Refrigerator control method and refrigerator

Abstract

The invention relates to a refrigerator control method and a refrigerator. The method comprises the steps that the food material type, the storage duration and the freshness degree of target food materials in the refrigerator and the opening frequency of the refrigerator in a storage time period corresponding to the storage duration are obtained; determining a target corruption risk value corresponding to the target food material based on the food material type, the storage duration, the freshness degree and the opening frequency; and when the target corruption risk value is greater than or equal to a first preset corruption threshold value, corruption reminding information is output. According to the method, the state of the food materials in the refrigerator is evaluated on the basis of the food material storage duration, the temperature fluctuation in the refrigerator and the real-time freshness of the food materials, the decay risk of the food materials is determined, the user is reminded on the basis of the decay risk, and by fusing multi-dimensional factors, the accuracy of food material state evaluation is improved, and the user is reminded to process the food materials in time.

Description

Technical Field

[0001] This application relates to the field of kitchen appliance technology, and in particular to a refrigerator control method and a refrigerator. Background Technology

[0002] Existing technologies for detecting whether food stored in refrigerators is spoiling mainly include gas detection technology and image detection technology. Gas detection technology uses gas sensors to monitor the gases inside the refrigerator in real time; when the detected gas concentration exceeds a preset threshold, it determines that the food may have spoiled. Image detection technology uses a camera to periodically or in real-time image the food, and determines whether the food is spoiled through analysis and processing of the image data.

[0003] However, existing detection technologies have the following drawbacks: (1) Odor sensors can only acquire the overall odor concentration of the refrigerator compartment and cannot distinguish the low-concentration gas signals produced by the decay of a single food item, resulting in limited detection accuracy; (2) Cameras have limited detection coverage and cannot achieve comprehensive monitoring of all food items inside the refrigerator, which may result in blind spots and prevent the timely detection of the decay of some food items; (3) Image recognition technology may make misjudgments due to the diversity of food items, shapes, colors, and lighting conditions. Summary of the Invention

[0004] To address the aforementioned technical issues, this application discloses a refrigerator control method and a refrigerator. The method assesses the condition of food in the refrigerator based on storage time, internal temperature fluctuations, and real-time freshness, determines the risk of spoilage, and alerts the user based on the risk of spoilage. By integrating multiple factors, the method improves the accuracy of food condition assessment and promptly reminds the user to process the food.

[0005] On one hand, this application provides a refrigerator control method, the method comprising: The refrigerator is used to obtain the type of food, storage time, freshness, and number of times the refrigerator is opened within the storage time period corresponding to the storage time of the target food in the refrigerator. The target spoilage risk value corresponding to the target ingredient is determined based on the ingredient type, storage time, freshness, and number of times it has been opened. If the target corruption risk value is greater than or equal to the first preset corruption threshold, a corruption alert message will be output.

[0006] In some embodiments, determining the target spoilage risk value corresponding to the target ingredient based on the ingredient type, storage duration, freshness, and number of openings includes: The first spoilage parameter corresponding to the target ingredient is determined based on the ingredient type and the storage duration. A second spoilage parameter corresponding to the target ingredient is determined based on the ingredient type and the freshness. The third spoilage parameter corresponding to the target ingredient is determined based on the ingredient type and the number of times it has been opened. The first corruption parameter, the second corruption parameter, and the third corruption parameter are fused together to obtain the target corruption risk value.

[0007] In some embodiments, determining the first spoilage parameter corresponding to the target ingredient based on the ingredient type and the storage duration includes: Obtain the internal environment information of the refrigerator; the internal environment information includes temperature information and humidity information. An environmental spoilage coefficient is determined based on the temperature and humidity information; the environmental spoilage coefficient characterizes the degree of influence of the storage environment on the rate of food spoilage. The spoilage coefficient of the target ingredient is determined based on the type of ingredient; the spoilage coefficient represents the perishability of the target ingredient. The environmental spoilage coefficient, the food spoilage coefficient, and the storage duration are fused to obtain the first spoilage parameter.

[0008] In some embodiments, determining the second spoilage parameter corresponding to the target ingredient based on the ingredient type and the freshness includes: A freshness sensitivity coefficient is determined based on the type of food ingredient; the freshness sensitivity coefficient characterizes the degree to which changes in the freshness of the target food ingredient affect its spoilage risk. The freshness sensitivity coefficient and the freshness are fused together to obtain the second spoilage parameter.

[0009] In some embodiments, determining the third spoilage parameter corresponding to the target ingredient based on the ingredient type and the number of times it has been opened includes: The cumulative temperature fluctuation of the refrigerator during the storage period is determined based on the number of times it is opened. The temperature sensitivity coefficient corresponding to the target ingredient is determined based on the ingredient type; the temperature sensitivity coefficient characterizes the temperature resistance of the target ingredient. The cumulative temperature fluctuation value and the temperature sensitivity coefficient are fused to obtain the third spoilage parameter.

[0010] In some embodiments, after determining the target spoilage risk value corresponding to the target ingredient based on the ingredient type, storage duration, freshness, and number of openings, the method further includes: When the target spoilage risk value is greater than or equal to the second preset spoilage threshold and less than the first preset spoilage threshold, a target preservation instruction is generated; the target preservation instruction is used to instruct the water outlet device in the refrigerator to spray water that conforms to the preservation water quality information corresponding to the target food.

[0011] In some embodiments, the method further includes: If the target food item is detected to have been removed from the refrigerator, the historical cleaning information of the target user is obtained. At least one candidate cleaning mode is determined based on the type of food. Based on the historical cleaning information and the preset cleaning parameters corresponding to each candidate cleaning mode, the target cleaning value corresponding to each candidate cleaning mode is determined. Determine the target cleaning mode corresponding to the target ingredient based on the target cleaning value; A target cleaning instruction is generated based on the target cleaning mode; the target cleaning instruction is used to instruct the water purification equipment to discharge water according to the target cleaning mode.

[0012] In some embodiments, the preset cleaning parameters include cleanliness, energy efficiency, and water cost. Determining the target cleaning value for each candidate cleaning mode based on the historical cleaning information and the preset cleaning parameters corresponding to each candidate cleaning mode includes: Based on the historical cleaning information, a cleaning weight coefficient is determined for the target user; the cleaning weight coefficient includes cleaning priority, energy saving priority, and water saving priority. Based on the cleaning priority and the cleaning degree corresponding to each candidate cleaning mode, a first target value corresponding to each candidate cleaning mode is determined; Based on the energy-saving priority and the energy-saving degree corresponding to each candidate cleaning mode, a second target value corresponding to each candidate cleaning mode is determined; Based on the water-saving priority and the water cost corresponding to each candidate cleaning mode, a third target value corresponding to each candidate cleaning mode is determined. The first target value, the second target value, and the third target value are fused together to obtain the target cleaning value corresponding to each candidate cleaning mode.

[0013] In some embodiments, determining the target cleaning mode corresponding to the target ingredient based on the target cleaning value includes: The candidate cleaning mode corresponding to the largest target cleaning value among the target cleaning values ​​corresponding to each candidate cleaning mode is determined as the target cleaning mode.

[0014] On the other hand, this application also provides a refrigerator, the refrigerator including a controller for performing the refrigerator control method as described above.

[0015] Implementing the embodiments of this application has the following beneficial effects: The refrigerator control method disclosed in this application assesses the status of each type of food in the refrigerator based on the storage time of the food, the temperature fluctuation inside the refrigerator, and the real-time freshness of the food, determines the spoilage risk of each type of food, and reminds the user based on the spoilage risk. By integrating multi-dimensional information, the accuracy of the food status assessment is improved, and the user can be promptly reminded to handle the food when the risk of spoilage is high. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A schematic flowchart of a refrigerator control method provided in an embodiment of this application; Figure 2 A flowchart illustrating a method for determining a corruption risk value provided in an embodiment of this application; Figure 3 A flowchart illustrating a method for determining a cleaning value provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a refrigerator controller provided in an embodiment of this application; Figure 5 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0019] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. Furthermore, the terms "first," "second," etc., are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such information can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in a sequence other than that illustrated or described herein.

[0020] See Figure 1 , Figure 1 This is a flowchart illustrating a refrigerator control method provided in an embodiment of this application. The method is applied to a refrigerator controller and includes: S101, obtain the type of the target food in the refrigerator, the storage time, the freshness, and the number of times the refrigerator is opened within the storage time period corresponding to the storage time. In some embodiments, images of the target food can be captured by a camera in the refrigerator, and the type of food and freshness of the target food can be determined based on the image data. The freshness of the target food refers to its real-time freshness.

[0021] In some embodiments, the number of times the refrigerator is opened during the storage period of the target food can reflect the temperature fluctuation inside the refrigerator caused by opening and closing the refrigerator door during the storage period of the target food.

[0022] In some embodiments, the refrigerator controller can periodically acquire the type of the target food, storage duration, freshness, and the number of times the refrigerator was opened during the storage period of the target food. It can also respond to the user's food status detection command to acquire the type of the target food, storage duration, freshness, and the number of times the refrigerator was opened during the storage period of the target food.

[0023] S103, determine the target spoilage risk value corresponding to the target ingredient based on the ingredient type, storage time, freshness and number of times it has been opened; In some embodiments, the target spoilage risk value characterizes the spoilage risk of the target food. The higher the target spoilage risk value, the higher the spoilage risk of the target food. The target spoilage risk value is determined based on multi-dimensional information such as the type of target food, the storage time of the target food, the real-time freshness of the target food, and the temperature fluctuation inside the refrigerator during the storage period of the target food.

[0024] S105, if the target corruption risk value is greater than or equal to the first preset corruption threshold, output corruption reminder information.

[0025] In some embodiments, if the target spoilage risk value corresponding to the target food ingredient is greater than or equal to a first preset spoilage threshold, it indicates that the target food ingredient has a high spoilage risk, meaning that the target food ingredient is about to spoil or has already spoiled. The refrigerator controller outputs a spoilage reminder message to remind the user to handle the target food ingredient in a timely manner. The first preset spoilage threshold can be set according to actual needs.

[0026] In some embodiments, see Figure 2 , Figure 2 This is a flowchart illustrating a method for determining a spoilage risk value according to an embodiment of this application. The step of determining the target spoilage risk value corresponding to the target ingredient based on the ingredient type, storage duration, freshness, and number of openings includes: S201, determine the first spoilage parameter corresponding to the target ingredient based on the ingredient type and the storage time; In some embodiments, the first spoilage parameter reflects the impact of the storage time of the target food on the spoilage risk of the target food, and the first spoilage parameter is determined based on the type of the target food and the storage time of the target food in the refrigerator.

[0027] S203, determine the second spoilage parameter corresponding to the target ingredient based on the ingredient type and the freshness; In some embodiments, the second spoilage parameter reflects the impact of the real-time freshness of the target ingredient on the risk of spoilage of the target ingredient, and the second spoilage parameter is determined based on the type of the target ingredient and the freshness of the target ingredient.

[0028] S205, determine the third spoilage parameter corresponding to the target ingredient based on the ingredient type and the number of times it is opened; In some embodiments, the third spoilage parameter reflects the impact of internal temperature fluctuations caused by opening and closing the refrigerator door during the storage period of the target food on the risk of spoilage of the target food. The third spoilage parameter is determined based on the type of the target food and the number of times the refrigerator is opened during the storage period of the target food.

[0029] S207, perform data fusion processing on the first corruption parameter, the second corruption parameter, and the third corruption parameter to obtain the target corruption risk value.

[0030] In some embodiments, the formula for calculating the target spoilage risk value corresponding to the target ingredient is as follows: R spoilage =R1+R2+R3 Among them, R spoilageR1 represents the target spoilage risk value corresponding to the target ingredient, R2 represents the first spoilage parameter corresponding to the target ingredient, and R3 represents the third spoilage parameter corresponding to the target ingredient.

[0031] This application embodiment assesses the condition of each food item in the refrigerator based on the storage time, temperature fluctuation inside the refrigerator, and real-time freshness of the food, and determines the spoilage risk of each food item. By integrating multi-dimensional information, the accuracy of the food condition assessment is improved.

[0032] In some embodiments, determining the first spoilage parameter corresponding to the target ingredient based on the ingredient type and the storage duration includes: Obtain the internal environment information of the refrigerator; the internal environment information includes temperature information and humidity information. An environmental spoilage coefficient is determined based on the temperature and humidity information; the environmental spoilage coefficient characterizes the degree of influence of the storage environment on the rate of food spoilage. The spoilage coefficient of the target ingredient is determined based on the type of ingredient; the spoilage coefficient represents the perishability of the target ingredient. The environmental spoilage coefficient, the food spoilage coefficient, and the storage duration are fused to obtain the first spoilage parameter.

[0033] In some embodiments, the internal environment information of the refrigerator is the storage environment information of the target food, including storage temperature and storage humidity. Based on the storage temperature and storage humidity of the target food, the environmental spoilage coefficient corresponding to the storage environment of the target food can be determined. The higher the storage temperature and storage humidity, the greater the environmental spoilage coefficient. The greater the environmental spoilage coefficient, the faster the food spoils under the corresponding storage environment.

[0034] In some embodiments, the food spoilage coefficient reflects the perishability of the target food. The larger the food spoilage coefficient, the easier the food is to spoil. The food spoilage coefficient is related to the type of food. For example, the food spoilage coefficient of meat is greater than that of root vegetables.

[0035] In some embodiments, the rate of food spoilage typically increases exponentially with the storage time of the food; therefore, the formula for calculating the first spoilage parameter corresponding to the target food is as follows: R1=α·e β·t Where R1 is the first spoilage parameter corresponding to the target ingredient, α is the food spoilage coefficient corresponding to the target ingredient, β is the environmental spoilage coefficient corresponding to the storage environment of the target ingredient, and t is the storage time of the target ingredient in hours.

[0036] For example, if the food spoilage coefficient of spinach is α=0.1, and the environmental spoilage coefficient of the storage environment is β=0.05, then the first spoilage parameter of spinach after 24 hours of storage is: 0.1*e 0.05*24 ≈0.33; The first spoilage parameter for spinach stored for 48 hours is: 0.1*e 0.05*48 ≈1.10. According to the calculation results, the longer the food is stored, the larger the first spoilage parameter becomes.

[0037] This application embodiment determines the impact of food storage time on food spoilage risk based on food type, food storage environment, and food storage time, namely the first spoilage parameter. The exponential term in the calculation formula of the first spoilage parameter can accurately reflect the explosive growth law of microorganisms. Furthermore, based on the impact of food storage time on food spoilage risk, the impact of refrigerator internal temperature fluctuations on food spoilage risk, and the impact of real-time food freshness on food spoilage risk, the state of food in the refrigerator is assessed to determine the food spoilage risk. By integrating multi-dimensional information, the accuracy of food state assessment is improved.

[0038] In some embodiments, determining the second spoilage parameter corresponding to the target ingredient based on the ingredient type and the freshness includes: A freshness sensitivity coefficient is determined based on the type of food ingredient; the freshness sensitivity coefficient characterizes the degree to which changes in the freshness of the target food ingredient affect its spoilage risk. The freshness sensitivity coefficient and the freshness are fused together to obtain the second spoilage parameter.

[0039] In some embodiments, the freshness sensitivity coefficient reflects the degree to which changes in the freshness of the target ingredient affect its risk of spoilage. The larger the freshness sensitivity coefficient, the greater the risk of spoilage caused by a decrease in the freshness of the ingredient. The freshness sensitivity coefficient is related to the type of the target ingredient. For example, the freshness sensitivity coefficient of seafood is greater than that of dried goods.

[0040] In some embodiments, the formula for calculating the second spoilage parameter corresponding to the target ingredient is as follows: R2=δ·(1 S fresh ) Where R2 is the second spoilage parameter corresponding to the target ingredient, δ is the freshness sensitivity coefficient corresponding to the target ingredient, and S fresh The freshness of the target ingredient can be assessed in real time using a spectral sensor, odor sensor, and / or camera within the refrigerator. freshThe scores are standardized from 0 to 1, with 1 representing the freshest.

[0041] For example, if the freshness of salmon is S... fresh =0.7, the sensitivity coefficient for freshness of salmon is δ=0.5, then the second spoilage parameter for salmon is: 0.5*(1 0.7) = 0.15, meaning that if the freshness of salmon decreases by 30%, its risk of spoilage increases by 0.15.

[0042] This application embodiment determines the impact of real-time freshness on the risk of food spoilage based on the type and freshness of the food. Furthermore, it assesses the state of the food in the refrigerator based on the impact of storage time, internal temperature fluctuations, and real-time freshness on the risk of food spoilage, thereby determining the risk of food spoilage. By integrating multi-dimensional information, the accuracy of the food state assessment is improved.

[0043] In some embodiments, determining the third spoilage parameter corresponding to the target ingredient based on the ingredient type and the number of times it has been opened includes: The cumulative temperature fluctuation of the refrigerator during the storage period is determined based on the number of times it is opened. The temperature sensitivity coefficient corresponding to the target ingredient is determined based on the ingredient type; the temperature sensitivity coefficient characterizes the temperature resistance of the target ingredient. The cumulative temperature fluctuation value and the temperature sensitivity coefficient are fused to obtain the third spoilage parameter.

[0044] In some embodiments, frequent opening and closing of the refrigerator door can cause internal temperature fluctuations, accelerating cell damage and microbial activity in food. The cumulative value of internal temperature fluctuations caused by opening and closing the refrigerator door during the storage period of the target food is determined based on the number of times the refrigerator is opened during the storage period of the target food.

[0045] In some embodiments, the temperature sensitivity coefficient reflects the temperature resistance of the target ingredient. The larger the temperature sensitivity coefficient, the worse the temperature resistance of the ingredient. The temperature sensitivity coefficient is related to the type of the target ingredient. For example, the temperature sensitivity coefficient of ice cream is greater than that of apples.

[0046] In some embodiments, the formula for calculating the third spoilage parameter corresponding to the target ingredient is as follows: R3=γ·ΔT door Where R3 is the third spoilage parameter corresponding to the target ingredient, γ is the temperature sensitivity coefficient corresponding to the target ingredient, and ΔT doorThis represents the cumulative temperature fluctuation of the refrigerator during the storage period of the target food ingredient, expressed in °C·h.

[0047] For example, if the temperature sensitivity coefficient γ = 0.02 for a certain food ingredient, the cumulative temperature fluctuation ΔT in the refrigerator during the storage period of that food ingredient is... door =15℃·h, then the third spoilage parameter for this ingredient is: 0.02*15=0.3.

[0048] This application embodiment determines the impact of internal refrigerator temperature fluctuations on food spoilage risk based on food type and the number of times the refrigerator is opened during the food storage period. Furthermore, it assesses the state of the food in the refrigerator based on the impact of food storage time, internal refrigerator temperature fluctuations, and real-time freshness of the food, thereby determining the food spoilage risk. By integrating multi-dimensional information, the accuracy of food state assessment is improved.

[0049] In some embodiments, after determining the target spoilage risk value corresponding to the target ingredient based on the ingredient type, storage duration, freshness, and number of openings, the method further includes: When the target spoilage risk value is greater than or equal to the second preset spoilage threshold and less than the first preset spoilage threshold, a target preservation instruction is generated; the target preservation instruction is used to instruct the water outlet device in the refrigerator to spray water that conforms to the preservation water quality information corresponding to the target food.

[0050] In some embodiments, if the target spoilage risk value corresponding to the target food ingredient is greater than or equal to the second preset spoilage threshold and less than the first preset spoilage threshold, that is, the target spoilage risk value corresponding to the target food ingredient is in the range between the second preset spoilage threshold and the first preset spoilage threshold, it indicates that the target food ingredient is not spoiled but needs to be preserved. The refrigerator controller determines the preservation water quality information corresponding to the target food ingredient according to the preset preservation database, generates a target preservation instruction based on the preservation water quality information, and sends the target preservation instruction to the water outlet device in the refrigerator so that the water outlet device in the refrigerator dispenses water according to the preservation water quality information. The water outlet device in the refrigerator can be a micro-mist nozzle, used to spray water mist onto the target food to increase its freshness. The water outlet device in the refrigerator can be connected to a water purification device, which is used to generate water that meets the freshness information of the target food by activating different filter cartridges or filter cartridge combinations, and then spray the generated water onto the target food through the water outlet device in the refrigerator. The freshness water quality information can include pH value, residual chlorine concentration, dissolved oxygen (DO), total dissolved solids (TDS), water temperature, mineral content (such as calcium and magnesium ions), oxidation-reduction potential (ORP), and microbial indicators (such as the number of E. coli).

[0051] For example, if the target ingredient is spinach, the corresponding water quality information for spinach is obtained through a preset preservation database: pH 6.2±0.3, residual chlorine <0.1ppm. Then, a target preservation instruction is generated, causing the water outlet device in the refrigerator to spray water mist with pH 6.2±0.3 and residual chlorine <0.1ppm onto the spinach.

[0052] In some embodiments, the weight of the target food can be obtained by a weight sensor in the refrigerator, and the amount of water sprayed or the spraying time of the water dispensing device in the refrigerator can be determined based on the weight of the target food.

[0053] In some embodiments, the preset preservation database stores the preservation water quality information corresponding to different ingredients. The preset preservation database can be established through experimental data and machine learning models.

[0054] Specifically, during the data collection phase, ingredients are categorized by type (leafy vegetables, root vegetables, meat, seafood, fruits, etc.), and representative samples are selected for each category (e.g., spinach, salmon, blueberries, etc.). For each experiment, other environmental conditions are kept constant, and only water quality parameters are changed. Water quality parameters may include pH value, residual chlorine concentration, dissolved oxygen (DO), total dissolved solids (TDS), water temperature, mineral content (e.g., calcium and magnesium ions), oxidation-reduction potential (ORP), and microbial indicators (e.g., E. coli count). Through experiments, preservation indicators of ingredients under different water quality parameters are obtained. Preservation indicators may include sensory scores (color, odor, texture), nutrient loss rate (vitamin C, protein content), and microbial growth (total colony count).

[0055] In the data processing stage, the data is first cleaned, including outlier removal: outliers (such as pH mutations caused by sensor malfunctions) are identified using box plot method (IQR), and missing value imputation: missing parameters in the experiment are filled using KNN interpolation method (such as missing data records). Next, feature encoding and standardization are performed. Categorical variables such as food type and cutting status (whole / sliced) are encoded using one-hot encoding, while continuous variables such as pH and residual chlorine concentration are scaled to the [0,1] interval using Min-Max standardization. For time-series features, the preservation period is segmented by hour to extract the trend of water quality parameter changes within the time window. Finally, feature association analysis is performed. The linear relationship between water quality parameters and preservation indicators is quantified using Pearson correlation coefficient (such as the negative correlation between residual chlorine concentration and total bacterial count). Principal component analysis (PCA) is used to reduce the dimensionality of high-dimensional data (such as considering pH, TDS, and ORP simultaneously) and extract the main influencing factors.

[0056] During the model training phase, pre-defined machine learning models can include Random Forest, Gradient Boosting Tree (XGBoost / LightGBM), and Neural Networks (MLP / Transformer). Random Forest is used to handle high-dimensional features and nonlinear preservation patterns, Gradient Boosting Tree is used to optimize prediction accuracy and computational efficiency, and Neural Networks are used for modeling large-scale data and complex relationships. First, the data is partitioned into training, validation, and test sets according to a certain ratio. Second, hyperparameter tuning is performed, using Grid Search or Bayesian Optimization to determine the optimal parameter combination. Finally, model fusion is performed, training models separately for regression tasks (input food type, output optimal water quality parameters) and classification tasks (input food type, output recommended water purification mode for water purifiers), and improving robustness through weighted averaging.

[0057] By inputting different types of ingredients into a trained machine learning model, the optimal water quality parameters corresponding to different ingredients can be obtained, i.e., preservation water quality information. Then, a preset preservation database can be established based on the correspondence between ingredients and preservation water quality information.

[0058] In some embodiments, after the refrigerator controller obtains the type of the target food, if the type of the target food already exists in the preset preservation database, it directly obtains the preservation water quality information corresponding to the target food; if the target food is a new food that has not been recorded, it predicts the preservation water quality information corresponding to the target food through a transfer learning model. The establishment of the transfer learning model includes a pre-training stage, a fine-tuning stage, and a zero-shot learning stage. The pre-training stage trains the basic model based on experimental data to learn the general rules of water quality and preservation. The fine-tuning stage adjusts the model parameters using a small amount of actual user data to adapt to personalized scenarios (such as regional water quality differences). The zero-shot learning stage infers the optimal water quality parameters for uncovered foods through attribute similarity (such as moisture content, cell structure, etc.).

[0059] In some embodiments, after the refrigerator controller obtains the preservation water quality information corresponding to the target food, it can also fine-tune the preservation water quality information by combining environmental information (such as high temperature environment in summer) and user historical behavior information, and then generate the target preservation instruction based on the fine-tuned preservation water quality information.

[0060] In some embodiments, after the preset preservation database is established, it can be verified and iterated. Verification refers to offline verification, which involves experimentally reproducing the actual preservation scenario and comparing the experimental preservation effect with the actual preservation effect (e.g., vitamin C retention rate). Iteration refers to online learning, which involves recording the actual water quality and actual preservation results after each spray of preservation mist and automatically updating the preset preservation database. For example, if a user reports that spinach preservation has failed, i.e., premature spoilage, the upper limit of pH value will be adjusted from 6.5 to 6.3, and a new experiment will be triggered for verification.

[0061] In some embodiments, to reduce water waste, the wastewater from food preservation can be purified and used for humidification or secondary preservation in the refrigerator. Specifically, a wastewater collection chamber is installed at the bottom of the water tank, which is connected to a multi-stage purification unit, such as an ultrafiltration membrane and biological activated carbon, through pipes. The purified water is then transported to a micro-mist system in the refrigerator or a home plant irrigation system. Water consumption is monitored by a flow sensor, and the purified water is dynamically allocated for different uses, with the priority being: drinking water > preservation mist > irrigation.

[0062] In this embodiment, when the spoilage risk value of the food is between the second preset spoilage threshold and the first preset spoilage threshold, the refrigerator controller determines the preservation water quality information of the food according to the preset preservation database, generates a preservation instruction based on the preservation water quality information, and sends the preservation instruction to the water outlet device in the refrigerator, so that the water outlet device in the refrigerator dispenses water according to the preservation water quality information, spraying water mist onto the food to increase the preservation time of the food and improve the adaptability preservation effect for different foods.

[0063] In some embodiments, the method further includes: If the target food item is detected to have been removed from the refrigerator, the historical cleaning information of the target user is obtained. At least one candidate cleaning mode is determined based on the type of food. Based on the historical cleaning information and the preset cleaning parameters corresponding to each candidate cleaning mode, the target cleaning value corresponding to each candidate cleaning mode is determined. Determine the target cleaning mode corresponding to the target ingredient based on the target cleaning value; A target cleaning instruction is generated based on the target cleaning mode; the target cleaning instruction is used to instruct the water purification equipment to discharge water according to the target cleaning mode.

[0064] In some embodiments, if the target food is taken out of the refrigerator, it can be assumed that the target user is about to clean the target food. At this time, the refrigerator controller obtains the target user's historical cleaning information, which includes the cleaning mode selected by the target user in the past.

[0065] In some embodiments, different types of ingredients are suitable for different cleaning modes. Based on the ingredient type of the target ingredient, at least one cleaning mode suitable for the target ingredient can be determined, i.e., a candidate cleaning mode. Furthermore, based on the target user's historical cleaning information, the target user's preferred cleaning mode can be added to the candidate cleaning modes.

[0066] In some embodiments, based on the target user's historical cleaning information and the preset cleaning parameters corresponding to each candidate cleaning mode, a target cleaning value corresponding to each candidate cleaning mode is calculated. The preset cleaning parameters include the degree of cleanliness, the degree of energy saving, and the water cost. Based on the target cleaning value, a target cleaning mode corresponding to the target food is determined. A target cleaning instruction is generated based on the target cleaning mode and sent to the water purification device, so that the water purification device outputs water according to the target cleaning mode to clean the target food.

[0067] In other embodiments, upon detecting that the target food item has been removed from the refrigerator, the refrigerator controller can send a food item removal command to the water purification device. The water purification device then obtains the target user's historical cleaning information based on the food item removal command; determines at least one candidate cleaning mode based on the food type of the target food item; determines a target cleaning value for each candidate cleaning mode based on the target user's historical cleaning information and the preset cleaning parameters corresponding to each candidate cleaning mode; and determines the target cleaning mode corresponding to the target food item based on the target cleaning value. That is, the target cleaning mode can be determined by the refrigerator or by the water purification device.

[0068] In this embodiment of the application, when food is detected to be taken out of the refrigerator, a cleaning mode that matches the user's usage preferences and is suitable for the food is determined based on the user's historical cleaning information. The water purifier is then controlled to dispense water according to the cleaning mode to clean the food, so that the food cleaning meets the user's personalized needs, while balancing the cleaning effect, the energy consumption of the water purifier and the water cost.

[0069] In some embodiments, the preset cleaning parameters include cleanliness, energy efficiency, and water cost. Determining the target cleaning value for each candidate cleaning mode based on the historical cleaning information and the preset cleaning parameters corresponding to each candidate cleaning mode includes: S301, determine the cleaning weight coefficient corresponding to the target user based on the historical cleaning information; the cleaning weight coefficient includes cleaning priority, energy saving priority and water saving priority; In some embodiments, historical cleaning information includes the cleaning modes historically selected by the target user. Based on the historical cleaning modes selected by the target user, the user's usage preferences can be determined, i.e., whether the target user prioritizes cleaning effect, water purification equipment energy consumption, or water cost when cleaning food. The cleaning priority w1 defaults to 0.5, the energy saving priority w2 defaults to 0.3, and the water saving priority w3 defaults to 0.2, satisfying w1 + w2 + w3 = 1.

[0070] For example, if historical cleaning information indicates that users frequently select the "deep sterilization mode," then the target users are more health-conscious and are health-sensitive users. In other words, they prioritize cleaning effectiveness, so the cleaning priority should be appropriately increased, setting cleaning priority w1 to 0.7, energy-saving priority w2 to 0.2, and water-saving priority w3 to 0.1. If historical cleaning information indicates that the target users are more concerned about the energy consumption of water purifiers and water costs, then they are environmentally conscious users, requiring an increase in energy-saving and water-saving priorities. The cleaning priority w1 should be set to 0.3, energy-saving priority w2 to 0.4, and water-saving priority w3 to 0.3. If water prices are high in the target user's area, the water-saving priority can be appropriately increased, setting water-saving priority w3 to 0.5.

[0071] S303, based on the cleaning priority and the cleaning degree corresponding to each candidate cleaning mode, determine the first target value corresponding to each candidate cleaning mode; In some embodiments, the cleanliness level is in the range of 0-100%, determined by detecting stain residue rate and microbial inactivation rate (e.g., ATP biofluorescence detection) using sensors, or by comparing differences before and after cleaning using image recognition. The formula for calculating the first target value is as follows: y1=w1 F clean Where y1 is the first target value corresponding to each candidate cleaning mode, w1 is the cleaning priority corresponding to the target user, and F clean The level of cleanliness corresponding to each candidate cleaning mode.

[0072] S305, based on the energy-saving priority and the energy-saving degree corresponding to each candidate cleaning mode, determine the second target value corresponding to each candidate cleaning mode; In some embodiments, the energy saving level is in the standardized range of 0 to 1, referring to the energy consumption difference between the candidate cleaning mode and the baseline cleaning mode, i.e., the energy saving level E. save =1 Actual energy consumption / maximum energy consumption of candidate cleaning modes. The formula for calculating the second target value is as follows: y2=w2 Esave Where y2 is the second target value corresponding to each candidate cleaning mode, w2 is the energy saving priority corresponding to the target user, and E save The energy efficiency corresponding to each candidate cleaning mode.

[0073] S307, Based on the water-saving priority and the water cost corresponding to each candidate cleaning mode, determine the third target value corresponding to each candidate cleaning mode; In some embodiments, the unit of water cost is currency or resource cost, calculated based on water price (yuan / liter) and water consumption, or determined by a weighted average using a water scarcity index (such as the WRI index). The formula for calculating the third target value is as follows: y3=w3 C water Where y3 is the third target value corresponding to each candidate cleaning mode, w3 is the water-saving priority corresponding to the target user, and C water The water cost for each candidate cleaning mode.

[0074] S309, perform data fusion processing on the first target value, the second target value and the third target value to obtain the target cleaning value corresponding to each candidate cleaning mode.

[0075] In some embodiments, the target cleaning value Y is calculated using the following formula: Y = y1 + y2 - y3 = w1 F clean + w2 E save -w3 C water The target cleaning value corresponding to each candidate cleaning mode can be calculated using the above formula.

[0076] In this embodiment of the application, when food is detected to be taken out of the refrigerator, a cleaning mode that matches the user's usage preferences and is suitable for the food is determined based on the user's historical cleaning information. The water purifier is then controlled to dispense water according to the cleaning mode to clean the food, so that the food cleaning meets the user's personalized needs, while balancing the cleaning effect, the energy consumption of the water purifier and the water cost.

[0077] In some embodiments, determining the target cleaning mode corresponding to the target ingredient based on the target cleaning value includes: The candidate cleaning mode corresponding to the largest target cleaning value among the target cleaning values ​​corresponding to each candidate cleaning mode is determined as the target cleaning mode.

[0078] In some embodiments, the candidate cleaning mode corresponding to the largest target cleaning value is selected as the target cleaning mode corresponding to the target ingredient, i.e., Maximize(w1) F clean + w2 E save -w3 C water ).

[0079] For example, if a target user takes a batch of strawberries from the refrigerator and needs to wash them, and strawberries are perishable fruits, the corresponding candidate washing modes could include high-pressure spray mode and microbubble water-saving mode. Specifically, for the high-pressure spray mode, F... clean =90%, E save =0.6, C water =3 yuan; For the microbubble water-saving mode, F clean =85%, E save =0.8, C water =1.5 yuan, the cleaning weight coefficients corresponding to the target users are w1=0.4, w2=0.4, w3=0.2, then the target cleaning value corresponding to the high-pressure spray mode is 0.4×90+0.4×60 0.2 × 3 = 36 + 24 0.6 = 59.4, the target cleaning value corresponding to the microbubble water-saving mode is 0.4 × 85 + 0.4 × 80 0.2 × 1.5 = 34 + 32 0.3 = 65.7. Since the target cleaning value corresponding to the microbubble water-saving mode is the highest, the microbubble water-saving mode is determined as the target cleaning mode.

[0080] In some embodiments, the target user can select or customize an acceptable energy consumption range. When the energy consumption of a candidate cleaning mode exceeds the acceptable energy consumption range for the target user, the candidate cleaning mode can be removed from the candidate schemes.

[0081] In this embodiment of the application, when food is detected to be taken out of the refrigerator, a cleaning mode that matches the user's usage preferences and is suitable for the food is determined based on the user's historical cleaning information. The water purifier is then controlled to dispense water according to the cleaning mode to clean the food, so that the food cleaning meets the user's personalized needs, while balancing the cleaning effect, the energy consumption of the water purifier and the water cost.

[0082] This application provides a refrigerator control method, which includes: acquiring the food type, storage time, freshness, and number of times the refrigerator is opened within a storage period corresponding to the storage time of a target food item in the refrigerator; determining a target spoilage risk value corresponding to the target food item based on the food type, storage time, freshness, and number of openings; and outputting a spoilage reminder message when the target spoilage risk value is greater than or equal to a first preset spoilage threshold. This application assesses the status of each food item in the refrigerator based on the food storage time, internal temperature fluctuations, and real-time freshness, determines the spoilage risk of each food item, and reminds the user based on the spoilage risk. By integrating multi-dimensional information, the accuracy of food status assessment is improved, and the user can be promptly reminded to handle the food when the spoilage risk is high.

[0083] This application also provides a refrigerator, see [link to relevant documentation] Figure 4 The refrigerator includes a controller, the controller comprising: The information acquisition module 410 is used to acquire the type of the target food in the refrigerator, the storage time, the freshness, and the number of times the refrigerator is opened within the storage time period corresponding to the storage time. The spoilage risk value determination module 420 is used to determine the target spoilage risk value corresponding to the target ingredient based on the ingredient type, storage time, freshness and number of times it has been opened; The corruption alert information output module 430 is used to output corruption alert information when the target corruption risk value is greater than or equal to a first preset corruption threshold.

[0084] In some embodiments, the corruption risk value determination module 420 includes: The first spoilage parameter determination unit is used to determine the first spoilage parameter corresponding to the target ingredient based on the ingredient type and the storage time. The second spoilage parameter determination unit is used to determine the second spoilage parameter corresponding to the target ingredient based on the ingredient type and the freshness. The third spoilage parameter determination unit is used to determine the third spoilage parameter corresponding to the target ingredient based on the ingredient type and the number of times it is opened. The target corruption risk value determination unit is used to perform data fusion processing on the first corruption parameter, the second corruption parameter, and the third corruption parameter to obtain the target corruption risk value.

[0085] In some embodiments, the first corruption parameter determining unit includes: A storage environment information acquisition subunit is used to acquire the internal environment information of the refrigerator; the internal environment information includes temperature information and humidity information. An environmental spoilage coefficient determination subunit is used to determine the environmental spoilage coefficient based on the temperature information and the humidity information; the environmental spoilage coefficient characterizes the degree of influence of the storage environment on the rate of food spoilage. The food spoilage coefficient determination subunit is used to determine the food spoilage coefficient corresponding to the target food based on the food type; the food spoilage coefficient characterizes the perishability of the target food. The first spoilage parameter determination subunit is used to perform data fusion processing on the environmental spoilage coefficient, the food spoilage coefficient, and the storage time to obtain the first spoilage parameter.

[0086] In some embodiments, the second corruption parameter determining unit includes: The freshness sensitivity coefficient determination subunit is used to determine the freshness sensitivity coefficient corresponding to the target ingredient based on the ingredient type; the freshness sensitivity coefficient characterizes the degree of influence of changes in the freshness of the target ingredient on the spoilage risk of the target ingredient; The second spoilage parameter determination subunit is used to perform data fusion processing on the freshness sensitivity coefficient and the freshness to obtain the second spoilage parameter.

[0087] In some embodiments, the third corruption parameter determining unit includes: The temperature fluctuation information determination subunit is used to determine the cumulative value of the temperature fluctuation of the refrigerator during the storage period based on the number of openings. A temperature sensitivity coefficient determination subunit is used to determine the temperature sensitivity coefficient corresponding to the target ingredient based on the ingredient type; the temperature sensitivity coefficient characterizes the temperature resistance of the target ingredient. The third decay parameter determination subunit is used to perform data fusion processing on the cumulative value of temperature fluctuation and the temperature sensitivity coefficient to obtain the third decay parameter.

[0088] In some embodiments, the controller further includes: The target preservation instruction generation module is used to generate a target preservation instruction when the target spoilage risk value is greater than or equal to a second preset spoilage threshold and the target spoilage risk value is less than a first preset spoilage threshold; the target preservation instruction is used to instruct the water outlet device in the refrigerator to spray water that conforms to the preservation water quality information corresponding to the target food.

[0089] In some embodiments, the controller further includes: The historical cleaning information acquisition module is used to acquire the historical cleaning information of the target user when the target food is detected to be taken out of the refrigerator. A candidate cleaning mode determination module is used to determine at least one candidate cleaning mode based on the type of food ingredient. The target cleaning value determination module is used to determine the target cleaning value corresponding to each candidate cleaning mode based on the historical cleaning information and the preset cleaning parameters corresponding to each candidate cleaning mode. A target cleaning mode determination module is used to determine the target cleaning mode corresponding to the target ingredient based on the target cleaning value; A target cleaning instruction generation module is used to generate a target cleaning instruction based on the target cleaning mode; the target cleaning instruction is used to instruct the water purification equipment to discharge water according to the target cleaning mode.

[0090] In some embodiments, the preset cleaning parameters include cleanliness, energy efficiency, and water cost, and the target cleaning value determination module includes: A cleaning weight coefficient determination unit is used to determine the cleaning weight coefficient corresponding to the target user based on the historical cleaning information; the cleaning weight coefficient includes cleaning priority, energy saving priority, and water saving priority. The first target value determination unit is used to determine the first target value corresponding to each candidate cleaning mode based on the cleaning priority and the cleaning degree corresponding to each candidate cleaning mode. The second target value determination unit is used to determine the second target value corresponding to each candidate cleaning mode based on the energy saving priority and the energy saving degree corresponding to each candidate cleaning mode. The third target value determination unit is used to determine the third target value corresponding to each candidate cleaning mode based on the water saving priority and the water cost corresponding to each candidate cleaning mode. The target cleaning value determination unit is used to perform data fusion processing on the first target value, the second target value, and the third target value to obtain the target cleaning value corresponding to each candidate cleaning mode.

[0091] In some embodiments, the target cleaning pattern determination module includes: The target cleaning mode determination unit is used to determine the candidate cleaning mode corresponding to the largest target cleaning value among the target cleaning values ​​corresponding to each candidate cleaning mode as the target cleaning mode.

[0092] The apparatus provided in the above embodiments can execute the method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in the above embodiments can be found in a refrigerator control method provided in any embodiment of this application.

[0093] This embodiment also provides a computer-readable storage medium storing computer-executable instructions, which are loaded by a processor and executed by the refrigerator control method described above in this embodiment.

[0094] This embodiment also provides an electronic device, which includes a processor and a memory, wherein the memory stores a computer program adapted to be loaded by the processor and executed as described above in this embodiment of a refrigerator control method.

[0095] The electronic device may be a computer terminal, a mobile terminal, or a server, and may also participate in constituting the apparatus or system provided in the embodiments of this application. For example... Figure 5 As shown, the electronic device 5 may include one or more (shown as 502a, 502b, ..., 502n in the figure) processors 502 (processors 502 may include, but are not limited to, microprocessors MCUs or programmable logic devices FPLDs), a memory 504 for storing information, and a transmission device 506 for communication functions. In addition, it may also include input / output interfaces (I / O interfaces) and network interfaces. Those skilled in the art will understand that... Figure 5 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, electronic device 5 may also include... Figure 5 The more or fewer components shown, or having the same Figure 5 The different configurations shown.

[0096] It should be noted that the aforementioned one or more processors 502 and / or other information processing circuits are generally referred to herein as "information processing circuits". These information processing circuits may be wholly or partially embodied in software, hardware, firmware, or any other combination thereof. Furthermore, the information processing circuits may be a single, independent processing module, or may be wholly or partially integrated into any other element in the electronic device 5.

[0097] The memory 504 can be used to store software programs and modules of application software, such as the program instruction / information storage device corresponding to the method described in the embodiments of this application. The processor 502 executes various functional applications and information processing by running the software programs and modules stored in the memory 504, thereby realizing the above-mentioned refrigerator control method. The memory 504 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 504 may further include memory remotely located relative to the processor 502, and these remote memories can be connected to the electronic device 5 via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0098] The transmission device 506 is used to receive or send information via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the electronic device 5. In one example, the transmission device 506 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 506 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0099] This specification provides the operational steps of the methods described in the embodiments or flowcharts, but more or fewer operational steps may be included based on conventional or non-inventive labor. The steps and order listed in the embodiments are merely one possible execution order among many steps and do not represent the only execution order. In actual system or interrupt product execution, the methods shown in the embodiments or drawings can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0100] The structure shown in this embodiment is only a partial structure related to the solution of this application and does not constitute a limitation on the device to which the solution of this application is applied. Specific devices may include more or fewer components than shown, or combinations of certain components, or arrangements of different components. It should be understood that the methods, apparatuses, etc., disclosed in this embodiment can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or unit modules through some interfaces.

[0101] Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0102] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this specification can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0103] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A refrigerator control method, characterized in that, The method includes: The refrigerator is used to obtain the type of food, storage time, freshness, and number of times the refrigerator is opened within the storage time period corresponding to the storage time of the target food in the refrigerator. The target spoilage risk value corresponding to the target ingredient is determined based on the ingredient type, storage time, freshness, and number of times it has been opened. If the target corruption risk value is greater than or equal to the first preset corruption threshold, a corruption alert message will be output.

2. The refrigerator control method according to claim 1, characterized in that, The determination of the target spoilage risk value corresponding to the target ingredient based on the ingredient type, storage time, freshness, and number of openings includes: The first spoilage parameter corresponding to the target ingredient is determined based on the ingredient type and the storage duration. A second spoilage parameter corresponding to the target ingredient is determined based on the ingredient type and the freshness. The third spoilage parameter corresponding to the target ingredient is determined based on the ingredient type and the number of times it has been opened. The first corruption parameter, the second corruption parameter, and the third corruption parameter are fused together to obtain the target corruption risk value.

3. The refrigerator control method according to claim 2, characterized in that, The step of determining the first spoilage parameter corresponding to the target ingredient based on the ingredient type and the storage duration includes: Obtain the internal environment information of the refrigerator; the internal environment information includes temperature information and humidity information. An environmental spoilage coefficient is determined based on the temperature and humidity information; the environmental spoilage coefficient characterizes the degree of influence of the storage environment on the rate of food spoilage. The spoilage coefficient of the target ingredient is determined based on the type of ingredient; the spoilage coefficient represents the perishability of the target ingredient. The environmental spoilage coefficient, the food spoilage coefficient, and the storage duration are fused to obtain the first spoilage parameter.

4. The refrigerator control method according to claim 2, characterized in that, The determination of the second spoilage parameter corresponding to the target ingredient based on the ingredient type and the freshness includes: A freshness sensitivity coefficient is determined based on the type of food ingredient; the freshness sensitivity coefficient characterizes the degree to which changes in the freshness of the target food ingredient affect its spoilage risk. The freshness sensitivity coefficient and the freshness are fused together to obtain the second spoilage parameter.

5. The refrigerator control method according to claim 2, characterized in that, The process of determining the third spoilage parameter corresponding to the target ingredient based on the ingredient type and the number of times it has been opened includes: The cumulative temperature fluctuation of the refrigerator during the storage period is determined based on the number of times it is opened. The temperature sensitivity coefficient corresponding to the target ingredient is determined based on the ingredient type; the temperature sensitivity coefficient characterizes the temperature resistance of the target ingredient. The cumulative temperature fluctuation value and the temperature sensitivity coefficient are fused to obtain the third spoilage parameter.

6. The refrigerator control method according to claim 1, characterized in that, After determining the target spoilage risk value corresponding to the target ingredient based on the ingredient type, storage time, freshness, and number of openings, the method further includes: When the target spoilage risk value is greater than or equal to the second preset spoilage threshold and less than the first preset spoilage threshold, a target preservation instruction is generated; the target preservation instruction is used to instruct the water outlet device in the refrigerator to spray water that conforms to the preservation water quality information corresponding to the target food.

7. The refrigerator control method according to claim 1, characterized in that, The method further includes: If the target food item is detected to have been removed from the refrigerator, the historical cleaning information of the target user is obtained. At least one candidate cleaning mode is determined based on the type of food. Based on the historical cleaning information and the preset cleaning parameters corresponding to each candidate cleaning mode, the target cleaning value corresponding to each candidate cleaning mode is determined. Determine the target cleaning mode corresponding to the target ingredient based on the target cleaning value; A target cleaning instruction is generated based on the target cleaning mode; the target cleaning instruction is used to instruct the water purification equipment to discharge water according to the target cleaning mode.

8. The refrigerator control method according to claim 7, characterized in that, The preset cleaning parameters include cleanliness, energy efficiency, and water cost. The step of determining the target cleaning value for each candidate cleaning mode based on the historical cleaning information and the preset cleaning parameters corresponding to each candidate cleaning mode includes: Based on the historical cleaning information, a cleaning weight coefficient is determined for the target user; the cleaning weight coefficient includes cleaning priority, energy saving priority, and water saving priority. Based on the cleaning priority and the cleaning degree corresponding to each candidate cleaning mode, a first target value corresponding to each candidate cleaning mode is determined; Based on the energy-saving priority and the energy-saving degree corresponding to each candidate cleaning mode, a second target value corresponding to each candidate cleaning mode is determined; Based on the water-saving priority and the water cost corresponding to each candidate cleaning mode, a third target value corresponding to each candidate cleaning mode is determined. The first target value, the second target value, and the third target value are fused together to obtain the target cleaning value corresponding to each candidate cleaning mode.

9. The refrigerator control method according to claim 8, characterized in that, Determining the target cleaning mode corresponding to the target ingredient based on the target cleaning value includes: The candidate cleaning mode corresponding to the largest target cleaning value among the target cleaning values ​​corresponding to each candidate cleaning mode is determined as the target cleaning mode.

10. A refrigerator, characterized in that, The refrigerator includes a controller for performing the method as described in any one of claims 1-9.

Images