Maintenance suggestion determination method and device, storage medium and electronic device

Abstract

The invention discloses a maintenance suggestion determination method and device, a storage medium and an electronic device, and relates to the technical field of smart home, and the maintenance suggestion determination method comprises the steps: obtaining the operation data of a household appliance in a use state; according to the operation data, establishing a digital twinborn body corresponding to the household appliance, the digital twinborn body being used for simulating the operation characteristics of the household appliance according to the operation data and estimating the component fault probability of the household appliance in the target period; and determining maintenance suggestions of the household appliance based on the fault probabilities of different components output by the digital twin. The problem that high-precision real-time monitoring and intelligent maintenance cannot be carried out on household appliances in the prior art is solved.

Description

Technical Field

[0001] This application relates to the field of smart home technology, and more specifically, to a method, apparatus, storage medium, and electronic device for determining maintenance recommendations. Background Technology

[0002] With the rise of the smart home concept, more and more traditional home appliances are being given network connectivity for remote monitoring and control. Traditional remote monitoring technologies mainly rely on sensors to collect basic operating data from devices, such as temperature, humidity, and power consumption, and upload this data to cloud servers via wireless communication technologies such as Wi-Fi or Bluetooth. Users then access this information through smartphone applications or other internet interfaces. While these technologies improve the convenience of using home appliances, existing monitoring systems often only diagnose after a noticeable malfunction occurs, and cannot predict potential failure risks. For example, taking smart air conditioners as an example, although indoor temperature and fan speed can be remotely adjusted via a user app, energy efficiency management can only provide basic energy-saving modes, such as automatic cooling at night and automatic shutdown. While these functions have some energy-saving effect, they do not consider the actual operating status of the device (such as changes in outdoor temperature and indoor occupancy) or the specific needs of the user (such as sleep preferences and activity patterns). Therefore, the optimization effect is limited, and personalized services cannot be provided, such as automatically adjusting indoor temperature and humidity according to the user's sleep cycle, or automatically entering a deep energy-saving state when the user leaves the house.

[0003] Therefore, no effective solution has yet been proposed for the problem of high-precision real-time monitoring and intelligent maintenance of home appliances in related technologies. Summary of the Invention

[0004] This application provides a method, apparatus, storage medium, and electronic device for determining maintenance recommendations, in order to at least solve the problem in the related art that it is impossible to perform high-precision real-time monitoring and intelligent maintenance of home appliances.

[0005] According to one embodiment of this application, a method for determining maintenance recommendations is provided, comprising: acquiring operating data of a home appliance in its usage state; establishing a digital twin corresponding to the home appliance based on the operating data, wherein the digital twin is used to simulate the operating characteristics of the home appliance based on the operating data and to estimate the component failure probability of the home appliance within a target period; and determining maintenance recommendations for the home appliance based on the failure probabilities of different components output by the digital twin.

[0006] In an exemplary embodiment, after establishing a digital twin corresponding to the home appliance based on the operating data, the method further includes: determining the target object's operating preferences for using the home appliance based on the operating characteristics in the digital twin; in the case of obtaining multiple operating preferences for multiple home appliances in the target object's home area, establishing a linkage scenario for multiple home appliances based on the multiple operating preferences; and sending the linkage scenario to the target object for confirmation.

[0007] In one exemplary embodiment, determining maintenance recommendations for home appliances based on the failure probabilities of different components output by a digital twin includes: identifying the corresponding target component as a component to be maintained when the failure probability is greater than a preset probability threshold; identifying the corresponding target component as a component not to be maintained when the failure probability is less than or equal to the preset probability threshold; counting a first number of components to be maintained and a second number of components not to be maintained in the home appliances; and determining maintenance recommendations for the home appliances based on the first number, the second number, and the after-sales maintenance template associated with the home appliances.

[0008] In an exemplary embodiment, establishing a digital twin of a home appliance based on operational data includes: determining the type of home appliance corresponding to the operational data; obtaining a physical model corresponding to the type of appliance, wherein the physical model has simulation components with the same functions as the home appliance and a model of connection information between different simulation components; synchronizing the operational data to the physical model for simulation and deduction; and determining the digital twin based on the deduction results, wherein the digital twin is a virtual simulation device with the same operational data as the home appliance.

[0009] In an exemplary embodiment, after establishing a digital twin corresponding to the home appliance based on operational data, the method further includes: when repeated device operations are found in the operational data, determining the time parameters and operating mode of the same device operation on the home appliance, wherein the time parameters include at least one of the following: the initial time point at which the device operation begins, and the duration of the continuous operation; performing virtual operation based on the control digital twin according to the time parameters, operating mode, and preset lifecycle of the home appliance, wherein the preset lifecycle includes multiple life periods; determining fault information of the home appliance that occurs in different life periods based on the virtual operation results; and assessing the failure probability of different components in the home appliance through the fault information.

[0010] In an exemplary embodiment, after determining the maintenance recommendations for home appliances based on the failure probabilities of different components output by the digital twin, the method further includes: sending the maintenance recommendations to the target object and determining the target object's feedback on the maintenance recommendations; generating a task work order corresponding to the home appliance based on the feedback; and synchronizing the task work order to the after-sales service outlets in the area where the home appliance is located.

[0011] In an exemplary embodiment, after establishing a digital twin of a home appliance based on operational data, the method further includes: determining the preference features of each target object using the digital twin of the home appliance when different target objects all use the same home appliance; determining the usage habits of the home appliance based on multiple preference features; and developing an intelligent recommendation scenario that matches the usage habits, wherein the intelligent recommendation scenario is used to link multiple devices to provide services to the target object.

[0012] According to another aspect of the embodiments of this application, a maintenance recommendation determination apparatus is also provided, comprising: an acquisition module for acquiring operating data of a home appliance in its usage state; an establishment module for establishing a digital twin corresponding to the home appliance based on the operating data, wherein the digital twin is used to simulate the operating characteristics of the home appliance based on the operating data and to estimate the component failure probability of the home appliance within a target period; and a determination module for determining maintenance recommendations for the home appliance based on the failure probabilities of different components output by the digital twin.

[0013] According to yet another embodiment of this application, a computer-readable storage medium is also provided, wherein a computer program is stored therein, and the computer program is configured to perform the steps in any of the above method embodiments when it is run.

[0014] According to yet another embodiment of this application, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0015] According to yet another embodiment of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0016] In this embodiment, operational data of home appliances under usage conditions is acquired. Based on the collected operational data, a digital twin of the home appliance is established using a combination of physical models and data-driven models. Based on the digital twin, abnormal changes in the device's operational characteristics are analyzed to predict the failure probability of each key component within a target period (e.g., the next month). Based on the failure probabilities of different components output by the digital twin, the overall operational status of the device is further analyzed. Combined with user habits and device maintenance history, maintenance suggestions are generated. This solves the problem in related technologies of the inability to perform high-precision real-time monitoring and intelligent maintenance of home appliances. It achieves the ability to mine user preferences for home appliance use and recommend suitable maintenance solutions to target users, thereby realizing personalized usage and maintenance of the device. Attached Figure Description

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

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

[0019] Figure 1 This is a schematic diagram of the hardware environment for a method of determining maintenance recommendations according to an embodiment of this application;

[0020] Figure 2 This is a flowchart of a method for determining maintenance recommendations according to an embodiment of this application;

[0021] Figure 3 This is a schematic diagram of the architecture of a digital twin-based home appliance software lifecycle management system according to an embodiment of this application;

[0022] Figure 4 This is a timing diagram of energy efficiency optimization based on digital twin according to an embodiment of this application;

[0023] Figure 5 This is a structural block diagram of a maintenance suggestion determination device according to an embodiment of this application. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, apparatus, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, apparatus, or devices.

[0026] According to one aspect of the embodiments of this application, a method for determining maintenance recommendations is provided. This method for determining maintenance recommendations is widely applicable to whole-house intelligent digital control application scenarios such as smart homes, smart home ecosystems, and intelligence house ecosystems. Optionally, in this embodiment, the above-mentioned method for determining maintenance recommendations can be applied to, for example... Figure 1 The hardware environment shown consists of terminal device 102 and server 104. Figure 1 This is a schematic diagram of the hardware environment for a method of determining maintenance recommendations according to an embodiment of this application, such as... Figure 1 As shown, server 104 is connected to terminal device 102 via a network and can be used to provide services (such as application services) to the terminal or clients installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services for server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data processing services for server 104.

[0027] The aforementioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network, metropolitan area network, local area network. The aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless FiDelity), Bluetooth. The terminal device 102 may not be limited to PC, mobile phone, tablet computer, smart air conditioner, smart range hood, smart refrigerator, smart oven, smart stove, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projector, smart TV, smart clothes rack, smart curtains, smart audio-visual equipment, smart socket, smart speaker, smart speaker box, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart robot vacuum cleaner, smart window cleaning robot, smart mopping robot, smart air purifier, smart steam oven, smart microwave oven, smart water heater, smart air purifier, smart water dispenser, smart door lock, etc.

[0028] This embodiment provides a method for determining maintenance recommendations, applied to the aforementioned terminal device. Figure 2 This is a flowchart of a method for determining maintenance recommendations according to an embodiment of this application, the process including the following steps:

[0029] Step S202: Obtain the operating data of the home appliances in use.

[0030] In this step, various sensors installed on the home appliance (such as temperature sensors, humidity sensors, vibration sensors, current sensors, etc.) are used to collect real-time parameters and status information of the device in the actual operating environment. This data includes, but is not limited to:

[0031] Temperature and humidity data: Monitoring changes in temperature and humidity inside and around the equipment is crucial for assessing the health status of heat-sensitive equipment such as air conditioners and refrigerators.

[0032] Vibration data: By analyzing the vibration frequency and amplitude of components such as motors and compressors, it is possible to identify whether there is potential mechanical wear or imbalance in the equipment.

[0033] Current and energy consumption data: Monitoring the real-time current consumption and long-term energy consumption trends of equipment helps to assess the electrical system health and energy efficiency of the equipment.

[0034] User interaction data: Records users' usage habits and preferences for the device, including usage time, mode selection, fault reports, etc., which is very important for personalized function recommendations and maintenance suggestions.

[0035] Step S204: Establish a digital twin corresponding to the home appliance based on the operating data, wherein the digital twin is used to simulate the operating characteristics of the home appliance based on the operating data and to estimate the component failure probability of the home appliance within the target period.

[0036] After acquiring real-time operational data, a digital twin is constructed based on this data to accurately reflect the current state and potential future evolution of home appliances. The construction of the digital twin involves the following aspects:

[0037] Physical modeling: Based on the physical principles of the equipment (thermodynamics, fluid mechanics, electricity, etc.), mathematical models of each component and system are established to describe the behavior of the equipment under normal operating conditions.

[0038] Data-driven modeling: Utilizing machine learning algorithms (such as deep learning, reinforcement learning, etc.) to learn complex patterns of equipment behavior from historical operating data, and to identify abnormal states and fault symptoms.

[0039] Model fusion: Combining physical models and data-driven models to form a comprehensive and dynamic digital twin that can adjust its own state based on real-time data and simulate the behavior of equipment under different operating conditions.

[0040] Failure probability prediction: The digital twin estimates the failure probability of each key component within a target period (such as the next month or a quarter) through in-depth analysis of the equipment's operating characteristics. These probability values ​​will be used to generate subsequent maintenance recommendations.

[0041] Subsequently, the established digital twin technology was used to accurately simulate the operating status of equipment and predict faults, providing data reference for proactive health management of home appliances.

[0042] Step S206: Determine maintenance recommendations for the home appliances based on the failure probabilities of different components output by the digital twin.

[0043] After the digital twin estimates the failure probability of different components, specific maintenance recommendations are generated based on these probability values. This includes:

[0044] Fault warning: For components with a high probability of failure, the system will issue a warning to the user, suggesting that the user take maintenance measures in advance, such as scheduling a professional inspection or replacing vulnerable parts.

[0045] Preventive maintenance recommendations: Based on the overall operating status of the equipment and user habits, we recommend customized preventive maintenance strategies, such as regular cleaning and adjusting the working mode to reduce the load on specific components.

[0046] Spare parts replacement recommendations: For components that are expected to fail, the system will provide spare parts replacement recommendations, including the spare parts model, supplier information, and the best time window for replacement.

[0047] Maintenance time window optimization: Based on the frequency of equipment use, user behavior patterns, and component wear and tear, the system recommends the most suitable maintenance time for users to avoid maintenance during peak usage periods and reduce the impact on users' lives.

[0048] Through the above steps, operational data of home appliances under usage conditions is obtained. Based on the collected operational data, a digital twin of the home appliances is established using a combination of physical models and data-driven models. Based on the digital twin, by analyzing abnormal changes in the equipment's operational characteristics, the failure probability of each key component within a target period (e.g., the next month) is estimated. Based on the failure probabilities of different components output by the digital twin, the overall operational status of the equipment is further analyzed. Combining user habits and equipment maintenance history, maintenance suggestions are generated. This solves the problem of high-precision real-time monitoring and intelligent maintenance of home appliances in related technologies, achieving the ability to mine user preferences for home appliances and recommend suitable maintenance solutions to target users, thereby realizing personalized usage and maintenance of equipment.

[0049] In an exemplary embodiment, after establishing a digital twin corresponding to the home appliance based on the operating data, the method further includes: determining the target object's operating preferences for using the home appliance based on the operating characteristics in the digital twin; in the case of obtaining multiple operating preferences for multiple home appliances in the target object's home area, establishing a linkage scenario for multiple home appliances based on the multiple operating preferences; and sending the linkage scenario to the target object for confirmation.

[0050] By leveraging device usage data recorded by digital twins, and through data analysis and machine learning techniques, unique user preferences when operating home appliances are uncovered. This includes:

[0051] Usage time analysis: Identify the time periods when users most frequently use their devices. For example, some users may tend to use the coffee machine in the early morning and the washing machine in the evening.

[0052] Operating mode learning: Learns how users set up their devices under specific conditions, such as choosing "cinema" mode when using the TV on a weekend evening, or choosing "silent" mode when using the air conditioner in the early morning.

[0053] Interaction frequency and type: Analyze the frequency and type of user interactions with the device to identify user preferences for device functions, such as frequently adjusting the refrigerator's temperature settings or frequently using the washing machine's "quick wash" function.

[0054] Through these analyses, a portrait of the user's operation preferences is constructed, providing a basis for the establishment of subsequent linkage scenarios.

[0055] In the case of obtaining multiple operation preferences of multiple household appliances in the household area where the target object is located, multiple linkage scenarios of the multiple household appliances are established according to the multiple operation preferences.

[0056] After collecting the operation preference data of multiple household appliances in the home, it can further analyze the correlation between these preferences and establish a linkage scenario between the devices. For example, the morning wake-up scenario includes recognizing that the user has the habit of using the coffee machine immediately after waking up in the morning, which can link the refrigerator to automatically adjust to the "quick access" mode, and at the same time turn on the air conditioner and adjust it to the user's preferred temperature, thus providing the user with a comfortable and convenient morning experience. The energy-saving scenario when leaving home includes: analyzing the user's habit of turning off electrical appliances when leaving home, automatically creating a linkage scenario, when it is detected that the user leaves home (such as through the geographical location information of the mobile phone App), then automatically turn off unnecessary devices and adjust the air conditioner to the energy-saving mode, realizing intelligent energy management.

[0057] After generating the linkage scenario, through the user App or other interaction interfaces, the proposed linkage solution is presented to the user for confirmation by the user. To ensure that the linkage scenario truly meets the user's needs and preferences, avoiding the inconvenience that may be brought by the system acting on its own initiative. After receiving the linkage scenario suggestion, if the user believes that the proposed linkage scenario conforms to his / her usage habits, he / she can directly confirm it, and then the set linkage process will be automatically executed. Adjust or reject: The user may also fine-tune the linkage scenario according to personal circumstances or directly reject the execution, ensuring the user's control over the home environment.

[0058] Through the above method, this embodiment not only improves the intelligent level of the use of household appliances, but also enhances the user adaptability and friendliness of the system, providing the user with a more personalized and convenient smart home environment.

[0059] In an exemplary embodiment, determining the maintenance suggestions for household appliances based on the failure probabilities of different components output by the digital twin includes: in the case where the failure probability is greater than the preset probability threshold, determining the corresponding target component as the component to be maintained; in the case where the failure probability is less than or equal to the preset probability threshold, determining the corresponding target component as the component not to be maintained; counting the first number of components to be maintained and the second number of components not to be maintained in the household appliance; and determining the maintenance suggestions for the household appliance according to the first number, the second number, and the after-sales maintenance template associated with the household appliance.

[0060] First, the digital twin uses a pre-trained machine learning model to assess the probability of failure of each component within a future target period (such as one month or one quarter) based on real-time operational data collected from home appliances. If the probability of failure of a component is higher than a preset probability threshold (for example, a threshold of 80%), the component is marked as a "component requiring maintenance," meaning it has a high potential risk of failure and should be included in the near-term maintenance plan. Conversely, if the probability of failure of a component is lower than or equal to the preset probability threshold, it is marked as a "component not requiring maintenance," indicating that the component's operating status is relatively healthy and does not require special attention or maintenance in the near future.

[0061] Further statistics are collected on the number of home appliances marked as "Components Needing Maintenance" and the number of "Components Not Needing Maintenance" to gain a comprehensive understanding of the equipment's health status. After determining the number of components needing maintenance and those not needing maintenance, maintenance recommendations are generated using the equipment's after-sales maintenance template. The maintenance template typically includes information such as the basic equipment maintenance process, recommended maintenance cycles, and troubleshooting steps for common faults. Specific content includes:

[0062] Based on the first quantity (number of components to be maintained) and the second quantity (number of components not to be maintained), and in conjunction with the equipment's maintenance template, a customized maintenance strategy is developed. For example, if the first quantity is high, it may be necessary to recommend that the user schedule a professional on-site inspection; if the first quantity is low, the user may be advised to perform a simple self-check or maintenance.

[0063] Based on the maintenance strategy, specific maintenance suggestions are generated. Optionally, these suggestions may include: maintenance time, maintenance recommendations, and spare parts replacement. The maintenance time is primarily determined by considering the user's lifestyle and equipment usage patterns, recommending the most suitable maintenance window to avoid peak usage periods. Maintenance recommendations suggest whether the appliance requires scheduled professional maintenance or allows for simple self-maintenance. Spare parts replacement recommendations suggest appropriate replacements based on anticipated component failures, providing the spare parts' model number, supplier information, and optimal replacement time. Furthermore, these maintenance suggestions can also be preventative, such as cleaning filters or adjusting operating modes, to mitigate potential malfunctions.

[0064] In summary, by implementing the methods described above and quantitatively analyzing the health status of the equipment, combined with the guidance of after-sales maintenance templates, more accurate, personalized, and forward-looking maintenance guidance can be provided to users. This not only improves the reliability and lifespan of the equipment but also significantly enhances the user experience and satisfaction. Simultaneously, it helps reduce unnecessary maintenance costs, achieving a dual improvement in the economic benefits of equipment maintenance and the user experience.

[0065] In an exemplary embodiment, establishing a digital twin of a home appliance based on operational data includes: determining the type of home appliance corresponding to the operational data; obtaining a physical model corresponding to the type of appliance, wherein the physical model has simulation components with the same functions as the home appliance and a model of connection information between different simulation components; synchronizing the operational data to the physical model for simulation and deduction; and determining the digital twin based on the deduction results, wherein the digital twin is a virtual simulation device with the same operational data as the home appliance.

[0066] After collecting operational data from home appliances, the first step is to identify which specific appliance corresponds to this data, such as a refrigerator, washing machine, or air conditioner. This identification process typically relies on information such as device identifiers and model numbers within the data to ensure that the data matches the correct device type and model. Once the device type is determined, the next step is to retrieve the corresponding physical model from the database. The physical model is the core component of the digital twin; it contains simulation modules of all key components of the home appliance, as well as information on the connections and interactions between these components. The construction of the physical model is based on the device's original design drawings, technical specifications, and physical principles, ensuring a high degree of consistency and accuracy with the actual device.

[0067] The simulation components in the physical model include, but are not limited to: thermal management models for simulating the refrigeration cycle of equipment such as refrigerators and air conditioners, including thermodynamic behavior of components such as compressors, condensers, expansion valves, and evaporators; mechanical models for simulating the transmission and vibration characteristics of equipment such as washing machines and dryers, including mechanical models of motors, belts, drums, etc.; and circuit models for simulating the operating state of the internal circuits of the equipment, including electrical relationships such as power modules, control circuits, and sensor circuits.

[0068] After acquiring the physical model, real-time operational data is synchronized to the model. Simulations are then performed using the physical model and data-driven models (such as state estimation and parameter identification techniques) to simulate the dynamic behavior of the equipment under current operating conditions. This step is crucial for building a digital twin, enabling the model to reflect the equipment's operating status and performance in real time. Finally, based on the simulation results from the physical model, a virtual simulation device with the same operational data as the actual equipment—the digital twin—is constructed. The digital twin not only reflects the current state of the equipment but also predicts its future behavior under different conditions, including performance degradation and failure probability.

[0069] In summary, a digital twin, created by combining physical models and operational data, can accurately reflect the actual operating status of a device, including the health level of its internal components. Furthermore, the digital twin can respond instantly to changes in device status, providing real-time analysis and predictions. This facilitates targeted after-sales service for home appliances.

[0070] In an exemplary embodiment, after establishing a digital twin corresponding to the home appliance based on operational data, the method further includes: when repeated device operations are found in the operational data, determining the time parameters and operating mode of the same device operation on the home appliance, wherein the time parameters include at least one of the following: the initial time point at which the device operation begins, and the duration of the continuous operation; performing virtual operation based on the control digital twin according to the time parameters, operating mode, and preset lifecycle of the home appliance, wherein the preset lifecycle includes multiple life periods; determining fault information of the home appliance that occurs in different life periods based on the virtual operation results; and assessing the failure probability of different components in the home appliance through the fault information.

[0071] First, analyze the operational data to identify repetitive user operation patterns. For example, a user might use the washing machine every morning, the air conditioner in "cooling" mode at night, or the oven in "toasting" mode weekly. For these patterns, record the start time, duration, frequency, and other time parameters of the operation, as well as the specific operating mode of the device during the operation. The lifecycle of home appliances is preset as a series of life periods, each representing a stage of the device's operation. For example, the lifecycle of an appliance might be divided into stages such as "new machine operation period," "stable operation period," "aging period," and "frequent maintenance period." The device's performance and failure modes may differ in each stage; therefore, segmenting the preset lifecycle helps to more accurately analyze the health status of the device at specific stages.

[0072] After acquiring the time parameters, operating mode, and preset lifecycle of the device, the control digital twin is used to perform virtual operation. The virtual operation simulates the device's operation during various lifecycle periods in actual use, including the frequency and duration of device operation and the impact of operating modes.

[0073] Optional, the steps of virtual execution include, but are not limited to:

[0074] Initialize the digital twin state: Set the initial state of the digital twin based on the current operating data of the device.

[0075] Simulated operation process: According to the recorded time parameters and operating mode, the digital twin is controlled to run virtually for a long time to simulate the use of the equipment throughout its entire life cycle.

[0076] Fault mode simulation: In virtual operation, fault modes are preset through AI algorithms to simulate various faults that the equipment may encounter at different stages of its life cycle.

[0077] After the virtual run concludes, the output of the twin is analyzed to determine potential fault information that may occur during each lifecycle period of the device. Fault information typically includes:

[0078] Fault types: such as refrigeration system leakage, motor wear, circuit short circuit, etc.

[0079] Failure probability: Based on the twin's operational data, assess the probability of different failures occurring within each lifespan.

[0080] Failure Timing: Predicts the most likely time of failure to help users and maintenance personnel prepare in advance.

[0081] Finally, based on the results of the virtual operation, a comprehensive assessment of the failure probabilities of different components in the home appliance is conducted. Then, using the equipment operating status and failure information simulated by the digital twin, combined with component wear and tear, historical failure records, and other data, a failure probability is assigned to each component. These probability values ​​will be used to guide subsequent maintenance recommendations, such as preventative maintenance of high-risk components or optimizing equipment operating modes to reduce potential damage.

[0082] In an exemplary embodiment, after determining the maintenance recommendations for home appliances based on the failure probabilities of different components output by the digital twin, the method further includes: sending the maintenance recommendations to the target object and determining the target object's feedback on the maintenance recommendations; generating a task work order corresponding to the home appliance based on the feedback; and synchronizing the task work order to the after-sales service outlets in the area where the home appliance is located.

[0083] Optionally, after determining maintenance recommendations for home appliances using digital twin technology, the generated recommendations are sent to the appliance owner or user—the target audience—via a user app, email, or other communication channels. Maintenance recommendations may include equipment malfunction warnings, recommended maintenance times, specific maintenance actions (such as cleaning, replacing spare parts, etc.), and possible consequences and preventative measures. Upon receiving the maintenance recommendations, the target audience can confirm, adjust, or reject them. For example, a user might need to adjust the recommended maintenance time to fit their personal schedule or raise questions about the recommended maintenance actions, seeking more detailed guidance.

[0084] After receiving user feedback, a work order will be generated based on the feedback. The work order serves as a guide for after-sales service personnel to perform maintenance operations. It includes equipment information such as the device model, serial number, and location; fault prediction based on the digital twin; maintenance recommendations confirmed by the user; information on which components need inspection or replacement; and the specific maintenance requirements corresponding to each maintenance action. Work orders are prioritized based on the severity of the fault and the user's needs, ensuring that urgent or important maintenance is performed first. The maintenance time window provided by the user is considered to determine the specific time and date for on-site service by after-sales personnel. Finally, the work order is synchronized in real-time to the after-sales service center or outlet in the area where the appliance is located, ensuring that the after-sales service team can receive and execute the work order promptly. This synchronization process includes:

[0085] Work order distribution: Based on the device's location information, work orders are automatically distributed to the nearest after-sales service center to ensure rapid response.

[0086] Resource scheduling: After receiving a work order, the after-sales service outlet will schedule the corresponding technical personnel and spare parts resources according to the work order requirements to prepare for on-site service.

[0087] Notification and Confirmation: The after-sales service center sends the work order details to the designated technician. After the technician confirms the work order, he / she prepares to go to the site. At the same time, the system may notify the user of the specific service information via the App or by phone.

[0088] Through the above process, this embodiment achieves a seamless connection from fault prediction and maintenance suggestion generation to after-sales service execution, ensuring that equipment maintenance can be carried out efficiently and accurately. This not only improves the reliability and lifespan of the equipment but also significantly enhances the user experience and satisfaction. The efficient response and resource scheduling of the after-sales service center helps build brand reputation, reduces user inconvenience caused by equipment failures, and reflects the intelligent and humanized characteristics of smart home services.

[0089] In an exemplary embodiment, after establishing a digital twin of a home appliance based on operational data, the method further includes: determining the preference features of each target object using the digital twin of the home appliance when different target objects all use the same home appliance; determining the usage habits of the home appliance based on multiple preference features; and developing an intelligent recommendation scenario that matches the usage habits, wherein the intelligent recommendation scenario is used to link multiple devices to provide services to the target object.

[0090] Digital twins not only reflect the operating status and performance of the devices themselves, but also identify the preferences of different users when using home appliances by analyzing user interaction data. This process includes:

[0091] Data collection: Collect interaction records between each target object and home appliances, such as power-on time, operating mode selection, operation frequency, and setting adjustments.

[0092] Preference analysis: Using machine learning and data mining techniques, behavioral patterns and preference characteristics of target objects are extracted from collected interaction data, such as users who prefer low-temperature operation or those who prefer timed power-on / off functions.

[0093] User profile building: Based on preference features, a user profile is built for each target object to facilitate subsequent personalized services and scenario recommendations.

[0094] By comparing and analyzing the user preference characteristics of multiple digital twins, a set of typical usage habits for home appliances can be summarized. These usage habits reflect the general needs and preferences of user groups for the devices, and may include:

[0095] Time period preference: Discovered a concentrated pattern of most users using home appliances within a specific time period.

[0096] Feature preferences: Identify which features are most popular and which features are used less frequently.

[0097] Maintenance behavior: Analyze the frequency and methods users use to maintain equipment and understand their maintenance habits.

[0098] Energy consumption mode: Analyze users' sensitivity to energy consumption during use and identify energy-saving preferences.

[0099] Based on the summarized usage habits, a series of matching intelligent recommendation scenarios were developed. These scenarios aim to optimize the user's life experience through intelligent interaction between devices. The scenario design considers user preferences, device characteristics, and environmental factors, and may include:

[0100] Morning wake-up scenario: If it is found that the user usually uses the coffee machine and toaster in the morning, then at the set wake-up time, the smart curtains will automatically open, the coffee machine will start brewing, and the toaster will preheat, creating a warm and comfortable morning atmosphere.

[0101] Energy-saving scenario when leaving home: Based on the user's departure pattern, the air conditioner automatically enters energy-saving mode, and all lights and appliances are turned off to reduce unnecessary energy consumption.

[0102] Nighttime sleep scenario: It recognizes the user's rest time at night, automatically adjusts the bedroom temperature to the optimal sleep temperature, turns off the living room lights, and turns on the bedroom night light to create a good sleep environment.

[0103] These intelligent recommendation scenarios leverage the collaborative work between devices, such as determining whether a user has left home based on Wi-Fi signal strength, thereby automatically adjusting smart home settings.

[0104] To achieve intelligent recommendation scenarios, follow these steps:

[0105] Scene configuration: In the cloud, developers design intelligent recommendation scenes based on usage habits and configure the linkage logic between devices to ensure that the scenes are coordinated and consistent across different devices.

[0106] User authorization: Push intelligent recommendation scenarios to the target audience, and the user confirms authorization through the App or smart speaker and other devices to allow the scenario to be executed.

[0107] Device linkage: Once authorized by the user, control commands will be sent to multiple devices participating in the scene through the IoT platform to coordinate their actions and achieve the scene effect.

[0108] Scene feedback and optimization: Collect user feedback after scene execution, continuously optimize scene design to ensure it better meets users' actual needs and preferences, and improve user satisfaction.

[0109] Through the above process, this embodiment not only deepens the application of digital twins in the smart home field, but also realizes intelligent linkage between devices through the development of intelligent recommendation scenarios, greatly improving the level of intelligence and personalized experience of home life. This innovation not only enhances users' reliance on smart homes, but also provides new value-added service opportunities for home equipment manufacturers.

[0110] To better understand the process of determining the above maintenance recommendations, the following description, in conjunction with optional embodiments, further illustrates the process of determining the above maintenance recommendations, but is not intended to limit the technical solutions of the embodiments of this application.

[0111] As intelligent scenarios become increasingly complex, the home appliance industry currently faces the following key technological challenges:

[0112] 1. Insufficient equipment failure prediction capability: Traditional home appliance maintenance mainly relies on regular inspections or repairs after failure, which cannot predict potential failures of key components (such as compressors, motors, bearings, etc.) in advance, resulting in poor user experience, high maintenance costs, and shortened equipment life.

[0113] 2. Lack of intelligent energy efficiency optimization: Most existing home appliances have fixed preset energy-saving modes, which cannot be dynamically optimized according to the actual usage environment and user habits, thus limiting the potential for energy efficiency improvement.

[0114] 3. Lack of personalization in software function updates: Traditional OTA upgrades use a unified firmware push mode, which cannot provide customized functions according to different users' usage habits and needs, resulting in low user stickiness and satisfaction.

[0115] 4. Fragmented equipment lifecycle management: There is a lack of a unified digital platform to manage home appliances in an integrated manner throughout their entire lifecycle, from production and use to maintenance.

[0116] To address the aforementioned issues, this application proposes an optional embodiment of a home appliance software lifecycle management method and system based on digital twins. The aim is to achieve proactive predictive maintenance, dynamic energy efficiency optimization, personalized function iteration, and the construction of an intelligent service loop by building a hybrid digital twin based on physical modeling and data-driven approaches. Specifically, by constructing a digital twin of the home appliance and utilizing AI algorithms for deep analysis, potential faults in key components can be predicted in advance, transforming passive repair into proactive service, improving equipment reliability, and optimizing user experience. Multi-scenario energy efficiency simulations are performed using the digital twin to recommend or automatically execute optimal energy-saving operation strategies for users, achieving refined energy management. By deeply analyzing user behavior data recorded by the digital twin, user preferences are mined, and customized software functions are pushed via OTA (Over-The-Air) updates, enabling home appliances to "self-evolve" and continuously meet user needs. The entire chain from equipment monitoring, fault prediction, user notification to after-sales dispatch is streamlined, achieving an efficient and automated service process and improving overall service efficiency and quality.

[0117] For example, predictive maintenance of smart refrigerators using hybrid digital twins is handled in the following way:

[0118] Scenario description: After two years of operation, a user's smart refrigerator detected an abnormal vibration spectrum in the compressor.

[0119] Data acquisition: Acquire data from vibration sensors (example: detected abnormal peak at 1.2kHz), current sensors (example: power consumption increased by 8%), and temperature sensors (example: cooling efficiency decreased by 5%) on home appliances.

[0120] AI analysis: FFT+CNN identifies bearing wear characteristics, LSTM predicts performance degradation trends, and the failure confidence level is 92% (meaning that the compressor bearing has a high probability of failure after analysis).

[0121] Intelligent response includes: push notifications from the user's app (recommendation for repair within 15 days), after-sales system (automatic generation of work orders), and spare parts reservation (compressor bearings).

[0122] Ultimately, through the above analysis and response, fault information such as compressor bearings can be predicted in advance, thus avoiding sudden shutdowns, improving user satisfaction, and reducing maintenance costs.

[0123] As an optional implementation method, Figure 3This is a schematic diagram of the architecture of a home appliance software lifecycle management system based on digital twins, according to an embodiment of this application. It includes: an application service layer, a cloud-based intelligent analysis layer, a data processing layer, a device access layer, and a physical device layer. It should be noted that building this digital twin requires multi-source data acquisition, such as layered acquisition (1Hz-10Hz / 0.1Hz-1Hz / event-triggered) of data from physical sensors, status sensors, user behavior, environmental data, etc., and preprocessing of the acquired data. This data preprocessing may include: outlier detection, timestamp alignment, feature extraction, Kalman filter fusion, and other data operations.

[0124] Optionally, the aforementioned digital twin employs hybrid modeling, constructed by combining physical models (thermodynamics / fluid / mechanical / circuit) with data-driven (CNN / LSTM / Autoencoder) fusion strategies. Furthermore, to ensure effective data processing between the digital twin and home appliances / applications, real-time synchronization is achieved between terminals via MQTT protocol, edge computing, and cloud processing. The available standard for real-time synchronization is a latency of less than 1 second for key parameters and less than 10 seconds for general parameters.

[0125] Furthermore, the core data flows in the aforementioned digital twin-based home appliance software lifecycle management system include:

[0126] Uplink data stream (device → cloud): Device sensor → Edge preprocessing → Data compression → Encrypted transmission → Cloud reception → Data cleaning → Feature extraction → Digital twin update → AI analysis → Result storage.

[0127] Downlink control flow (cloud → device): AI decision-making → security verification → instruction generation → digital signature → encrypted transmission → device reception → instruction verification → execution control → status feedback.

[0128] Horizontal collaborative flow (between services): Predictive maintenance service ↔ Energy efficiency optimization service ↔ Personalized service ↔ User management service ↔ Equipment management service.

[0129] External integration flow: Weather service → Environmental data → System decision-making; Electricity price service → Cost optimization → Energy saving strategy; After-sales system ← Repair work order ← Fault prediction; Supply chain system ← Spare parts demand ← Predictive maintenance.

[0130] Optionally, the core of building and synchronizing digital twins of home appliances lies in combining a well-defined physical model with an AI model based on big data, and establishing a low-latency, adaptive real-time synchronization and update mechanism.

[0131] Optionally, predictive maintenance of home appliances based on digital twins is based on the use of specific AI algorithm combinations (such as LSTM, Autoencoder, FFT+CNN, etc.) to comprehensively analyze the multidimensional data of the twin, so as to achieve early and accurate prediction and quantitative assessment of specific fault modes (such as refrigerant leakage, capacitor aging, mechanical wear).

[0132] Optionally, the core of home appliance energy efficiency optimization based on digital twin simulation lies in using the twin to conduct multi-scenario "What-if" simulations in a virtual environment, and combining optimization algorithms (such as reinforcement learning) to find and automatically distribute the optimal operating strategy to achieve closed-loop energy efficiency management.

[0133] Optionally, the core of personalized function iteration for home appliances based on digital twins lies in conducting deep pattern mining on user behavior data recorded by the twin, identifying unique user preferences, and dynamically generating or pushing customized software function modules based on these preferences, so as to achieve "personalized features" and continuous evolution of the device.

[0134] Optionally, the intelligent home appliance full lifecycle management system includes the data acquisition device, the core processing cloud platform (including a digital twin engine, AI analysis engine, and simulation engine), and the interactive application. Specifically, the closed-loop data flow and control flow between the components include:

[0135] As an optional implementation method, Figure 4 This is a timing diagram illustrating energy efficiency optimization based on digital twins according to embodiments of this application. Specifically, it includes the following stages:

[0136] The data acquisition phase t1 includes: 1. The user triggers an optimization request and synchronizes it with the digital twin; 2. The digital twin collects data from the physical device to obtain the current status of the device; 3. The digital twin receives the status data returned by the physical device; 4. The digital twin updates the relevant model based on the status data.

[0137] The simulation analysis phase t2 includes: 5. After the digital twin has completed the relevant model update, send the operation information to start the simulation analysis to the simulation engine; 6. The simulation engine executes the simulation; 7. The simulation engine sends the generated simulation results back to the digital twin.

[0138] The optimization calculation phase t3 includes: 8. Upon receiving the simulation results, the digital twin sends a "call optimization algorithm" prompt to the optimization algorithm function; 9. For example, it processes the data using the genetic algorithm optimization method in the optimization algorithm; 10. It feeds back the current optimization scheme to the digital twin; 11. The digital twin performs security verification on the current optimization scheme, and if the verification is successful, it iteratively optimizes the model associated with the digital twin based on the current optimization scheme.

[0139] The control execution phase consists of a control issuance sub-phase t4 and a control feedback sub-phase t5. The control issuance sub-phase t4 includes: 12. The digital twin sends control commands to the control system corresponding to the physical device. After verification and parsing, the control system issues control commands to the corresponding physical device to execute the control. The control feedback sub-phase t5 includes: after the physical device has executed the control commands, the digital twin that issued the control commands provides feedback on the execution result.

[0140] In summary, this application constructs a high-fidelity digital twin for each home appliance, achieving real-time mapping between the physical and digital worlds. This enables unprecedented depth of insight and precise simulation of the device's internal state and behavior, forming the foundation for advanced intelligent applications. Utilizing advanced AI algorithms for predictive maintenance shifts the service model from "remedial action" to "preventative action," significantly reducing the rate of sudden failures, shortening repair cycles, minimizing user losses, and enhancing brand reputation. Introducing a simulation engine for energy efficiency optimization provides users with data-verified, personalized energy-saving solutions, transforming user energy-saving behavior from "gut feeling" to "scientific basis," resulting in significant energy savings. Pushing personalized functions based on user habits transforms home appliances from static hardware into intelligent partners that "grow" with users and continuously provide new value, greatly enhancing user stickiness and product competitiveness. Integrating and constructing a complete closed-loop system from data to decision-making to execution enables efficient collaboration of information and business flows among home appliance manufacturers, users, and after-sales service providers, creating entirely new service models and commercial value.

[0141] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software device. This computer software device is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0142] Figure 5 This is a structural block diagram of a maintenance suggestion determination device according to an embodiment of this application; as shown... Figure 5 As shown, it includes:

[0143] Module 52 is used to acquire operating data of home appliances in use.

[0144] The module 54 is used to establish a digital twin of the home appliance based on the operating data. The digital twin is used to simulate the operating characteristics of the home appliance based on the operating data and to estimate the component failure probability of the home appliance within the target period.

[0145] The determination module 56 is used to determine maintenance recommendations for the home appliances based on the failure probabilities of different components output by the digital twin.

[0146] The aforementioned device acquires operational data of home appliances during their usage. Based on this data, a digital twin of the home appliance is created using a combination of physical and data-driven models. Based on this digital twin, abnormal changes in the device's operational characteristics are analyzed to predict the failure probability of each key component within a target period (e.g., the next month). Based on the failure probabilities of different components output by the digital twin, the overall operational status of the device is further analyzed. Combining user habits and device maintenance history, maintenance recommendations are generated. This solves the problem of inability to perform high-precision real-time monitoring and intelligent maintenance of home appliances in related technologies. It achieves the ability to mine user preferences for home appliances and recommend suitable maintenance solutions to target users, thus realizing personalized usage and maintenance for each individual.

[0147] In an exemplary embodiment, the above-mentioned apparatus further includes: a scenario module, configured to, after establishing a digital twin corresponding to the home appliance based on the operating data, determine the target object's operating preferences for using the home appliance based on the operating characteristics in the digital twin; in the case of obtaining multiple operating preferences of multiple home appliances in the target object's home area, establish a linkage scenario of multiple home appliances based on the multiple operating preferences; and send the linkage scenario to the target object for confirmation.

[0148] In an exemplary embodiment, the determining module is further configured to: determine the corresponding target component as a component to be maintained when the failure probability is greater than a preset probability threshold; determine the corresponding target component as a component not to be maintained when the failure probability is less than or equal to the preset probability threshold; count the first number of components to be maintained and the second number of components not to be maintained in the home appliance; and determine maintenance recommendations for the home appliance based on the first number, the second number, and the after-sales maintenance template associated with the home appliance.

[0149] In an exemplary embodiment, the aforementioned establishment module is further configured to determine the type of home appliance corresponding to the operating data; obtain a physical model corresponding to the type of appliance, wherein the physical model has simulation components with the same functions as the home appliance and a model with connection information between different simulation components; synchronize the operating data to the physical model for simulation and deduction; and determine a digital twin based on the deduction results, wherein the digital twin is a virtual simulation device with the same operating data as the home appliance.

[0150] In an exemplary embodiment, the above-described apparatus further includes: a virtual module, configured to, after establishing a digital twin corresponding to the home appliance based on operational data, determine the time parameters and operating mode of the same device operation on the home appliance when repeated device operations are found in the operational data, wherein the time parameters include at least one of the following: the initial time point at which the device operation begins, and the duration of the device operation; control the digital twin to perform virtual operation based on the time parameters, operating mode, and preset lifespan of the home appliance, wherein the preset lifespan includes multiple life periods; determine fault information of the home appliance that occurs in different life periods based on the virtual operation results; and evaluate the failure probability of different components in the home appliance through the fault information.

[0151] In an exemplary embodiment, the above-mentioned apparatus further includes: a work order module, configured to determine maintenance recommendations for home appliances based on the failure probabilities of different components output by the digital twin, send the maintenance recommendations to a target object, and determine the target object's feedback on the maintenance recommendations; generate a task work order corresponding to the home appliance based on the feedback; and synchronize the task work order to after-sales service outlets in the area where the home appliance is located.

[0152] In one exemplary embodiment, the above apparatus further includes: a development module, configured to, after establishing a digital twin corresponding to the home appliance based on operational data, determine the preference features of each target object using the digital twin corresponding to the home appliance when different target objects all use the same home appliance; determine the usage habits of the home appliance based on multiple preference features; and develop an intelligent recommendation scenario that matches the usage habits, wherein the intelligent recommendation scenario is used to link multiple devices to provide services to the target object.

[0153] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same target processor; or, the above modules are located in different target processors in any combination.

[0154] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to perform the steps in any of the above method embodiments when it is run.

[0155] Embodiments of this application also provide an electronic device, including a target memory and a target processor, wherein the target memory stores a computer program and the target processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0156] Embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0157] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0158] Embodiments of this application also provide a computer program that includes computer instructions stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps in any of the above method embodiments.

[0159] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0160] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0161] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of N computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or N modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0162] The foregoing has provided a detailed description of the method, apparatus, device, storage medium, and procedure for determining maintenance recommendations provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are merely for the purpose of helping to understand the method and core ideas of this application. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A method for determining maintenance recommendations, characterized in that, include: Acquire operational data of home appliances while they are in use; A digital twin of the home appliance is established based on the operating data. The digital twin is used to simulate the operating characteristics of the home appliance based on the operating data and to predict the probability of component failure of the home appliance within the target period. Maintenance recommendations for the home appliances are determined based on the failure probabilities of different components output by the digital twin.

2. The method for determining maintenance recommendations according to claim 1, characterized in that, After creating a digital twin of the home appliance based on the operational data, the method further includes: The operational preferences of the target object in using the home appliance are determined based on the operational characteristics in the digital twin; Given multiple operational preferences of multiple home appliances in the home area where the target object is located, a linkage scenario for multiple home appliances is established based on the multiple operational preferences. The linked scenario is sent to the target object for confirmation.

3. The method for determining maintenance recommendations according to claim 1, characterized in that, Maintenance recommendations for the home appliances are determined based on the failure probabilities of different components output by the digital twin, including: If the failure probability is greater than a preset probability threshold, the corresponding target component is identified as a component to be maintained. If the failure probability is less than or equal to a preset probability threshold, the corresponding target component is determined as a non-maintained component. Count the first number of the components requiring maintenance and the second number of the components not requiring maintenance in the home appliances; The maintenance recommendations for the home appliances are determined based on the first quantity, the second quantity, and the after-sales maintenance template associated with the home appliances.

4. The method for determining maintenance recommendations according to claim 1, characterized in that, Based on the aforementioned operational data, a digital twin of the home appliance is created, including: Determine the type of home appliance corresponding to the operational data; Obtain the physical model corresponding to the device type, wherein the physical model has simulation components with the same function as the home appliances and a model of the connection information between different simulation components; The operational data is synchronized to the physical model for simulation and deduction. A digital twin is determined based on the simulation results. The digital twin is a virtual simulation device that has the same operational data as the home appliance.

5. The method for determining maintenance recommendations according to claim 1, characterized in that, After creating a digital twin of the home appliance based on the operational data, the method further includes: In the case of repeated device operations in the operation data, the time parameters and operation mode of the same device operation on the home appliance are determined, wherein the time parameters include at least one of the following: the initial time point at which the device operation begins, and the duration of the device operation. The digital twin is controlled to run virtually according to the time parameters, the operating mode, and the preset life cycle of the home appliance, wherein the preset life cycle includes multiple life periods; Based on the virtual operation results, fault information of the home appliances that malfunctioned at different stages of their lifespan was determined; The fault information is used to assess the probability of failure of different components in home appliances.

6. The method for determining maintenance recommendations according to claim 1, characterized in that, After determining the maintenance recommendations for the home appliance based on the failure probabilities of different components output by the digital twin, the method further includes: The maintenance recommendations are sent to the target object, and the target object's response to the maintenance recommendations is determined. Based on the feedback results, a task work order corresponding to the home appliance is generated; The task work order will be synchronized to the after-sales service outlets in the area where the home appliance is located.

7. The method for determining maintenance recommendations according to claim 1, characterized in that, After creating a digital twin of the home appliance based on the operational data, the method further includes: When different target objects all use the same home appliance, determine the preference characteristics of the digital twin corresponding to the home appliance use of each target object; The usage habits of the home appliances are determined based on multiple preference features; Develop intelligent recommendation scenarios that match the aforementioned usage habits, wherein the intelligent recommendation scenarios are used to link multiple devices to provide services to the target object.

8. A device for determining maintenance recommendations, characterized in that, include: The acquisition module is used to acquire operating data of home appliances while they are in use. A module is established to create a digital twin of the home appliance based on the operating data. The digital twin is used to simulate the operating characteristics of the home appliance based on the operating data and to estimate the component failure probability of the home appliance within a target period. A determination module is used to determine maintenance recommendations for the home appliances based on the failure probabilities of different components output by the digital twin.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method described in any one of claims 1 to 7.

10. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method described in any one of claims 1 to 7 through the computer program.

Images