Refrigerator control method and device, electronic equipment and storage medium
By acquiring multimodal sensing data from the refrigerator, a target sterilization strategy is determined, and the combined use of adsorption, photocatalysis, and electrocatalysis units is controlled. This solves the problem that existing refrigerator sterilization modules cannot adaptively sterilize, achieving efficient sterilization and preservation functions.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-01-05
- Publication Date
- 2026-04-03
AI Technical Summary
Existing refrigerator sterilization modules typically operate by turning on according to a preset cycle or manually, which can lead to insufficient or excessive sterilization and an inability to adapt sterilization to the conditions inside the refrigerator.
By acquiring multimodal sensing data from the refrigerator, including image data, odor data, temperature data, and door status data, the target sterilization strategy is determined, and the corresponding sterilization modules and operating strategies are controlled, including the combined use of adsorption units, photocatalytic units, and electrocatalytic units, to achieve adaptive sterilization.
It enables matching sterilization strategies according to the degree of contamination in the refrigerator, avoiding insufficient or excessive sterilization, improving the adaptability and efficiency of sterilization, delaying the ripening and spoilage process of fruits and vegetables, and achieving active preservation.
Smart Images
Figure CN121782811A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of refrigerator technology, and particularly relates to a refrigerator control method, control device, electronic device and storage medium. Background Technology
[0002] With the development of science and technology, some refrigerators are now equipped with sterilization modules to sterilize and disinfect the refrigerator. However, the existing sterilization modules usually operate according to a preset cycle or are manually turned on, which can lead to insufficient or excessive sterilization and cannot sterilize according to the conditions inside the refrigerator. Summary of the Invention
[0003] This application provides a refrigerator control method, control device, electronic device, and storage medium to solve the problem that existing refrigerator sterilization modules are usually turned on according to a preset cycle or manually, resulting in insufficient or excessive sterilization.
[0004] This application provides a refrigerator control method, the method comprising: Acquire multimodal sensing data of the refrigerator; The target sterilization strategy is determined based on the multimodal sensing data; The refrigerator is sterilized according to the target sterilization strategy; The target sterilization strategy is one of a set of preset sterilization strategies, and the sterilization intensity of the preset sterilization strategies is different.
[0005] Optionally, controlling the refrigerator sterilization according to the target sterilization strategy includes: The target sterilization module and target operation strategy are determined based on the target sterilization strategy. Control the target sterilization module to operate according to the target operating strategy; The target sterilization module includes one or more of an adsorption unit, a photocatalytic unit, and an electrocatalytic unit. The adsorption unit includes a carrier and metal ions disposed on the carrier. The photocatalytic unit includes a light emitter and a photocatalyst. The light emitter emits light to excite the photocatalyst to generate sterilizing ions. The electrocatalytic unit includes a negative ion generator and an ozone generator.
[0006] Optionally, the target sterilization strategy includes a passive sterilization strategy, a first active sterilization strategy, a second active sterilization strategy, and a third active sterilization strategy; The step of determining the target sterilization module and target operation strategy based on the target sterilization strategy includes: If the target sterilization strategy is the passive sterilization strategy, then the target sterilization module is determined to include the adsorption unit, and the target operation strategy is determined to include controlling the carrier exposure of the adsorption unit; If the target sterilization strategy is the first active sterilization strategy, then the target sterilization module is determined to include the adsorption unit, the photocatalytic unit and the negative ion generator, and the target operation strategy is determined to include controlling the carrier of the adsorption unit to be exposed, controlling the photocatalytic unit to operate according to the first on-off ratio and controlling the negative ion generator to be turned on. If the target sterilization strategy is the second active sterilization strategy, then the target sterilization module is determined to include the adsorption unit, the photocatalytic unit and the ozone generator, and the target operation strategy is determined to include controlling the carrier of the adsorption unit to be exposed, controlling the photocatalytic unit to operate according to the second on-off ratio, and controlling the ozone generator to operate according to the first power, wherein the second on-off ratio is greater than the first on-off ratio; If the target sterilization strategy is the third active sterilization strategy, then the target sterilization module is determined to include the adsorption unit, the photocatalytic unit, and the ozone generator. The target operation strategy is determined to include controlling the carrier of the adsorption unit to be exposed, controlling the photocatalytic unit to be turned on for a first preset time, and controlling the ozone generator to operate at a second power, wherein the second power is greater than the first power.
[0007] Optionally, the multimodal sensing data includes one or more of image data, odor data, temperature data, humidity data, and door status data; the method further includes: Based on the image data analysis, deterioration data is included, which comprises mold data, discoloration data, and deformation data. Based on the odor data, preset gas concentration data is analyzed, wherein the preset gas includes one or more of total volatile organic compounds, ethylene, and hydrogen sulfide; Based on the door status data, analyze the door opening frequency data and opening duration data; The deterioration data, the preset gas concentration data, the door opening frequency data, the opening duration data, the temperature data, and the humidity data are determined as multiple target data. The step of determining the target sterilization strategy based on the multimodal sensing data includes: The target sterilization strategy is determined based on the multiple target data.
[0008] Optionally, determining the target sterilization strategy based on the plurality of target data includes: The multiple target data are normalized separately to obtain multiple normalized data. The pollution index is obtained by weighting the multiple normalized data according to preset dynamic weights. The target sterilization strategy is determined from the preset multiple sterilization strategies based on the pollution index.
[0009] Optionally, the preset dynamic weights include preset weight reorganization and adjusted weight reorganization; The weighting process of the multiple normalized data according to preset dynamic weights includes: When all the normalized data are within a preset range, the normalized data are weighted according to the preset weighting. When some normalized data exceeds the preset range, the multiple normalized data are weighted according to the adjustment weight reorganization. Among them, the odor data has the largest weight in the preset weighted recombination, and the normalized data that exceeds the preset range has the largest weight in the adjusted weighted recombination.
[0010] Optionally, it also includes: Based on the image data analysis, determine whether there is any new storage; If the newly added storage item exists, the refrigerator is controlled to sterilize for a second preset time according to the first active sterilization strategy.
[0011] This application embodiment also provides a refrigerator control device, the device comprising: The multimodal sensing data acquisition module is configured to acquire multimodal sensing data of the refrigerator; The analysis module is configured to determine the target sterilization strategy based on the multimodal sensing data; The control module is configured to control the refrigerator to sterilize according to the target sterilization strategy; The target sterilization strategy is one of a set of preset sterilization strategies, and the sterilization intensity of the preset sterilization strategies is different.
[0012] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the refrigerator control method described above.
[0013] This application embodiment also provides a storage medium storing control instructions, which, when executed by a processor, implement the refrigerator control method described above.
[0014] The refrigerator control method provided in this application determines the corresponding target sterilization strategy from a variety of preset sterilization strategies with different sterilization intensities based on the refrigerator's multimodal sensing data, i.e., uniformity data, so that the current strategy matches the degree of contamination of the refrigerator, and avoids the problems of insufficient or excessive sterilization while meeting the sterilization requirements of the current refrigerator environment. Attached Figure Description
[0015] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.
[0016] To gain a more complete understanding of this application and its beneficial effects, the following description will be provided in conjunction with the accompanying drawings. In the following description, the same reference numerals denote the same parts.
[0017] Figure 1 This is a first flowchart illustrating the refrigerator control method provided in an embodiment of this application.
[0018] Figure 2 This is a second flowchart illustrating the refrigerator control method provided in an embodiment of this application.
[0019] Figure 3 This is a schematic diagram of the control device for a refrigerator provided in an embodiment of this application.
[0020] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.
[0021] Figure 5 This is a schematic diagram of the structure of a refrigerator provided in an embodiment of this application.
[0022] Explanation of reference numerals in the attached figures: 201. Multimodal sensing data acquisition module; 202. Analysis module; 203. Control module; 300. Electronic device; 301. Memory; 3011. Computer program; 302. Processor. Detailed Implementation
[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. 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.
[0024] In the description of the embodiments of this application, "module" and "processor" can include hardware, software, or a combination of both. A module can include hardware circuitry, various suitable sensors, communication ports, and memory, and may also include software components, such as program code, or a combination of software and hardware. A processor can be a central processing unit, a microprocessor, a digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor can be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media includes any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc.
[0025] This application provides a refrigerator control method, control device, electronic device, and storage medium to solve the problem that existing refrigerator sterilization modules are usually turned on according to a preset cycle or manually, resulting in insufficient or excessive sterilization. The following description is in conjunction with the accompanying drawings.
[0026] The refrigerator control method provided in this application embodiment is described in detail below. Figure 1 The method includes the following steps: S101: Acquire multimodal sensing data of the refrigerator.
[0027] The multimodal sensing data of the refrigerator refers to its operational data, including but not limited to one or more of the following: image data, odor data, temperature data, humidity data, and door status data. For example, image data can be acquired through an image sensor, which captures visual information about food inside the refrigerator and uses image recognition technology to determine the type, quantity, and freshness of the food (e.g., by color or mold spots). Odor data can be acquired through an odor sensor to detect the concentration of volatile organic compounds, hydrogen sulfide, ammonia, and ethylene gases inside the refrigerator, quantifying air quality. Temperature data can be acquired through a temperature sensor, humidity data through a humidity sensor, and door status data through a door open / close sensor.
[0028] For example, the multimodal sensing data of the refrigerator can be acquired in real time, or at preset intervals, or when specific trigger conditions are met, such as when a certain data exceeds a safety threshold or an abnormal pattern is detected (such as excessive frost).
[0029] S102: Determine the target sterilization strategy based on multimodal sensing data. The target sterilization strategy is one of several preset sterilization strategies, each with different sterilization intensities. In other words, based on the multimodal sensing data, a strategy matching the current sterilization requirements is determined from the preset sterilization strategies; this is the target sterilization strategy.
[0030] S103: Control refrigerator sterilization according to the target sterilization strategy.
[0031] The refrigerator control method provided in this application determines the corresponding target sterilization strategy from a variety of preset sterilization strategies with different sterilization intensities based on the refrigerator's multimodal sensing data, i.e., uniformity data, so that the current strategy matches the degree of contamination of the refrigerator, and avoids the problems of insufficient or excessive sterilization while meeting the sterilization requirements of the current refrigerator environment.
[0032] Optionally, controlling refrigerator sterilization according to the target sterilization strategy includes: determining the target sterilization module and the target operating strategy based on the target sterilization strategy; controlling the target sterilization module to operate according to the target operating strategy; please refer to Figure 2 The target sterilization module includes one or more of an adsorption unit, a photocatalytic unit, and an electrocatalytic unit. The adsorption unit includes a carrier and metal ions disposed on the carrier. The photocatalytic unit includes a light emitter and a photocatalyst. The light emitter emits light to excite the photocatalyst to generate sterilizing ions. The electrocatalytic unit includes a negative ion generator and an ozone generator.
[0033] The adsorption unit can be supported by honeycomb ceramic, and the metal ions can be Ag. + or Zn² + This allows for the sustained inhibition of microbial activity and the decomposition of organic gases through physical adsorption and chemical catalysis. Specifically, the adsorption unit can use honeycomb ceramics or activated carbon-molecular sieve composite materials as a carrier, loading nano-silver and zinc ions through impregnation, and installing them in the air ducts of cold storage and variable temperature rooms as a background purification unit, operating continuously year-round. Its main function is to continuously adsorb and decompose trace amounts of odors and ethylene, and provide a basic antibacterial surface.
[0034] Photocatalysts emit ultraviolet light, and the photocatalyst can be TiO2, which generates highly oxidizing hydroxyl radicals and superoxide anions, capable of indiscriminately decomposing organic matter and killing microorganisms. Specifically, the photocatalytic unit can be a TiO2 photocatalytic layer coated on the inner wall of the air duct and the surface of the storage shelf, with a low-power UVC LED array configured next to it. The UVC LEDs are only turned on by system commands to excite the photocatalytic reaction. Simultaneously, the photocatalytic unit can also include independently controlled UVC LED strips, which provide short-term, timed direct irradiation sterilization to the top space after the refrigerator door is closed, treating airborne bacteria brought in from the outside.
[0035] The electrocatalytic unit ionizes air using a high-voltage electric field, generating various active particles such as ozone, positive and negative ions. These particles diffuse throughout the space, achieving comprehensive gas-phase sterilization and odor decomposition. Specifically, the electrocatalytic unit can be a miniaturized ionization module powered by a DC high-voltage power supply, also installed within the air duct, producing low concentrations of ozone and positive and negative ions. Its power is adjustable to achieve different modes, from "negative ion freshening" to "powerful ozone sterilization."
[0036] The sterilization module comprises multiple modules. Based on the target sterilization strategy with corresponding sterilization intensity, a specific target sterilization module and its corresponding operating strategy can be selected from these modules to achieve the desired sterilization effect, thus realizing adaptive sterilization. Simultaneously, the sterilization module also decomposes ethylene and odor gases, effectively delaying the ripening and spoilage process of fruits and vegetables, achieving active preservation.
[0037] Optionally, the target sterilization strategy includes a passive sterilization strategy, a first active sterilization strategy, a second active sterilization strategy, and a third active sterilization strategy; determining the target sterilization module and the target operating strategy based on the target sterilization strategy includes the following steps: If the target sterilization strategy is a passive sterilization strategy, then the target sterilization module includes an adsorption unit, and the target operating strategy includes controlling the exposure of the carrier of the adsorption unit. That is, the adsorption unit can be in a normally open state, and the refrigerator can achieve a certain degree of passive sterilization through the adsorption unit without any operation, resulting in no energy consumption and low cost.
[0038] If the target sterilization strategy is the first active sterilization strategy, then the target sterilization module includes an adsorption unit, a photocatalytic unit, and a negative ion generator. The target operating strategy includes controlling the exposure of the carrier in the adsorption unit, controlling the photocatalytic unit to operate according to a first on-off ratio, and controlling the negative ion generator to turn on. It can be understood that the sterilization intensity of the first active sterilization strategy is higher than that of the passive sterilization strategy. The negative ion generator, when turned on, produces positive and negative ions, which can diffuse throughout the space, achieving comprehensive gas-phase sterilization and odor decomposition. The photocatalytic unit operates according to the first on-off ratio, meaning it is intermittently turned on according to the first on-off ratio to achieve the sterilization requirements, without needing to be continuously turned on, thus saving energy.
[0039] If the target sterilization strategy is the second active sterilization strategy, then the target sterilization module includes an adsorption unit, a photocatalytic unit, and an ozone generator. The target operating strategy includes controlling the carrier exposure of the adsorption unit, controlling the photocatalytic unit to operate at a second on-off ratio, and controlling the ozone generator to operate at a first power level. The second on-off ratio is greater than the first on-off ratio. It can be understood that a greater second on-off ratio means the photocatalytic unit is on for a longer period, thus generating more highly oxidizing hydroxyl radicals and superoxide anions, resulting in a stronger sterilization effect. Furthermore, the ozone generated by the ozone generator has a stronger sterilization effect than positive and negative ions; therefore, the sterilization intensity of the second active sterilization strategy is higher than that of the first active sterilization strategy.
[0040] If the target sterilization strategy is the third active sterilization strategy, then the target sterilization module includes an adsorption unit, a photocatalytic unit, and an ozone generator. The target operating strategy includes controlling the exposure of the carrier in the adsorption unit, controlling the photocatalytic unit to operate for a first preset duration, and controlling the ozone generator to operate at a second power, which is greater than the first power. In this case, the photocatalytic unit is continuously activated for the first preset duration, working without interruption. Therefore, more highly oxidizing hydroxyl radicals and superoxide anions are excited, resulting in a stronger sterilization effect. Furthermore, since the ozone generator's power is higher than the first power, the sterilization intensity of the third active sterilization strategy is higher than that of the second active sterilization strategy.
[0041] It should be noted that after the refrigerator's ozone generator is turned on and sterilization begins, the door's open / closed status needs to be checked. If the door is detected to be open, the ozone generator should be immediately turned off to prevent the generated ozone particles from entering the room and polluting the indoor air. Preferably, when the door is detected to be open, if the ozone concentration inside the refrigerator reaches 0.15 ppm, the ozone generator should be turned off.
[0042] Similarly, if the refrigerator turns on the independently controlled UVC LED light strip of the photocatalytic unit, it also needs to detect the opening and closing status of the door. If the door is detected to be open, the UVC LED light strip should be turned off immediately to prevent ultraviolet leakage from affecting human health.
[0043] Optionally, the photocatalytic unit or the electrocatalytic unit can both adopt a low-power design and be powered by the refrigerator's standard 12V power supply. No additional high-voltage components are required, the cost is controllable, and overall energy saving is achieved.
[0044] Optionally, the multimodal sensing data includes one or more of image data, odor data, temperature data, humidity data, and door status data; the method further includes: analyzing deterioration data based on image data, whereby the deterioration data includes mold data, discoloration data, and deformation data; analyzing preset gas concentration data based on odor data, whereby the preset gases include one or more of total volatile organic compound concentration, ethylene, and hydrogen sulfide; analyzing door opening frequency data and opening duration data based on door status data; identifying the deterioration data, preset gas concentration data, door opening frequency data, opening duration data, temperature data, and humidity data as multiple target data; and determining a target sterilization strategy based on the multimodal sensing data, including: determining a target sterilization strategy based on multiple target data.
[0045] This involves analyzing multimodal sensing data separately to obtain multiple target data that can measure the current level of pollution in the refrigerator, removing invalid data, reducing noise, and improving the accuracy of the analysis.
[0046] For example, analyzing deterioration data based on image data, where the deterioration data includes mold data, discoloration data, and deformation data, may include: Data acquisition: Deploy multispectral or high-resolution RGB cameras inside the refrigerator (each compartment and door shelf) and use supplementary lighting to ensure uniform illumination.
[0047] Image preprocessing: orthogonalization, size uniformity, contrast enhancement, and food segmentation (separating it from the refrigerator wall and container).
[0048] Multi-dimensional deterioration feature extraction and identification: Mold Data Identification: Features: Identifying cotton-like, speckled, and velvety textures; common colors are white, green, black, and blue. Methods: Using texture analysis algorithms (such as Local Binary Pattern (LBP) and Gray-Level Co-occurrence Matrix (GLCM)) combined with color space analysis (separating mold spots in HSV / La*b* space). Deep learning can be used, employing segmentation networks such as U-Net for pixel-level mold region segmentation.
[0049] Discoloration Data Recognition: Characteristics: The surface color of food deviates from its freshness (e.g., leafy greens turn yellow, meat turns brown, and fruits develop black spots). Method: Establish a reference color model (color histogram of the fresh state or La*b* value range), and quantify the degree of discoloration by comparing color histograms and calculating color difference (e.g., ΔE*ab). Deep learning methods can train a classification or regression network to directly output the discoloration level or freshness score.
[0050] Deformation data identification: Features: shrunken, wilted, and shriveled fruits and vegetables; solidification or separation of liquid foods; bulging of packaging (gas production and spoilage). Methods: Contour analysis (comparing changes in perimeter, area, and roundness with a standard contour), 3D reconstruction (obtaining depth information through multi-view or structured light to analyze volume shrinkage), or using optical flow to detect dynamic changes in surface wrinkles and textures.
[0051] For example, analyzing preset gas concentration data based on odor data, where the preset gas includes one or more of total volatile organic compounds, ethylene, and hydrogen sulfide, may include the following steps: Sensor nodes are deployed in the refrigerator compartment, fruit and vegetable compartment, and freezer compartment to monitor the gas environment in different areas. Dynamic features such as steady-state values, response slopes, recovery slopes, and integral areas are extracted from the sensor response curves, rather than just instantaneous concentration values, to obtain gas concentration data.
[0052] Total volatile organic compounds (TVOCs) primarily originate from microbial metabolism, lipid oxidation, fruit and vegetable respiration, and release from plastic packaging. TVOCs are a comprehensive spoilage indicator, reflecting the overall degree of organic matter decomposition; abnormally high levels indicate severe spoilage or cross-contamination. Ethylene primarily originates from ripening hormones released by fruits and vegetables (especially apples, bananas, and tomatoes). Ethylene is an indicator of senescence and overripeness in fruits and vegetables: high concentrations of ethylene accelerate the ripening and spoilage process of other fruits and vegetables. Hydrogen sulfide primarily originates from the spoilage of sulfur-containing proteins (meat, eggs, and dairy products) and the metabolism of certain bacteria (such as Shewanella putrefactive bacteria). Hydrogen sulfide is a specific indicator of protein spoilage: it has extremely strong indicative significance; even very low concentrations (ppb level) indicate severe spoilage of high-protein foods such as meat and seafood. By monitoring the concentrations of TVOCs, ethylene, and hydrogen sulfide, multi-faceted monitoring of stored goods can be achieved, further improving the accuracy of data sources.
[0053] For example, analyzing door opening frequency and duration data based on door status data includes the following steps: installing a reed switch / Hall sensor to detect the opening / closing status; the sensor generates a real-time "timestamp-door status" event stream; preprocessing the event stream (de-jittering, event pairing, and invalid event filtering); opening frequency analysis: identifying peak usage periods throughout the day (e.g., breakfast, lunch, and dinner preparation times) through statistical analysis (e.g., hourly aggregation); and opening duration analysis: statistically analyzing "long-open" events exceeding a reasonable threshold (e.g., 30 seconds) and their occurrence times.
[0054] Optionally, determining a target sterilization strategy based on multiple target data includes: normalizing the multiple target data separately to obtain multiple normalized data; weighting the multiple normalized data according to preset dynamic weights to obtain a contamination index; and determining the target sterilization strategy from a variety of preset sterilization strategies based on the contamination index.
[0055] By normalizing multiple target data separately, sensor data with different dimensions and numerical ranges (such as TVOC concentration (ppm), mold area ratio (%), and door opening time (seconds)) are uniformly mapped to the same scale (such as the [0,1] interval), eliminating dimensional differences and enhancing model stability. Multiple normalized data are weighted according to preset dynamic weights, assigning appropriate weights to each pollution indicator based on its importance, real-time performance, and impact on health, calculating a comprehensive and quantitative pollution score. This enables multi-dimensional comprehensive pollution evaluation, outputting a clear quantitative indicator, the pollution index. The target sterilization strategy is then determined based on the pollution index, simplifying the selection criteria by using only a single value, significantly reducing computational load. Furthermore, the pollution index is a single, intuitive number, facilitating system-level decision-making and allowing users to understand the severity of current environmental pollution (e.g., "Pollution Index: 65 / 100").
[0056] This section does not further limit the specific method of normalization. For example, it can use min-max normalization (which maps the minimum and maximum values of the original data to the two ends of the target interval through linear scaling), Z-Score standardization (which converts the data into a standard normal distribution with a mean of 0 and a standard deviation of 1 (approximately)), robust standardization (which uses the median instead of the mean and the interquartile range instead of the standard deviation. The median and IQR are not sensitive to outliers), etc.
[0057] Optionally, the preset dynamic weights include preset weight reorganization and adjusted weight reorganization; weighting multiple normalized data according to the preset dynamic weights includes: when multiple normalized data are all within a preset range, weighting multiple normalized data according to the preset weight reorganization; when some normalized data exceed the preset range, weighting multiple normalized data according to the adjusted weight reorganization; wherein, the odor data has the largest weight in the preset weight reorganization, and the part of normalized data exceeding the preset range has the largest weight in the adjusted weight reorganization.
[0058] This includes two weighting strategies, which are intelligently switched based on the data status. When all sensor data are within the normal range, it is suitable for the "normal monitoring" mode, where the system defaults to giving the highest weight to odor data (such as TVOC and ethylene). When any or some sensor data exceed the preset normal range, the system immediately switches the weighting strategy to the "abnormal alarm" mode, which increases the weight of abnormal indicators to the maximum.
[0059] Since biochemical reactions and microbial metabolism typically precede physical changes, assigning the highest sensitivity to odor data allows the system to detect potential spoilage trends before they are visually apparent or perceived by the user, thus preventing problems before they occur. However, some foods may be exceptions, where other indicators might exceed safety thresholds (i.e., preset ranges) first. Therefore, if any or some sensor data exceeds the preset normal range, the weight of the abnormal indicator is increased to the maximum. By maximizing the weight of important data, faults are amplified and observed to maintain the system's high sensitivity.
[0060] Optionally, it also includes: analyzing image data to determine if there are any new storage items; if there are new storage items, controlling the refrigerator to sterilize for a second preset time according to the first active sterilization strategy.
[0061] It is understandable that when new storage items are placed in the refrigerator, airborne bacteria or odors may be introduced at the same time. Therefore, when new storage items are detected, the refrigerator is directly controlled to sterilize according to the first active sterilization strategy for the second preset time, so as to inhibit the growth of bacteria at the first time and prevent it in advance.
[0062] It should be noted that if new storage items are detected, but the refrigerator is currently using the second or third active sterilization strategy, there is no need to change the refrigerator's sterilization strategy; simply continue using the current strategy.
[0063] As an alternative implementation, a target sterilization strategy can be directly selected based on multiple target data, without needing to calculate the pollution index. For example, when the TVOC concentration is below a first concentration and there is no spoilage data, the refrigerator is controlled to execute a passive sterilization strategy; when the TVOC concentration is greater than or equal to the first concentration but lower than the second concentration, and the door is detected to have been opened once, the refrigerator is controlled to execute a first active sterilization strategy; when the ethylene concentration is greater than a third concentration, or when image data analysis indicates that the stored items contain a large amount of fruits and vegetables, the refrigerator is controlled to execute a second active sterilization strategy; when the TVOC concentration is greater than a fourth concentration and the proportion of mold in the spoilage data is greater than a preset ratio, the refrigerator is controlled to execute a third active sterilization strategy.
[0064] This application also provides a refrigerator control device; please refer to [link / reference]. Figure 3 The device includes a multimodal sensing data acquisition module 201, an analysis module 202, and a control module 203. The multimodal sensing data acquisition module 201 is configured to acquire multimodal sensing data from the refrigerator; the analysis module 202 is configured to determine a target sterilization strategy based on the multimodal sensing data; and the control module 203 is configured to control the refrigerator to sterilize according to the target sterilization strategy. The target sterilization strategy is one of several preset sterilization strategies, each with different sterilization intensities.
[0065] This constructs a complete "closed-loop control" system. The perception layer (odor and image sensors) collects operational data, the decision-making layer (AI controller) performs fusion analysis and assesses risks, and the execution layer (adsorption unit, photocatalytic unit, and electrocatalytic unit) receives instructions and coordinates actions. This is an intelligent sterilization system with feedback and adaptive capabilities, achieving adaptive sterilization and avoiding insufficient or excessive sterilization.
[0066] This application also provides an electronic device 300, please refer to... Figure 4 The system includes a memory 301, a processor 302, and a computer program 3011 stored in the memory 301 and executable on the processor 302. When the processor 302 executes the computer program 3011, it implements the refrigerator control method described above. The method includes the following steps: S101: Acquire multimodal sensing data of the refrigerator. S102: Determine a target sterilization strategy based on the multimodal sensing data. S103: Control the refrigerator to sterilize according to the target sterilization strategy.
[0067] This application embodiment also provides a storage medium storing control instructions. When the control instructions are executed by a processor, they implement the refrigerator control method described above. The method includes the following steps: S101: Acquire multimodal sensing data of the refrigerator. S102: Determine a target sterilization strategy based on the multimodal sensing data. S103: Control the refrigerator to sterilize according to the target sterilization strategy.
[0068] This application embodiment also provides a refrigerator, which includes a controller configured to execute the refrigerator control method described above. The method includes the following steps: S101: Acquiring multimodal sensing data of the refrigerator. S102: Determining a target sterilization strategy based on the multimodal sensing data. S103: Controlling the refrigerator to sterilize according to the target sterilization strategy. The refrigerator structure can be found in the attached document. Figure 5 .
[0069] For example, a computer program can be divided into one or more modules / units, which are stored in memory and executed by a processor to perform the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in an electronic device.
[0070] Electronic devices can be desktop computers, laptops, handheld computers, and cloud servers, among other electronic devices. Electronic devices may include, but are not limited to, processors and memory. For example, electronic devices may also include input / output devices, network access devices, buses, etc.
[0071] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.
[0072] In the embodiments provided by this invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. Multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.
[0073] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units.
[0074] If integrated modules / units are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program may include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. Computer-readable media may include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.
[0075] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.
[0076] In the description of this application, 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, features defined with "first" and "second" may explicitly or implicitly include one or more features.
[0077] The control method, control device, electronic device, and storage medium for a refrigerator provided in the embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. A method for controlling a refrigerator, characterized in that, The method includes: Acquire multimodal sensing data of the refrigerator; The target sterilization strategy is determined based on the multimodal sensing data; The refrigerator is sterilized according to the target sterilization strategy; The target sterilization strategy is one of a set of preset sterilization strategies, and the sterilization intensity of the preset sterilization strategies is different.
2. The refrigerator control method according to claim 1, characterized in that, The step of controlling the refrigerator sterilization according to the target sterilization strategy includes: The target sterilization module and target operation strategy are determined based on the target sterilization strategy. Control the target sterilization module to operate according to the target operating strategy; The target sterilization module includes one or more of an adsorption unit, a photocatalytic unit, and an electrocatalytic unit. The adsorption unit includes a carrier and metal ions disposed on the carrier. The photocatalytic unit includes a light emitter and a photocatalyst. The light emitter emits light to excite the photocatalyst to generate sterilizing ions. The electrocatalytic unit includes a negative ion generator and an ozone generator.
3. The refrigerator control method according to claim 2, characterized in that, The target sterilization strategy includes a passive sterilization strategy, a first active sterilization strategy, a second active sterilization strategy, and a third active sterilization strategy; The step of determining the target sterilization module and target operation strategy based on the target sterilization strategy includes: If the target sterilization strategy is the passive sterilization strategy, then the target sterilization module is determined to include the adsorption unit, and the target operation strategy is determined to include controlling the carrier exposure of the adsorption unit; If the target sterilization strategy is the first active sterilization strategy, then the target sterilization module is determined to include the adsorption unit, the photocatalytic unit and the negative ion generator, and the target operation strategy is determined to include controlling the carrier of the adsorption unit to be exposed, controlling the photocatalytic unit to operate according to the first on-off ratio and controlling the negative ion generator to be turned on. If the target sterilization strategy is the second active sterilization strategy, then the target sterilization module is determined to include the adsorption unit, the photocatalytic unit and the ozone generator, and the target operation strategy is determined to include controlling the carrier of the adsorption unit to be exposed, controlling the photocatalytic unit to operate according to the second on-off ratio, and controlling the ozone generator to operate according to the first power, wherein the second on-off ratio is greater than the first on-off ratio; If the target sterilization strategy is the third active sterilization strategy, then the target sterilization module is determined to include the adsorption unit, the photocatalytic unit, and the ozone generator. The target operation strategy is determined to include controlling the carrier of the adsorption unit to be exposed, controlling the photocatalytic unit to be turned on for a first preset time, and controlling the ozone generator to operate at a second power, wherein the second power is greater than the first power.
4. The refrigerator control method according to claim 1, characterized in that, The multimodal sensing data includes one or more of image data, odor data, temperature data, humidity data, and door status data; the method further includes: Based on the image data analysis, deterioration data is included, which comprises mold data, discoloration data, and deformation data. Based on the odor data, preset gas concentration data is analyzed, wherein the preset gas includes one or more of total volatile organic compounds, ethylene, and hydrogen sulfide; Based on the door status data, analyze the door opening frequency data and opening duration data; The deterioration data, the preset gas concentration data, the door opening frequency data, the opening duration data, the temperature data, and the humidity data are determined as multiple target data. The step of determining the target sterilization strategy based on the multimodal sensing data includes: The target sterilization strategy is determined based on the multiple target data.
5. The refrigerator control method according to claim 4, characterized in that, The step of determining the target sterilization strategy based on the multiple target data includes: The multiple target data are normalized separately to obtain multiple normalized data. The pollution index is obtained by weighting the multiple normalized data according to preset dynamic weights. The target sterilization strategy is determined from the preset multiple sterilization strategies based on the pollution index.
6. The refrigerator control method according to claim 5, characterized in that, The preset dynamic weights include preset weight reorganization and adjustment weight reorganization; The weighting process of the multiple normalized data according to preset dynamic weights includes: When all the normalized data are within a preset range, the normalized data are weighted according to the preset weighting. When some normalized data exceeds the preset range, the multiple normalized data are weighted according to the adjustment weight reorganization. Among them, the odor data has the largest weight in the preset weighted recombination, and the normalized data that exceeds the preset range has the largest weight in the adjusted weighted recombination.
7. The refrigerator control method according to claim 1, characterized in that, Also includes: Based on image data analysis, is there any new storage? If the newly added storage item exists, the refrigerator is controlled to sterilize for a second preset time according to the first active sterilization strategy.
8. A control device for a refrigerator, characterized in that, The device includes: The multimodal sensing data acquisition module is configured to acquire multimodal sensing data of the refrigerator; The analysis module is configured to determine the target sterilization strategy based on the multimodal sensing data; The control module is configured to control the refrigerator to sterilize according to the target sterilization strategy; The target sterilization strategy is one of a set of preset sterilization strategies, and the sterilization intensity of the preset sterilization strategies is different.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the refrigerator control method as described in any one of claims 1-7.
10. A storage medium, characterized in that, The storage medium stores control instructions, which, when executed by a processor, implement the refrigerator control method as described in any one of claims 1-7.