Household device energy consumption and accessory life prediction and pre-departure prompting method and system

Abstract

The application discloses a household device energy consumption and accessory life prediction and pre-outgoing prompt method and system, and the method comprises the following steps: S1, device operation data acquisition; S2, device historical data learning and feature construction; S3, device energy consumption and accessory life prediction; S4, outgoing scene identification; S5, device risk assessment in the outgoing period; S6, generating pre-outgoing prompt information; S7, prompt information display and user interaction. The application introduces artificial intelligence, edge computing and other technologies, learns and predicts the power consumption and accessory consumption of the intelligent devices in the household for a long time, and automatically generates risk assessment and maintenance prompts before the user needs to go out for a long time, so that the reliability and user experience of the smart home system are improved.

Description

Technical Field

[0001] This invention relates to the field of smart home technology, and in particular to a method and system for predicting energy consumption and accessory lifespan of home devices and providing pre-departure reminders. Background Technology

[0002] With the popularization of smart homes, smart home systems with smart gateways as the control center are gradually being deployed in homes. These systems typically connect to various smart devices, such as smart door locks, security sensors, cameras, air purifiers, robot vacuums, and other environmental control devices, through smart gateways to achieve unified management and linkage control. Existing smart home systems mainly focus on the functional control and status display of devices. For the power consumption trend of devices and the remaining lifespan of accessories, they mostly adopt passive alarm methods, that is, they only remind users when the battery is too low or the accessory lifespan is about to run out. In practical applications, users often experience extended periods of absence, such as business trips or long holiday travel. During these times, if the smart devices in the home exhibit the following issues: 1. Security devices often use button batteries, which may fail if the batteries run out while the user is away; 2. Smart door locks rely on batteries or rechargeable batteries, and running out of power will prevent the user from entering the house; 3. Air purifiers, water purifiers, and other devices may reach their replacement threshold while the user is away, affecting their normal operation. When the user returns home, these problems often become apparent, causing inconvenience and severely impacting the user experience. Current technology lacks a solution to predict and proactively alert users to device power consumption and accessory wear before they plan to leave for extended periods. Therefore, this application proposes a method and system for predicting home device energy consumption and accessory lifespan, as well as providing pre-departure alerts. Summary of the Invention

[0003] Based on the technical problems existing in the background technology, the present invention proposes a method and system for predicting the energy consumption and lifespan of household equipment and providing pre-trip reminders.

[0004] The method for predicting energy consumption and component lifespan of household appliances and providing pre-trip reminders proposed in this invention includes the following steps: S1: Device operation data collection: The smart device periodically reports its operation data to the smart gateway, and the smart gateway uniformly receives and stores the data; S2: Device historical data learning and feature construction: Based on historical data collection, the smart gateway constructs a smart device-level time series and extracts features such as the frequency of use of smart devices, power consumption trends, and accessory consumption rates, while also performing collaborative learning. S3: Device Energy Consumption and Component Life Prediction: The edge computing and prediction module uses a time series prediction model to predict the trend of remaining power consumption of smart devices and the remaining usable lifespan of components over a period of time. The prediction results include, but are not limited to, the expected depletion time and the number of remaining usable days. S4: Outing Scene Recognition: When the smart gateway determines a user's outing scene, it determines that the user has been out for an extended period of time if at least one of the following conditions is met: (1) Users manually set their outing plans in the terminal; (2) The family enters the away-from-home mode and the duration exceeds the preset threshold; (3) Automatically infer the user's outing status based on their historical behavior; S5: Device Risk Assessment During Off-Duty Period: Based on the prediction results of S3 and the off-duty duration of S4, the risk assessment module determines whether there is a risk of battery depletion or accessory failure during the user's off-duty period, and generates a risk level for the corresponding device. S6: Generate pre-departure reminder information: When the risk level exceeds the preset threshold, generate a maintenance or replacement reminder for the corresponding equipment; S7: Display of prompts and user interaction: The prompts from S6 are displayed to the user via the user terminal APP before the user leaves, and the user's confirmation, ignore or delay operation is received. The user feedback can be used for subsequent model parameter adjustments.

[0005] Preferably, in step S1, the data reported by the smart device includes, but is not limited to, battery level, power supply voltage, device runtime, cumulative accessory usage, and usage time.

[0006] Preferably, in step S6, the prompt includes the device type, the cause of the risk, and suggested actions.

[0007] Preferably, in step S3, when using a time series prediction model for prediction, it is necessary to model the device power consumption, battery degradation, and filter consumption. Furthermore, during prediction, it is necessary to combine the device usage frequency, environmental factors, and user behavior characteristics to improve prediction accuracy.

[0008] Preferably, in step S2, the learning process can be carried out continuously locally, regardless of whether the user is away from home, and a cloud-edge collaborative learning mechanism can be adopted for learning. The cloud AI platform gathers anonymized data from multiple families for unified model training, and the smart gateway receives the model parameters and performs local fine-tuning to adapt to the personalized usage habits of families.

[0009] Preferably, in step S4, the user can manually set the duration of their absence through a user terminal APP, or the system can automatically identify long-term absence scenarios through calendar, location, and flight information.

[0010] This invention also proposes a home appliance energy consumption and accessory lifespan prediction and pre-departure reminder system, including a smart device layer, a smart gateway, an edge computing and prediction module, a risk assessment module, a pre-departure reminder strategy module, a user terminal APP, and a cloud-based AI model training platform; The intelligent device layer is used to generate device operation data, but does not perform prediction or prompt logic; The intelligent gateway, as the executor of the method, is responsible for data collection, processing, prediction, and decision-making suggestions. The edge computing and prediction module is used to execute the energy consumption and component life prediction steps in the method. The risk assessment module is used to perform the outing risk assessment step in the method. The pre-departure reminder strategy module is used to execute the reminder generation step in the method; The user terminal APP serves as the interface for displaying and interacting with the method results; The cloud-based AI model training platform is used to provide model parameter updates for the method, but does not directly participate in the decision-making process.

[0011] Compared with existing technologies, the beneficial effects of this invention are: 1. Upgrade the passive alarm mode of device power consumption and component lifespan in the existing technology to an active predictive reminder mode. By predicting in advance the problems that may occur when users are away for a long time, such as device power depletion and component failure, and issuing maintenance reminders, the problem is prevented from erupting at the root. This effectively solves the pain point of users encountering device failure after returning home, significantly optimizes the user experience when going out and returning home, reduces the inconvenience caused by security equipment failure, unusable smart door locks, and environmental control equipment shutdown, and greatly improves the user satisfaction and reliability of smart home systems. 2. By accurately predicting power consumption trends, the risk of device failure during absence is reduced, further enhancing the stability and security of home security. 3. By integrating edge computing and AI technology, real-time prediction and risk assessment can be completed locally on the smart gateway. This reduces reliance on the cloud, improves system response speed, and avoids the large-scale uploading of private data, thus balancing real-time prediction, accuracy of results, and user privacy and security. This invention introduces technologies such as artificial intelligence and edge computing to learn and predict the power consumption and component consumption of smart devices in the home over a long period of time. It proactively generates risk assessments and maintenance reminders before users need to be away for extended periods, thereby improving the reliability of smart home systems and user experience. Attached Figure Description

[0012] Figure 1 This is a timing diagram of the method for predicting energy consumption and accessory lifespan of household devices and providing pre-trip reminders proposed in this invention. Figure 2 This is a block diagram of the household equipment energy consumption and accessory lifespan prediction and pre-departure reminder system proposed in this invention. Detailed Implementation

[0013] The present invention will be further explained below with reference to specific embodiments. Example

[0014] Reference Figure 1 This embodiment proposes a method for predicting energy consumption and component lifespan of household appliances and providing pre-trip reminders, including the following steps: S1: Device operation data collection: The smart device periodically reports its operation data to the smart gateway. The smart gateway receives and stores the data in a unified manner. The data reported by the smart device includes, but is not limited to, battery level, power supply voltage, device running time, cumulative usage of accessories, and usage time. S2: Device historical data learning and feature construction: Based on historical data collection, the smart gateway constructs a smart device-level time series and extracts features such as the frequency of use of smart devices, power consumption trends, and accessory consumption rates, while also performing collaborative learning. The learning process can be carried out continuously locally, regardless of whether the user is away from home. It can also adopt a cloud-edge collaborative learning mechanism. The cloud AI platform gathers anonymized data from multiple families to train the model in a unified manner. The smart gateway receives the model parameters and performs local fine-tuning to adapt to the personalized usage habits of families. S3: Device Energy Consumption and Component Life Prediction: The edge computing and prediction module uses a time series prediction model to predict the trend of remaining power consumption of smart devices and the remaining usable lifespan of components over a period of time. The prediction results include, but are not limited to, the expected depletion time and the number of remaining usable days. When using time series prediction models for prediction, it is necessary to model the device power consumption, battery degradation and filter consumption. In addition, during the prediction, it is necessary to combine the device usage frequency, environmental factors and user behavior characteristics to improve the prediction accuracy. S4: Outing Scene Recognition: When the smart gateway determines a user's outing scene, it determines that the user has been out for an extended period of time if at least one of the following conditions is met: (1) Users manually set their outing plans in the terminal; (2) The family enters the away-from-home mode and the duration exceeds the preset threshold; (3) Automatically infer the user's outing status based on their historical behavior; Users can manually set the duration of their absence through the user terminal APP, or the system can automatically identify long-term absence scenarios through calendar, location, and flight information. S5: Device Risk Assessment During Off-Duty Period: Based on the prediction results of S3 and the off-duty duration of S4, the risk assessment module determines whether there is a risk of battery depletion or accessory failure during the user's off-duty period, and generates a risk level for the corresponding device. S6: Generate pre-trip reminder information: When the risk level exceeds the preset threshold, generate a maintenance or replacement reminder for the corresponding equipment. The reminder content includes the equipment type, the reason for the risk, and suggested actions. S7: Display of prompts and user interaction: The prompts from S6 are displayed to the user via the user terminal APP before the user leaves, and the user's confirmation, ignore or delay operation is received. The user feedback can be used for subsequent model parameter adjustments.

[0015] Reference Figure 2 This embodiment also proposes a home device energy consumption and accessory life prediction and pre-departure reminder system, including a smart device layer, a smart gateway, an edge computing and prediction module, a risk assessment module, a pre-departure reminder strategy module, a user terminal APP, and a cloud AI model training platform; The intelligent device layer is used to generate device operation data, but does not perform prediction or prompting logic; The smart gateway, as the executor of the method, is responsible for data collection, processing, prediction, and decision-making suggestions. The edge computing and prediction module is used to execute the energy consumption and component life prediction steps in the method. The risk assessment module is used to determine the risk of going out in the execution method. The pre-departure prompt strategy module is used to execute the prompt generation step in the method; The user terminal APP serves as the interface for displaying and interacting with the method results; The cloud-based AI model training platform is used to provide model parameter updates for the method, but does not directly participate in the decision-making process.

[0016] This embodiment introduces technologies such as artificial intelligence and edge computing to learn and predict the power consumption and component consumption of smart devices in the home over a long period of time. It proactively generates risk assessments and maintenance reminders before users need to be away for an extended period of time, thereby improving the reliability of the smart home system and the user experience.

[0017] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for predicting household appliance energy consumption and accessory lifespan, and providing pre-trip reminders, characterized in that... Includes the following steps: S1: Device operation data collection: The smart device periodically reports its operation data to the smart gateway, and the smart gateway uniformly receives and stores the data; S2: Device historical data learning and feature construction: Based on historical data collection, the smart gateway constructs a smart device-level time series and extracts features such as the frequency of use of smart devices, power consumption trends, and accessory consumption rates, while also performing collaborative learning. S3: Device Energy Consumption and Component Life Prediction: The edge computing and prediction module uses a time series prediction model to predict the trend of remaining power consumption of smart devices and the remaining usable lifespan of components over a period of time. The prediction results include, but are not limited to, the expected depletion time and the number of remaining usable days. S4: Outing Scene Recognition: When the smart gateway determines a user's outing scene, it determines that the user has been out for an extended period of time if at least one of the following conditions is met: (1) Users manually set their outing plans in the terminal; (2) The family enters the away-from-home mode and the duration exceeds the preset threshold; (3) Automatically infer the user's outing status based on their historical behavior; S5: Device Risk Assessment During Off-Duty Period: Based on the prediction results of S3 and the off-duty duration of S4, the risk assessment module determines whether there is a risk of battery depletion or accessory failure during the user's off-duty period, and generates a risk level for the corresponding device. S6: Generate pre-departure reminder information: When the risk level exceeds the preset threshold, generate a maintenance or replacement reminder for the corresponding equipment; S7: Display of prompts and user interaction: The prompts from S6 are displayed to the user via the user terminal APP before the user leaves, and the user's confirmation, ignore or delay operation is received. The user feedback can be used for subsequent model parameter adjustments.

2. The method for predicting household appliance energy consumption and accessory lifespan and providing pre-trip reminders according to claim 1, characterized in that, In S1, the data reported by the smart device includes, but is not limited to, battery level, power supply voltage, device runtime, cumulative accessory usage, and usage time.

3. The method for predicting household appliance energy consumption and accessory lifespan and providing pre-trip reminders according to claim 1, characterized in that, In step S6, the prompt includes the device type, the cause of the risk, and suggested actions.

4. The method for predicting household appliance energy consumption and accessory lifespan and providing pre-trip reminders according to claim 1, characterized in that, In S3, when using a time series prediction model for prediction, it is necessary to model the device power consumption, battery degradation and filter consumption. Furthermore, during prediction, it is necessary to combine the device usage frequency, environmental factors and user behavior characteristics to improve prediction accuracy.

5. The method for predicting household appliance energy consumption and accessory lifespan and providing pre-trip reminders according to claim 1, characterized in that, In S2, the learning process can be carried out continuously locally, regardless of whether the user is away from home. It can also adopt a cloud-edge collaborative learning mechanism. The cloud AI platform gathers anonymized data from multiple families for unified model training. The smart gateway receives the model parameters and performs local fine-tuning to adapt to the personalized usage habits of families.

6. The method for predicting household equipment energy consumption and accessory lifespan and providing pre-trip reminders according to claim 1, characterized in that, In S4, users can manually set the duration of their absence through a user terminal APP, or the system can automatically identify long-term absence scenarios through calendar, location, and flight information.

7. A system for predicting energy consumption and component lifespan of household appliances and providing pre-trip reminders, used to implement the method described in any one of claims 1-6, characterized in that, It includes a smart device layer, a smart gateway, an edge computing and prediction module, a risk assessment module, a pre-trip alert strategy module, a user terminal APP, and a cloud-based AI model training platform; The intelligent device layer is used to generate device operation data, but does not perform prediction or prompt logic; The intelligent gateway, as the executor of the method, is responsible for data collection, processing, prediction, and decision-making suggestions. The edge computing and prediction module is used to execute the energy consumption and component life prediction steps in the method. The risk assessment module is used to perform the outing risk assessment step in the method. The pre-departure reminder strategy module is used to execute the reminder generation step in the method; The user terminal APP serves as the interface for displaying and interacting with the method results; The cloud-based AI model training platform is used to provide model parameter updates for the method, but does not directly participate in the decision-making process.

Images