Food material decay prediction method and device, electronic equipment and storage medium

Abstract

The invention discloses a food material decay prediction method and device, electronic equipment and a storage medium, and the method comprises the steps: determining the food material type of a target food material if it is detected that the target food material is put into a refrigerator, and matching a target sensor set corresponding to the food material type from a preset detection library; controlling each target sensor to carry out data acquisition, and carrying out food material decay detection processing according to the acquired target data to obtain a decay detection result; determining a sensor weight of the target sensor according to the quality parameter and the food material coefficient; performing fusion processing on the putrefaction detection result corresponding to each target sensor and the sensor weight to obtain a comprehensive putrefaction detection result corresponding to the target food material; according to the comprehensive decay detection result and the actual storage temperature of the refrigerator, the remaining storage duration of the target food materials is determined, and the actual storable duration of the food materials placed in the refrigerator can be accurately predicted through dynamic fusion of the detection results of the multiple sensors and combination of the actual storage temperature.

Description

Technical Field

[0001] The present application relates to the field of refrigerator control, and in particular to a method, device, electronic device and storage medium for predicting food spoilage. Background Art

[0002] Refrigerators, as common fresh-keeping devices, have become ubiquitous in every household. Users can place food into the refrigerator's fresh-keeping space to maintain its freshness for a certain period of time, effectively storing it. However, because users may not fully understand the time the food has been in the refrigerator and its actual shelf life, they often fail to process the food in the refrigerator in a timely manner, leading to spoilage and food waste.

[0003] In the prior art, a fixed storage time is usually set for food, and when the fixed storage time is reached, the user is reminded to dispose of the food. However, this method cannot perform targeted spoilage prediction on food, and the food spoilage prediction results are low in accuracy.

[0004] Therefore, how to accurately predict the actual storage time of food in the refrigerator is a technical problem that needs to be solved urgently. Summary of the Invention

[0005] The present application provides a food spoilage prediction method, device, electronic device and storage medium, which can accurately predict the actual storage time of food placed in a refrigerator.

[0006] In one aspect, an embodiment of the present application provides a method for predicting food spoilage, the method comprising:

[0007] If it is detected that the target food is placed in the refrigerator, the type of the target food is determined, and a target sensor set corresponding to the type of food is matched from a preset detection library;

[0008] Controlling each target sensor in the target sensor set to collect data, and performing food spoilage detection processing based on the target data collected by each target sensor to obtain a spoilage detection result corresponding to each target sensor; the spoilage detection result represents the degree of spoilage of the target food;

[0009] Obtaining a quality parameter of each target sensor in the target sensor set during a data acquisition process, and obtaining a food coefficient of each target sensor in the target sensor set from the preset detection library; the food coefficient represents the importance of the target sensor for food spoilage detection of the target food;

[0010] determining a sensor weight of the target sensor according to the quality parameter and the food coefficient;

[0011] Fusing the corruption detection result corresponding to each target sensor with the sensor weight to obtain a comprehensive corruption detection result corresponding to the target food;

[0012] The remaining storage time of the target food is determined based on the comprehensive corruption detection result and the actual storage temperature of the refrigerator.

[0013] In an exemplary embodiment, obtaining a quality parameter of each target sensor in the target sensor set during data acquisition includes:

[0014] For each target sensor in the target sensor set, obtaining a target range of the target sensor;

[0015] determining signal quality according to a ratio between a fluctuation amplitude of the target data and the target range during data acquisition;

[0016] Obtaining the historical accuracy of the target sensor;

[0017] The historical accuracy rate and the signal quality are weighted and fused according to preset weights to obtain the quality parameter of the target sensor.

[0018] In an exemplary embodiment, obtaining the historical accuracy of the target sensor includes:

[0019] Obtaining a historical prediction record table corresponding to the target sensor, wherein the historical prediction record table includes historical feedback information corresponding to a preset number of historical comprehensive corruption detection results;

[0020] Determining the correct number of historical comprehensive corruption detection results in the historical prediction record table based on the historical feedback information;

[0021] The ratio of the correct number to the preset number is determined as the historical accuracy rate of the target sensor.

[0022] In an exemplary embodiment, determining the sensor weight of the target sensor according to the quality parameter and the food coefficient includes:

[0023] For each target sensor in the target sensor set, taking the product of the food coefficient corresponding to each target sensor and the quality parameter as an initial weight;

[0024] Based on the initial weight of each target sensor, determine the sum of the initial weights;

[0025] A ratio of the initial weight of each target sensor to the sum of the initial weights is determined as the sensor weight of each target sensor.

[0026] In an exemplary embodiment, determining the remaining storage time of the target food according to the comprehensive corruption detection result and the actual storage temperature of the refrigerator includes:

[0027] Obtaining an ideal storage time for the target food, where the ideal storage time represents the time required for the target food to reach a spoilage state at an ideal storage temperature;

[0028] Matching the corruption sensitivity coefficient corresponding to the food type from the preset detection library;

[0029] determining a corruption magnitude based on the corruption sensitivity coefficient and the comprehensive corruption detection result;

[0030] The remaining storage time of the target food is determined based on the actual storage temperature of the refrigerator, the ideal storage time and the degree of spoilage.

[0031] In an exemplary embodiment, the method further comprises:

[0032] issuing an early warning prompt based on the comprehensive corruption detection result and the remaining storage time;

[0033] In response to a feedback operation on the early warning prompt, obtaining feedback information;

[0034] adjusting the quality parameter of the target sensor according to the feedback information to obtain an adjusted quality parameter; wherein the feedback information indicates whether the comprehensive corruption detection result is correct;

[0035] The corruption detection result corresponding to each target sensor and the adjusted quality parameter are fused to obtain the adjusted comprehensive corruption detection result corresponding to the target food.

[0036] In an exemplary embodiment, adjusting the quality parameter of the target sensor according to the feedback information to obtain the adjusted quality parameter includes:

[0037] If the feedback information indicates that the comprehensive corruption detection result is correct, determining an improvement magnitude based on the corruption detection result corresponding to the target sensor and a preset improvement ratio;

[0038] Determining the adjusted quality parameter according to the quality parameter and the improvement margin;

[0039] If the feedback information indicates that the comprehensive corruption detection result is erroneous, determining a reduction range based on the corruption detection result corresponding to the target sensor and a preset reduction ratio;

[0040] The adjusted quality parameter is determined according to the quality parameter and the reduction amplitude.

[0041] On the other hand, the present application also provides a food spoilage prediction device, which includes:

[0042] A target sensor set matching module is used to determine the type of target food if it is detected that the target food is placed in the refrigerator, and match the target sensor set corresponding to the type of food from a preset detection library;

[0043] a corruption prediction module, configured to control each target sensor in the target sensor set to collect data, and perform food corruption detection processing based on the target data collected by each target sensor, thereby obtaining a corruption detection result corresponding to each target sensor; the corruption detection result represents the degree of corruption of the target food;

[0044] a parameter acquisition module, configured to acquire quality parameters of each target sensor in the target sensor set during data acquisition, and to acquire a food coefficient of each target sensor in the target sensor set from the preset detection library; the food coefficient represents the importance of the target sensor for food spoilage detection of the target food;

[0045] a sensor weight determination module, configured to determine a sensor weight of the target sensor according to the quality parameter and the food coefficient;

[0046] A result integration module is used to fuse the corruption detection result corresponding to each target sensor and the sensor weight to obtain a comprehensive corruption detection result corresponding to the target food;

[0047] A remaining storage time determination module is configured to determine the remaining storage time of the target food based on the comprehensive spoilage detection result and the actual storage temperature of the refrigerator. In another aspect, the present application further provides an electronic device comprising a processor and a memory, wherein the memory stores at least one instruction or at least one program, the at least one instruction or at least one program being loaded and executed by the processor to implement the food spoilage prediction method described above.

[0048] On the other hand, the present application also provides a computer storage medium, which stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by a processor to implement the food spoilage prediction method as described above.

[0049] In another aspect, the present application further provides a computer program product or computer program, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to implement the food spoilage prediction method described above.

[0050] The food spoilage prediction method provided by this application has the following technical effects:

[0051] In the present application, if it is detected that the target food is placed in the refrigerator, the food type of the target food is determined, and a target sensor set corresponding to the food type is matched from a preset detection library; each target sensor in the target sensor set is controlled to collect data, and food corruption detection processing is performed based on the target data collected by each target sensor to obtain a corruption detection result corresponding to each target sensor; different target sensors are controlled to collect data according to the food type, which on the one hand makes the collected data more targeted, and on the other hand also improves the service life of the sensor and saves the computing resources required for data processing; the quality parameters of each target sensor in the target sensor set during the data collection process are obtained, and the food coefficient of each target sensor is obtained from the preset detection library; the sensor weight of the target sensor is determined based on the quality parameters and the food coefficient; the corruption detection result and sensor weight corresponding to each target sensor are fused to obtain a comprehensive corruption detection result corresponding to the target food; the present application collects multimodal data through multiple sensors to detect food corruption, and determines the comprehensive corruption detection result through decision fusion. Compared with corruption detection by a single sensor, the detection result of the present application has a higher accuracy rate. At the same time, this application dynamically determines the decision weights of each sensor based on the food coefficient and quality parameters to fuse the detection results, thereby further improving the accuracy of the comprehensive corruption detection results; and then determines the remaining storage time of the target food based on the comprehensive corruption detection results and the actual storage temperature of the refrigerator. This application dynamically fuses the detection results of multiple sensors and combines them with the actual storage temperature to accurately predict the actual storage time of food placed in the refrigerator. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0053] Figure 1 This is a diagram of the application environment of the food spoilage prediction method provided in an embodiment of the present application;

[0054] Figure 2 This is a flow chart of the food spoilage prediction method provided in an embodiment of the present application;

[0055] Figure 3 is a schematic diagram of a process for determining quality parameters of a target sensor provided by an embodiment of the present application;

[0056] Figure 4 This is a schematic diagram of a process for determining the remaining storage time of a target food provided by an embodiment of the present application;

[0057] Figure 5 This is a flow chart of providing feedback on prediction results according to an embodiment of the present application;

[0058] Figure 6 Schematic diagram of the structure of the food spoilage prediction device provided in an embodiment of the present application;

[0059] Figure 7 This is a hardware structure block diagram of a server for a food spoilage prediction method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0060] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0061] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0062] Figure 1 This is an application environment diagram of the food spoilage prediction method provided in the embodiment of the present application.

[0063] like Figure 1 As shown, the application environment may at least include a server 01 and an electronic device 02 .

[0064] In an optional embodiment, the electronic device 02 can be used to store food, including but not limited to refrigerators, freezers, and other types of fresh-keeping devices; it can also be software running on the above electronic devices, such as applications, applets, etc. The operating system running on the electronic device in the embodiment of the present application can include but is not limited to Android, iOS, Linux, Windows, etc.

[0065] In an optional embodiment, after terminal device 02 detects the presence of food, server 01 can perform food spoilage detection on the target data collected by sensors, obtaining spoilage detection results corresponding to each target sensor. Server 01 transmits the spoilage detection results to electronic device 02, enabling electronic device 02 to integrate spoilage detection results corresponding to multiple sensors. Server 01 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0066] Figure 2 This is a flow chart of the food spoilage prediction method provided in an embodiment of the present application.

[0067] S201: If it is detected that a target food is placed in the refrigerator, determine the type of the target food, and match a target sensor set corresponding to the type of food from a preset detection library;

[0068] In one embodiment, if it is detected that the refrigerator door is opened, an image inside the refrigerator can be captured by an image capture device built into the refrigerator. If food is detected to be placed inside, the food is used as the target food.

[0069] Then, the food image recognition model is used to identify the type of the target food. Specifically, the training process of the food image recognition model is as follows:

[0070] Acquire a sample food image, wherein the sample food image is marked with a food type label;

[0071] Constructing a preset neural network model, and using the preset neural network model to perform food type recognition processing on the sample food image to obtain a prediction result;

[0072] A loss value is determined according to the difference between the prediction result and the food type label, and the model parameters of the preset neural network model are adjusted based on the loss value, so as to train the food image recognition model.

[0073] After determining the type of food, a target sensor set corresponding to the food type is matched from a preset detection library; the target sensor set includes at least two target sensors; and the preset detection library contains a correspondence between preset food types and preset sensor sets.

[0074] In one implementation, the correspondence between the preset food types and the preset sensor sets includes but is not limited to: the sensor set corresponding to fruits and vegetables may include a multispectral camera and a gas sensor; the sensor set corresponding to seafood may include a gas sensor and a weight-touch sensor, etc.

[0075] S203: Controlling each target sensor in the target sensor set to collect data, and performing food spoilage detection processing based on the target data collected by each target sensor to obtain a spoilage detection result corresponding to each target sensor;

[0076] Wherein, the corruption detection result represents the corruption degree of the target food;

[0077] For example, the target food ingredient is strawberries. The target sensor set includes a multispectral camera and a gas sensor. The multispectral camera is controlled to capture images and process the collected data for food spoilage detection. Simultaneously, the gas sensor is controlled to collect gas information and process the collected data for food spoilage detection. In this way, each target sensor generates a corresponding spoilage detection result.

[0078] The multispectral camera is controlled to capture images and the collected data is processed for food spoilage detection. Specifically, a mold detection model can be used to detect whether mold appears in the images captured by the multispectral camera to determine the spoilage degree of the target food. In one example, the mold detection model outputs P1 = 0.9, indicating that mold appears on the target food and the spoilage degree is 90%. The mold detection model training process is as follows:

[0079] Acquire a sample image of a food material with mold spots; the sample image of the food material with mold spots is annotated with a corruption degree label;

[0080] Constructing a preset neural network model, and using the preset neural network model to perform corruption degree identification processing on the sample moldy food image to obtain a corruption detection result; the corruption detection result represents the corruption degree of the food;

[0081] A loss value is determined according to the difference between the corruption detection result and the corruption degree label, and model parameters of the preset neural network model are adjusted based on the loss value, thereby training the mold spot detection model.

[0082] The gas sensor is controlled to collect gas information and then processed for food spoilage detection. Specifically, the data collected in real time is directly compared with the preset spoilage gas concentration-corruption degree comparison table to output the spoilage detection results. Still using the strawberry detection scenario as an example, Table 1 is the spoilage gas concentration-corruption degree comparison table provided by this application.

[0083] Table 1

[0084] Corruption stage Ethylene (ppm) Hydrogen sulfide (ppm) Ethanol (ppm) Corruption level (P) Fresh 10-20 0-1 0-5 0.0-0.2 Early stage 30-60 1-3 5-15 0.2-0.5 mid-term 60-100 3-5 15-25 0.5-0.8 serious >100 >5 >25 0.8-1.0

[0085] As shown in Table 1, strawberries typically release gases containing ethylene, hydrogen sulfide, and ethanol when they spoil. By monitoring the gas concentration range, the strawberry spoilage detection result can be matched. For example, if the gas sensor detects an ethylene concentration of 45 ppm, a hydrogen sulfide concentration of 2 ppm, and an ethanol concentration of 10 ppm, a comparison of these three components will show that 45 ppm of ethylene falls within the "initial" range; 2 ppm of hydrogen sulfide falls within the "initial" range; and 10 ppm of ethanol falls within the "initial" range. Since the concentrations of all three components match the initial stage, the spoilage level can be set to a value between 0.2 and 0.5, such as 0.3.

[0086] S205: Acquire a quality parameter of each target sensor in the target sensor set during data collection, and acquire an ingredient coefficient of each target sensor in the target sensor set from the preset detection library; the ingredient coefficient represents the importance of the target sensor for detecting food spoilage of the target ingredient;

[0087] It should be understood that different target sensors have different degrees of importance for certain types of food. For example, for meat, more emphasis is placed on touch. Therefore, the corruption detection results of the weight-touch sensor are more practical and valuable than the corruption detection results of the multispectral camera and the gas sensor. For fruits and vegetables, more emphasis is placed on color changes. Therefore, the corruption detection results of the multispectral camera are more practical and valuable than the corruption detection results of the gas sensor and the weight-touch sensor. In the present application, a correspondence is established in advance between each food and the corresponding target sensor set in the preset detection library, and further, a food coefficient is set for each target sensor in the target sensor set. For example, in the strawberry detection scenario, the food coefficient corresponding to the target sensor multispectral camera is 0.6, and the food coefficient corresponding to the target sensor gas sensor is 0.4. It should be noted that different types of food correspond to different target sensor sets, and the food coefficients corresponding to the target sensors are often different. In other words, the food coefficient of the target sensor is also determined according to the type of food.

[0088] The quality parameter is a detection parameter of the target sensor itself, used to indicate the reliability of the target sensor. For example, if the target sensor maintains a stable connection during data collection and the spoilage detection results determined based on the target data collected by the target sensor are highly accurate, then the target sensor has a high reliability for food spoilage detection and, accordingly, the target sensor's quality parameter is high.

[0089] S207: Determine a sensor weight of the target sensor according to the quality parameter and the food coefficient;

[0090] In this application, both quality parameters and food coefficients are taken into consideration to determine the sensor weight of each target sensor for subsequent corruption detection result fusion.

[0091] S209: fusing the corruption detection result corresponding to each target sensor and the sensor weight to obtain a comprehensive corruption detection result corresponding to the target food;

[0092] The comprehensive corruption detection result in this application is the sum of the products of each sensor weight (Wi) and the corresponding corruption detection result (Pi). In an example, assuming that the sensor weight of target sensor 1 is 0.7 and the corruption detection result is 0.9; the sensor weight of target sensor 2 is 0.3 and the corruption detection result is 0.3; then the comprehensive corruption detection result P = 0.7 × 0.9 + 0.3 × 0.3 = 0.72.

[0093] S211: Determine the remaining storage time of the target food according to the comprehensive corruption detection result and the actual storage temperature of the refrigerator.

[0094] It should be understood that the higher the actual storage temperature of the food, the faster the food will spoil. This application combines the actual storage temperature of the refrigerator. After obtaining the comprehensive spoilage detection results of the target food, it can further determine the remaining storage time of the target food, that is, the predicted time for the target food to reach complete spoilage, thereby accurately quantifying the food spoilage rate.

[0095] It should be noted that the comprehensive corruption result obtained in step S209 and the remaining storage time predicted in step S211 can be used together as the food corruption prediction result. The food corruption prediction result can be saved on the refrigerator operation interface or in the corresponding application of the refrigerator for users to view.

[0096] It should be noted that the time when the target food is placed in the refrigerator can also be recorded, and after the remaining storage time is reached, a prompt message will be issued to remind the user to dispose of the target food in time to avoid contaminating the refrigerator storage environment.

[0097] In an embodiment of the present application, if it is detected that a target food is placed in a refrigerator, the food type of the target food is determined, and a target sensor set corresponding to the food type is matched from a preset detection library; each target sensor in the target sensor set is controlled to collect data, and food corruption detection processing is performed based on the target data collected by each target sensor to obtain a corruption detection result corresponding to each target sensor; different target sensors are controlled to collect data according to the food type, which on the one hand makes the collected data more targeted, and on the other hand also improves the service life of the sensor and saves the computing resources required for data processing; the quality parameters of each target sensor in the target sensor set during the data collection process are obtained, and the food coefficient of each target sensor is obtained from the preset detection library; the sensor weight of the target sensor is determined based on the quality parameters and the food coefficient; the corruption detection result and sensor weight corresponding to each target sensor are fused to obtain a comprehensive corruption detection result corresponding to the target food; the present application collects multimodal data through multiple sensors to detect food corruption, and determines the comprehensive corruption detection result through decision fusion. Compared with corruption detection by a single sensor, the detection result of the present application has a higher accuracy rate. At the same time, this application dynamically determines the decision weights of each sensor based on the food coefficient and quality parameters to fuse the detection results, thereby further improving the accuracy of the comprehensive corruption detection results; and then determines the remaining storage time of the target food based on the comprehensive corruption detection results and the actual storage temperature of the refrigerator. This application dynamically fuses the detection results of multiple sensors and combines them with the actual storage temperature to accurately predict the actual storage time of food placed in the refrigerator.

[0098] Figure 3 The process of determining the quality parameters of the target sensor according to the embodiment of the present application is shown in FIG. The process of obtaining the quality parameters of each target sensor in the target sensor set during the data acquisition process may include:

[0099] S301: For each target sensor in the target sensor set, obtaining a target range of the target sensor;

[0100] S303: determining signal quality according to a ratio between the fluctuation amplitude of the target data and the target range during data acquisition;

[0101] It should be noted that the data collection process may be to control each target sensor in the target sensor set to collect data for a preset time period to obtain target data. The preset time period may be 1 minute, for example, controlling a gas sensor to collect gas data within 1 minute.

[0102] Signal quality characterizes the stability of the signal during data acquisition. In one implementation, the signal quality is calculated as follows:

[0103] A=1-m / M

[0104] Where A represents signal quality, m represents the fluctuation range of the target data, and M represents the target range. For example, if the gas sensor's range is 0 to 200 ppm and the target data fluctuation range is ±10 ppm, then the gas sensor's signal quality is A = 1 - 10 / 200 = 0.95.

[0105] S305: Obtaining the historical accuracy of the target sensor;

[0106] The historical accuracy rate is used to characterize the accuracy of the corruption detection results determined by the target data collected by the target sensor in the historical detection scenario.

[0107] In one implementation, a historical prediction record table corresponding to the target sensor may be obtained, wherein the historical prediction record table includes historical feedback information corresponding to a preset number of historical comprehensive corruption detection results;

[0108] Determining the correct number of historical comprehensive corruption detection results in the historical prediction record table based on the historical feedback information;

[0109] The ratio of the correct number to the preset number is determined as the historical accuracy rate of the target sensor.

[0110] It should be noted that each time food is placed in the refrigerator for food spoilage testing, the historical prediction record table is updated based on the spoilage test results. User feedback on the spoilage test results is also stored in the table, forming a single test record along with the spoilage test results. The historical prediction record table can retain only a preset number of test records, such as the most recent 30 historical prediction records.

[0111] In one implementation, the historical accuracy is calculated as follows:

[0112] B=n / N

[0113] Where B represents the historical accuracy rate, N represents the number of test records stored in the historical prediction record table, and n represents the number of correct comprehensive corruption test results. For example, if the gas sensor was correct 27 times out of the past 30 tests, the historical accuracy rate is B = 27 / 30 = 0.9.

[0114] By saving the most recent historical detection records, the historical accuracy rate is dynamically updated, making the historical accuracy rate more accurate.

[0115] S307: Perform weighted fusion processing on the historical accuracy and the signal quality according to preset weights to obtain the quality parameter of the target sensor.

[0116] In an example, the preset weight corresponding to the historical accuracy rate may be 0.3; the preset weight corresponding to the signal quality may be 0.7. Taking the signal quality as 0.95 and the historical accuracy rate as 0.9 as an example, the value of the quality parameter S is 0.7×0.95+0.3×0.9=0.935.

[0117] In an embodiment of the present application, by dynamically determining the historical accuracy rate and determining the quality parameters, and weightedly fusing the two, the quality parameters of the target sensor can be dynamically determined, making the quality parameters more accurate, and at the same time making the sensor weight of the sensor determined subsequently more accurate.

[0118] In one embodiment, determining the sensor weight of the target sensor according to the quality parameter and the food coefficient includes:

[0119] For each target sensor in the target sensor set, the product of the food coefficient and the quality parameter corresponding to each target sensor is used as the initial weight; based on the initial weight of each target sensor, the sum of the initial weights is determined; and the ratio of the initial weight of each target sensor to the sum of the initial weights is determined as the sensor weight of each target sensor.

[0120] Taking the above-mentioned camera's food coefficient as 0.6 and quality parameter as 0.8, and the gas sensor's food coefficient as 0.4 and quality parameter as 0.5 as an example, the initial weight of the camera is 0.6×0.8=0.48; the initial weight of the gas sensor is 0.4×0.5=0.2; the sum of the initial weights is 0.48+0.2=0.68; then the sensor weight of the camera is 0.48 / 0.68≈0.7, and the sensor weight of the gas sensor is 0.2 / 0.68≈0.3.

[0121] In the embodiment of the present application, the sensor weight is determined by combining the food coefficient and the quality parameter, which takes into account the type of food and the credibility of the sensor itself, making the sensor weight more reasonable and accurate.

[0122] Figure 4 The flowchart of determining the remaining storage time of target food provided by an embodiment of the present application is as follows. The determining the remaining storage time of the target food based on the comprehensive corruption detection result and the actual storage temperature of the refrigerator may include:

[0123] S401: Obtaining an ideal storage time for the target food, where the ideal storage time represents the time required for the target food to reach a spoilage state at an ideal storage temperature;

[0124] In one implementation, a preset detection library can be queried to match the ideal storage time and ideal storage temperature corresponding to the target ingredient. For example, if the target ingredient is strawberries, the ideal storage temperature can be found to be 4 degrees Celsius. At this ideal storage temperature, the ideal storage time for strawberries is 120 hours. After 120 hours, the strawberries will become spoiled.

[0125] S403: Matching the corruption sensitivity coefficient corresponding to the food type from the preset detection library;

[0126] Different ingredients have different corruption sensitivity coefficients. For example, fruits and vegetables are high in moisture and easily perishable, and have a higher sensitivity. Therefore, the corruption sensitivity coefficient of fruits and vegetables can be set to 0.7; meat spoils slowly at low temperatures and has medium sensitivity, and the corruption sensitivity coefficient of meat can be set to 0.5; nuts are resistant to storage and have a lower sensitivity, and the corruption sensitivity coefficient of nuts can be set to 0.3; it should be understood that the specific values ​​of the above corruption sensitivity coefficients are only examples, and the corruption sensitivity coefficients corresponding to different types of ingredients can be set according to actual conditions.

[0127] S405: Determine the corruption range based on the corruption sensitivity coefficient and the comprehensive corruption detection result;

[0128] Because the ideal storage times are determined experimentally with completely fresh ingredients, and the target ingredients placed in the refrigerator by the user are not necessarily completely fresh, this application further determines the corruption amplitude by multiplying the comprehensive corruption detection result detected in step S209 by the corruption sensitivity coefficient. The larger the comprehensive corruption detection result, the larger the corruption sensitivity coefficient, and the larger the corruption amplitude, the shorter the remaining storage time of the target ingredient.

[0129] S407: Determine the remaining storage time of the target food according to the actual storage temperature of the refrigerator, the ideal storage time and the degree of spoilage.

[0130] Changes in the actual storage temperature of the refrigerator can accelerate the spoilage of food. It should be noted that for every 1°C increase in temperature, spoilage will accelerate by 15%. Therefore, this application first determines the temperature impact coefficient based on the difference between the actual storage temperature and the ideal storage temperature. In an example, assuming that the actual storage temperature of the refrigerator is 6°C, which is 2°C higher than the ideal storage temperature, the spoilage is accelerated by 30%, and the temperature impact coefficient is 1 / 1.3 = 0.77.

[0131] Specifically, the calculation formula for the remaining storage time is as follows:

[0132] Tr=Tb*(1-k*P)*f(Tfridge)

[0133] Here, Tr represents the remaining storage time, Tb represents the ideal storage time, k represents the corruption sensitivity coefficient, P represents the comprehensive corruption detection result, k*P represents the corruption amplitude, and f(Tfridge) represents the temperature influence coefficient. Using the strawberry scenario above as an example, the remaining storage time is Tr = 120(1 - 0.5 × 0.72) * 0.77 ≈ 59 hours.

[0134] In this embodiment, by incorporating the actual storage temperature of the refrigerator, the impact of temperature fluctuations on the storage time of ingredients is taken into account, thereby making the prediction of the remaining storage time more accurate. Furthermore, this application also takes into account the degree of spoilage of ingredients when placed in the refrigerator, making the predicted remaining storage time more consistent with real-life scenarios, thereby accurately predicting the actual storage time of ingredients placed in the refrigerator.

[0135] Figure 5 This is a flow chart of providing feedback on prediction results provided by the embodiment of the present application. Figure 5 As shown, the method provided by this application also includes:

[0136] S501: issuing an early warning prompt based on the comprehensive corruption detection result and the remaining storage time;

[0137] Warning prompts include but are not limited to voice playback, text prompts, etc., and this application does not limit the specific prompt form of the warning prompt. In one implementation, the warning prompt can be displayed on the refrigerator's operating panel or in a message prompt pop-up window of the refrigerator's corresponding application. This application does not limit the interface of the warning prompt display.

[0138] In one example, the early warning prompt may be "corruption level 72%, remaining storage time is approximately 59 hours."

[0139] S503: In response to a feedback operation on the early warning prompt, obtaining feedback information; wherein the feedback information indicates whether the comprehensive corruption detection result is correct;

[0140] After receiving the warning, users can choose to provide feedback on the comprehensive spoilage detection result in the warning. If the user confirms "correct," the warning is correct, and the feedback indicates that the comprehensive spoilage detection result is correct. If the user marks it "false positive," it indicates that the target ingredient was mistakenly identified as spoilage, and the feedback indicates that the comprehensive spoilage detection result is incorrect.

[0141] S505: Adjusting the quality parameter of the target sensor according to the feedback information to obtain an adjusted quality parameter;

[0142] Specifically, if the feedback information indicates that the comprehensive corruption detection result is correct, determining an improvement range according to the corruption detection result corresponding to the target sensor and a preset improvement ratio;

[0143] Determining the adjusted quality parameter according to the quality parameter and the improvement margin;

[0144] Specifically, in this case, the calculation formula of the adjusted quality parameter is as follows:

[0145] Sinew=Siold+β·Pi

[0146] Wherein, Sinew represents the adjusted quality parameter, Siold represents the quality parameter, β represents the preset improvement ratio, which can be a set value of 0.1, Pi represents the corruption detection result of the target sensor, and β·Pi represents the improvement amplitude.

[0147] It should be noted that if the target sensor i gives a high corruption level Pi this time and the user confirms that it is correct, it means that the sensor is reliable and its quality parameters need to be improved.

[0148] For example, if the camera's old quality parameter S1old = 0.8, the current test result P1 = 0.9, and the user confirms it is correct, then the adjusted quality parameter S1new = 0.8 + 0.1 × 0.9 = 0.89. If the gas sensor's old quality parameter S2old = 0.5, the current test result P2 = 0.3, and the user confirms it is correct, then the adjusted quality parameter S2new = 0.5 + 0.1 × 0.3 = 0.53.

[0149] If the feedback information indicates that the comprehensive corruption detection result is erroneous, determining a reduction range based on the corruption detection result corresponding to the target sensor and a preset reduction ratio;

[0150] The adjusted quality parameter is determined according to the quality parameter and the reduction amplitude.

[0151] Specifically, in this case, the calculation formula of the adjusted quality parameter is as follows:

[0152] Sinew=Siold-β·(1-Pi)

[0153] Wherein, Sinew represents the adjusted quality parameter, Siold represents the quality parameter, β represents the preset reduction ratio, which can be a set value of 0.1, Pi represents the corruption detection result of the target sensor, and β·(1-Pi) represents the reduction amplitude.

[0154] It should be noted that if the target sensor i gives a high corruption level Pi this time, but the user feedback is a false alarm, it means that the target sensor is unreliable and its quality parameters need to be significantly reduced.

[0155] For example, if the camera's old quality parameter S1old = 0.8, the current detection P1 = 0.9, and the user marks a false alarm, the adjusted quality parameter S1new = 0.8 - 0.1 × (1 - 0.9) = 0.79. If the gas sensor's old quality parameter S2old = 0.5, the current detection P2 = 0.3, and the user marks a false alarm, the adjusted quality parameter S2new = 0.5 - 0.1 × (1 - 0.3) = 0.43.

[0156] By designing that when the target sensor correctly warns, the improvement range is positively correlated with the current corruption detection result Pi; when the target sensor gives an incorrect warning, the reduction range is positively correlated with the current corruption detection result Pi. This allows accurate updating of quality parameters, thereby achieving rapid calibration of the corruption detection results, and facilitating subsequent accurate adjustment of the comprehensive corruption detection results.

[0157] S507: Fusing the corruption detection result corresponding to each target sensor and the adjusted quality parameter to obtain an adjusted comprehensive corruption detection result corresponding to the target food.

[0158] If the user feedback, the application again according to the adjusted quality parameters of the corruption detection results integration. It should be noted that after the comprehensive corruption detection results are adjusted, the remaining storage time can be further adjusted according to the calculation formula of the remaining storage time in the above embodiment.

[0159] In one embodiment, the adjusted quality parameters can also be directly used as the quality parameters of the target sensor during the next food spoilage detection, so that the quality parameters for each detection are data adjusted based on historical feedback information, realizing dynamic adjustment and application of quality parameters, which is conducive to improving the accuracy of quality parameters, and thus helping to improve the accuracy of sensor weights.

[0160] In an embodiment of the present application, the comprehensive corruption detection results are adjusted by receiving user feedback information, so that the early warning prompt displayed on the refrigerator operation panel or the refrigerator's corresponding application can be further updated to make the early warning prompt more accurate.

[0161] Figure 6 It is a structural diagram of the food spoilage prediction device provided in an embodiment of the present application.

[0162] like Figure 6 As shown, the apparatus 600 includes:

[0163] The target sensor set matching module 601 is used to determine the type of the target food if it is detected that the target food is placed in the refrigerator, and match the target sensor set corresponding to the type of food from the preset detection library;

[0164] a corruption prediction module 602 for controlling each target sensor in the target sensor set to collect data, and performing food corruption detection processing based on the target data collected by each target sensor, to obtain a corruption detection result corresponding to each target sensor; the corruption detection result represents the degree of corruption of the target food;

[0165] The parameter acquisition module 603 is configured to acquire the quality parameters of each target sensor in the target sensor set during the data acquisition process, and to acquire the food coefficient of each target sensor in the target sensor set from the preset detection library; the food coefficient represents the importance of the target sensor for food spoilage detection of the target food;

[0166] a sensor weight determination module 604, configured to determine a sensor weight of the target sensor according to the quality parameter and the food coefficient;

[0167] A result integration module 605 is configured to integrate the corruption detection result corresponding to each target sensor and the sensor weight to obtain a comprehensive corruption detection result corresponding to the target food;

[0168] The remaining storage time determination module 606 is used to determine the remaining storage time of the target food according to the comprehensive corruption detection result and the actual storage temperature of the refrigerator.

[0169] In some embodiments, the parameter acquisition module may include:

[0170] a range acquisition submodule, configured to acquire, for each target sensor in the target sensor set, a target range of the target sensor;

[0171] a signal quality determination submodule, configured to determine the signal quality according to a ratio between the fluctuation amplitude of the target data and the target range during data acquisition;

[0172] A historical accuracy acquisition submodule, configured to acquire the historical accuracy of the target sensor;

[0173] The quality parameter determination submodule is used to perform weighted fusion processing on the historical accuracy rate and the signal quality according to preset weights to obtain the quality parameter of the target sensor.

[0174] In some embodiments, the historical accuracy acquisition submodule includes:

[0175] a historical feedback information acquisition unit, configured to acquire a historical prediction record table corresponding to the target sensor, wherein the historical prediction record table includes historical feedback information corresponding to a preset number of historical comprehensive corruption detection results;

[0176] a correct number determination unit, configured to determine the correct number of the historical comprehensive corruption detection results in the historical prediction record table based on the historical feedback information;

[0177] The historical accuracy rate determining unit is configured to determine a ratio of the correct number of times to the preset number as the historical accuracy rate of the target sensor.

[0178] In some embodiments, the sensor weight determination module includes:

[0179] an initial weight determination submodule, configured to take, for each target sensor in the target sensor set, a product of the food coefficient corresponding to each target sensor and the quality parameter as an initial weight;

[0180] A weight addition submodule, for determining the sum of initial weights based on the initial weights of each target sensor;

[0181] The sensor weight determination submodule is configured to determine the sensor weight of each target sensor by taking the ratio of the initial weight of each target sensor to the sum of the initial weights.

[0182] In some embodiments, the remaining storage duration determination module includes:

[0183] An ideal storage time acquisition submodule, configured to acquire an ideal storage time for the target food, wherein the ideal storage time represents the time required for the target food to reach a spoilage state at an ideal storage temperature;

[0184] a corruption sensitivity coefficient matching submodule, configured to match the corruption sensitivity coefficient corresponding to the food type from the preset detection library;

[0185] a corruption range determination submodule, configured to determine the corruption range based on the corruption sensitivity coefficient and the comprehensive corruption detection result;

[0186] The remaining storage time determination submodule is used to determine the remaining storage time of the target food according to the actual storage temperature of the refrigerator, the ideal storage time and the degree of spoilage.

[0187] In some embodiments, the apparatus 600 may further include:

[0188] An early warning prompt module, configured to issue an early warning prompt based on the comprehensive corruption detection result and the remaining storage time;

[0189] A feedback module, configured to obtain feedback information in response to a feedback operation on the warning prompt;

[0190] a quality parameter adjustment module, configured to adjust the quality parameter of the target sensor according to the feedback information to obtain an adjusted quality parameter; wherein the feedback information indicates whether the comprehensive corruption detection result is correct;

[0191] The comprehensive result adjustment module is used to fuse the corruption detection result corresponding to each target sensor and the adjusted quality parameter to obtain the adjusted comprehensive corruption detection result corresponding to the target food.

[0192] In some embodiments, the quality parameter adjustment module may include:

[0193] a boosting range determining submodule, configured to determine a boosting range based on the corruption detection result corresponding to the target sensor and a preset boosting ratio if the feedback information indicates that the comprehensive corruption detection result is correct;

[0194] A first adjustment module, configured to determine the adjusted quality parameter according to the quality parameter and the improvement range;

[0195] a reduction range determination submodule, configured to determine a reduction range based on the corruption detection result corresponding to the target sensor and a preset reduction ratio if the feedback information indicates that the comprehensive corruption detection result is erroneous;

[0196] The second adjustment module is configured to determine the adjusted quality parameter according to the quality parameter and the reduction range.

[0197] The device and method embodiments in the device embodiments are based on the same inventive concept.

[0198] An embodiment of the present application provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the method provided in the above method embodiment.

[0199] An embodiment of the present application also provides a computer storage medium, which can be set in a terminal to store at least one instruction or at least one program related to a method provided in the above method embodiment for implementing a method embodiment, and the at least one instruction or at least one program is loaded and executed by the processor to implement the method provided in the above method embodiment.

[0200] The embodiments of the present application further provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the method provided in the above method embodiment.

[0201] Optionally, in an embodiment of the present application, the storage medium may be located in at least one of a plurality of network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0202] The memory described in the embodiment of the present application can be used to store software programs and modules, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required for functions, etc.; the data storage area can store data created according to the use of the device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory.

[0203] The method provided in the embodiment of the present application can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking running on a server as an example, Figure 7 This is a hardware structure diagram of a server for a food spoilage prediction method provided by an embodiment of the present application. Figure 7As shown, the server 700 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPUs) 710 (the central processing unit 710 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 730 for storing data, and one or more storage media 720 (such as one or more mass storage devices) for storing application programs 723 or data 722. Among them, the memory 730 and the storage medium 720 can be temporary storage or permanent storage. The program stored in the storage medium 720 may include one or more modules, each module may include a series of instruction operations on the server. Furthermore, the central processing unit 710 can be configured to communicate with the storage medium 720 to execute a series of instruction operations in the storage medium 720 on the server 700. The server 700 may also include one or more power supplies 760, one or more wired or wireless network interfaces 750, one or more input and output interfaces 740, and / or one or more operating systems 721, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0204] The input / output interface 740 can be used to receive or send data via a network. Specific examples of the aforementioned network may include a wireless network provided by the communication provider of the server 700. In one embodiment, the input / output interface 740 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one embodiment, the input / output interface 740 can be a radio frequency (RF) module for wirelessly communicating with the Internet.

[0205] It can be understood by those skilled in the art that Figure 7 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 7 More or fewer components than shown, or with Figure 7 Different configurations shown.

[0206] As can be seen from the embodiments of the food spoilage prediction method, device, electronic device and storage medium provided by the present application, in the present application, if it is detected that a target food is placed in a refrigerator, the food type of the target food is determined, and a target sensor set corresponding to the food type is matched from a preset detection library; each target sensor in the target sensor set is controlled to collect data, and food spoilage detection processing is performed based on the target data collected by each target sensor to obtain a spoilage detection result corresponding to each target sensor; controlling different target sensors to collect data according to the food type makes the collected data more targeted on the one hand, and on the other hand, it also increases the service life of the sensor and saves the computing resources required for data processing; the quality parameters of each target sensor in the target sensor set during the data collection process are obtained, and the food coefficient of each target sensor is obtained from the preset detection library; the sensor weight of the target sensor is determined based on the quality parameters and the food coefficient; the spoilage detection result corresponding to each target sensor and the sensor weight are fused to obtain a comprehensive spoilage detection result corresponding to the target food; the present application collects multimodal data through multiple sensors to detect food spoilage, and determines the comprehensive spoilage detection result through decision fusion. Compared with spoilage detection by a single sensor, the detection result of the present application has a higher accuracy. At the same time, this application dynamically determines the decision weights of each sensor based on the food coefficient and quality parameters to fuse the detection results, thereby further improving the accuracy of the comprehensive corruption detection results; and then determines the remaining storage time of the target food based on the comprehensive corruption detection results and the actual storage temperature of the refrigerator. This application dynamically fuses the detection results of multiple sensors and combines them with the actual storage temperature to accurately predict the actual storage time of food placed in the refrigerator.

[0207] It should be noted that the order of the embodiments of the present application described above is for descriptive purposes only and does not represent the superiority or inferiority of the embodiments. The above description is of specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0208] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, equipment, and storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant portions, refer to the descriptions of the method embodiments.

[0209] Those skilled in the art will understand that all or part of the steps of implementing the above embodiments may be accomplished by hardware, or by a program instructing the relevant hardware to accomplish the steps. The program may be stored in a computer storage medium, and the above-mentioned storage medium may be a read-only memory, a disk, or an optical disk, etc.

[0210] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method for predicting food spoilage, characterized in that: The method comprises: If it is detected that the target food is placed in the refrigerator, the type of the target food is determined, and a target sensor set corresponding to the type of food is matched from a preset detection library; Controlling each target sensor in the target sensor set to collect data, and performing food spoilage detection processing based on the target data collected by each target sensor to obtain a spoilage detection result corresponding to each target sensor; the spoilage detection result represents the degree of spoilage of the target food; Obtaining a quality parameter of each target sensor in the target sensor set during a data acquisition process, and obtaining a food coefficient of each target sensor in the target sensor set from the preset detection library; the food coefficient represents the importance of the target sensor for food spoilage detection of the target food; determining a sensor weight of the target sensor according to the quality parameter and the food coefficient; Fusing the corruption detection result corresponding to each target sensor with the sensor weight to obtain a comprehensive corruption detection result corresponding to the target food; The remaining storage time of the target food is determined based on the comprehensive corruption detection result and the actual storage temperature of the refrigerator.

2. The method according to claim 1, wherein obtaining the quality parameter of each target sensor in the target sensor set during the data acquisition process comprises: For each target sensor in the target sensor set, obtaining a target range of the target sensor; determining signal quality according to a ratio between a fluctuation amplitude of the target data and the target range during data acquisition; Obtaining a historical accuracy rate of the target sensor; The historical accuracy rate and the signal quality are weighted and fused according to preset weights to obtain the quality parameter of the target sensor.

3. The method according to claim 2, characterized in that The obtaining of the historical accuracy of the target sensor includes: Obtaining a historical prediction record table corresponding to the target sensor, wherein the historical prediction record table includes historical feedback information corresponding to a preset number of historical comprehensive corruption detection results; Determining the correct number of historical comprehensive corruption detection results in the historical prediction record table based on the historical feedback information; The ratio of the correct number to the preset number is determined as the historical accuracy rate of the target sensor.

4. The method according to claim 1, wherein The determining the sensor weight of the target sensor according to the quality parameter and the food coefficient includes: For each target sensor in the target sensor set, taking the product of the food coefficient corresponding to each target sensor and the quality parameter as an initial weight; Based on the initial weight of each target sensor, determine the sum of the initial weights; A ratio of the initial weight of each target sensor to the sum of the initial weights is determined as the sensor weight of each target sensor.

5. The method according to claim 1, wherein The determining, based on the comprehensive corruption detection result and the actual storage temperature of the refrigerator, of the remaining storage time of the target food includes: Obtaining an ideal storage time for the target food, where the ideal storage time represents the time required for the target food to reach a spoilage state at an ideal storage temperature; Matching the corruption sensitivity coefficient corresponding to the food type from the preset detection library; determining a corruption magnitude based on the corruption sensitivity coefficient and the comprehensive corruption detection result; The remaining storage time of the target food is determined based on the actual storage temperature of the refrigerator, the ideal storage time and the degree of spoilage.

6. The method according to claim 1, characterized in that The method further comprises: issuing an early warning prompt based on the comprehensive corruption detection result and the remaining storage time; In response to a feedback operation on the early warning prompt, obtaining feedback information; adjusting the quality parameter of the target sensor according to the feedback information to obtain an adjusted quality parameter; wherein the feedback information indicates whether the comprehensive corruption detection result is correct; The corruption detection result corresponding to each target sensor and the adjusted quality parameter are fused to obtain the adjusted comprehensive corruption detection result corresponding to the target food.

7. The method according to claim 6, characterized in that The step of adjusting the quality parameter of the target sensor according to the feedback information to obtain the adjusted quality parameter includes: If the feedback information indicates that the comprehensive corruption detection result is correct, determining an improvement magnitude based on the corruption detection result corresponding to the target sensor and a preset improvement ratio; Determining the adjusted quality parameter according to the quality parameter and the improvement margin; If the feedback information indicates that the comprehensive corruption detection result is erroneous, determining a reduction range based on the corruption detection result corresponding to the target sensor and a preset reduction ratio; The adjusted quality parameter is determined according to the quality parameter and the reduction amplitude.

8. A food spoilage prediction device, characterized in that: The device comprises: A target sensor set matching module is used to determine the type of target food if it is detected that the target food is placed in the refrigerator, and match the target sensor set corresponding to the type of food from a preset detection library; a corruption prediction module, configured to control each target sensor in the target sensor set to collect data, and perform food corruption detection processing based on the target data collected by each target sensor, thereby obtaining a corruption detection result corresponding to each target sensor; the corruption detection result represents the degree of corruption of the target food; a parameter acquisition module, configured to acquire quality parameters of each target sensor in the target sensor set during data acquisition, and to acquire a food coefficient of each target sensor in the target sensor set from the preset detection library; the food coefficient represents the importance of the target sensor for food spoilage detection of the target food; a sensor weight determination module, configured to determine a sensor weight of the target sensor according to the quality parameter and the food coefficient; A result integration module is used to fuse the corruption detection result corresponding to each target sensor and the sensor weight to obtain a comprehensive corruption detection result corresponding to the target food; The remaining storage time determination module is used to determine the remaining storage time of the target food according to the comprehensive corruption detection result and the actual storage temperature of the refrigerator.

9. An electronic device, characterized in that: The electronic device includes: a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the food spoilage prediction method as described in any one of claims 1-7.

10. A computer storage medium, characterized in that The computer storage medium stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the food spoilage prediction method according to any one of claims 1 to 7.

Images