typical point are combined to comprehensively calculate the corrected power, ensuring precise adjustment of operating power and improving cooking results. This corrected power is applied in real time to dynamically adjust the equipment's operating status, ensuring temperature and power matching, optimizing the cooking process, improving food taste and quality, and achieving intelligent cooking management.

[0091] As an improvement to the above embodiment, in S400, adjusting the current operating power based on the reference compensation power and the corrected power includes:

[0092] The current operating power, the reference compensation power and the corrected power are accumulated to obtain the adjusted operating power.

[0093] Specifically, the current operating power is added to the benchmark compensation power and the corrected power to obtain a new operating power value, and the equipment operating status is updated in real time to ensure that the temperature and power are accurately matched, further improving cooking efficiency and food quality, and achieving more intelligent cooking control.

[0094] refer to Figure 2 The embodiment of the present invention further provides a control system for an intelligent cooking machine, comprising:

[0095] at least one processor;

[0096] at least one memory for storing at least one program;

[0097] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0098] The contents of the above method embodiments are all applicable to this embodiment. The functions specifically implemented by this embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments, which will not be repeated here.

[0099] Although the description of the present disclosure has been quite detailed and particularly describes several embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but should be considered to provide a broad possible interpretation of these claims by reference to the appended claims in view of the prior art, thereby effectively covering the intended scope of the present disclosure. In addition, the above description of the present disclosure is based on the embodiments foreseen by the inventors, which is intended to provide a useful description, and those non-substantial changes to the present disclosure that have not yet been foreseen may still represent equivalent changes to the present disclosure.

Claims

1. A control method for an intelligent cooking machine, characterized in that: The method comprises the following steps: Acquire multiple historical temperature sequences collected recently, divide the historical temperatures in the historical temperature sequences into multiple historical temperature subsequences according to corresponding cooking stages, and generate fitting curves corresponding to the respective historical temperature subsequences; determining a temperature offset value based on the historical temperature of each peak point in the fitting curve and the corresponding target temperature, and determining a typical temperature drift value of the fitting curve corresponding to the cooking stage based on the multiple temperature offset values ​​in the fitting curve; Obtaining each real-time temperature and corresponding operating power in the current cooking stage, determining an average offset coefficient based on each real-time temperature and corresponding operating power, and determining a reference compensation power for the current cooking stage based on the average offset coefficient and a typical temperature drift value; Determine the cumulative offset value of the current cooking stage based on each real-time temperature and the corresponding target temperature, determine the corrected power at the current moment based on the offset coefficient mean and the cumulative offset value, and adjust the current operating power based on the reference compensation power and the corrected power; The method of determining a temperature offset value based on the historical temperature of each peak point in the fitting curve and the corresponding target temperature, and determining a typical temperature drift value of the fitting curve corresponding to the cooking stage based on the multiple temperature offset values ​​in the fitting curve, includes: Identify each peak point in the fitting curve and extract the corresponding historical temperature. Subtract the peak point historical temperature from the target temperature to obtain the initial temperature offset value. If the initial temperature offset value is determined to be within the preset temperature tolerance range, several sampling points on both sides of the peak point are extracted, and the weight value of each sampling point is determined based on the time distance between the peak point and the sampling point and normalized. Based on the normalized weight value, the historical temperature of each sampling point is fused to obtain the characteristic temperature; After replacing the historical temperature of the corresponding peak point with the characteristic temperature, a quadratic curve fitting is performed, and the temperature offset value of each peak point is determined based on the fitting curve obtained by the quadratic curve fitting; Determine the time interval between adjacent peak points, determine the weight corresponding to the temperature offset value of each peak point based on the length of the time interval and the position in the fitting curve, and obtain the preliminary temperature drift value by taking the weighted average of each temperature offset value; Determine the offset rate deviation between the preliminary temperature offset value and the historical temperature offset value. Process the offset rate deviation according to the number of times the cooking machine is run and the cumulative usage time to obtain a deviation correction factor. Based on the deviation correction factor, correct the preliminary temperature drift value to obtain a typical temperature drift value.

2. The method according to claim 1, characterized in that The weight value of each sampling point is determined based on the time distance between the peak point and the sampling point, and normalized, and the historical temperature of each sampling point is fused based on the normalized weight value to obtain the characteristic temperature, including: Determine the time distance between the peak point and each sampling point, perform index processing on the time distance, and obtain the weight value of each sampling point; The weight values ​​of each sampling point are normalized, and the historical temperatures corresponding to each sampling point are weighted and fused based on the normalized weight values ​​to obtain the characteristic temperature.

3. The method according to claim 1, characterized in that The obtaining of each real-time temperature and the corresponding operating power in the current cooking stage, and determining the mean value of the offset coefficient based on each real-time temperature and the corresponding operating power, includes: Get each real-time temperature and corresponding operating power; The ratio of each real-time temperature to the corresponding operating power is calculated to obtain the offset coefficient of each sampling point, and the average value of multiple offset coefficients is used as the mean offset coefficient.

4. The method according to claim 3, characterized in that The determining of the reference compensation power of the current cooking stage based on the offset coefficient mean value and the typical temperature drift value includes: Multiply the mean offset coefficient and the typical temperature drift value to obtain the reference compensation power.

5. The method according to claim 1, wherein The method of determining a reference offset value of the current cooking stage based on each real-time temperature and the corresponding target temperature, and determining a corrected power at the current moment based on the offset coefficient mean and the reference offset value, includes: The real-time temperature and operating power are collected at equal intervals during the elapsed period of the current cooking stage to obtain multiple collection points; Determine the temperature difference between the real-time temperature and the target temperature at each collection point to form a first temperature difference data set, and use Gaussian filtering to smooth the temperature difference at each collection point to obtain a second temperature difference data set; Calculate the absolute residuals between the first and second temperature difference datasets. If the absolute residual of any sampling point is greater than or equal to the upper quintile of all absolute residuals, then record that sampling point as the reference point. The reference power is determined based on the temperature difference value and the mean of the offset coefficient of the reference point. The two-tuple consisting of the temperature difference value and the reference power of each reference point is recorded as a power correction pair. The time period between any reference point and the first non-continuous reference point in the reverse time direction is recorded as a typical period. The power correction pairs corresponding to the mean values ​​of the offset coefficients in each typical time period are obtained, and the reference powers of each power correction pair are averaged to obtain the corrected power.

6. A control system for an intelligent cooking machine, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 5.

Images