Cooking parameter optimization method based on personalized health data

Abstract

The invention discloses a cooking parameter optimization method based on personalized health data, and the method comprises the steps: obtaining body fluid balance data and a medicine taking record from a user health file, and generating a personalized health index set; according to the personalized health index set, in combination with drug metabolism characteristics, cooking parameter influence factors are determined; aiming at the cooking parameter influence factor and combining with a medicinal and edible interaction limiting condition to obtain a cooking parameter boundary value; extracting real-time environment data from a kitchen environment monitoring device, and generating an initial cooking temperature and a water consumption reference value; dynamically adjusting working parameters of the cooking equipment according to a deviation evaluation result to obtain a stable cooking environment state; according to the stable cooking environment state, a final cooking execution instruction is generated and transmitted to the cooking equipment through the communication interface, and an accurate control result is obtained. According to the invention, by fusing the health condition of the user, the drug influence and the environmental factors, intelligent and personalized cooking control is realized, the diet safety of special crowds is effectively guaranteed, and the cooking quality and efficiency are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of information technology, and in particular to a cooking parameter optimization method based on personalized health data. BACKGROUND

[0002] In the context of modern health management and smart home technology, intelligent cooking recommendation methods and systems based on health data have become a crucial research field. This field aims to provide personalized dietary solutions for users, especially for chronic disease patients, by integrating personal health information and cooking technology. The core of this field is to improve the safety and adaptability of meals, and to help health management move towards precision. However, current related solutions still have significant shortcomings. Many systems only focus on a single health indicator or general dietary recommendations, failing to deeply combine individual user states and external factors, resulting in a lack of targetedness and practicality in recommended solutions.

[0003] Through in-depth analysis of the challenges in this field, we find that the core problem lies in how to effectively integrate multi-dimensional health data and apply it to the dynamic adjustment of cooking parameters. The primary challenge is the complexity of user health status. For example, the body fluid balance of chronic disease patients fluctuates due to pathological changes. If the system cannot real-time perceive and adapt to this change, the cooking plan may deviate from the actual needs. A further difficulty arising from this is the influence of drug metabolism, as certain drugs can change the user's absorption and response to food. If the cooking system ignores this factor, it may increase the risk of drug-food interactions. These two factors are closely related, with the former determining the dynamic nature of health data and the latter further increasing the complexity of data fusion and parameter regulation. Together, they constitute the technical bottleneck of intelligent cooking recommendation.

[0004] Therefore, how to dynamically regulate the water quantity and temperature parameters in the cooking process based on comprehensive consideration of user body fluid balance and drug metabolism, to ensure the personalized adaptation and safety of meal plans, has become a key problem in this field that needs to be solved. SUMMARY

[0005] The present application discloses a cooking parameter optimization method based on personalized health data, mainly including:

[0006] The body fluid balance data and the medicine taking record are acquired from a user health record to generate a personalized health index set; according to the personalized health index set, a cooking parameter influence factor is determined in combination with a medicine metabolism characteristic; for the cooking parameter influence factor, a cooking parameter boundary value is acquired in combination with a medicine-food interaction restriction condition; real-time environment data are extracted from a kitchen environment monitoring device to generate initial cooking temperature and water consumption reference values; according to the cooking parameter influence factor and the cooking parameter boundary value, the initial cooking temperature and water consumption reference values are adjusted in combination with a water metabolism rate and a medicine solubility to obtain a personalized cooking configuration scheme; in a cooking execution process, real-time state data are acquired through a device sensor to judge whether the personalized cooking configuration scheme is deviated to generate a deviation evaluation result; according to the deviation evaluation result, a cooking device working parameter is dynamically adjusted to obtain a stable cooking environment state; according to the stable cooking environment state, a final cooking execution instruction is generated and transmitted to a cooking device through a communication interface to obtain an accurate control result.

[0007] Further, the body fluid balance data and the medicine taking record are acquired from a user health record to generate a personalized health index set, including: through data cleaning and standardization processing, a structured health record data set is generated; for the health record data set, a principal component analysis algorithm is used to extract key features to generate a feature vector set; if the health record data set has missing values, the missing data is filled by a mean interpolation method to obtain a complete feature vector set; according to the feature vector set, in combination with a pre-established physiological parameter mapping table, a medicine absorption rate and a metabolic enzyme activity value are calculated to obtain a medicine metabolism parameter set; for the medicine metabolism parameter set, a support vector machine algorithm is used for classification to judge whether the metabolism characteristic is in a normal range to generate a classification result; through matching of the classification result and the physiological parameter mapping table, the personalized health index set is generated; if the index value in the personalized health index set exceeds a preset threshold range, a health state abnormal risk is predicted by a logistic regression algorithm to obtain a prediction result.

[0008] Further, the cooking parameter influence factor is determined according to the personalized health index set in combination with the drug metabolism characteristics, including: extracting drug metabolism related features from the personalized health index set, combining drug half-life and plasma concentration peak, calculating metabolic interference weight through linear regression algorithm to obtain a weight set; for the weight set, using a pre-established cooking parameter mapping table, analyzing the influence proportion on cooking temperature and water quantity to obtain a cooking parameter influence factor set; if the proportion in the cooking parameter influence factor set exceeds a preset threshold, generating an adjusted factor set through data standardization processing; according to the adjusted factor set, using a clustering algorithm for grouping to obtain a cooking parameter classification set; extracting metabolic interference features from the cooking parameter classification set to generate an association rule set; if the association strength in the association rule set is higher than a preset threshold, a high-impact cooking parameter set is determined.

[0009] Further, the cooking parameter influence factor is determined according to the personalized health index set in combination with the drug metabolism characteristics, including: extracting drug metabolism related features from the personalized health index set, combining drug half-life and plasma concentration peak, calculating metabolic interference weight through linear regression algorithm to obtain a weight set; for the weight set, using a pre-established cooking parameter mapping table, analyzing the influence proportion on cooking temperature and water quantity to obtain a cooking parameter influence factor set; if the proportion in the cooking parameter influence factor set exceeds a preset threshold, generating an adjusted factor set through data standardization processing; according to the adjusted factor set, using a clustering algorithm for grouping to obtain a cooking parameter classification set; extracting metabolic interference features from the cooking parameter classification set to generate an association rule set; if the association strength in the association rule set is higher than a preset threshold, a high-impact cooking parameter set is determined.

[0010] Further, the cooking parameter influence factor is determined according to the personalized health index set in combination with the drug metabolism characteristics, including: extracting drug metabolism related features from the personalized health index set, combining drug half-life and plasma concentration peak, calculating metabolic interference weight through linear regression algorithm to obtain a weight set; for the weight set, using a pre-established cooking parameter mapping table, analyzing the influence proportion on cooking temperature and water quantity to obtain a cooking parameter influence factor set; if the proportion in the cooking parameter influence factor set exceeds a preset threshold, generating an adjusted factor set through data standardization processing; according to the adjusted factor set, using a clustering algorithm for grouping to obtain a cooking parameter classification set; extracting metabolic interference features from the cooking parameter classification set to generate an association rule set; if the association strength in the association rule set is higher than a preset threshold, a high-impact cooking parameter set is determined.

[0011] Further, the adjusting the initial cooking temperature and water quantity reference value according to the cooking parameter influence factor and the cooking parameter boundary value, in combination with the water metabolism rate and the drug solubility comprises: obtaining environmental data from the kitchen environment monitoring device, screening a feature set related to water metabolism and drug dissolution; according to the feature set, in combination with a pre-established boundary value range database, comparing the initial cooking temperature and water quantity reference value, if the difference exceeds a preset threshold range, then performing preliminary correction to obtain a preliminary adjusted parameter set; for the preliminary adjusted parameter set, using a dynamic allocation method to analyze the adjustment range to obtain a dynamically allocated parameter combination; through a data mapping table, performing secondary calibration to determine a parameter scheme suitable for the adaptation scenario; if the difference value exceeds the preset threshold range, then fine-tuning the parameter scheme to obtain a personalized configuration set.

[0012] Further, the obtaining real-time state data through the device sensor during the cooking execution process, and judging whether to deviate from the personalized cooking configuration scheme comprises: continuously collecting temperature fluctuation data and water usage deviation data through the device sensor, in combination with a preset refresh frequency, to generate a state monitoring record; according to the state monitoring record, comparing the data, if the difference exceeds a preset threshold range, then marking an abnormal state point to obtain an abnormal marker set; for the abnormal marker set, classifying abnormal distribution features to generate an abnormal feature description; according to the abnormal feature description, in combination with the reference parameters in the personalized cooking configuration scheme, generating a preliminary adjustment suggestion set; if the change range in the preliminary adjustment suggestion set exceeds a preset safety range, then performing restrictive filtering to determine an adjusted parameter correction set; through matching degree verification, generating a deviation evaluation result.

[0013] Further, the dynamically adjusting the cooking device working parameters according to the deviation evaluation result to obtain a stable cooking environment state comprises: obtaining the deviation evaluation result, determining an abnormal trigger point set by comparing a preset threshold range; for the abnormal trigger point set, extracting the feature distribution of the temperature recovery time and the water quantity calibration period to generate a deviation feature description; according to the deviation feature description, calculating an adjustment coefficient through a feedback control logic to obtain a parameter fine-tuning set; if the adjustment coefficient in the parameter fine-tuning set exceeds a preset safety range, then screening through a restrictive filtering algorithm to determine a safety parameter set; through the safety parameter set, dynamically adjusting the cooking device working parameters to obtain an adjusted running state; according to the adjusted running state, judging whether to meet the stable environment state requirement.

[0014] The technical scheme provided by the embodiment of the application can include the following beneficial effects:

[0015] The application discloses an intelligent cooking control method based on user health conditions and environmental factors. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the attached drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the attached drawings in the following description are only some embodiments of the present application, and other attached drawings can be obtained by those skilled in the art without any creative labor on the basis of these attached drawings.

[0017] Figure 1 A flowchart of a cooking parameter optimization method based on personalized health data according to the present application.

[0018] Figure 2 A flowchart of another cooking parameter optimization method based on personalized health data according to the present application.

[0019] Figure 3 A schematic diagram of generating an environmental feature vector set according to the present application. DETAILED DESCRIPTION

[0020] It should be understood that when used in the specification and the appended claims of the present application, the term "comprising" indicates the presence of the 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 groups thereof.

[0021] It should also be understood that the term "and / or" used in the specification and the appended claims of the present application means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0022] As used in the specification and the appended claims, the term “if’ can be interpreted as meaning “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 [the described condition or event] is detected” can be interpreted as meaning “upon determining” or “in response to determining” or “upon detecting [the described condition or event]” or “in response to detecting [the described condition or event]” depending on the context.

[0023] In addition, in the description of the present application and the appended claims, the terms “first”, “second”, “third”, etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0024] Reference in the specification to “one embodiment” or “some embodiments” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrases “in one embodiment”, “in some embodiments”, “in other embodiments”, “in additional embodiments” and so on, in various places in the specification are not necessarily all referring to the same embodiment, unless otherwise specifically stated. The terms “comprising”, “including”, “having” and their variants mean “including but not limited to”, unless otherwise specifically stated.

[0025] The technical solutions in the embodiments of the application will be described in detail below with reference to the accompanying drawings of the embodiments of the application. The described embodiments are only some of the embodiments of the application.

[0026] As Figure 1 The cooking parameter optimization method based on personalized health data according to the embodiment can specifically include the following steps.

[0027] S101, obtain body fluid balance data and drug taking records from a user health record, analyze the drug absorption rate and metabolic enzyme activity, and obtain a current personalized health index set of the user through a pre-established physiological parameter mapping table.

[0028] The user health record can be obtained in the following ways, such as: physical examination data and reports provided by a hospital official website, an APP or offline, hospital diagnosis results, user medical records, user-stored individual health information, wearable health detection devices, etc.

[0029] The user health record generally contains the following information: routine physical examination indicators: height, weight, BMI, blood pressure, heart rate, vision, hearing, and other basic physiological indicators; blood routine, urine routine, liver function, kidney function, blood lipid, blood glucose, and other biochemical indicators, and some records will record the comparison of the past years' physical examination data (such as cholesterol trend); imaging examination: X-ray, B-ultrasound, CT and other examination reports and films (part of the electronic records are stored in digital form); current medical history: current illness, including symptom onset time, severity, treatment history, etc. (such as "diagnosed with type 2 diabetes in March 2025, currently taking metformin"); past medical history: past diseases (such as pneumonia, surgical history), trauma history, allergy history (such as penicillin allergy), etc., and some records will mark whether the disease is cured or has sequelae. Outpatient medical record: visit time, chief complaint, doctor's diagnosis, prescription (such as "ibuprofen, 3 times / day, for 5 days"), examination application form, etc.; inpatient medical record: admission record, course record, operation record, discharge summary (including discharge diagnosis, rehabilitation suggestion, follow-up plan), etc. such as "laparoscopic surgery for acute appendicitis in August 2023, postoperative recovery is good". Long-term medication record (such as the name, dose, and frequency of antihypertensive and hypoglycemic drugs), vaccination record (such as the time and dose of new crown vaccine inoculation), physiotherapy or rehabilitation treatment plan, etc.

[0030] The body fluid balance data and medication record in the user health record are obtained, and through data cleaning and standardization processing, a structured health record dataset is obtained. If the health record dataset is complete and has no missing values, the principal component analysis algorithm is used to extract the key features of the body fluid balance data and the medication record to generate a feature vector set; if there are missing values, the missing data is filled by the mean interpolation method to obtain a complete feature vector set. According to the feature vector set, combined with the pre-established physiological parameter mapping table, the numerical value of the drug absorption rate and the metabolic enzyme activity is calculated to obtain a drug metabolism parameter set. For the drug metabolism parameter set, the support vector machine algorithm is used for classification to determine whether the drug metabolism characteristics are within the normal range to obtain a metabolism characteristic classification result. Through the matching of the metabolism characteristic classification result and the physiological parameter mapping table, a set of user's current personalized health indicators is generated. If the indicator value in the set of personalized health indicators exceeds the preset threshold range, the logistic regression algorithm is used to predict the abnormal risk of the user's health status to obtain a health status prediction result. According to the health status prediction result, combined with the body fluid balance data and the drug metabolism characteristics, the dynamic change trend of the user's health indicators is generated to obtain a health indicator trend dataset.

[0031] As an illustrative example, fluid balance data and medication intake records are obtained from the user's health profile. Assuming the system obtains user A's fluid balance data through a database query, including daily water intake of 2.5 liters, urine output of 1.8 liters, and sweat loss of 0.4 liters, the net fluid balance is calculated as 2.5 - 1.8 - 0.4 = 0.3 liters, indicating a mild positive balance. The medication intake record shows that user A takes aspirin 100 mg daily, with a dosing time of 08:00, and the system confirms the medication regularity as 95% through timestamp comparison. For drug absorption rate analysis, a first-order absorption kinetic model is used, with the formula dC / dt = ka*D - ke*C, where ka (absorption rate constant) is 0.5 h-1, D is the drug dose of 100 mg, and ke (elimination rate constant) is 0.2 h-1. Through numerical solution (Euler method, step size 0.1 hour), the peak blood concentration 2 hours after medication is calculated as Cmax = 12.5 μg / mL, indicating a reasonable absorption rate. Metabolic enzyme activity analysis is based on CYP2C9 enzyme activity data, assuming user A's genetic test shows CYP2C9*1 / *2 genotype, with enzyme activity at 80% of normal level. Through the enzyme reaction rate formula v = Vmax*[S] / (Km+[S]), where Vmax is 100 μmol / min, Km is 5 μmol, and [S] (substrate concentration) is 10 μmol, the metabolic rate v = 100*10 / (5+10) = 66.7 μmol / min is calculated, indicating slightly lower metabolic capacity than standard. The physiological parameter mapping table includes body weight 60 kg, age 40 years, kidney function (creatinine clearance 90 mL / min), etc. The system maps to health indicators through a weighted algorithm (weights: body weight 0.4, age 0.3, kidney function 0.3), and calculates a comprehensive health index of 0.85 (range 0-1), indicating that the user's health status is good but needs to pay attention to the risk of edema caused by mild fluid positive balance. All calculations are automatically performed by a backend Python script, and data is stored in a MySQL database to ensure logical rigor and traceability.

[0032] S102、According to the set of personalized health indicators, combined with the drug half-life and plasma concentration peak, a metabolic interference weight calculation method is used to determine the specific influence of drug metabolism on cooking temperature and water quantity, and a cooking parameter influence factor is obtained.

[0033] The drug metabolism related features are extracted from the personalized health indicator set, combined with the drug half-life and the peak plasma concentration, the metabolic interference weight is calculated by the linear regression algorithm, and the metabolic interference weight set is obtained. For the metabolic interference weight set, the pre-established cooking parameter mapping table is used to analyze the influence of the weight on the cooking temperature and the water amount, the influence proportion is calculated, and the cooking parameter influence factor set is obtained. If the influence proportion in the cooking parameter influence factor set exceeds the preset threshold, the adjusted cooking parameter factor set is generated through data standardization processing; if it does not exceed, the cooking parameter factor set is directly determined. According to the adjusted cooking parameter factor set, combined with the health indicator set, the clustering algorithm is used to group the factor set, and the cooking parameter classification set is obtained. The metabolic interference features corresponding to each group of factors are extracted from the cooking parameter classification set, and the association rule set of metabolic interference and cooking parameters is generated through the feature matching method. For the association rule set, combined with the drug metabolism characteristics, the logical judgment method is used, if the association strength in the rule set is higher than the preset threshold, the high-impact cooking parameter set is determined; if it is lower than the threshold, the low-impact cooking parameter set is determined. According to the high-impact cooking parameter set and the low-impact cooking parameter set, the dynamic influence trend of cooking parameters on drug metabolism is generated, and the dynamic influence trend set is obtained.

[0034] As an illustrative example, the system first extracts the relevant data of user B from the personalized health indicator set, assuming that the health indicator shows that the metabolic efficiency of user B is 0.75 (range 0-1), combined with the drug half-life data, assuming that the half-life of the antihypertensive drug taken by the user is 6 hours, through the peak plasma concentration analysis, the system calculates that the peak concentration 4 hours after taking the medicine is 18.2 micrograms / milliliter, based on this, the system adopts the metabolic interference weight calculation method, sets the metabolic efficiency interference weight on the cooking parameter as 0.6, the drug half-life interference weight on the cooking parameter as 0.3, and the peak plasma concentration weight as 0.1, through the formula: influence proportion = metabolic efficiency weight x 0.75 + half-life weight x (6 / 24) + peak value weight x (18.2 / 20), the influence proportion is calculated as 0.6 x 0.75 + 0.3 x 0.25 + 0.1 x 0.09 = 0.6, that is, the metabolic efficiency of user B is 0.75, the half-life of the drug is 6 hours, and the peak plasma concentration is 18.2 micrograms / milliliter, the influence proportion is 0.6.

[0035] 0.1x0.91=0.45+0.075+0.091=0.616, indicating that the overall proportion of drug metabolism to cooking parameters is 61.6%. Subsequently, the system further maps this proportion to the cooking temperature and water volume, assuming that the basic cooking temperature is 100 degrees Celsius and the water volume is 1.5 liters, combined with the impact proportion, the system calculates the adjusted cooking temperature as 100x(1-0.616 / 2)=69.2 degrees Celsius and the water volume adjustment as 1.5x(1+0.616 / 3)=1.81 liters through a linear adjustment algorithm to avoid further interference of high temperature or excessive moisture on drug metabolism. Next, the system compares the adjusted parameters with the user's dietary habit database to confirm that the adjustment value is within the safe range and generates a cooking parameter influence factor of 0.82 (range 0-1), indicating that the current cooking parameters have a low impact on drug metabolism. Finally, the system stores all the calculation results to the cloud health management platform and automatically updates the user B's personalized dietary suggestion template to ensure that the subsequent dietary plan is consistent with the drug metabolism requirements, forming a complete logical chain from health indicators to cooking parameter adjustment.

[0036] In S103, if the drug metabolism shows a high-risk drug-food interaction, the cooking temperature upper limit and water volume ratio constraint corresponding to the gastrointestinal reaction and heat-sensitive ingredients are obtained from the preset drug-food interaction restriction table to obtain the cooking parameter boundary value.

[0037] From the preset drug-food interaction restriction table, the high-risk characteristics related to drug metabolism are obtained, and the corresponding constraint conditions are extracted for the influence of gastrointestinal reaction and heat-sensitive ingredients to obtain the initial data set of cooking temperature upper limit and water volume ratio limit. For the cooking temperature upper limit and water volume ratio limit in the initial data set, the constraint conditions are processed using a data standardization method to generate a standardized parameter constraint set. According to the standardized parameter constraint set, combined with the high-risk characteristics of drug metabolism, the influence degree of gastrointestinal reaction and heat-sensitive ingredients is classified by a logistic regression algorithm to determine a high-impact parameter subset and a low-impact parameter subset. For the high-impact parameter subset, if the cooking temperature upper limit exceeds the preset threshold, the temperature upper limit is adjusted to generate an adjusted temperature constraint value; if it does not exceed, the original temperature constraint value is directly retained. According to the adjusted temperature constraint value and water volume ratio limit, combined with the characteristics of drug-food interaction, a mapping rule table is used to generate a cooking parameter boundary value set matched with the high-risk characteristics. For the cooking parameter boundary value set, through a data comparison method, it is judged whether there is an abnormal constraint related to gastrointestinal reaction, if there is an abnormal constraint, the boundary value set is corrected to obtain the final parameter boundary value set. According to the final parameter boundary value set, combined with the characteristics of heat-sensitive ingredients, a cooking parameter recommendation set suitable for drug metabolism characteristics is generated.

[0038] For example, the system first detects the drug metabolism data of user C through the intelligent health analysis platform, assuming that the detection result shows that the anti-inflammatory drug taken by user C has a high-risk interaction with certain food ingredients, which may cause gastrointestinal discomfort. The system extracts relevant information from the drug-food interaction database, confirms that the sensitivity of this drug to heat-sensitive ingredients is 0.85 (range 0-1), and combines the user's historical diet records to analyze that the user often eats food containing heat-sensitive ingredients at a proportion of 40%. Subsequently, the system calls the preset drug-food interaction restriction table to obtain the corresponding cooking temperature upper limit of the drug as 85 degrees Celsius, and the water quantity ratio constraint as 0.8 liters of water per 100 grams of food. Based on this, the system calculates the gastrointestinal reaction risk factor through the risk assessment algorithm, the formula is: risk factor = heat-sensitive sensitivity x 0.85 + food proportion x 0.4, the result is 0.85 x 0.85 + 0.4 x 0.4 = 0.7225 + 0.16 = 0.8825, indicating that the risk is high. Then, the system dynamically restricts the cooking parameter boundary value according to the risk factor, sets the temperature adjustment coefficient as 1-0.8825 / 2 = 0.55875, calculates the final cooking temperature boundary value as 85 x 0.55875 = 47.5 degrees Celsius, and the water quantity boundary value is adjusted to 1.6 liters of water for 200 grams of food through the ratio constraint, and further analyzes that if the food quantity increases to 300 grams, the water quantity boundary value is automatically updated to 2.4 liters to ensure the balance of water proportion. Finally, the system matches the calculated cooking parameter boundary value with the user's diet preference database, confirms that the parameters meet the user's daily habits, and synchronizes the boundary value data to the intelligent cooking equipment to ensure that the equipment automatically limits the temperature and water quantity in the cooking process, avoiding the influence of drug-food interaction on user health, forming a complete logical chain from risk detection to parameter constraint.

[0039] S104, extract real-time humidity, air pressure and equipment running state from the kitchen environment monitoring device, adopt environmental adaptability calibration logic for environmental interference factors and equipment response delay, get initial cooking temperature and water quantity reference value suitable for current scene.

[0040] The real-time humidity, air pressure data and equipment running state are acquired from the kitchen environment monitoring device, the acquired data is preprocessed by using a data standardization method to generate an initial environment data set in a unified format. According to the initial environment data set, the main environmental characteristics are extracted from the real-time humidity, air pressure data and environmental interference factors by using a principal component analysis algorithm to generate an environmental characteristic vector set. If the humidity or air pressure value in the environmental characteristic vector set exceeds a preset threshold value, the characteristic vector is adjusted by an environmental adaptability calibration logic to generate a calibrated environmental characteristic set; if it does not exceed, the original characteristic vector set is directly retained. According to the calibrated environmental characteristic set, combined with the equipment running state and response delay, an initial cooking temperature and water consumption reference value set matching the current scene are generated by using a pre-established mapping rule table. For the initial cooking temperature and water consumption reference value set, whether there is an abnormal value related to the environmental interference factor is judged by a data comparison method, if there is an abnormal value, the reference value set is modified to generate a modified cooking parameter set. According to the modified cooking parameter set, combined with the dynamic changes of real-time humidity and air pressure data, the adjustment amplitude of the cooking parameter is predicted by using a linear regression algorithm to generate a final cooking temperature and water consumption parameter set. For the final cooking temperature and water consumption parameter set, whether the parameter set meets the dynamic needs of the current kitchen environment is judged by a scene adaptability verification logic, if it does not meet, the calibration step is returned to adjust to generate an adaptive cooking parameter set.

[0041] For example, by real-time data acquisition through the kitchen environment monitoring device, the system first extracts the humidity value of the current environment from the sensor as 65%, the air pressure value as 1013 hundred pascals, and simultaneously acquires the equipment running state display as normal operation without failure. For the environmental interference factors, the system uses the environmental adaptability calibration logic to analyze the humidity influence factor on the cooking temperature as 0.03 and the air pressure influence factor on the temperature as 0.02, calculates the initial temperature calibration value, the formula is: reference temperature = default temperature 100 degrees Celsius x (1-humidity influence factor 0.03-air pressure influence factor 0.02) = 100 x 0.95 = 95 degrees Celsius. Then, the system combines the device response delay data, assumes that the average delay from the instruction to the actual execution of the device is 3 seconds, further adjusts the temperature by a delay compensation algorithm, the compensation coefficient is 1-delay seconds x 0.01 = 1-3 x 0.01 = 0.97, and the final initial cooking temperature reference value is 95 x 0.97 = 92.15 degrees Celsius.

[0042] W b = W s x C h

[0043] W b represents the reference water consumption, the unit is liter; W s represents the standard water consumption, the value is 1 liter; C hC represents the humidity correction coefficient, and when the humidity is 65%, C h = 0.9. According to the formula, when the humidity is 65%, the reference water consumption = 1 liter x 0.9 = 0.9 liters. The formula is used to correct the standard water consumption according to the environmental humidity to adapt to the actual water demand under different humidity conditions. At the same time, for the water consumption reference value, the system analyzes the influence of humidity on water evaporation according to the humidity, sets the evaporation correction coefficient corresponding to the humidity of 65% to be 0.9, and obtains the initial water consumption reference value through the formula: reference water consumption = standard water consumption 1 liter x correction coefficient 0.9 = 0.9 liters. To ensure the integrity of the logic chain, the system compares the above reference value with the historical environmental data of the kitchen, confirms that the temperature and water consumption fluctuation rate under the current humidity and air pressure combination is less than 5%, and meets the stability standard, and automatically sets 92.15 degrees Celsius and 0.9 liters as the initial parameters of the current scene, which are transmitted to the cooking control module to provide basic data for the subsequent cooking process, forming a complete closed loop from environmental monitoring to parameter calibration.

[0044] S105, for the cooking parameter influence factor and the cooking parameter boundary value, combining the water metabolism rate and the drug solubility, a dynamic parameter deployment method is used to adjust the initial cooking temperature and the water consumption reference value, and an optimized personalized cooking configuration scheme is obtained.

[0045] From the kitchen environment monitoring device, environmental data and equipment state data related to cooking parameters are obtained, and preliminary screening is performed on the influence factors to obtain an environmental feature set related to water metabolism and drug solubility. According to the environmental feature set, combining the pre-established boundary value domain database, the initial temperature and water reference are compared, if the data in the feature set exceeds the preset threshold range, the initial temperature and water reference are preliminarily corrected to determine the preliminary adjusted parameter set. For the preliminary adjusted parameter set, a dynamic deployment method is used to analyze the temperature adjustment and water adjustment range in combination with the influence of water metabolism rate, and a dynamically deployed parameter combination is obtained. According to the dynamically deployed parameter combination, combining the characteristics of drug solubility, the temperature adjustment and water adjustment are calibrated twice through the data mapping table to determine the parameter scheme adapted to the current scene. For the parameter scheme adapted to the current scene, a linear regression algorithm is used to analyze the difference in personalized cases, if the difference value exceeds the preset threshold range, the parameter scheme is fine-tuned to obtain a personalized adjusted configuration set. According to the personalized adjusted configuration set, through the comparison logic with the optimization configuration target, it is judged whether the matching degree of the current environment and user demand is met, if not, the dynamic deployment step is returned to be recalibrated to obtain the final cooking configuration scheme. For the final cooking configuration scheme, a data storage tool is used to associate and save it with the environmental feature set and the influence factor to determine the optimized configuration record that can be called subsequently.

[0046] For example, the system collects kitchen environment data in real time through sensors, obtains the current food material moisture metabolism rate as 0.75, the drug solubility as 0.85 g / L, combines the cooking parameter influence factor and the boundary value, and adopts a dynamic parameter deployment method to optimize the initial cooking temperature and the water quantity. The system first analyzes the influence of the moisture metabolism rate on the temperature, sets the influence factor as 0.04, and calculates the formula as: initial temperature = standard temperature 100 degrees Celsius x (1-moisture metabolism rate influence factor 0.04) = 100 x 0.96 = 96 degrees Celsius. Then, the system evaluates the adjustment requirement of the drug solubility on the temperature, sets the temperature gain coefficient corresponding to the solubility 0.85 g / L as 0.02, and adjusts the temperature as 96 x (1+0.02) = 97.92 degrees Celsius. To ensure the parameter stability, the system introduces the boundary value constraint, sets the upper limit of the temperature as 98 degrees Celsius, and takes 97.92 degrees Celsius as the initial temperature reference value. For the water quantity, the system analyzes the water retention requirement according to the moisture metabolism rate 0.75, sets the retention coefficient as 0.88, and calculates the formula as: reference water quantity = standard water quantity 1 L x retention coefficient 0.88 = 0.88 L. At the same time, the dissolution efficiency factor corresponding to the drug solubility 0.85 g / L is 0.95, and the adjusted water quantity is 0.88 x 0.95 = 0.836 L. The system further compares the historical cooking data, confirms that the parameter fluctuation rate under the current combination of the moisture metabolism rate and the solubility is less than 4%, and meets the optimization standard. Finally, the system takes 97.92 degrees Celsius and 0.836 L as the personalized cooking configuration parameters, transmits them to the control module, and forms a closed-loop logic from data collection to parameter optimization.

[0047] In S106, during the cooking execution process, the temperature fluctuation amplitude and the water quantity deviation value are obtained through the built-in sensors of the device, the sensor refresh frequency is combined, it is judged whether the current cooking state deviates from the personalized cooking configuration scheme, and a real-time deviation evaluation result is obtained.

[0048] The temperature fluctuation data and water deviation data in the cooking process are continuously collected by the built-in sensor module of the device, and real-time state monitoring records are generated in combination with the preset refresh frequency. According to the state monitoring records, the temperature fluctuation data and water deviation data are compared by using a pre-established threshold range table. If any data is detected to be outside the threshold range, it is marked as an abnormal state point, and an abnormal marker set is obtained. For the abnormal marker set, the distribution characteristics of the abnormal state points are classified by a data processing tool to determine the frequency and duration of the abnormality, and an abnormal feature description is generated. According to the abnormal feature description, in combination with the reference parameters in the individual configuration scheme, the temperature fluctuation and water deviation corresponding to the abnormal state points are parameter-mapped to obtain a preliminary adjustment suggestion set. For the preliminary adjustment suggestion set, a logical judgment tool is used. If the parameter change amplitude in the adjustment suggestion set exceeds the preset safety range, the suggestion set is limitedly filtered to determine an adjusted parameter correction set. Through the parameter correction set, in combination with the real-time analysis module, the corrected parameters are matched with the current cooking state for degree of matching verification to obtain a matching degree evaluation result. According to the matching degree evaluation result, if the matching degree is lower than the preset threshold range, the abnormal feature description step is returned to regenerate the adjustment suggestion set until the matching degree requirement is met to determine the final cooking parameter adjustment scheme.

[0049] For example, during the cooking execution process, the device built-in sensor continuously monitors the cooking environment at a refresh frequency of 5 times per second, first obtains the temperature fluctuation amplitude data, assuming that the current temperature target value is 98.5 degrees Celsius, the sensor detects that the actual temperature fluctuates between 97.8 and 99.2 degrees Celsius, and the calculation shows that the fluctuation amplitude is 1.4 degrees Celsius. The system compares this value with the preset allowed fluctuation range of 0.8 degrees Celsius, and the analysis result shows that the fluctuation amplitude exceeds the standard value by 0.6 degrees Celsius, indicating that the temperature control is deviated. Then, the system detects the water usage deviation value, sets the target water usage to 0.9 liters, and the actual detection value is 0.87 liters, the deviation value is 0.03 liters, combined with the preset deviation threshold of 0.02 liters, the analysis shows that the water usage deviation exceeds the allowed range by 0.01 liters, and there is a slight deficiency. Further, the system combines the data acquisition rate of the sensor refresh frequency of 5 times per second to calculate the duration of temperature and water usage deviation, assuming that the temperature fluctuation exceeds the range for 10 seconds, the cumulative deviation time accounts for 5%, while the water usage deviation lasts for 15 seconds, accounting for 7.5%, the system evaluates according to the preset deviation duration threshold of 3%, and determines that both parameters exceed the stable range, and the current cooking state deviates from the personalized configuration scheme. In order to form a closed loop logic, the system compares the deviation evaluation result with the historical cooking record, extracts the adjustment strategy under the similar deviation scene, for example, when the temperature fluctuation is 1.3 degrees Celsius in the historical data, the system reduces the heating power by 5% to restore stability, and generates real-time adjustment instructions according to the system, and transmits them to the control module, to ensure that the cooking process gradually returns to the target parameter range, and completes the automatic process from monitoring to evaluation.

[0050] S107, if the real-time deviation evaluation result exceeds the preset threshold range, the feedback control fine-tuning logic is adopted for temperature recovery time and water usage calibration period, and the working parameters of the cooking device are dynamically adjusted to obtain a stable cooking environment state.

[0051] The real-time deviation evaluation result is obtained, and by comparing with the preset threshold range, it is determined whether the deviation triggers the adjustment condition to obtain an abnormal trigger point set. For the abnormal trigger point set, a data analysis tool is used to extract the temperature recovery time and the water consumption calibration period feature distribution to generate a deviation feature description. According to the deviation feature description, the adjustment coefficient of the temperature recovery time and the water consumption calibration period is calculated through the feedback control logic to obtain a parameter fine-tuning set. If the adjustment coefficient in the parameter fine-tuning set exceeds the preset safety range, the fine-tuning set is filtered through a restrictive filtering algorithm to determine a safety parameter set. Through the safety parameter set, a real-time control module is used to dynamically adjust the working parameters of the cooking equipment to obtain an adjusted equipment running state. According to the adjusted equipment running state, new temperature data acquisition and water consumption data processing results are obtained to determine whether the requirements of the stable environment state are met. If the requirements of the stable environment state are not met, the deviation feature description step is returned to regenerate the parameter fine-tuning set until the stable environment state is met.

[0052] For example, during the cooking process, when the real-time deviation evaluation result exceeds the preset threshold range, the system dynamically adjusts the equipment parameters through the feedback control fine-tuning logic to stabilize the cooking environment. Assuming that the target cooking temperature is 75°C, the sensor detects that the actual temperature fluctuates between 72.8°C and 77.3°C at a frequency of 10 times per second, the temperature deviation range is calculated to be 4.5°C, which exceeds the preset threshold of 2.0°C, triggering temperature recovery time analysis. The system uses a proportional-integral (PI) algorithm, sets the proportional coefficient Kp = 0.5 and the integral coefficient Ki = 0.02, and calculates the control output: u(t) = Kp·e(t) + Ki·∫e(t)dt, where e(t) is the difference between the target temperature and the actual temperature. The current e(t) = 75-73.5 = 1.5°C, the integral term is based on the past 60 seconds of deviation accumulation, assuming an average deviation of 1.2°C, ∫e(t)dt = 1.2·60 = 72, and u(t) = 0.5·1.5 + 0.02·72 = 2.19, the system accordingly increases the heating power by 2.19%. After monitoring for 10 seconds, the temperature recovers to 74.8°C, the deviation decreases to 0.2°C, and the recovery time meets the preset 15-second threshold. At the same time, the system detects the water consumption calibration period, the target water consumption is 1.2 liters, the actual detection is 1.28 liters, the deviation is 0.08 liters, and the threshold is 0.05 liters. The system analyzes the water consumption deviation for 20 seconds, which accounts for 10%, exceeding the stability threshold of 5%. A periodic calibration algorithm is used to check the water quantity every 30 seconds, and the calibration quantity is calculated: Q = deviation value·calibration factor (0.8), Q = 0.08·0.8 = 0.064 liters, and the system instructs the water valve to reduce the flow by 0.064 liters. Five seconds after calibration, the actual water consumption is adjusted to 1.21 liters, and the deviation is reduced to 0.01 liters. The system stores the adjustment data in the database, compares it with the historical records, optimizes the future PI parameters, generates closed-loop control instructions, and ensures the stability of the cooking environment.

[0053] S108. Based on the stable cooking environment state, combined with the control instruction accuracy and device response delay, a final cooking execution instruction is generated and transmitted to the cooking device through the device communication interface to obtain accurate cooking temperature and water consumption control results.

[0054] Real-time state data from the cooking environment is acquired and compared against various stability indicators to determine whether the preset stability conditions are met, resulting in an environmental state assessment result. Based on the environmental state assessment result and the control instruction accuracy requirements, pre-established mapping rules are used to generate an initial set of execution instructions and determine the basis for instruction generation. For this initial set of execution instructions, the latency characteristics of the device response are taken into account and the timing of instruction execution is adjusted using a time calibration tool to generate an optimized instruction sequence. Based on this optimized instruction sequence, a data transmission channel is established with the cooking device via a communication interface. The instruction sequence is sent to the device and a transmission confirmation feedback is obtained. If the transmission confirmation feedback indicates that the data is complete, the temperature control and water allocation modules of the cooking device are triggered to perform the corresponding parameter adjustments, resulting in an updated device operating state. Based on the updated device operating state, real-time temperature and water usage data are collected and compared with the preset precision result indicators to determine whether the target state has been achieved. If the target state has not been achieved, the process returns to the initial execution instruction set generation step, adjusts the precision requirement parameters, and regenerates the instruction sequence until the precision result conditions are met.

[0055] For example, in a stable cooking environment, the system first collects environmental data in real time through sensors, such as an ambient temperature of 25.3°C and a humidity of 60.5%, and combines it with the historical operation logs of the cooking equipment to analyze the current heat conduction efficiency. A prediction model is obtained that it takes 120 seconds for the equipment to preheat to the target temperature of 180°C, using the formula t = (T_target-T_env) / k, where k is the thermal conductivity coefficient of the equipment, 0.129°C / s. Then, based on the recipe requirements (such as roasting chicken at a constant temperature of 180°C for 40 minutes), a control instruction is generated, with the instruction accuracy controlled at ±0.5°C. The PID algorithm is used to calculate the output power P = K_p*e(t)+K_i*

[0056] ∫e(t)dt+K_d*de(t) / dt, where K_p=5.0, K_i=0.1, and K_d=0.5. The error e(t) is the difference between the target temperature and the real-time temperature. The heating power is dynamically adjusted to 800W to stabilize the temperature. To optimize device response latency, the system analyzed historical data and determined that the average latency from receiving a command to executing it is 0.8 seconds. A feedforward control model is used to send commands 0.8 seconds in advance to ensure a smooth temperature curve. The final command is transmitted via the device communication interface using the MQTT protocol, and the command format is JSON:

[0057] {“temp”: 180.0, “duration”: 2400, “water”: 0.2}, wherein the water quantity 0.2L is calculated according to the recipe (0.1L steam water is needed per kilogram of roasted chicken), and the valve opening is accurately controlled to 20% for 10 seconds by the flow meter. The system monitors the equipment feedback in real time, the temperature deviation is <0.5℃, and the water quantity error is <0.01L, confirming that the execution result is accurate. If the network delay exceeds 50ms, the system automatically switches to the local cache instruction to ensure the continuity of cooking.

[0058] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0059] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiment methods can be instructed by a computer program to complete related hardware, and the computer program can be stored in a computer-readable storage medium. When the processor executes the computer program, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include any entity or device that can carry a computer program code to a photographing device / terminal equipment, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0060] In the above-described embodiments, the description of each embodiment focuses on different aspects, and parts not described in detail or recorded in a certain embodiment can be referred to the relevant description of other embodiments.

[0061] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0062] In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented by other ways. For example, the above-described apparatus embodiments are only schematic, and the division of the modules or units is only a logical function division, and there can be another division way in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection between the units can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0063] The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0064] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be realized in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, the embodiments should be regarded as exemplary and non-limiting, and the scope of the present application is defined by the appended claims rather than the above description, and all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any reference signs in the claims should not be considered as limiting the claims.

Claims

1. A cooking parameter optimization method based on personalized health data, characterized in that: The method comprises: Fluid balance data and medication records are obtained from the user's health file to generate a personalized health indicator set, which is then combined to determine the influencing factors of cooking parameters; drug-food interaction restrictions are obtained, which are combined to obtain cooking parameter boundary values; real-time environmental data is extracted from the environmental monitoring device to generate initial cooking temperature and water consumption benchmark values; the initial cooking temperature and water consumption benchmark values ​​are adjusted based on the cooking parameter influencing factors and cooking parameter boundary values ​​to obtain a personalized cooking configuration plan.

2. The method according to claim 1, wherein The method further comprises: Generate a structured health record dataset, extract key features, and generate a feature vector set; According to the feature vector set, combined with the pre-established physiological parameter mapping table, the drug absorption rate and metabolic enzyme activity value are calculated to obtain the drug metabolism parameter set; Determine whether the metabolic characteristics are within the normal range, generate classification results, match the classification results with the physiological parameter mapping table, generate a personalized health indicator set, determine whether the indicator values ​​in the personalized health indicator set exceed the preset threshold, predict the abnormal health status risk based on the judgment results, and obtain the prediction results.

3. The method according to claim 1, wherein Based on a personalized health indicator set and combined with drug metabolism characteristics, we identify the factors influencing cooking parameters, including: Extract drug metabolism-related features from the personalized health indicator set, combine drug half-life and peak plasma concentration, calculate metabolic interference weights, and obtain a weight set; Using a pre-established cooking parameter mapping table, the impact ratios on cooking temperature and water consumption are analyzed to obtain a set of cooking parameter influencing factors; Clustering algorithm is used to group the adjusted factor set to obtain the cooking parameter classification set; Extract metabolic interference features from the cooking parameter classification set and generate an association rule set; If the association strength in the associated rule set is higher than a preset threshold, a high-impact cooking parameter set is determined.

4. The method according to claim 1, wherein Based on the influencing factors of cooking parameters, obtain the restriction conditions of drug-food interaction and the boundary values ​​of cooking parameters, including: Obtain high-risk features related to drug metabolism from the preset drug-food interaction restriction table, extract the cooking temperature upper limit and water ratio limit, generate an initial data set, and normalize the initial data set into a parameter constraint set; Based on the parameter constraint set, the impact of gastrointestinal reactions and heat-sensitive components is classified to determine a high-impact parameter subset; if the upper temperature limit in the high-impact parameter subset exceeds a preset threshold, the upper temperature limit is adjusted to generate an adjusted constraint value; Based on the adjusted constraint values ​​and in combination with a pre-established mapping rule table, a cooking parameter boundary value set matching the high-risk features is generated; Correct the abnormal constraints and obtain the final set of cooking parameter boundary values.

5. The method according to claim 1, wherein Extract real-time environmental data from kitchen environment monitoring devices to generate initial cooking temperature and water usage baseline values, including: Obtain real-time humidity, air pressure data and equipment operating status to generate an initial environmental data set; For the initial environmental data set, extract the main environmental features and generate an environmental feature vector set; If the value in the environmental feature vector set exceeds the preset threshold, the feature vector is adjusted through calibration logic to generate a calibrated feature set; Based on the calibrated feature set and combined with the equipment operating status, a baseline value set of initial cooking temperature and water consumption is generated; Correcting outliers to generate a corrected cooking parameter set; Based on the revised cooking parameter set, the adjustment range is predicted to generate the final parameter set.

6. The method according to claim 1, wherein According to the cooking parameter influencing factors and cooking parameter boundary values, combined with the water metabolism rate and drug solubility, adjust the initial cooking temperature and water consumption benchmark values, including: Obtain environmental data and filter feature sets related to water metabolism and drug dissolution; Based on the feature set and the pre-established boundary value database, the initial cooking temperature and water consumption baseline values ​​are compared. If they exceed the preset threshold, preliminary corrections are made to obtain a preliminary adjusted parameter set. For the parameter set after preliminary adjustment, analyze the adjustment range and obtain the parameter combination after dynamic allocation; Perform secondary calibration to determine the parameter solution that suits the scenario; If the difference value exceeds the preset threshold, the parameter scheme is fine-tuned to obtain a personalized configuration set.

7. The cooking parameter optimization method based on personalized health data according to claim 1, characterized in that: The method further includes: during the cooking execution process, obtaining real-time status data through device sensors to determine whether there is deviation from the personalized cooking configuration plan; dynamically adjusting the working parameters of the cooking device based on the judgment result to obtain a stable cooking environment state; and generating a final cooking execution instruction based on the stable cooking environment state, and outputting it to the cooking device to obtain a precise control result.

8. The method according to claim 7, wherein During the cooking process, real-time status data is obtained through device sensors to determine whether there is deviation from the personalized cooking configuration plan, including: Continuously collect temperature fluctuation data and water usage deviation data, and generate status monitoring records based on the preset refresh frequency; Compare the data with the status monitoring records. If the data exceeds the preset threshold, mark the abnormal status point, obtain the abnormal mark set, classify the abnormal distribution characteristics, and generate the abnormal feature description; Based on the abnormal feature description and combined with the baseline parameters in the personalized cooking configuration plan, a preliminary set of adjustment suggestions is generated; If the change range in the recommended set exceeds the preset safety range, restrictive filtering is performed to determine the adjusted parameter correction set; Through matching verification, the deviation assessment results are generated.

9. The method according to claim 7, wherein Based on the judgment results, the cooking equipment working parameters are dynamically adjusted to obtain a stable cooking environment state, including: Obtain the judgment results and determine the abnormal trigger point set by comparing them with the preset threshold; For the set of abnormal trigger points, the characteristic distribution of temperature recovery time and water consumption calibration period is extracted to generate deviation feature description; According to the deviation feature description, the adjustment coefficient is calculated to obtain the parameter fine-tuning set; If the adjustment coefficient in the parameter fine-tuning set exceeds the preset safety range, the safe parameter set is screened and determined; Dynamically adjust the working parameters of cooking equipment through the safety parameter set to obtain the adjusted operating status; Based on the adjusted operating status, determine whether the stable environmental state requirements are met.

Images