Refrigerator control method and device, refrigerator equipment and storage medium

Abstract

The invention relates to a refrigerator control method and device, refrigerator equipment and a storage medium. The method comprises the following steps: acquiring multi-dimensional detection data, generating a corresponding freshness score for the detection data of each dimension, and fusing the multi-dimensional freshness scores to generate a total freshness score, so that compared with single sensor data, the reliability of a freshness identification result can be improved, and the accuracy of the freshness identification result is improved. And the operation mode of the refrigerator is regulated and controlled based on the total freshness score, so that the combination of the freshness detection result and the fresh-keeping control means is realized, and the problems that a method for combining the freshness detection result and the fresh-keeping control means is lacked in the prior art, and the requirement for real-time and reliable monitoring of the freshness of food materials is difficult to meet are solved.

Description

Technical Field

[0001] This application relates to the field of refrigerator control, and more particularly to a refrigerator control method, device, refrigerator equipment, and storage medium. Background Technology

[0002] With food waste and food safety issues becoming increasingly prominent, refrigerator food freshness detection technology has become an important development direction for the smart home appliance industry. Current mainstream technologies mostly rely on single-sensor solutions. These solutions fail to consider the different dimensions of characteristics exhibited when the freshness of different foods changes, and lack methods to combine freshness detection results with preservation control measures. In general, existing solutions are insufficient to meet the need for real-time and reliable monitoring of food freshness. Summary of the Invention

[0003] This application provides a refrigerator control method, device, refrigerator equipment, and storage medium to solve the problem that the prior art lacks a method to combine freshness detection results with preservation control measures, making it difficult to meet the need for real-time and reliable monitoring of food freshness.

[0004] In a first aspect, this application provides a refrigerator control method, the method comprising: Acquire multi-source acquisition data of the refrigerator during the current acquisition period, wherein the multi-source acquisition data includes detection data from multiple dimensions; Based on the detection data from different dimensions, freshness scores corresponding to different dimensions are generated. A total freshness score is generated based on the freshness scores corresponding to different dimensions; The target control mode of the refrigerator is determined based on the overall freshness score. The refrigerator is controlled according to the target control mode.

[0005] Optionally, generating freshness scores corresponding to different dimensions based on the detection data of different dimensions includes: Based on spectral detection data, weight detection data, and odor detection data, a first freshness score corresponding to the spectral dimension, a second freshness score corresponding to the weight dimension, and a third freshness score corresponding to the odor dimension are generated.

[0006] Optionally, based on the spectral detection data, a first freshness score corresponding to the spectral dimension is generated, including: Based on the matching results between the spectral detection data and the reference spectral data corresponding to different ingredients in the database, the target ingredient type corresponding to the spectral detection data and the condensation identification result on the surface of the ingredient are determined. Based on the matching results between the spectral curves corresponding to the spectral detection data and the spectral curves of the target food ingredients at different freshness levels, the first freshness score corresponding to the spectral dimension is determined.

[0007] Optionally, based on the weight detection data, a second freshness score corresponding to the weight dimension is generated, including: The weight detection data is calibrated using the condensation recognition results to obtain the calibrated current detection weight. Get the weight of the previous detection within the previous collection cycle; When the current detected weight is greater than the previous detected weight, the first freshness score is used as the second freshness score; When the current detected weight is less than or equal to the previous detected weight, a second freshness score corresponding to the weight dimension is generated based on the weight change rate between the current detected weight and the previous detected weight.

[0008] Optionally, generating a second freshness score corresponding to the weight dimension based on the weight change rate between the current detected weight and the previous detected weight includes: When the weight change rate is greater than or equal to a preset change rate, the first freshness score is used as the second freshness score. When the weight change rate is less than the preset change rate, the previous freshness score corresponding to the weight dimension in the previous collection period is obtained, and the corresponding score change amount is determined according to the difference between the weight change rate and the preset change rate. The second freshness score is determined according to the difference between the previous freshness score and the score change amount.

[0009] Optionally, a total freshness score is generated based on the freshness scores corresponding to different dimensions, including: Based on the first freshness score and the odor detection data, determine the weighting coefficients corresponding to different dimensions; The freshness scores for each dimension are weighted and summed based on the weight coefficients corresponding to different dimensions to generate the total freshness score.

[0010] Optionally, based on the first freshness score and the odor detection data, weighting coefficients corresponding to different dimensions are determined, including at least one of the following: When the first freshness score is greater than the first preset score, and the concentration of the target gas in the odor detection data is less than the concentration of spoilage gas, the default weight of the target food type under different dimensions is used as the weight coefficient corresponding to different dimensions. When the first freshness score is less than or equal to the first preset score, and the concentration of the target gas in the odor detection data is less than the concentration of the putrefactive gas, the default weight of the target food type in the weight dimension is used as the weight coefficient corresponding to the weight dimension, the difference between the default weight of the target food type in the spectral dimension and the first adjustment amount is used as the weight coefficient corresponding to the spectral dimension, and the sum of the default weight of the target food type in the odor dimension and the first adjustment amount is used as the weight coefficient corresponding to the odor dimension. When the first freshness score is greater than the first preset score, and the target gas concentration in the odor detection data is greater than or equal to the spoilage gas concentration, the difference between the default weight of the target ingredient weight in the spectral dimension and the second adjustment amount is used as the weight coefficient corresponding to the spectral dimension, the difference between the default weight of the target ingredient type in the weight dimension and the first adjustment amount is used as the weight coefficient corresponding to the weight dimension, and the sum of the default weight of the target ingredient type in the odor dimension and the third adjustment amount is used as the weight coefficient corresponding to the odor dimension. When the first freshness score is less than or equal to the first preset score, and the target gas concentration in the odor detection data is greater than or equal to the spoilage gas concentration, the default weight of the target ingredient weight in the spectral dimension is used as the weight coefficient corresponding to the spectral dimension, the difference between the default weight of the target ingredient type in the weight dimension and the fourth adjustment amount is used as the weight coefficient corresponding to the weight dimension, and the sum of the default weight of the target ingredient type in the odor dimension and the fourth adjustment amount is used as the weight coefficient corresponding to the odor dimension.

[0011] Optionally, based on the overall freshness score, a target control mode for the refrigerator is determined, including: When the total freshness score is less than or equal to the first total score, the odor-removing and humidity-regulating mode is used as the target control mode. The odor-removing and humidity-regulating mode is used to start the odor-removing system and adjust the storage humidity to the preset humidity, and output food spoilage information, which includes food name and spoilage status. When the total freshness score is greater than the first total score and less than or equal to the second total score, the cooling and dehumidification mode is used as the target control mode. The cooling and dehumidification mode is used to reduce the refrigeration temperature and dehumidify according to the preset temperature control variable, and output the freshness information of the ingredients, which includes the ingredient name, the total freshness score and the ingredient consumption suggestion.

[0012] Secondly, this application provides a refrigerator control device, the device comprising: The acquisition module is used to acquire multi-source acquisition data of the refrigerator during the current acquisition period, wherein the multi-source acquisition data includes detection data of multiple dimensions; The scoring module is used to generate freshness scores for different dimensions based on the detection data for different dimensions. The scoring module is also used to generate a total freshness score based on the freshness scores corresponding to different dimensions; The processing module is used to determine the target control mode of the refrigerator based on the total freshness score; A control module is used to control the refrigerator according to the target control mode.

[0013] Thirdly, this application provides a refrigerator device, wherein the storage compartment of the refrigerator device is provided with a plurality of spectral cameras, a weight sensor, an odor sensor array, and a refrigerator control device as described above.

[0014] Fourthly, this application also provides a computer storage medium storing computer-executable instructions for executing the above-described refrigerator control method.

[0015] Compared with the prior art, the technical solution provided in this application has the following advantages: The method provided in this application acquires multi-source acquisition data of the refrigerator during the current acquisition cycle, wherein the multi-source acquisition data includes detection data of multiple dimensions; generates freshness scores corresponding to different dimensions based on the detection data of different dimensions; generates a total freshness score based on the freshness scores corresponding to different dimensions; determines the target control mode of the refrigerator based on the total freshness score; and controls the refrigerator according to the target control mode.

[0016] Based on the above method, by collecting multi-dimensional detection data and generating corresponding freshness scores for each dimension, and then merging the multi-dimensional freshness scores to generate a total freshness score, the reliability of freshness identification results can be improved compared to single sensor data. Furthermore, the refrigerator's operating mode can be adjusted based on the total freshness score, thereby combining freshness detection results with preservation control measures. This solves the problem that existing technologies lack methods to combine freshness detection results with preservation control measures, making it difficult to meet the need for real-time and reliable monitoring of food freshness. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0020] Figure 1 This is a schematic diagram of the structure of a refrigerator device provided in an embodiment of this application; Figure 2 A schematic flowchart of a refrigerator control method provided in an embodiment of this application; Figure 3 A structural block diagram of a refrigerator control device provided in an embodiment of this application; Figure 4 This is a schematic diagram of the internal structure of a refrigerator device provided in an embodiment of this application. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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 some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] The following disclosure provides numerous different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of the invention. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0023] Figure 1 This is a schematic diagram of a refrigerator device in one embodiment. The refrigerator control method is applied to the refrigerator device, see reference... Figure 1 The refrigerator's storage compartment is equipped with multiple spectral cameras, a weight sensor, an odor sensor array, and a refrigerator control device.

[0024] In one embodiment, Figure 2 This is a flowchart illustrating a refrigerator control method in one embodiment, with reference to... Figure 2 A refrigerator control method is provided. This embodiment mainly illustrates the application of this method to a refrigerator control device, and the refrigerator control method specifically includes the following steps: Step S210: Obtain multi-source acquisition data of the refrigerator during the current acquisition cycle, wherein the multi-source acquisition data includes detection data of multiple dimensions.

[0025] Specifically, the duration of the data collection cycle can be customized according to application requirements, such as 10 minutes, 1 hour, 2 hours, 1 day, 1 week, etc. Multiple dimensions of detection data can include temperature, humidity, energy consumption, food composition, and equipment operating status data.

[0026] The collected detection data are stored in a buffer queue according to the sorting order of each dimension, so that the freshness score corresponding to each dimension can be calculated in the sorting order.

[0027] Step S220: Generate freshness scores corresponding to different dimensions based on the detection data of different dimensions.

[0028] Specifically, the validity of multi-source collected data is verified. The validity verification includes data integrity verification and data timeliness verification to determine whether the detection data of multiple dimensions is incomplete or the feedback time exceeds the preset time. If there is incomplete data and / or the feedback time of the detection data exceeds the preset time (indicating response timeout), the verification is determined to be unsuccessful. Conversely, if all detection data is complete and the feedback time does not exceed the preset time, the verification is determined to be successful.

[0029] After the multi-source collected data successfully passes validity verification, a freshness score is generated for each dimension based on the test data from different dimensions. This means a freshness score is obtained for each dimension of the test data alone, without considering data from other dimensions. This method of independently generating freshness scores for each dimension is highly accurate and targeted. It clearly shows the freshness status of the item in each dimension, avoiding scoring errors that may be caused by interference between data from different dimensions. For example, in food freshness testing, scoring different dimensions such as color, odor, and texture separately allows testers to quickly pinpoint the specific aspect where the food's freshness has declined, enabling more targeted treatment measures. At the same time, this method also improves testing efficiency because it allows parallel processing of data from various dimensions, significantly shortening the overall testing time.

[0030] This independent scoring mechanism is highly flexible and scalable. New detection dimensions can be easily added according to actual needs without affecting the existing scoring system. For example, based on the original dimensions such as color, odor, and texture, new dimensions such as microbial content and changes in nutritional components can be added as detection technology advances.

[0031] Step S230: Generate a total freshness score based on the freshness scores corresponding to different dimensions.

[0032] Specifically, the freshness scores corresponding to different dimensions can be further integrated and analyzed. By comprehensively considering the freshness scores corresponding to each dimension, a comprehensive overall freshness score can be obtained, providing users with more comprehensive freshness information. Specifically, the overall freshness score can be based on the sum, product, or weighted sum of the freshness scores corresponding to different dimensions. Compared to a single-dimensional freshness score, the comprehensive overall freshness score can more accurately reflect the overall freshness of food. For example, when assessing food freshness, a single dimension may only consider appearance and color, but the comprehensive score combines scores from multiple dimensions such as appearance, smell, and taste, allowing consumers to more accurately judge whether food is fresh and edible, avoiding incorrect judgments based on only one aspect.

[0033] The calculation method, which is based on the sum, product, or weighted sum of scores from different dimensions, can be flexibly adjusted according to different application scenarios and needs. For example, when evaluating the freshness of fruit, if more emphasis is placed on the two dimensions of taste and nutritional components, a weighted sum method can be used to assign higher weights to these two dimensions, making the final overall freshness score more in line with actual needs.

[0034] Furthermore, the overall freshness score facilitates data comparison and ranking. When recommending foods stored in the refrigerator, different stored foods can be sorted in descending order based on the overall freshness score, prioritizing foods with high scores to users, thus improving their eating experience and satisfaction. Alternatively, stored foods can be sorted in ascending order based on the overall freshness score, recommending products with lower scores to reduce food waste caused by spoilage.

[0035] Step S240: Determine the target control mode of the refrigerator based on the total freshness score.

[0036] Specifically, the target control mode of the refrigerator is determined based on the overall freshness score of the stored food. The target control mode is used to match the storage needs of the stored food at different freshness levels in order to extend the storage time of the stored food.

[0037] Step S250: Control the refrigerator according to the target control mode.

[0038] Specifically, the refrigerator's operating mode is adjusted based on the overall freshness score, thereby combining freshness detection results with preservation control methods. This solves the problem that existing technologies lack methods to combine freshness detection results with preservation control methods, making it difficult to meet the need for real-time and reliable monitoring of food freshness.

[0039] In one embodiment, generating freshness scores corresponding to different dimensions based on the detection data of different dimensions includes: Based on spectral detection data, weight detection data, and odor detection data, a first freshness score corresponding to the spectral dimension, a second freshness score corresponding to the weight dimension, and a third freshness score corresponding to the odor dimension are generated.

[0040] Specifically, the detection data in different dimensions include spectral detection data, weight detection data, and odor detection data. Spectral detection data includes spectral characteristics and spectral curves, which are collected by a spectral camera inside the refrigerator compartment. Weight detection data is collected by a weight sensor inside the refrigerator, and odor detection data is detected by an odor sensor inside the refrigerator. Odor detection data can be compensated for by temperature and humidity sensors.

[0041] A first freshness score is generated based on spectral detection data, a second freshness score based on weight detection data, and a third freshness score based on odor detection data. This multi-dimensional approach provides users with more comprehensive and accurate information about food freshness. The spectral features and curves captured by the spectral camera accurately reflect changes in the food's internal composition, while the weight sensor monitors weight changes due to moisture evaporation and oxidation in real time. The odor sensor sensitively detects any off-odors produced by the food. These three sensors complement each other, significantly improving the accuracy of the detection.

[0042] In one embodiment, a first freshness score corresponding to a spectral dimension is generated based on spectral detection data, including: Based on the matching results between the spectral detection data and the reference spectral data corresponding to different ingredients in the database, the target ingredient type corresponding to the spectral detection data and the condensation identification result on the surface of the ingredient are determined. Based on the matching results between the spectral curves corresponding to the spectral detection data and the spectral curves of the target food ingredients at different freshness levels, the first freshness score corresponding to the spectral dimension is determined.

[0043] Specifically, spectral matching-based detection methods significantly improve the accuracy and efficiency of food identification and freshness assessment. This is because spectral detection technology can quickly and non-destructively acquire the characteristic information of food, avoiding damage and reducing human interference. By comparing with a large database of reference spectral data, the target food type can be accurately identified, even distinguishing between different foods that look similar. For identifying condensation on food surfaces, spectral detection can detect the subtle effects of condensation on light reflection and absorption, thus promptly identifying humidity issues in the food storage environment.

[0044] In terms of freshness scoring, the spectral curves of the same type of food are different under different freshness conditions. Therefore, the current freshness of the target food type can be determined based on the matching results of the spectral curves, and then the freshness can be determined as the first freshness score. The matching of spectral curves can reflect the changes of food at the molecular level, providing a scientific and objective basis for freshness assessment and making the scoring results more reliable.

[0045] In one embodiment, a second freshness score corresponding to the weight dimension is generated based on the weight detection data, including: The weight detection data is calibrated using the condensation recognition results to obtain the calibrated current detection weight. Get the weight of the previous detection within the previous collection cycle; When the current detected weight is greater than the previous detected weight, the first freshness score is used as the second freshness score; When the current detected weight is less than or equal to the previous detected weight, a second freshness score corresponding to the weight dimension is generated based on the weight change rate between the current detected weight and the previous detected weight.

[0046] Specifically, when the condensation identification result indicates no condensation, the weight detection data is used as the current detection weight; when the condensation identification result indicates condensation, the condensation weight is calculated based on the condensation identification result, and then the current detection weight is determined based on the difference between the current detection weight and the condensation weight. The formula for calculating the condensation weight is as follows: The current detected weight is This method deducts the weight of condensation from the weight measurement data, ensuring that the weight measurement data only reflects the actual weight of the food, greatly improving the accuracy of weight measurement. It avoids weight misjudgments caused by condensation and provides a reliable basis for subsequent judgments on food storage capacity and freshness assessments based on weight data.

[0047] If the weight detected in the previous collection period is obtained The weight is zero, or the previous detected weight was not zero but the current detected weight is greater than the previous detected weight. or This indicates an increase in food storage volume. At this point, the change in food moisture content cannot be accurately reflected, therefore, food freshness cannot be directly calculated based on a single weight data point. In this case, the first freshness score calculated based on spectral data in the previous embodiment is assigned to the second freshness score to be output in the weight dimension. The first freshness score is denoted as... The second freshness rating is recorded as ,at this time When the amount of food stored increases, the first freshness score calculated based on spectral data is used as the second freshness score to be output in terms of weight. This fully utilizes the advantages of spectral data in this situation and ensures the rationality of the freshness score.

[0048] If the current detected weight is less than or equal to the previous detected weight, that is This indicates a decrease in food storage volume. The weight change rate is calculated based on the current measured weight and the previous measured weight. The weight change rate is... A second freshness score is generated based on a comparison between the weight change rate and a preset change rate. When the amount of food stored decreases, the second freshness score is generated by calculating the weight change rate and comparing it with the preset change rate, enabling a dynamic and scientific assessment of the food's freshness. This freshness assessment method based on the weight change rate considers the dynamic changes in food weight over time, making it more accurate and comprehensive than assessments based solely on weight data.

[0049] In one embodiment, generating a second freshness score corresponding to the weight dimension based on the weight change rate between the current detected weight and the previous detected weight includes: When the weight change rate is greater than or equal to a preset change rate, the first freshness score is used as the second freshness score. When the weight change rate is less than the preset change rate, the previous freshness score corresponding to the weight dimension in the previous collection period is obtained, and the corresponding score change amount is determined according to the difference between the weight change rate and the preset change rate. The second freshness score is determined according to the difference between the previous freshness score and the score change amount.

[0050] Specifically, the preset rate of change is denoted as ,like This indicates that the amount of food stored has decreased. When the amount of food stored has decreased, the weight change cannot accurately reflect the change in the moisture content of the food. Therefore, the first freshness score calculated based on spectral data in the previous embodiment is assigned to the second freshness score to be output in the weight dimension.

[0051] like If the weight is too low, it is determined to be due to moisture loss in the food, and the previous freshness score corresponds to the weight dimension in the previous collection period. The score is reduced based on the difference between the weight change rate and the preset change rate. Specifically, the score change is determined by the difference between the weight change rate and the preset change rate; that is, for every 1% difference between the weight change rate and the preset change rate, the score needs to be reduced by a specified amount. The specified score can be 1, 2, or 3 points. In this embodiment, a zero score is 2 points, meaning that for every 1% change in weight change rate relative to the preset change rate, the freshness score is reduced by 2 points from the previous score. The score change amount is... The second freshness rating at this time Then, in the next collection cycle, the second freshness score is used as the previous freshness score, and the current detection weight is used as the previous detection weight, so as to continue to identify the freshness of the stored food in the refrigerator by weight in the next collection cycle.

[0052] In one embodiment, a total freshness score is generated based on the freshness scores corresponding to different dimensions, including: Based on the first freshness score and the odor detection data, determine the weighting coefficients corresponding to different dimensions; The freshness scores for each dimension are weighted and summed based on the weight coefficients corresponding to different dimensions to generate the total freshness score.

[0053] Specifically, based on the mapping relationship between preset gas concentrations and preset freshness scores, a third freshness score corresponding to the target gas concentration in the odor detection data is determined. Since weight data alone cannot accurately reflect the freshness of spoiled food, relying solely on spectral data, a gas sensor is added primarily to detect volatile odors associated with spoilage and deterioration, enhancing the reliability of the detection results. This is combined with the first freshness score corresponding to the target gas concentration and spectral dimension for dual verification, thereby calibrating the weighting coefficients for different dimensions. Finally, the freshness scores for each dimension are weighted and summed according to their respective weighting coefficients to generate a total freshness score. The total freshness score is... .

[0054] The addition of gas sensors to detect volatile odors complements spectral data. When spectral data may contain errors or be incomplete in certain situations, gas detection data can promptly supplement and correct it, significantly enhancing the reliability of the detection results. The dual verification mechanism makes the calibration weighting coefficients more scientific and reasonable, avoiding the bias that can arise from single-dimensional data. The overall freshness score generated after a reasonable weighted summation of freshness scores from different dimensions more accurately reflects the actual freshness of the ingredients. In practical applications, this technology can significantly improve the accuracy of judging the freshness of ingredients, helping users to understand the condition of ingredients in a timely manner and reducing food safety problems caused by stale ingredients.

[0055] In one embodiment, weighting coefficients for different dimensions are determined based on the first freshness score and the odor detection data, including at least one of the following: When the first freshness score is greater than the first preset score, and the concentration of the target gas in the odor detection data is less than the concentration of spoilage gas, the default weight of the target food type under different dimensions is used as the weight coefficient corresponding to different dimensions. When the first freshness score is less than or equal to the first preset score, and the concentration of the target gas in the odor detection data is less than the concentration of the putrefactive gas, the default weight of the target food type in the weight dimension is used as the weight coefficient corresponding to the weight dimension, the difference between the default weight of the target food type in the spectral dimension and the first adjustment amount is used as the weight coefficient corresponding to the spectral dimension, and the sum of the default weight of the target food type in the odor dimension and the first adjustment amount is used as the weight coefficient corresponding to the odor dimension. When the first freshness score is greater than the first preset score, and the target gas concentration in the odor detection data is greater than or equal to the spoilage gas concentration, the difference between the default weight of the target ingredient weight in the spectral dimension and the second adjustment amount is used as the weight coefficient corresponding to the spectral dimension, the difference between the default weight of the target ingredient type in the weight dimension and the first adjustment amount is used as the weight coefficient corresponding to the weight dimension, and the sum of the default weight of the target ingredient type in the odor dimension and the third adjustment amount is used as the weight coefficient corresponding to the odor dimension. When the first freshness score is less than or equal to the first preset score, and the target gas concentration in the odor detection data is greater than or equal to the spoilage gas concentration, the default weight of the target ingredient weight in the spectral dimension is used as the weight coefficient corresponding to the spectral dimension, the difference between the default weight of the target ingredient type in the weight dimension and the fourth adjustment amount is used as the weight coefficient corresponding to the weight dimension, and the sum of the default weight of the target ingredient type in the odor dimension and the fourth adjustment amount is used as the weight coefficient corresponding to the odor dimension.

[0056] Specifically, the first preset score is recorded as Let the first preset score be 60 points, and the target gas concentration be recorded as . The concentration of putrefactive gases is recorded as ,like ,and At this point, the stored food is determined not to be spoiled, and the corresponding status is marked as F0. The odor sensor does not participate in the scoring calculation; the score is calculated only by combining spectral and weight data. In this case, the default weight of the target food type in the spectral dimension is used as the weight coefficient corresponding to the spectral dimension. The default weight of the target ingredient type in the weight dimension is used as the weight coefficient for the corresponding weight dimension. The default weight of 0 for the target ingredient type in the odor dimension is used as the weight coefficient for the odor dimension. .

[0057] like ,and If the spectral data indicates spoilage, but the odor sensor indicates no spoilage, then it is classified as a Level 1 false alarm. The corresponding status label for this state is F1, meaning the spectral data indicates spoilage, but the odor sensor indicates no spoilage. The odor sensor is more reliable in determining whether food is spoiled. This situation is judged as a large error in the spectral data, so the weighting coefficient corresponding to the spectral dimension should be appropriately reduced. ,Right now ,in The default weight of the target ingredient's weight in the spectral dimension is set as follows: K1 is the first adjustment value, and in this embodiment, K1 = 0.2; since the ingredient is not spoiled, the weight coefficient corresponding to the weight dimension is... Keep it unchanged, but appropriately increase the weighting coefficient corresponding to the odor dimension. ,Right now To eliminate spectral data errors, The default weight of the target ingredient in the odor dimension.

[0058] like ,and If the spectral data indicates no spoilage, but the odor sensor indicates spoilage, then the food is classified as having secondary spoilage. This state is labeled F2, meaning the spectral data indicates no spoilage, but the odor sensor indicates spoilage. The odor sensor is more reliable in determining spoilage. In this case, the spectral data has a large error, so the weighting coefficient for the spectral dimension should be appropriately reduced. ,Right now K2 is the second adjustment value, and in this embodiment, K2 = 0.1; since the food has spoiled, the weight corresponding to the weight dimension is also appropriately reduced, that is... ,in The default weight of the target ingredient in the weight dimension is set, and the weight coefficient corresponding to the aroma dimension is appropriately increased. ,Right now K3 is the third adjustment value. In this embodiment, K3 is set to 0.3 to eliminate spectral errors and reduce the weight change score ratio.

[0059] like ,and If the spectral data indicates spoilage, the food is classified as Level 3 spoilage, with a status indicator of F3. This means that both the spectral data and the odor sensor indicate spoilage. In this case, the spectral data is considered normal, so there is no need to change the weighting coefficients for the spectral dimensions. The default weights for the target ingredient types in the spectral dimension are used. Since the ingredients have spoiled, changes in moisture content cannot accurately represent the freshness of the ingredients, so the weights corresponding to changes in weight need to be reduced. K4 is the fourth adjustment factor. In this embodiment, K4 is set to 0.4, and the odor weight is appropriately increased. To reduce the weight variation score.

[0060] By judging different situations and adjusting the weighting coefficients, the freshness of food can be fed back in a timely and accurate manner, avoiding food waste or consumption of stale food due to misjudgment.

[0061] In one embodiment, determining the target control mode of the refrigerator based on the overall freshness score includes: When the total freshness score is less than or equal to the first total score, the odor-removing and humidity-regulating mode is used as the target control mode. The odor-removing and humidity-regulating mode is used to start the odor-removing system and adjust the storage humidity to the preset humidity, and output food spoilage information, which includes food name and spoilage status. When the total freshness score is greater than the first total score and less than or equal to the second total score, the cooling and dehumidification mode is used as the target control mode. The cooling and dehumidification mode is used to reduce the refrigeration temperature and dehumidify according to the preset temperature control variable, and output the freshness information of the ingredients, which includes the ingredient name, the total freshness score and the ingredient consumption suggestion.

[0062] Specifically, if , If the overall score is first, the refrigerator deodorization system will be activated immediately and the storage humidity will be adjusted to the preset humidity. The preset humidity can be customized according to actual needs, such as 40%, 50%, 60%, etc. In this embodiment, the preset humidity is set to 50%, and the food spoilage information will be output. The structure of the food spoilage information is "food name + spoiled", such as: eggs + spoiled.

[0063] like S3 represents the second overall score. The refrigerator temperature is lowered and dehumidification mode is activated according to the preset temperature control variable. The freshness information of the ingredients is also output, with the structure being "Ingredient Name + Overall Freshness Score + Consumption Recommendation." The consumption recommendation is determined based on the overall freshness score. For example, if the overall freshness score is 60-70, the consumption recommendation is "Eat as soon as possible"; if it's 70-80, it's "Recommended to eat"; if it's 80-90, it's "Eat normally"; and if it's 90-100, it's "Optimal consumption condition." For instance, the freshness information could be: Apple, 90%, optimal consumption condition. The preset temperature control variable can be 1℃, 2℃, 3℃, etc. In this embodiment, the preset temperature control variable is set to 1℃.

[0064] The refrigerator display screen and / or terminal display information on food spoilage or food freshness. After the current collection cycle ends, the next collection cycle begins, and the above steps S210 to S250 are executed repeatedly.

[0065] After taking food, users can provide feedback on its taste via the terminal, such as "normal taste" (80-100 points), "slightly overcooked" (60-80 points), or "spoiled" (below 60 points). The refrigerator control device records the feedback, along with the freshness scores and weighting coefficients for each dimension of the food before it was taken out. The system statistically analyzes the freshness feedback accuracy of similar ingredients within a preset period (e.g., one month, one year). Freshness feedback accuracy = number of normal feedback samples / total number of samples. If the freshness feedback accuracy is less than the preset accuracy (e.g., 85%), the default weights for each dimension are fine-tuned with an adjustment precision of ±0.01, overriding the original default weights. If the freshness feedback accuracy is ≥85%, the default weights for each dimension remain unchanged.

[0066] The default weights for the spectral dimension and the weight dimension can be adjusted based on the accuracy of the spectral camera and weight sensor used.

[0067] Figure 2 This is a flowchart illustrating a refrigerator control method in one embodiment. It should be understood that, although... Figure 2 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0068] In one embodiment, such as Figure 3 As shown, a refrigerator control device is provided, comprising: The acquisition module 310 is used to acquire multi-source acquisition data of the refrigerator during the current acquisition period, wherein the multi-source acquisition data includes detection data of multiple dimensions. The scoring module 320 is used to generate freshness scores corresponding to different dimensions based on the detection data of different dimensions. The scoring module 320 is also used to generate a total freshness score based on the freshness scores corresponding to different dimensions; Processing module 330 is used to determine the target control mode of the refrigerator based on the total freshness score; The control module 340 is used to control the refrigerator according to the target control mode.

[0069] In one embodiment, the scoring module 320 is further configured to: Based on spectral detection data, weight detection data, and odor detection data, a first freshness score corresponding to the spectral dimension, a second freshness score corresponding to the weight dimension, and a third freshness score corresponding to the odor dimension are generated.

[0070] In one embodiment, the scoring module 320 is further configured to: Based on the matching results between the spectral detection data and the reference spectral data corresponding to different ingredients in the database, the target ingredient type corresponding to the spectral detection data and the condensation identification result on the surface of the ingredient are determined. Based on the matching results between the spectral curves corresponding to the spectral detection data and the spectral curves of the target food ingredients at different freshness levels, the first freshness score corresponding to the spectral dimension is determined.

[0071] In one embodiment, the scoring module 320 is further configured to: The weight detection data is calibrated using the condensation recognition results to obtain the calibrated current detection weight. Get the weight of the previous detection within the previous collection cycle; When the current detected weight is greater than the previous detected weight, the first freshness score is used as the second freshness score; When the current detected weight is less than or equal to the previous detected weight, a second freshness score corresponding to the weight dimension is generated based on the weight change rate between the current detected weight and the previous detected weight.

[0072] In one embodiment, the scoring module 320 is further configured to: When the weight change rate is greater than or equal to a preset change rate, the first freshness score is used as the second freshness score. When the weight change rate is less than the preset change rate, the previous freshness score corresponding to the weight dimension in the previous collection period is obtained, and the corresponding score change amount is determined according to the difference between the weight change rate and the preset change rate. The second freshness score is determined according to the difference between the previous freshness score and the score change amount.

[0073] In one embodiment, the scoring module 320 is further configured to: Based on the first freshness score and the odor detection data, determine the weighting coefficients corresponding to different dimensions; The freshness scores for each dimension are weighted and summed based on the weight coefficients corresponding to different dimensions to generate the total freshness score.

[0074] In one embodiment, the scoring module 320 is further configured to perform at least one of the following: When the first freshness score is greater than the first preset score, and the concentration of the target gas in the odor detection data is less than the concentration of spoilage gas, the default weight of the target food type under different dimensions is used as the weight coefficient corresponding to different dimensions. When the first freshness score is less than or equal to the first preset score, and the concentration of the target gas in the odor detection data is less than the concentration of the putrefactive gas, the default weight of the target food type in the weight dimension is used as the weight coefficient corresponding to the weight dimension, the difference between the default weight of the target food type in the spectral dimension and the first adjustment amount is used as the weight coefficient corresponding to the spectral dimension, and the sum of the default weight of the target food type in the odor dimension and the first adjustment amount is used as the weight coefficient corresponding to the odor dimension. When the first freshness score is greater than the first preset score, and the target gas concentration in the odor detection data is greater than or equal to the spoilage gas concentration, the difference between the default weight of the target ingredient weight in the spectral dimension and the second adjustment amount is used as the weight coefficient corresponding to the spectral dimension, the difference between the default weight of the target ingredient type in the weight dimension and the first adjustment amount is used as the weight coefficient corresponding to the weight dimension, and the sum of the default weight of the target ingredient type in the odor dimension and the third adjustment amount is used as the weight coefficient corresponding to the odor dimension. When the first freshness score is less than or equal to the first preset score, and the target gas concentration in the odor detection data is greater than or equal to the spoilage gas concentration, the default weight of the target ingredient weight in the spectral dimension is used as the weight coefficient corresponding to the spectral dimension, the difference between the default weight of the target ingredient type in the weight dimension and the fourth adjustment amount is used as the weight coefficient corresponding to the weight dimension, and the sum of the default weight of the target ingredient type in the odor dimension and the fourth adjustment amount is used as the weight coefficient corresponding to the odor dimension.

[0075] In one embodiment, the control module 340 is further configured to: When the total freshness score is less than or equal to the first total score, the odor-removing and humidity-regulating mode is used as the target control mode. The odor-removing and humidity-regulating mode is used to start the odor-removing system and adjust the storage humidity to the preset humidity, and output food spoilage information, which includes food name and spoilage status. When the total freshness score is greater than the first total score and less than or equal to the second total score, the cooling and dehumidification mode is used as the target control mode. The cooling and dehumidification mode is used to reduce the refrigeration temperature and dehumidify according to the preset temperature control variable, and output the freshness information of the ingredients, which includes the ingredient name, the total freshness score and the ingredient consumption suggestion.

[0076] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should also be noted that the above modules, as part of a device, can operate in environments such as... Figure 1 The hardware environment shown can be implemented either through software or through hardware.

[0077] like Figure 4 As shown, this application embodiment provides a refrigerator device, including a processor 711, a communication interface 712, a memory 713, and a communication bus 714. The processor 711, the communication interface 712, and the memory 713 communicate with each other through the communication bus 714. The memory 713 is used to store computer programs. When the processor 711 executes the program stored in the memory 713, it implements the refrigerator control method provided in any of the aforementioned method embodiments.

[0078] The memory and processor in the aforementioned electronic devices communicate with each other via a communication bus and a communication interface. The communication bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0079] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0080] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be 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, or discrete hardware components.

[0081] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the refrigerator device to which the present application is applied. A specific refrigerator device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0082] According to another aspect of the embodiments of this application, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a refrigerator device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the refrigerator device to perform the steps of any of the above embodiments.

[0083] In one embodiment, the refrigerator control device provided in this application can be implemented as a computer program, and the computer program can be implemented in such a way as... Figure 4 The refrigerator device shown operates on this system. The refrigerator device's memory can store the various program modules that make up the refrigerator's control unit, for example... Figure 3 The diagram shows an acquisition module 310, a scoring module 320, a processing module 330, and a control module 340. The computer program comprised of these modules causes the processor to execute the refrigerator control methods of the various embodiments of this application described in this specification.

[0084] Figure 4 The refrigerator shown can be used as follows Figure 3The refrigerator control device shown includes an acquisition module 310 that acquires multi-source data from the refrigerator during the current acquisition period. This multi-source data includes detection data across multiple dimensions. The refrigerator device can then use a scoring module 320 to generate freshness scores corresponding to different dimensions based on the detection data. The refrigerator device can also use the scoring module 320 to generate a total freshness score based on these different freshness scores. The refrigerator device can then use a processing module 330 to determine a target control mode based on the total freshness score. Finally, the refrigerator device can use a control module 340 to control the refrigerator according to the target control mode.

[0085] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the refrigerator control method provided in any of the foregoing method embodiments.

[0086] Optionally, in embodiments of this application, the computer-readable medium is configured to store program code for the processor to perform the following steps: Acquire multi-source acquisition data of the refrigerator during the current acquisition period, wherein the multi-source acquisition data includes detection data from multiple dimensions; Based on the detection data from different dimensions, freshness scores corresponding to different dimensions are generated. A total freshness score is generated based on the freshness scores corresponding to different dimensions; The target control mode of the refrigerator is determined based on the overall freshness score. The refrigerator is controlled according to the target control mode.

[0087] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated here.

[0088] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or combinations thereof.

[0089] For software implementation, the techniques described herein can be implemented by units that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented in the processor or external to the processor.

[0090] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are 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.

[0091] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0092] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules 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 through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0093] The device embodiments described above are merely illustrative. 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 modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0094] In addition, the functional units in the various embodiments of this application 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.

[0095] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a USB flash drive, a portable hard drive, ROM, RAM, a magnetic disk, or an optical disk, or other media capable of storing program code. It includes several instructions to cause a refrigerator device (which may be a personal computer, a server, or a network device, etc.) to execute the refrigerator control method described in various embodiments or some parts of the embodiments.

[0096] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also mean including the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that alternatives or substitutions may be used.

[0097] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A refrigerator control method, characterized in that, The method includes: Acquire multi-source acquisition data of the refrigerator during the current acquisition period, wherein the multi-source acquisition data includes detection data from multiple dimensions; Based on the detection data from different dimensions, freshness scores corresponding to different dimensions are generated. A total freshness score is generated based on the freshness scores corresponding to different dimensions; The target control mode of the refrigerator is determined based on the overall freshness score. The refrigerator is controlled according to the target control mode.

2. The refrigerator control method according to claim 1, characterized in that, The step of generating freshness scores for different dimensions based on the detection data from different dimensions includes: Based on spectral detection data, weight detection data, and odor detection data, a first freshness score corresponding to the spectral dimension, a second freshness score corresponding to the weight dimension, and a third freshness score corresponding to the odor dimension are generated.

3. The refrigerator control method according to claim 2, characterized in that, Based on the spectral detection data, a first freshness score corresponding to the spectral dimension is generated, including: Based on the matching results between the spectral detection data and the reference spectral data corresponding to different ingredients in the database, the target ingredient type corresponding to the spectral detection data and the condensation identification result on the surface of the ingredient are determined. Based on the matching results between the spectral curves corresponding to the spectral detection data and the spectral curves of the target food ingredients at different freshness levels, the first freshness score corresponding to the spectral dimension is determined.

4. The refrigerator control method according to claim 3, characterized in that, Based on the weight measurement data, a second freshness score corresponding to the weight dimension is generated, including: The weight detection data is calibrated using the condensation recognition results to obtain the calibrated current detection weight. Get the weight of the previous detection within the previous collection cycle; When the current detected weight is greater than the previous detected weight, the first freshness score is used as the second freshness score; When the current detected weight is less than or equal to the previous detected weight, a second freshness score corresponding to the weight dimension is generated based on the weight change rate between the current detected weight and the previous detected weight.

5. The refrigerator control method according to claim 4, characterized in that, The step of generating a second freshness score corresponding to the weight dimension based on the weight change rate between the current detected weight and the previous detected weight includes: When the weight change rate is greater than or equal to a preset change rate, the first freshness score is used as the second freshness score. When the weight change rate is less than the preset change rate, the previous freshness score corresponding to the weight dimension in the previous collection period is obtained, and the corresponding score change amount is determined according to the difference between the weight change rate and the preset change rate. The second freshness score is determined according to the difference between the previous freshness score and the score change amount.

6. The refrigerator control method according to claim 3, characterized in that, A total freshness score is generated based on the freshness scores corresponding to different dimensions, including: Based on the first freshness score and the odor detection data, determine the weighting coefficients corresponding to different dimensions; The freshness scores for each dimension are weighted and summed based on the weight coefficients corresponding to different dimensions to generate the total freshness score.

7. The refrigerator control method according to claim 6, characterized in that, Based on the first freshness score and the odor detection data, determine the weighting coefficients corresponding to different dimensions, including at least one of the following: When the first freshness score is greater than the first preset score, and the concentration of the target gas in the odor detection data is less than the concentration of spoilage gas, the default weight of the target food type under different dimensions is used as the weight coefficient corresponding to different dimensions. When the first freshness score is less than or equal to the first preset score, and the concentration of the target gas in the odor detection data is less than the concentration of the putrefactive gas, the default weight of the target food type in the weight dimension is used as the weight coefficient corresponding to the weight dimension, the difference between the default weight of the target food type in the spectral dimension and the first adjustment amount is used as the weight coefficient corresponding to the spectral dimension, and the sum of the default weight of the target food type in the odor dimension and the first adjustment amount is used as the weight coefficient corresponding to the odor dimension. When the first freshness score is greater than the first preset score, and the target gas concentration in the odor detection data is greater than or equal to the spoilage gas concentration, the difference between the default weight of the target ingredient weight in the spectral dimension and the second adjustment amount is used as the weight coefficient corresponding to the spectral dimension, the difference between the default weight of the target ingredient type in the weight dimension and the first adjustment amount is used as the weight coefficient corresponding to the weight dimension, and the sum of the default weight of the target ingredient type in the odor dimension and the third adjustment amount is used as the weight coefficient corresponding to the odor dimension. When the first freshness score is less than or equal to the first preset score, and the target gas concentration in the odor detection data is greater than or equal to the spoilage gas concentration, the default weight of the target ingredient weight in the spectral dimension is used as the weight coefficient corresponding to the spectral dimension, the difference between the default weight of the target ingredient type in the weight dimension and the fourth adjustment amount is used as the weight coefficient corresponding to the weight dimension, and the sum of the default weight of the target ingredient type in the odor dimension and the fourth adjustment amount is used as the weight coefficient corresponding to the odor dimension.

8. The refrigerator control method according to claim 1, characterized in that, Based on the overall freshness score, the target control mode of the refrigerator is determined, including: When the total freshness score is less than or equal to the first total score, the odor-removing and humidity-regulating mode is used as the target control mode. The odor-removing and humidity-regulating mode is used to start the odor-removing system and adjust the storage humidity to the preset humidity, and output food spoilage information, which includes food name and spoilage status. When the total freshness score is greater than the first total score and less than or equal to the second total score, the cooling and dehumidification mode is used as the target control mode. The cooling and dehumidification mode is used to reduce the refrigeration temperature and dehumidify according to the preset temperature control variable, and output the freshness information of the ingredients, which includes the ingredient name, the total freshness score and the ingredient consumption suggestion.

9. A refrigerator control device, characterized in that, The device includes: The acquisition module is used to acquire multi-source acquisition data of the refrigerator during the current acquisition period, wherein the multi-source acquisition data includes detection data of multiple dimensions; The scoring module is used to generate freshness scores for different dimensions based on the detection data for different dimensions. The scoring module is also used to generate a total freshness score based on the freshness scores corresponding to different dimensions; The processing module is used to determine the target control mode of the refrigerator based on the total freshness score; A control module is used to control the refrigerator according to the target control mode.

10. A refrigerator device, characterized in that, The refrigerator equipment is equipped with multiple spectral cameras, a weight sensor, an odor sensor array, and the refrigerator control device as described in claim 9.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the refrigerator control method according to any one of claims 1 to 8.

Images