Cooking equipment life prediction method and device, electronic equipment and storage medium

Abstract

The invention relates to a service life prediction method and device of cooking equipment, electronic equipment and a storage medium. The method comprises the following steps: acquiring life-related information of the cooking equipment in a life prediction period, wherein the life-related information comprises at least one of equipment part information, use environment information and equipment use information; according to an information type included in the life-related information, calling a feature extraction mode matched with the information type to perform feature extraction on the life-related information to obtain life-related feature data of the cooking equipment; inputting the life-related characteristic data into a life prediction model for life prediction to obtain a life prediction result of the cooking equipment; the life prediction model is obtained through training according to historical life-related information of the cooking equipment. The method can improve the accuracy of predicting the service life of the cooking equipment.

Description

Technical Field

[0001] The present application relates to the field of household appliance control technology, and in particular to a method, device, computer equipment, storage medium and computer program product for predicting the life of a cooking device. Background Art

[0002] As people's living standards gradually improve, intelligently controlled kitchen appliances are gradually entering thousands of households, providing users with a high-quality cooking experience. At present, the repair and replacement of cooking equipment in the market is often based on the user's subjective judgment, or the recommended service life of the cooking equipment is pre-marked in the product manual.

[0003] However, due to the differences in the usage environments of cooking equipment, the corresponding service life will also be more or less different. If the service life is judged only based on the user's subjective judgment or the recommended service life, it is easy for the safety of the cooking equipment to be reduced due to inaccurate life judgment. At the same time, during use, the cooking equipment may be excessively aged, resulting in waste of resources and reducing the use effect of the cooking equipment. Summary of the invention

[0004] Based on this, it is necessary to provide a cooking equipment life prediction method, device, computer equipment, computer-readable storage medium and computer program product that can improve the accuracy of cooking equipment life prediction in order to address the above technical problems.

[0005] In a first aspect, the present application provides a method for predicting the life of a cooking device, the method comprising:

[0006] Acquire life-related information of the cooking device within a life prediction period, wherein the life-related information includes at least one of device component information, usage environment information, and device usage information;

[0007] According to the information type contained in the life-related information, calling a feature extraction method matching the information type to extract features from the life-related information to obtain life-related feature data of the cooking device;

[0008] The life-related characteristic data is input into a life-related prediction model to perform life-related prediction, thereby obtaining a life-related prediction result of the cooking device; the life-related prediction model is trained based on historical life-related information of the cooking device.

[0009] In one embodiment, the feature extraction method corresponding to the equipment component information includes image feature extraction; calling the feature extraction method matching the information type to extract the life-related information to obtain the life-related feature data of the cooking equipment includes:

[0010] In the case where the life-related information includes the device component information, extracting component images of each key component from the device component information according to a preset image processing algorithm;

[0011] Calling a component aging recognition model to perform aging recognition on each of the component images, and determining a component aging characteristic value of each of the key components;

[0012] The component aging characteristic value is determined as life-related characteristic data of the cooking device.

[0013] In one embodiment, the feature extraction method corresponding to the usage environment information includes trend feature extraction, and calling the feature extraction method matching the information type to extract features of the life-related information to obtain the life-related feature data of the cooking device includes:

[0014] In the case where the lifespan related information includes the usage environment information, extracting the information collection time and the corresponding environment information value from the usage environment information;

[0015] Generate change trend information according to the information collection time and the corresponding environmental information value;

[0016] The change trend information is determined as life-span-related characteristic data of the cooking device.

[0017] In one embodiment, the feature extraction method corresponding to the device usage information includes mapping feature extraction, and calling the feature extraction method matching the information type to extract features of the life-related information to obtain the life-related feature data of the cooking device includes:

[0018] In the case where the lifespan related information includes device usage information, calling a preset mapping relationship between the device usage information and the usage aging characteristic value;

[0019] Based on the preset mapping relationship, determining a usage aging characteristic value matching the device usage information;

[0020] The usage aging characteristic value is determined as the life-span-related characteristic data of the cooking device.

[0021] In one embodiment, the life prediction result includes the predicted life value of the cooking device and key aging factors; the method further includes:

[0022] In a case where the predicted life value is less than or equal to a preset life threshold, determining the factor type of the key aging factor;

[0023] Based on the factor types of the key aging factors, a life optimization solution for the cooking device is determined.

[0024] In one embodiment, the determining of the life optimization solution of the cooking device based on the factor type of the key aging factor includes:

[0025] If the factor type is a heating component of the device, calling the preset correspondence between the aging characteristic value of the heating component of the device and the adjustment value of each parameter in the cooking algorithm;

[0026] Based on the preset corresponding relationship, determining each adjustment parameter matching the aging characteristic value of the key aging factor, and the parameter adjustment value of each adjustment parameter;

[0027] According to the parameter adjustment values ​​of the respective adjustment parameters, the cooking algorithm of the cooking device is parameter adjusted to obtain an updated cooking algorithm.

[0028] In one embodiment, the determining of the life optimization solution of the cooking device based on the factor type of the key aging factor includes:

[0029] If the factor type is a non-equipment heating component, determining the aging cause of the key aging factor;

[0030] A lifespan optimization guide for the cooking device is generated and displayed based on the aging causes.

[0031] In one embodiment, the life prediction result also includes aging results of various aging factors; the method further includes:

[0032] When the predicted life value is greater than the preset life threshold, determining the respective pre-maintenance mode of each aging factor according to the aging result of each aging factor;

[0033] A preventive maintenance plan for the cooking device is generated and displayed based on each of the preventive maintenance methods.

[0034] In one embodiment, the method further comprises:

[0035] In response to a model update event, acquiring model update information of the life prediction model, wherein the model update information includes at least one of information related to the life of the cooking device within a model update period and user feedback information;

[0036] Based on the model update information, the model parameters of the life prediction model are optimized to update the life prediction model.

[0037] In one embodiment, the training method of the life prediction model includes:

[0038] Obtaining information related to the historical life of the cooking equipment and an initial life prediction model built based on preset life assessment indicators;

[0039] generating a training sample set of the cooking device based on the historical life-related information;

[0040] Performing model training on the initial life prediction model of the cooking device according to the training sample set;

[0041] When the initial life prediction model meets the model training end condition, the initial life prediction model is determined as the life prediction model of the cooking device.

[0042] In a second aspect, the present application further provides a life prediction device for a cooking device, the device comprising:

[0043] An information acquisition module, used to acquire life-related information of the cooking device within a life prediction period, wherein the life-related information includes at least one of device component information, use environment information, and device use information;

[0044] A feature extraction module, configured to extract features of the life-related information according to the information type contained in the life-related information and call a feature extraction method matching the information type to obtain life-related feature data of the cooking device;

[0045] The life prediction module is used to input the life-related characteristic data into a life prediction model to perform life prediction and obtain a life prediction result of the cooking device; the life prediction model is trained based on historical life-related information of the cooking device.

[0046] In a third aspect, the present application further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0047] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0048] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0049] The above-mentioned cooking equipment life prediction method, device, computer equipment, storage medium and computer program product obtain life-related information of the cooking equipment within the life prediction period, and the life-related information includes at least one of equipment component information, usage environment information and equipment usage information. According to the information type contained in the life-related information, a feature advance method matching the information type is called to extract features of the life-related information to obtain life-related feature data of the cooking equipment. The life-related feature data can accurately reflect the specific circumstances of the relevant factors related to the service life of the cooking equipment. The life-related feature data is input into the life prediction model to perform life prediction and obtain the life prediction result of the cooking equipment. Since the life prediction model is trained based on the historical life-related information of the cooking equipment, by inputting the life-related feature data into the life prediction model, the life prediction model can accurately predict the life of the cooking equipment based on the specific circumstances of the relevant factors related to the service life reflected by the life-related feature data, thereby effectively improving the accuracy of the life prediction of the cooking equipment, and thereby improving the safety and use effect of the cooking equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] FIG1 is a diagram showing an application environment of a method for predicting the life of a cooking device in one embodiment;

[0051] FIG2 is a schematic flow chart of a method for predicting the life of a cooking device in one embodiment;

[0052] 3 is a schematic diagram of a process of extracting features of life-related information by calling a feature extraction method that matches the information type to obtain life-related feature data of a cooking device in one embodiment;

[0053] FIG4 is a schematic diagram of a process of extracting features of life-related information by calling a feature extraction method that matches the information type to obtain life-related feature data of a cooking device in another embodiment;

[0054] 5 is a schematic diagram of a process of extracting features of life-related information by calling a feature extraction method that matches the information type to obtain life-related feature data of a cooking device in another embodiment;

[0055] FIG6 is a schematic diagram of a process for determining a life optimization solution for a cooking device based on the factor types of key aging factors in one embodiment;

[0056] FIG7 is a flow chart of a training method for a life prediction model in one embodiment;

[0057] FIG8 is a schematic flow chart of a method for predicting the life of a cooking device in another embodiment;

[0058] FIG9 is a structural block diagram of a device for predicting the life of a cooking device in one embodiment;

[0059] FIG. 10 is a diagram showing the internal structure of an electronic device in one embodiment. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0061] The life prediction method of a cooking device provided in an embodiment of the present application can be applied to a cooking device 100 as shown in FIG1 . The cooking device 100 includes an information acquisition component 101 and a controller 102, and the controller 102 is in communication with the information acquisition component 101, and can obtain life-related information of the cooking device 100 through the information acquisition component 101. The data storage system can store data that the controller 102 needs to process. The data storage system can be integrated on the controller 102, or can be placed on a cloud or other network server. The controller 102 obtains life-related information of the cooking device 100 within the life prediction period based on the information acquisition component 101, and the life-related information may include at least one of equipment component information, use environment information, and equipment use information. The controller 102 extracts features of the life-related information by calling a feature extraction method matching the information type according to the information type contained in the life-related information, and obtains life-related feature data of the cooking device 100. The life-related feature data is input into a life prediction model for life prediction, and a life prediction result of the cooking device 100 is obtained, wherein the life prediction model is trained according to the historical life-related information of the cooking device 100.

[0062] The cooking device 100 may be any smart kitchen device for cooking food, such as a microwave oven, a steam oven, etc.

[0063] The information collection component 101 may be any device component capable of collecting life-related information. For example, when the life-related information includes usage environment information, the information collection component 101 may include a device component that collects environmental information about the device usage environment of the cooking device 100, such as a temperature collection component, a humidity collection component, an odor collection component, etc. When the life-related information includes device component information, the information collection component 101 may include an image collection component that collects image information about the device components of the cooking device 100. When the life-related information includes device usage information, the information collection component 101 may include a usage information collection module in the controller 102 that collects usage information about the cooking device 100.

[0064] The controller 102 may be any control device having a logic processing function, such as an MCU, a single-chip microcomputer, etc.

[0065] In one embodiment, as shown in FIG. 2 , a method for predicting the life of a cooking device is provided, and the method is described by taking the controller 102 in FIG. 1 as an example, including the following steps:

[0066] S202, obtaining life-related information of the cooking device within a life prediction period, where the life-related information includes at least one of device component information, usage environment information, and device usage information.

[0067] The life prediction cycle is the usage cycle of the cooking device when the life prediction is performed on the cooking device. The life prediction cycle corresponds to a preset cycle length, and the controller needs to predict the life of the cooking device based on the life-related information collected within the life prediction cycle.

[0068] It is understandable that in some embodiments, the process of predicting the life of the cooking device can be a periodic process, and when the use cycle of the cooking device is within the life prediction cycle, the life prediction of the cooking device can be performed. In other embodiments, the life prediction cycle of the cooking device can be generated by triggering a life prediction operation for the cooking device. For example, the designer can pre-set the cycle duration corresponding to the life prediction cycle of the cooking device. When the cooking device needs to perform life prediction, such as when the user triggers the life prediction operation for the cooking device, or when the cooking device triggers a preset life prediction event, the controller can determine the life prediction cycle for predicting the life of the cooking device according to the cycle duration corresponding to the life prediction cycle.

[0069] The life-span related information is information data that is correlated with the service life of the cooking device, wherein the life-span related information may include at least one of device component information, usage environment information, and device usage information.

[0070] The equipment component information is information data that can reflect the usage of the equipment components of the cooking equipment, and can be obtained by collecting images of the equipment components through the information collection component. For example, the information collection component includes an image collection component, and the image collection component can collect images of different parts of the cooking equipment at a fixed time or according to the usage to obtain equipment component information, such as pictures or video streams of the equipment components. The equipment components may include heating elements, the inner wall of the oven cavity, the sealing material of the door, the control panel, etc.

[0071] The use environment information is information data that can reflect the use environment of the cooking device, and can be obtained by collecting information about the setting environment of the cooking device through the information collection component. For example, the information collection component includes at least one of a temperature sensor, a humidity sensor, and an odor sensor. During the life prediction period, the information collection component can collect environmental information about the setting environment of the cooking device to obtain, for example, temperature information, humidity information, odor information, etc. of the setting environment of the cooking device.

[0072] The equipment usage information is information data that can reflect the use and operation of the cooking equipment, such as the use frequency of the cooking equipment, the working cycle, the heating stability of the heating tube, the peak use period, etc. The equipment usage information can be obtained by acquiring the recorded information of the cooking equipment during use through the information collection component, and in this case, the information collection component may include a usage information collection module in the controller.

[0073] It should be noted that when the equipment usage information includes the heating stability of the heating tube, the information collection component includes not only the usage information collection module in the controller, but also the temperature sensor corresponding to the heating tube. The usage information collection module can be used to collect the actual control input temperature during the use of the cooking equipment, such as the setting temperature, the temperature in the temperature maintenance stage, etc. The temperature sensor corresponding to the heating tube can be used to detect the actual heating temperature of the heating tube during operation. The controller can compare the actual heating temperature with the actual control input temperature, and determine the heating stability of the heating tube based on the error range obtained by multiple comparisons and the number of deviations with error deviations. For example, the smaller the error and the fewer the number of deviations, the more stable the heating stability of the heating tube.

[0074] Specifically, when the controller determines that the cooking equipment enters a life prediction period, it can obtain life-related information of the cooking equipment within the life prediction period based on the information acquisition component. The life-related information includes at least one of equipment component information, usage environment information, and equipment usage information.

[0075] S204, according to the information type included in the life-related information, calling a feature extraction method matching the information type to extract features from the life-related information, and obtaining life-related feature data of the cooking device.

[0076] Among them, the information type included in the life-related information is at least one of equipment component information, usage environment information and equipment usage information. Since the information recording format of each information type may be different, the corresponding feature extraction method is also different. Therefore, it is necessary to perform feature extraction on the corresponding life-related information through a feature extraction method matching the information type to obtain the life-related feature data of the cooking equipment.

[0077] Life-related feature data is feature data that can characterize the relevant impact of various life-influencing factors. By performing feature extraction operations on life-related information, feature data corresponding to each life-influencing factor related to the service life of cooking equipment can be extracted from a large amount of information, which is more suitable for the use of subsequent life prediction models.

[0078] Specifically, after obtaining the life-related information of the cooking equipment within the life prediction period, the controller can first determine the information type contained in the life-related information, and then call the feature extraction method that matches the information type from a plurality of pre-set candidate feature extraction methods according to the information type contained in the life-related information, and perform feature extraction on the life-related information corresponding to the information type through the feature extraction method that matches the information type to obtain the life-related feature data of the cooking equipment.

[0079] For example, when the controller determines that the information types included in the life-related information are equipment component information, usage environment information, and equipment usage information, the controller can call a feature extraction method that matches the equipment component information based on the equipment component information to extract features from the equipment component information, and obtain relevant feature data corresponding to the equipment component information. Call a feature extraction method that matches the usage environment information based on the usage environment information to extract features from the usage environment information, and obtain relevant feature data corresponding to the usage environment information. Call a feature extraction method that matches the equipment usage information based on the equipment usage information to extract features from the equipment usage information, and obtain relevant feature data corresponding to the equipment usage information. The relevant feature data corresponding to the three types of information are collectively determined as the life-related feature data of the cooking equipment.

[0080] In some of the embodiments, the controller may search for a correspondence between a pre-configured type identifier and a feature extraction method according to a type identifier corresponding to the information type, and determine the feature extraction method matching the type identifier as the feature extraction method matching the information type.

[0081] S206, inputting the life-related characteristic data into a life prediction model to perform life prediction, and obtaining a life prediction result of the cooking device.

[0082] Among them, the life prediction model is trained based on the historical life-related information of the cooking equipment. By using the historical life-related information to train the initial life prediction model, the prediction accuracy of the life prediction model can be effectively improved, and an accurate prediction tool can be provided for subsequent life prediction of the cooking equipment. It can be understood that the life prediction model can be a multimodal prediction model, such as a support vector machine (SVM), a random forest model, a deep neural network (DNN) model, etc.

[0083] Specifically, the controller can input the life-related feature data obtained after feature extraction into the pre-trained life prediction model to predict the life of the cooking device and obtain the life prediction result of the cooking device. It can be understood that the life prediction result can only include the predicted life value of the cooking device, or can also include, for example, the aging value of each aging factor, the aging result, and the key aging factor among the aging factors according to the actual subsequent maintenance needs.

[0084] In the above-mentioned life prediction method for cooking equipment, life-related information of the cooking equipment within the life prediction period is obtained, and the life-related information includes at least one of equipment component information, usage environment information and equipment usage information. According to the information type contained in the life-related information, a feature advance method matching the information type is called to extract features of the life-related information to obtain life-related feature data of the cooking equipment. The life-related feature data can accurately reflect the specific circumstances of the relevant factors related to the service life of the cooking equipment. The life-related feature data is input into the life prediction model to perform life prediction, and the life prediction result of the cooking equipment is obtained. Since the life prediction model is trained based on the historical life-related information of the cooking equipment, by inputting the life-related feature data into the life prediction model, the life prediction model can accurately predict the life of the cooking equipment based on the specific circumstances of the relevant factors related to the service life reflected by the life-related feature data, thereby effectively improving the accuracy of the life prediction of the cooking equipment, and thereby improving the safety and use effect of the cooking equipment.

[0085] Since the life-related information includes at least one of equipment component information, usage environment information and equipment usage information, how to perform feature extraction will be specifically described below through several embodiments.

[0086] In some embodiments, as shown in FIG. 3 , the feature extraction method corresponding to the equipment component information includes image feature extraction, and the feature extraction method matching the information type is called in S204 to extract the life-related information to obtain the life-related feature data of the cooking equipment, including:

[0087] S302: When the life-related information includes equipment component information, component images of key components are extracted from the equipment component information according to a preset image processing algorithm.

[0088] Among them, the preset image processing algorithm is an image processing algorithm used to extract the key component image in the image information. The preset image processing algorithm can be designed by the designer in advance according to the key components to be extracted, and can accurately determine the key components to be extracted from the graphic information, and cut and segment the component image of the key component from the overall image information to obtain the component image of the key component. For example, the preset image processing algorithm can be an image segmentation algorithm based on deep learning, which can automatically learn the features of the key components in the image and accurately segment the target object.

[0089] Specifically, when the controller determines that the life-related information includes equipment component information, it can determine that the feature extraction method that matches the equipment component information is image feature extraction. Since the information acquisition component, such as the image acquisition component, may perform image acquisition on one area when acquiring images of cooking equipment, the obtained equipment component information may contain component information that is not relevant to life prediction. In order to reduce the complexity and computational complexity of subsequent image feature extraction, the controller can first call a preset image processing algorithm to extract component images of each key component from the equipment component information.

[0090] S304, calling a component aging recognition model to perform aging recognition on each component image, and determining a component aging feature value of each key component.

[0091] Among them, the component aging recognition model is a preset model used to identify the aging of component images and determine the corresponding component aging feature values. The component aging recognition model can be obtained by pre-training the model based on the historical component image data of key components. Similarly, the component aging recognition model can be a support vector machine (SVM), a random forest model, a deep neural network (DNN) model, etc.

[0092] Specifically, after extracting the component images of each key component from the equipment component information, the controller can call the pre-trained component aging recognition model, input the component images of each key component into the component aging recognition model, and use the component aging recognition model to perform aging recognition on each component image to determine the component aging feature value of each key component. It can be understood that the component aging feature value can be a specific numerical value or a feature vector.

[0093] S306: Determine the component aging characteristic value as life-span-related characteristic data of the cooking device.

[0094] Specifically, the controller may determine the obtained component aging characteristics as the life-related characteristic data of the cooking device. It is understandable that, when the life-related information only includes the device component information, the component aging characteristic value is all the life-related characteristic data of the cooking device, and when the life-related information also includes other information types, such as usage environment information and / or device usage information, the component aging characteristic value is part of the life-related characteristic data of the cooking device.

[0095] In the above embodiment, a component image of each key component is extracted from the equipment component information through a preset image processing algorithm, and a component aging recognition model is called to perform aging recognition on each component image to determine the component aging characteristic value of each key component. This can effectively improve the feature extraction efficiency and extraction accuracy of life-related feature data, and provide an accurate data basis for subsequent life prediction.

[0096] In some embodiments, as shown in FIG. 4 , the feature extraction method corresponding to the use environment information includes trend feature extraction, and the feature extraction method matching the information type is called in S204 to extract the life-related information to obtain the life-related feature data of the cooking device, including:

[0097] S402: When the lifespan-related information includes usage environment information, extract information collection time and corresponding environment information value from the usage environment information.

[0098] The use environment information is information data obtained after collecting information about the setting environment of the cooking device. When collecting the environment information, a sensor component is usually used to perform the information collection task to obtain a corresponding sensor signal, that is, the use environment information is mostly an environment information collection signal. For example, the information collection component may include a temperature sensor, a humidity sensor, and an odor sensor, which are respectively used to collect temperature information, humidity information, and odor information of the setting environment of the cooking device.

[0099] Specifically, after obtaining the usage environment information, the controller can determine that the feature extraction method that matches the usage environment information is trend feature extraction. The controller can process the sensor signal in the usage environment information to obtain the corresponding environment information value and the information collection time corresponding to the environment information value.

[0100] In some of the embodiments, when the usage environment information includes temperature information, the controller may process the sensor data collected by the temperature sensor to obtain a corresponding environment temperature value, and simultaneously obtain a temperature collection time corresponding to the environment temperature value.

[0101] In some of the embodiments, when the environmental information includes humidity information, the controller may process the sensor data collected by the humidity sensor to obtain a corresponding environmental humidity value, and simultaneously obtain a humidity collection time corresponding to the environmental humidity value.

[0102] In some embodiments, when the use environment information includes odor information, the controller can process the sensor data collected by the odor sensor, such as the electronic nose, to obtain the corresponding environment odor information, and then determine the types of environment odors contained in the environment where the cooking device is located, and the odor concentration values ​​corresponding to each environment odor type according to the environment odor information, and then obtain the odor collection time corresponding to the odor concentration value. It can be understood that the types of environment odors can include material aging odors (odors generated by thermal decomposition of plastic or rubber seals), food residue odors, electrical or mechanical failure odors (such as odors generated by wire insulation loss, motor overheating, or grease decomposition), etc.

[0103] S404: Generate change trend information according to the information collection time and the corresponding environmental information value.

[0104] Specifically, after obtaining each environmental information value and the information collection time corresponding to each environmental information value, the controller can generate change trend information according to the information collection time and the corresponding environmental information value.

[0105] In some of the embodiments, the controller may generate change trend information based only on environmental information values ​​collected within the current life prediction period and the corresponding information collection time.

[0106] In other embodiments, the controller may generate change trend information based on the environmental information values ​​collected in the current life prediction period and the corresponding information collection time, and the historical environmental information values ​​collected in the historical life prediction period and the corresponding historical information collection time. It is understandable that the historical life prediction period may be the previous life prediction period or the previous several life prediction periods, which may be determined by the designer according to the actual prediction accuracy.

[0107] It should be noted that, since the use environment information may include, for example, at least one of the environment temperature information, environment humidity information, and environment odor information, the change trend contained in the corresponding change trend information should match the type of information contained in the use environment information. For example, the change trend information may include at least one of the temperature change trend, humidity change trend, and odor change trend, and the odor change trend may also be divided into material aging odor change trend, food residue odor change trend, electrical or mechanical failure odor change trend, etc.

[0108] S406: Determine the change trend information as life-span-related characteristic data of the cooking device.

[0109] Specifically, after obtaining the change trend information, the controller can determine the change trend information as the life-related characteristic data of the cooking equipment. Similarly, when the life-related information only includes the usage environment information, the change trend information is all the life-related characteristic data of the cooking equipment. When the life-related information also includes other information types, such as equipment component information and / or equipment usage information, the change trend information is part of the life-related characteristic data of the cooking equipment.

[0110] In the above embodiment, by extracting the usage environment information and generating change trend information based on the extracted information collection time and the corresponding environmental information value, the life-related characteristic data can effectively reflect the environmental information of the cooking equipment usage environment, thereby improving the prediction accuracy of subsequent cooking equipment life prediction.

[0111] In some embodiments, as shown in FIG. 5 , the feature extraction method corresponding to the device usage information includes mapping feature extraction, and the feature extraction method matching the information type is called in S204 to extract the life-related information to obtain the life-related feature data of the cooking device, including:

[0112] S502: When the lifespan-related information includes device usage information, a preset mapping relationship between the device usage information and the usage aging characteristic value is called.

[0113] Among them, the equipment usage information is information data that can reflect the use and operation of the cooking equipment, such as the use frequency of the cooking equipment, the working cycle, the heating stability of the heating tube, the peak use period, etc. Since the equipment usage information is relatively clear information content, the designer can determine the corresponding use aging characteristic value for the equipment usage information in advance based on experimental values ​​or empirical values. For example, the use frequency of twice a week corresponds to the use aging characteristic value A, and the use frequency of twice a day corresponds to the use aging characteristic value B, etc., and generate a preset mapping relationship based on the equipment usage information and the corresponding use aging characteristic value, and configure the preset mapping relationship in the controller so that the controller can call it at any time when predicting the life of the cooking equipment.

[0114] Specifically, when determining that the life-related information includes device usage information, the controller may determine that the feature extraction method matching the device usage information is mapping feature extraction, and the controller may call a preset mapping relationship between the pre-stored device usage information and the usage aging feature value.

[0115] S504: Determine, based on a preset mapping relationship, a usage aging characteristic value that matches the device usage information.

[0116] Specifically, after obtaining the preset mapping relationship between the device usage information and the usage aging characteristic value, the controller may search for the usage aging characteristic value matching the device usage information in the preset mapping relationship.

[0117] In some of the embodiments, since the equipment usage information may include at least one of, for example, usage frequency, duty cycle, heating stability of the heating tube, and peak usage period, the corresponding usage aging characteristic value may also include aging characteristic values ​​corresponding to each type of information, such as usage aging characteristic values ​​corresponding to usage frequency, usage aging characteristic values ​​corresponding to heating stability, etc.

[0118] S506: Determine the usage aging characteristic value as life-span-related characteristic data of the cooking device.

[0119] Specifically, after obtaining the usage aging characteristic value that matches the device usage information, the controller can determine the usage aging characteristic value as the life-related characteristic data of the cooking device. Similarly, when the life-related information only includes the device usage information, the usage aging characteristic value is all the life-related characteristic data of the cooking device. When the life-related information also includes other types of information, such as device component information and / or usage environment information, the usage aging characteristic value is part of the life-related characteristic data of the cooking device.

[0120] In the above embodiment, by pre-setting a preset mapping relationship between equipment usage information and usage aging characteristic values ​​in the controller, when it is determined that the life-related information includes equipment usage information, the controller can directly call the preset mapping relationship between the equipment usage information and the usage aging characteristic values, and quickly determine the usage aging characteristic values ​​that match the equipment usage information, thereby effectively improving the efficiency and accuracy of determining the life-related characteristic data, thereby improving the prediction efficiency and prediction accuracy when performing subsequent cooking equipment life prediction.

[0121] The above embodiments elaborate on the process of how to extract features of life-related information and obtain life-related feature data. In the life prediction scheme, in addition to accurate life prediction, how to optimize the cooking equipment accordingly based on the life prediction results is also an important step to improve the service life of the cooking equipment.

[0122] In some embodiments, the life prediction results include a predicted life value of the cooking equipment and key aging factors. The life prediction method of the cooking equipment also includes: when the predicted life value is less than or equal to a preset life threshold, determining the factor type of the key aging factor, and determining a life optimization plan for the cooking equipment based on the factor type of the key aging factor.

[0123] The preset life threshold is a preset judgment threshold parameter used to determine whether the cooking device needs equipment maintenance. When the preset life value is less than or equal to the preset life threshold, it means that the cooking device may be aged, but it has little impact on the use of the cooking device. There is no need to perform additional after-sales maintenance on the cooking device, such as replacing parts or deep cleaning, and the cooking device only needs to be optimized according to the life optimization plan.

[0124] The key aging factor is an aging factor that has a key impact on the aging of the cooking device. In some embodiments, the key aging factor may be an aging factor with the largest corresponding aging value among the aging factors. In other embodiments, the key aging factor may also be an aging factor with the highest correlation with the service life of the cooking device among the aging factors.

[0125] Among them, based on the different subsequent life optimization schemes, the aging factors can be divided into two types of factors, one is the equipment heating component, and the other is the non-equipment heating component. It can be understood that the equipment heating component can be considered as a key factor affecting the cooking effect of the cooking device. If the heating component is aged, even if the preset life value of the cooking device is less than or equal to the preset life threshold, that is, the cooking device can still continue to be used, but its cooking effect will be greatly reduced. Therefore, the controller needs to determine the subsequent life optimization scheme for optimizing the life of the cooking device according to the factor type of the key aging factor, so as to improve the matching of the life optimization scheme with the actual situation of the cooking device.

[0126] Specifically, after obtaining the predicted life value and key aging factors output by the life prediction model, the controller can compare the predicted life value with the preset life threshold. If the predicted life value is less than or equal to the preset life threshold, the controller can determine the factor type of the key aging factor and determine the life optimization plan for the cooking equipment based on the factor type of the key aging factor.

[0127] In the above embodiment, when the predicted life value is less than or equal to the preset life threshold, by determining the factor type of the key aging factor and determining the life optimization plan of the cooking equipment based on the factor type, the matching between the life optimization plan and the actual situation of the cooking equipment can be effectively improved, thereby improving the life optimization effect of the cooking equipment and increasing the service life of the cooking equipment.

[0128] In some embodiments, as shown in FIG6 , determining a life optimization solution for a cooking device based on the factor type of a key aging factor includes:

[0129] S602: If the factor type is a heating component of the equipment, the preset correspondence between the aging characteristic value of the heating component of the equipment and the adjustment value of each parameter in the cooking algorithm is called.

[0130] Among them, if the factor type is the equipment heating component, it means that although the cooking equipment can still continue to be used, the cooking effect of the cooking equipment will be greatly reduced in the current state. In order to eliminate the impact of the aging of the heating component on the cooking effect as much as possible, the algorithm parameters in the cooking algorithm can be adjusted so that the adjusted cooking algorithm can adapt to the current aging of the equipment heating component and still maintain the cooking effect before aging. Designers can determine the parameter adjustment values ​​corresponding to each algorithm parameter in the cooking algorithm in the case of various aging characteristic values ​​of the equipment heating component based on experimental data or empirical data in advance, and generate a preset corresponding relationship based on various aging characteristic values ​​and corresponding parameter adjustment values, so as to obtain the preset corresponding relationship between the aging characteristic value of the equipment heating component and the parameter adjustment value of each parameter in the cooking algorithm, and store the preset corresponding relationship in the controller in advance so that the controller can call it at any time.

[0131] Specifically, when determining that the factor type of the key aging factor is the device heating component, the controller can call the preset correspondence between the aging characteristic value of the device heating component and the adjustment value of each parameter in the cooking algorithm.

[0132] It can be understood that when there are multiple heating components of the device, the controller can call the preset correspondence between the aging characteristic value of the corresponding heating component of the device and the adjustment value of each parameter in the cooking algorithm according to the factor identifier of the key aging factor.

[0133] S604: Based on the preset corresponding relationship, determine each adjustment parameter that matches the aging characteristic value of the key aging factor, and the parameter adjustment value of each adjustment parameter.

[0134] Specifically, the controller may search for each adjustment parameter that matches the aging characteristic value of the key aging factor and the parameter adjustment value of each adjustment parameter from the preset corresponding relationship based on the preset corresponding relationship.

[0135] S606: Perform parameter adjustment on the cooking algorithm of the cooking device according to the parameter adjustment values ​​of the adjustment parameters to obtain an updated cooking algorithm.

[0136] Specifically, after obtaining the adjustment parameters that match the aging characteristic values ​​of the key aging factors and the parameter adjustment values ​​of each adjustment parameter, the controller can perform parameter adjustment on the cooking algorithm of the cooking device according to the parameter adjustment values ​​of each adjustment parameter to obtain an updated cooking algorithm, and subsequently directly control the cooking device to perform cooking operations according to the updated cooking algorithm.

[0137] In the above embodiment, when the factor type of the key aging factor is determined to be the heating component of the equipment, the impact of the aging of the heating component on the cooking effect can be effectively eliminated by dynamically adjusting the cooking algorithm, so that the adjusted cooking algorithm can adapt to the current aging of the heating component of the equipment and still maintain the cooking effect before aging.

[0138] In other embodiments, based on the factor type of the key aging factor, a life optimization plan for the cooking equipment is determined, including: if the factor type is a non-equipment heating component, the aging cause of the key aging factor is determined, and based on the aging cause, a service life optimization guide for the cooking equipment is generated and displayed.

[0139] The service life optimization guide is used to provide users with advice information on extending the service life of cooking equipment, such as follow-up usage advice, cleaning advice, and safety inspection advice for cooking equipment, which can be considered as follow-up usage guide information for cooking equipment.

[0140] Specifically, when the controller determines that the factor type of the key aging factor is a non-equipment heating component, it can determine the aging cause of the key aging factor based on the key aging factor, generate a service life optimization guide for the cooking equipment based on the aging cause, and display the corresponding service life optimization guide to the user.

[0141] In some of the embodiments, the controller may search for an aging cause matching the factor identifier of the key aging factor from an aging cause library of aging factors according to the factor identifier of the key aging factor to obtain the aging cause of the key aging factor.

[0142] In some embodiments, the controller may display the life optimization guide on a display component of the cooking device, for example, through a human-computer interaction interface of the cooking device.

[0143] In some of the embodiments, the controller may send the life optimization guide to a user terminal for terminal display.

[0144] In the above embodiment, when the factor type of the key aging factor is determined to be a non-equipment heating component, by generating a service life optimization guide for the cooking equipment based on the aging cause of the key aging factor, it is possible to provide the user with usage suggestions for subsequent use of the cooking equipment, thereby improving the service life of the cooking equipment.

[0145] In some embodiments, the life prediction result also includes the aging results of each aging factor, and the life prediction method of the cooking device further includes: when the predicted life value is greater than a preset life threshold, determining the respective pre-maintenance methods of each aging factor according to the aging results of each aging factor. Generate and display a pre-maintenance plan for the cooking device based on each pre-maintenance method.

[0146] The aging result of the aging factor is result data used to reflect the aging degree of the aging factor. For example, the aging result of the aging factor can be the aging degree of the aging factor, or the impact of the aging of the aging factor. For example, when the aging factor is material aging, the corresponding aging result can be severe aging, or material aging has a potential fire risk.

[0147] Among them, the preventive maintenance method is a maintenance method for equipment maintenance based on aging factors. For example, if the aging factor is material aging, the corresponding preventive maintenance method may be replacement of materials.

[0148] The predictive maintenance plan is a plan information used to provide users with maintenance recommendations for cooking equipment, such as replacement of related parts, deep cleaning, estimated maintenance time, etc.

[0149] Specifically, the controller compares the predicted life value with the preset life threshold. If the predicted life value is greater than the preset life threshold, it means that the aging of the cooking device has affected the normal use of the cooking device and the cooking device needs to be maintained, such as replacing parts or deep cleaning. Before the control, the pre-maintenance method of the cooking device can be determined according to the aging results of each aging factor, and a pre-maintenance plan for the cooking device is generated based on the pre-maintenance method, and the pre-maintenance plan is displayed to the user.

[0150] In some embodiments, the controller may display the pre-maintenance plan on a display component of the cooking device, for example, through a human-computer interaction interface of the cooking device.

[0151] In some of the embodiments, the controller may send the pre-maintenance plan to a user terminal for terminal display.

[0152] In the above embodiment, when it is determined that the predicted life value of the cooking equipment is greater than the preset life threshold, a corresponding pre-maintenance plan can be generated and displayed according to the pre-maintenance method of each aging factor of the cooking equipment, which can guide the user to make appropriate maintenance or replacement decisions, reduce unnecessary maintenance costs, and maximize the use value of the cooking equipment.

[0153] Since the use environment of the cooking device is not static, in order to improve the accuracy of the life prediction of the cooking device, in some embodiments, the life prediction method of the cooking device may further include: in response to a model update event, obtaining model update information of the life prediction model. Based on the model update information, the model parameters of the life prediction model are optimized to update the life prediction model.

[0154] The model update event is a preset event for triggering a model update. For example, the model update event may be a user triggering a model update control, or the usage time of the cooking device reaches a preset model update triggering time, etc.

[0155] The model update information is information data used to update the life prediction model. The model update information may include at least one of information related to the life of the cooking device within the model update cycle and user feedback information.

[0156] Among them, the model update cycle is the use cycle of the cooking equipment when the life prediction model is updated. It can be understood that the model update cycle corresponds to a preset cycle length, and the model update cycle can overlap with the life prediction cycle.

[0157] User feedback information is information data provided by users regarding the use of cooking equipment when using the cooking equipment, such as feedback on the use effect of the cooking equipment, or maintenance records of the cooking equipment, such as component update records.

[0158] Specifically, in response to the model update event, the controller can obtain at least one of the life-related information of the cooking device and the user feedback information within the model update cycle, obtain the model update information of the life prediction model, optimize the model parameters of the life prediction model based on the model update information, and update the life prediction model. When the controller subsequently predicts the life of the cooking device, it will use the updated life prediction model to perform life prediction.

[0159] In some embodiments, when the model update information only includes life-related information of the cooking device within the model update period, the controller can compare the life-related information of the cooking device within the model update period with the life-related information collected within the previous life prediction period, determine the difference information within the two periods, call the preset correspondence between the difference information and the model adjustment parameter, determine the model adjustment parameter matching the difference information, and the model parameter adjustment value corresponding to the model adjustment parameter. The life prediction model is updated according to the model parameter adjustment value corresponding to the model adjustment parameter to obtain an updated life prediction model.

[0160] In some embodiments, when the model update information only includes user feedback information, the life-related information of the time period corresponding to the feedback time information can be obtained according to the feedback time information based on the feedback time information, and the life-related information of the time period corresponding to the feedback time information and the user feedback information can be used to update the life prediction model to obtain an updated life prediction model. The user feedback information can be used as a predicted theoretical value, and the model update process is to make the model output value continuously approach the predicted theoretical value until the error between the model output value and the predicted theoretical value is less than a preset error range.

[0161] In some embodiments, when the model update information includes information related to the life of the cooking device within the model update period and user feedback information, the life prediction model can be directly updated based on the model update information including information related to the life of the cooking device within the model update period and user feedback information to obtain an updated life prediction model. Similarly, the user feedback information can be used as a predicted theoretical value, and the life prediction model is called according to the information related to the life of the cooking device within the model update period to perform life prediction to obtain a model output value. The model update process is to make the model output value continuously approach the predicted theoretical value until the error between the model output value and the predicted theoretical value is less than a preset error range.

[0162] In the above embodiment, the life prediction model is dynamically updated by acquiring model update information, and the life prediction model is regularly adjusted and optimized, which can effectively improve the matching of the life prediction model with the use environment and conditions of the cooking equipment, and further improve the accuracy and practicality of the life prediction of the cooking equipment.

[0163] In some embodiments, as shown in FIG7 , the training method of the life prediction model includes:

[0164] S702, obtaining information related to the historical life of the cooking equipment and an initial life prediction model built based on preset life evaluation indicators.

[0165] The historical life-related information is life-related information obtained by collecting life-related information of the cooking equipment during the historical use period. The preset life evaluation index is the index information used for life prediction evaluation. For example, the preset life evaluation index may include index parameters used to reflect the performance degradation of the cooking equipment, such as heating efficiency degradation index, temperature control accuracy index, etc. It may also include index parameters used to reflect the safety of the cooking equipment, such as overheating risk index, fire risk index, etc.

[0166] Specifically, when the controller is training the model, it can obtain information related to the historical life of the cooking equipment, as well as an initial life prediction model built based on preset life assessment indicators.

[0167] S704: Generate a training sample set of cooking equipment based on historical life-span related information.

[0168] Specifically, after obtaining the historical life-related information, the controller may generate a training sample set of the cooking device based on the historical life-related information.

[0169] In some of the embodiments, the controller can perform feature extraction on historical life-related information to obtain historical life-related feature data, and bind the historical life-related feature data with its corresponding theoretical life value to obtain a training sample set for the cooking equipment.

[0170] S706: Perform model training on the initial life prediction model of the cooking equipment according to the training sample set.

[0171] Specifically, the controller may perform model training on the initial life prediction model of the cooking device according to the training sample set, so that the model output value gradually approaches the theoretical life value corresponding to the historical life-related characteristic data.

[0172] S708: When the initial life prediction model meets the model training end condition, the initial life prediction model is determined as the life prediction model of the cooking device.

[0173] Among them, the model training end condition is a preset judgment condition used to determine whether the initial life prediction model has been trained and can accurately predict the service life of the cooking equipment.

[0174] Specifically, when the initial life prediction model meets the model training end condition, the initial life prediction model is determined as the life prediction model of the cooking device.

[0175] In some of the embodiments, the model training termination condition may be that the difference between the model output value and the theoretical life value is less than a preset training difference threshold.

[0176] In some embodiments, the model training termination condition may also be that the difference between the model verification output value obtained by performing model verification on the initial life prediction model and the verification theoretical life is less than a preset training difference threshold. That is, when the difference between the model output value and the theoretical life value is less than the preset training difference threshold, the initial life prediction model is model verified using the verification data set to obtain a model verification output value, and the difference between the model verification output value and the verification theoretical life is compared with the preset training difference threshold. When the difference between the model verification output value and the verification theoretical life is less than the preset training difference threshold, it is determined that the initial life prediction model meets the model training termination condition.

[0177] In the above embodiment, by using historical life-related information to train the initial life prediction model built based on preset life assessment indicators, the prediction performance of the final life prediction model can be effectively improved, thereby improving the accuracy of life prediction of the cooking equipment.

[0178] In some embodiments, as shown in FIG8 , a method for predicting the life of a cooking device is provided. Taking a steam oven as an example, the method may specifically include the following steps:

[0179] First, the controller can collect device component information of the steam oven through an image acquisition component to obtain device component information of the steam oven. Specifically, the image acquisition component can be a camera built into or outside the steam oven, which can capture images or video streams of different parts of the steam oven at a fixed time or according to usage, such as heating elements, inner walls of the oven cavity, sealing materials of the door, control panel, etc.

[0180] The controller can collect environmental information of the steam oven through the environmental information collection component to obtain the use environment information of the steam oven. Specifically, the environmental information collection component may include a temperature sensor, a humidity sensor, and an odor sensor. The temperature and humidity information of the environment in which the steam oven is located can be obtained in real time through the temperature sensor and the humidity sensor. The odor information of the environment in which the steam oven is located can be obtained in real time through the odor sensor, such as odor information generated by material aging (thermal decomposition of plastic or rubber seals), food residues (long-term accumulation may cause odor, affecting cleaning and heating efficiency), electrical or mechanical failures (such as wire insulation damage, motor overheating, or odor generated by grease decomposition), etc.

[0181] You can also obtain the equipment usage information of the steam oven, such as the usage frequency of the steam oven, peak usage period, working cycle, heating stability of the heating tube, fault records, maintenance history and other information.

[0182] Subsequently, the controller may perform feature extraction on the collected life-related information to obtain life-related feature data.

[0183] Specifically, the controller can use image processing algorithms and deep learning models to identify features that may cause the oven to age or malfunction, such as oxidation of heating elements, corrosion of the inner wall of the oven cavity, wear of door sealing materials, wear of control panel buttons, etc. At the same time, the sensor data, that is, the use of environmental information, can be analyzed to obtain the temperature, humidity, and odor change trends of the oven's use environment. It can also extract features from the equipment use information to determine the load and aging degree of the oven.

[0184] After obtaining the above-mentioned life-related characteristic data, the controller can call the pre-trained life prediction model, input the life-related characteristic data into the life prediction model for life prediction, and obtain the life prediction result of the steam oven. The life prediction result includes the predicted life value of the cooking equipment, key aging factors and aging results of each aging factor.

[0185] Among them, the life prediction model is a prediction model obtained by pre-training the model according to the training samples. Specifically, the controller can generate training samples for the model in combination with historical life-related information, such as historical image data, historical temperature and humidity data, historical odor data, historical fan speed, usage history data, fault records, maintenance history and other information of the steam oven. Then, a multimodal prediction model is constructed through the training samples, such as a support vector machine, a random forest, a deep neural network, etc., to obtain a life prediction model for predicting the remaining service life of the steam oven and identifying key aging factors. The life prediction model is based on historical data and machine learning algorithms, and can predict the remaining life of the steam oven through life-related feature data. At the same time, the life prediction model can also be adjusted and optimized through user feedback information and new data. For example, the controller can regularly adjust and optimize the life prediction model based on the new life-related information collected to adapt to changes in the use environment and conditions of the steam oven, and at the same time combine user feedback and maintenance records to further improve the accuracy and practicality of the model prediction.

[0186] The controller can compare the obtained predicted life value with the preset life threshold. When the predicted life value is less than or equal to the preset life threshold, the controller can determine the factor type of the key aging factor. If the factor type is the equipment heating component, the controller will call the preset correspondence between the aging characteristic value of the equipment heating component and the parameter adjustment value of each parameter in the cooking algorithm, and determine the various adjustment parameters that match the aging characteristic value of the key aging factor based on the preset correspondence, as well as the parameter adjustment value of each adjustment parameter. The cooking algorithm of the cooking equipment is dynamically adjusted according to the parameter adjustment value of each condition parameter to obtain an updated cooking algorithm, which can avoid the situation where the cooking effect of the steam oven deteriorates due to load aging.

[0187] If the factor type is a non-equipment heating component, the controller can determine the aging cause of the key aging factor, generate and display a service life optimization guide for the steam oven based on the aging cause.

[0188] When the predicted life value is greater than the preset life threshold, the controller can determine the pre-maintenance method of each aging factor according to the aging results of each aging factor, generate and display the pre-maintenance plan of the steam oven based on each pre-maintenance method. Users can receive the system's maintenance suggestions and estimated replacement time through smart devices or the human-machine interface of the home appliance itself, guiding users to make appropriate maintenance or replacement decisions to maximize the use value of the steam oven.

[0189] Through the life prediction method of the cooking equipment in this embodiment, the actual service life of the steam oven can be effectively monitored and predicted, reducing unnecessary maintenance and replacement costs, while improving the safety and reliability of the use of the steam oven and improving the user experience.

[0190] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0191] Based on the same inventive concept, the embodiment of the present application also provides a life prediction device for a cooking device for implementing the life prediction method for a cooking device involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the life prediction device for one or more cooking devices provided below can refer to the limitations of the life prediction method for a cooking device above, and will not be repeated here.

[0192] In one embodiment, as shown in FIG. 9 , a life prediction device 900 for a cooking device is provided, comprising: an information acquisition module 901, a feature extraction module 902 and a life prediction module 903, wherein:

[0193] An information acquisition module 901 is used to acquire life-related information of a cooking device within a life prediction period, where the life-related information includes at least one of device component information, use environment information, and device use information;

[0194] A feature extraction module 902 is used to extract features of the life-related information according to the information type contained in the life-related information and to obtain life-related feature data of the cooking device;

[0195] The life prediction module 903 is used to input the life-related feature data into the life prediction model to perform life prediction and obtain the life prediction result of the cooking device; the life prediction model is trained based on the historical life-related information of the cooking device.

[0196] In some embodiments, the feature extraction method corresponding to the equipment component information includes image feature extraction. The feature extraction module 902 is used to: when the life-related information includes equipment component information, extract component images of each key component from the equipment component information according to a preset image processing algorithm; call a component aging recognition model to perform aging recognition on each component image to determine the component aging feature value of each key component; and determine the component aging feature value as the life-related feature data of the cooking device.

[0197] In some embodiments, the feature extraction method corresponding to the usage environment information includes trend feature extraction, and the feature extraction module 902 is used to: when the life-related information includes the usage environment information, extract the information collection time and the corresponding environment information value from the usage environment information; generate change trend information according to the information collection time and the corresponding environment information value; and determine the change trend information as the life-related feature data of the cooking equipment.

[0198] In some embodiments, the feature extraction method corresponding to the device usage information includes mapping feature extraction, and the feature extraction module 902 is used to: when the life-related information includes device usage information, call the preset mapping relationship between the device usage information and the usage aging characteristic value; based on the preset mapping relationship, determine the usage aging characteristic value that matches the device usage information; and determine the usage aging characteristic value as the life-related characteristic data of the cooking device.

[0199] In some embodiments, the life prediction result includes a predicted life value of the cooking device and key aging factors; the life prediction device of the cooking device further includes:

[0200] A factor type determination module, used to determine the factor type of the key aging factor when the predicted life value is less than or equal to a preset life threshold;

[0201] The life optimization plan determination module is used to determine the life optimization plan of the cooking equipment based on the factor types of the key aging factors.

[0202] In some embodiments, the life optimization scheme determination module is used to: if the factor type is the equipment heating component, then call the preset correspondence between the aging characteristic value of the equipment heating component and the parameter adjustment value of each parameter in the cooking algorithm; based on the preset correspondence, determine each adjustment parameter that matches the aging characteristic value of the key aging factor, as well as the parameter adjustment value of each adjustment parameter; according to the parameter adjustment value of each adjustment parameter, perform parameter adjustment on the cooking algorithm of the cooking equipment to obtain an updated cooking algorithm.

[0203] In some embodiments, the life optimization solution determination module is used to: if the factor type is non-equipment heating components, determine the aging cause of the key aging factor; generate and display the service life optimization guide of the cooking equipment based on the aging cause.

[0204] In some embodiments, the life prediction result further includes the aging result of each aging factor; and the life prediction device of the cooking device further includes:

[0205] The pre-maintenance method determination module is used to determine the pre-maintenance method of each aging factor according to the aging results of each aging factor when the predicted life value is greater than a preset life threshold.

[0206] The pre-maintenance plan generating module is used to generate and display a pre-maintenance plan for the cooking equipment based on various pre-maintenance methods.

[0207] In some embodiments, the life prediction device of the cooking device further includes:

[0208] The event response module is used to obtain model update information of the life prediction model in response to a model update event, wherein the model update information includes at least one of information related to the life of the cooking device within the model update cycle and user feedback information.

[0209] The model updating module is used to optimize the model parameters of the life prediction model based on the model updating information and update the life prediction model.

[0210] In some embodiments, the life prediction device of the cooking device further includes:

[0211] The model training module is used to obtain information related to the historical life of cooking equipment and an initial life prediction model built based on preset life evaluation indicators; generate a training sample set of cooking equipment based on the historical life related information; perform model training on the initial life prediction model of the cooking equipment according to the training sample set; and when the initial life prediction model meets the model training end conditions, determine the initial life prediction model as the life prediction model of the cooking equipment.

[0212] Each module in the above-mentioned cooking device life prediction device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0213] In one embodiment, an electronic device is provided, which may be a controller, and its internal structure diagram may be as shown in FIG10. The electronic device includes a processor, a memory, and a network interface connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store life-related information, feature extraction methods, life-related feature data, life prediction results, and other data within the life prediction period. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a life prediction method for a cooking device is implemented.

[0214] Those skilled in the art will understand that the structure shown in FIG. 10 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0215] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, specific implementation steps of the above-mentioned cooking device life prediction method embodiment are implemented.

[0216] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the specific implementation steps of the above-mentioned cooking device life prediction method embodiment are implemented.

[0217] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the specific implementation steps of the above-mentioned cooking device life prediction method embodiment.

[0218] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. In addition, the acquisition, storage, processing, and transmission of data are in compliance with relevant laws and regulations.

[0219] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0220] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0221] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for predicting the life of a cooking device, characterized in that: The method comprises: Acquire life-related information of the cooking device within a life prediction period, wherein the life-related information includes at least one of device component information, usage environment information, and device usage information; According to the information type contained in the life-related information, calling a feature extraction method matching the information type to extract features from the life-related information to obtain life-related feature data of the cooking device; The life-related characteristic data is input into a life-related prediction model to perform life-related prediction, thereby obtaining a life-related prediction result of the cooking device; the life-related prediction model is trained based on historical life-related information of the cooking device.

2. The method according to claim 1, characterized in that The feature extraction method corresponding to the equipment component information includes image feature extraction; the feature extraction method matching the information type is called to extract the life-related information to obtain the life-related feature data of the cooking equipment, including: In the case where the life-related information includes the device component information, extracting component images of each key component from the device component information according to a preset image processing algorithm; Calling a component aging recognition model to perform aging recognition on each of the component images, and determining a component aging characteristic value of each of the key components; The component aging characteristic value is determined as life-related characteristic data of the cooking device.

3. The method according to claim 1 or 2, characterized in that: The feature extraction method corresponding to the use environment information includes trend feature extraction, and the feature extraction method matching the information type is called to extract the life-related information to obtain the life-related feature data of the cooking device, including: In the case where the lifespan related information includes the usage environment information, extracting the information collection time and the corresponding environment information value from the usage environment information; Generate change trend information according to the information collection time and the corresponding environmental information value; The change trend information is determined as life-span-related characteristic data of the cooking device.

4. The method according to claim 1 or 2, characterized in that: The feature extraction method corresponding to the device usage information includes mapping feature extraction, and calling the feature extraction method matching the information type to extract the features of the life-related information to obtain the life-related feature data of the cooking device includes: In the case where the lifespan related information includes device usage information, calling a preset mapping relationship between the device usage information and the usage aging characteristic value; Based on the preset mapping relationship, determining a usage aging characteristic value matching the device usage information; The usage aging characteristic value is determined as the life-span-related characteristic data of the cooking device.

5. The method according to claim 1, characterized in that The life prediction result includes the predicted life value of the cooking device and key aging factors; the method further includes: In a case where the predicted life value is less than or equal to a preset life threshold, determining the factor type of the key aging factor; Based on the factor types of the key aging factors, a life optimization solution for the cooking device is determined.

6. The method according to claim 5, characterized in that The determining of the life optimization scheme of the cooking device based on the factor type of the key aging factor includes: If the factor type is a heating component of the device, calling the preset correspondence between the aging characteristic value of the heating component of the device and the adjustment value of each parameter in the cooking algorithm; Based on the preset corresponding relationship, determining each adjustment parameter matching the aging characteristic value of the key aging factor, and the parameter adjustment value of each adjustment parameter; According to the parameter adjustment values ​​of the respective adjustment parameters, the cooking algorithm of the cooking device is parameter adjusted to obtain an updated cooking algorithm.

7. The method according to claim 5, characterized in that The determining of the life optimization scheme of the cooking device based on the factor type of the key aging factor includes: If the factor type is a non-equipment heating component, determining the aging cause of the key aging factor; A lifespan optimization guide for the cooking device is generated and displayed based on the aging causes.

8. The method according to any one of claims 5 to 7, characterized in that: The life prediction result also includes the aging result of each aging factor; the method also includes: When the predicted life value is greater than the preset life threshold, determining the respective pre-maintenance mode of each aging factor according to the aging result of each aging factor; A preventive maintenance plan for the cooking device is generated and displayed based on each of the preventive maintenance methods.

9. The method according to claim 1, characterized in that: The method further comprises: In response to a model update event, acquiring model update information of the life prediction model, wherein the model update information includes at least one of information related to the life of the cooking device within a model update period and user feedback information; Based on the model update information, the model parameters of the life prediction model are optimized to update the life prediction model.

10. The method according to claim 1, characterized in that The training method of the life prediction model includes: Obtaining information related to the historical life of the cooking equipment and an initial life prediction model built based on preset life assessment indicators; generating a training sample set of the cooking device based on the historical life-related information; Performing model training on the initial life prediction model of the cooking device according to the training sample set; When the initial life prediction model meets the model training end condition, the initial life prediction model is determined as the life prediction model of the cooking device.

11. A life prediction device for a cooking device, characterized in that: The device comprises: An information acquisition module, used to acquire life-related information of the cooking device within a life prediction period, wherein the life-related information includes at least one of device component information, use environment information, and device use information; A feature extraction module, configured to extract features of the life-related information according to the information type contained in the life-related information and call a feature extraction method matching the information type to obtain life-related feature data of the cooking device; The life prediction module is used to input the life-related characteristic data into a life prediction model to perform life prediction and obtain a life prediction result of the cooking device; the life prediction model is trained based on historical life-related information of the cooking device.

12. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 10 are implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images