Intelligent household equipment health monitoring system based on hierarchical evaluation model

Abstract

The invention discloses a smart home equipment health monitoring system based on a hierarchical evaluation model, and relates to the technical field of smart home, and the system comprises a data collection module which is used for collecting all operation data of smart home equipment in real time, and the data comprises but is not limited to the voltage, current, temperature and working frequency of the equipment, and the specific state parameters of the equipment; and the hierarchical evaluation model module is electrically connected with the data acquisition module, analyzes and evaluates the acquired data layer by layer based on a preset hierarchical structure, and gradually and deeply judges the health condition of the equipment from a base layer, a middle layer to a core layer. Through the multi-parameter sensor unit and the equipment state acquisition subunit, various operation data of the intelligent household equipment can be comprehensively collected, compared with a traditional monitoring system, the data acquisition dimensionality is greatly broadened, a rich data basis is provided for accurately evaluating equipment health, and the equipment operation condition can be more accurately judged.

Description

Technical Field

[0001] The present invention relates to the technical field of smart home, and specifically to a smart home device health monitoring system based on a hierarchical evaluation model. Background Art

[0002] Smart home is a platform based on a residence, which integrates facilities related to home life by using technologies such as integrated wiring technology, network communication technology, security prevention technology, automatic control technology, and audio-video technology to build an efficient management system for residential facilities and household daily affairs, improving home security, convenience, comfort, artistry, and realizing an environmentally friendly and energy-saving living environment. Nowadays, smart home devices are widely penetrated into people's daily lives, from smart lighting, smart home appliances to smart security, covering every corner of life and bringing great convenience to people. With the wide application of smart home devices in daily life, their quantity and types are constantly increasing. The stable operation of smart home devices is crucial for the user experience. However, currently, traditional health monitoring methods are often relatively single and cannot comprehensively and accurately evaluate the actual operation status of the devices. In the field of smart home device health monitoring, although there are already some monitoring systems, most of them only simply monitor some parameters of the devices and lack in-depth analysis of the overall health status of the devices.

[0003] Although the hierarchical evaluation model has certain applications in other fields, its application in smart home device health monitoring is not yet mature. Existing monitoring systems fail to fully utilize the advantages of the hierarchical evaluation model to conduct multi-level and systematic analysis of device operation data. This makes it difficult to detect potential device failures in advance, unable to take effective measures in a timely manner to avoid device damage, thereby affecting the stability of the smart home system and the convenience of user use. At the same time, due to the lack of effective health monitoring, the maintenance cost of the devices is also relatively high, and precise maintenance cannot be carried out according to the actual health status of the devices. Summary of the Invention

[0004] To solve the above technical problems, a smart home device health monitoring system based on a hierarchical evaluation model is provided, and this technical solution solves the above problems.

[0005] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] A smart home device health monitoring system based on a hierarchical evaluation model, comprising:

[0007] A data acquisition module: used to collect various operation data of smart home devices in real time, including but not limited to the voltage, current, temperature, working frequency of the devices, and specific state parameters of the devices;

[0008] Hierarchical Evaluation Model Module: Electrically connected to the data acquisition module, the hierarchical evaluation model module analyzes and evaluates the collected data layer by layer based on a preset hierarchical structure, and gradually judges the health status of the device from the basic layer, intermediate layer to the core layer;

[0009] Health Status Determination Module: According to the analysis results of the hierarchical evaluation model module, determine the current health status of the smart home device, which is divided into three states: normal, warning, and fault;

[0010] Feedback and Control Module: Electrically connected to the health status determination module, when the device is in a warning or fault state, this module sends adjustment instructions to the smart home device and notification information to the user terminal according to preset rules.

[0011] Preferably, the data acquisition module includes:

[0012] Multi-parameter Sensor Unit: Includes a voltage sensor for monitoring the operating voltage of the device, a current sensor for measuring the operating current of the device, a temperature sensor for sensing the operating temperature of the device, and a frequency sensor for obtaining the operating frequency of the device;

[0013] Device Status Acquisition Unit: For different types of smart home devices, set corresponding status acquisition devices, including but not limited to the acquisition of the opening and closing times of smart locks and the recognition of the operating modes of smart home appliances;

[0014] Data Preprocessing Unit: Filter, denoise, and normalize the collected raw data to improve the data quality for subsequent analysis.

[0015] Preferably, the hierarchical structure of the hierarchical evaluation model module includes:

[0016] Basic Layer: Using statistical analysis methods, preliminarily analyze the basic operation data collected by the data acquisition module, calculate the mean, variance, and standard deviation of the data, and judge whether the data is within the normal fluctuation range;

[0017] Intermediate Layer: Based on the historical operation data of the device and the analysis results of the basic layer, use machine learning algorithms to build a prediction model to predict the change trend of the device's operation parameters in the future for a period of time;

[0018] Core Layer: Comprehensively analyze the results of the basic layer and the intermediate layer, and combine the design specifications and performance indicators of the device to comprehensively evaluate the health status of the device.

[0019] Preferably, the calculation formula for the basic layer to judge whether the data is within the normal fluctuation range using statistical analysis methods is:

[0020]

[0021] Among them, Z is the standard score, x is the collected original data value, μ is the historical data mean, and σ is the historical data standard deviation. When Z exceeds the preset threshold, the data is determined to be abnormal.

[0022] Preferably, the prediction model constructed by the middle layer using machine learning algorithms includes:

[0023] Adopt the time series analysis algorithm, and its formula is:

[0024]

[0025] Among them, y t is the predicted value at time t, is the autoregressive coefficient, θ j is the moving average coefficient, ∈ t is white noise, p is the autoregressive order, and q is the moving average order;

[0026] By training the historical operation data, the model parameters are determined to realize the prediction of the equipment operation parameters.

[0027] Preferably, the core layer comprehensively evaluates the equipment health status in combination with the design specifications and performance indicators of the equipment, including:

[0028] Establish an equipment health status evaluation matrix, and the matrix elements include the deviation degree between the actual value and the design value of each performance indicator of the equipment, and the deviation degree between the middle layer prediction result and the actual value;

[0029] Use the analytic hierarchy process to determine the weights of each element in the matrix, and obtain the comprehensive health status score of the equipment through weighted calculation, and determine the equipment health status according to the score.

[0030] Preferably, the formula for the comprehensive health status score is:

[0031]

[0032] Among them, S represents the final comprehensive health status score of the equipment, w 1i represents the weight coefficient of the deviation degree between the actual value and the design value of the i-th performance indicator in the weight vector w1, w 2i is the weight coefficient of the deviation degree between the middle layer prediction result and the actual value of the i-th performance indicator in the weight vector w2, represents the deviation degree between the actual value x i and the design value y i of the i-th performance indicator, z i that is, the deviation degree between the prediction result of the middle layer for the i-th performance indicator and the actual value.

[0033] Preferably, the rule for the health status determination module to determine the equipment health status is:

[0034] When the comprehensive score output by the hierarchical assessment model module is higher than the preset normal threshold, the device is judged to be in a normal state;

[0035] When the comprehensive score is between the warning threshold and the normal threshold, the device is judged to be in a warning state;

[0036] When the comprehensive score is lower than the warning threshold, the device is judged to be in a fault state.

[0037] Preferably, the feedback control method of the feedback and control module includes:

[0038] When the device is in the early warning state, an adjustment instruction is sent to the smart home device to adjust the device operating parameters to reduce the risk of device failure. The instruction sending rules are based on the preset device status and instruction mapping table;

[0039] When the device is in a fault state, a notification containing information such as the device fault type and fault location is immediately sent to the user terminal. The notification methods include SMS and APP push.

[0040] Preferably, when the feedback and control module sends notification information to the user terminal, the accompanying fault diagnosis suggestion content generation method is:

[0041] According to the fault type, the corresponding fault cause and solution are matched from the fault diagnosis knowledge base;

[0042] The matched fault causes and solutions are organized into text format and sent to the user.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] The smart home device health monitoring system based on the hierarchical evaluation model proposed in the present invention can comprehensively collect various operating data of smart home devices, including voltage, current, temperature, frequency and device-specific status parameters, through the multi-parameter sensor unit and device status acquisition subunit in the data acquisition module. Compared with the traditional monitoring system, it greatly broadens the dimension of data collection, provides a rich data foundation for accurately evaluating the health of the device, and is conducive to more accurate judgment of the device operation status.

[0045] The hierarchical assessment model module adopts a unique hierarchical structure, from statistical analysis at the base layer to machine learning prediction at the middle layer, and then to a comprehensive assessment at the core layer that combines design specifications and performance indicators. This hierarchical approach can deeply mine data information and more accurately judge the health status of equipment compared to traditional single assessment methods. The base layer preliminarily screens abnormal data, the middle layer predicts equipment operation trends, and the core layer makes comprehensive judgments, which is progressive and improves the accuracy and reliability of the assessment.

[0046] Based on the results of the hierarchical evaluation model module, the health status determination module clearly classifies the health status of the device into three types: normal, warning, and failure. This determination method enables users or maintenance personnel to quickly understand the device status. Compared with the traditional fuzzy determination method, it is more conducive to taking targeted measures in a timely manner to ensure the stable operation of smart home devices.

[0047] When the device is in a warning or failure state, the feedback and control module can send adjustment instructions according to preset rules or notify the user. When in a warning, it adjusts the device operation parameters to reduce the risk of failure; when in a failure, it notifies the user in a timely manner and provides fault diagnosis suggestions, effectively improving the device maintenance efficiency and reducing the losses caused by device damage. Description of the Drawings

[0048] Figure 1 It is the system framework diagram of the present invention. Detailed Embodiments

[0049] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments in the following description are only examples, and those skilled in the art can think of other obvious variations.

[0050] Refer to Figure 1 As shown, the smart home device health monitoring system based on the hierarchical evaluation model includes:

[0051] Data acquisition module: used to collect various operation data of smart home devices in real time, including but not limited to the voltage, current, temperature, working frequency of the device, and specific state parameters of the device;

[0052] Hierarchical evaluation model module: electrically connected to the data acquisition module. The hierarchical evaluation model module analyzes and evaluates the collected data layer by layer based on a preset hierarchical structure, and gradually and deeply judges the device health status from the basic layer, intermediate layer to the core layer;

[0053] Health status determination module: determines the current health status of the smart home device according to the analysis results of the hierarchical evaluation model module, and classifies it into three states: normal, warning, and failure;

[0054] Feedback and control module: electrically connected to the health status determination module. When the device is in a warning or failure state, this module sends adjustment instructions to the smart home device and notification information to the user terminal according to preset rules.

[0055] Specifically, the data acquisition module collects various operation data of smart home devices in real time. These data serve as the basis for subsequent analysis. The hierarchical evaluation model module processes the data step by step from the basic layer, intermediate layer to the core layer according to the preset hierarchical structure, and deeply analyzes the health status of the devices. The health status determination module clearly divides the current health status of the devices into three types: normal, warning, and failure based on the hierarchical evaluation results. The feedback and control module sends adjustment instructions to the devices or sends notification information to the user terminals according to the status of the devices, forming a complete monitoring closed-loop. Through this multi-module collaboration and hierarchical evaluation method, comprehensive and accurate health monitoring of smart home devices is achieved. Compared with traditional single monitoring means, it can grasp the device operation status more timely and accurately, greatly improving the stability of the smart home system and ensuring the convenient use experience of users.

[0056] The data acquisition module includes:

[0057] Multi-parameter sensor unit: It includes a voltage sensor for monitoring the device operating voltage, a current sensor for measuring the device operating current, a temperature sensor for sensing the device operating temperature, and a frequency sensor for obtaining the device operating frequency;

[0058] Device status acquisition unit: For different types of smart home devices, corresponding status acquisition devices are set, including but not limited to the acquisition of the opening and closing times of smart locks and the recognition of the operating modes of smart home appliances;

[0059] Data preprocessing unit: Filter, denoise, and normalize the collected raw data to improve the data quality for subsequent analysis.

[0060] Specifically, the multi-parameter sensor unit is configured with a variety of professional sensors. The voltage sensor monitors the device operating voltage in real time, the current sensor accurately measures the operating current, the temperature sensor senses the device operating temperature, and the frequency sensor obtains the device operating frequency, comprehensively covering the basic operating parameters of the device; the device status acquisition unit adopts customized acquisition devices for different types of smart home devices, such as the acquisition of the opening and closing times of smart locks and the recognition of the operating modes of smart home appliances, to obtain the unique status information of the device; the data preprocessing unit filters, denoises, and normalizes the collected raw data, removes interference data, and makes the data format unified for subsequent analysis. Comprehensive data acquisition provides rich and high-quality data support for device health assessment. The combination of the multi-parameter sensor and the device status acquisition unit ensures that the collected information is complete without omission, and the preprocessing operation improves the data quality, making the subsequent analysis more reliable and laying a solid foundation for accurately judging the health status of the device.

[0061] The hierarchical structure of the hierarchical evaluation model module includes:

[0062] Base layer: Using statistical analysis methods, perform preliminary analysis on the basic operation data collected by the data acquisition module, calculate the mean, variance, and standard deviation of the data, and determine whether the data is within the normal fluctuation range;

[0063] Middle layer: Based on the historical operation data of the device and the analysis results of the base layer, use machine learning algorithms to build a prediction model to predict the change trend of the device's operation parameters in the future for a period of time;

[0064] Core layer: Comprehensively combine the analysis results of the base layer and the middle layer, and combine the design specifications and performance indicators of the device to comprehensively evaluate the health status of the device.

[0065] Specifically, the base layer uses statistical analysis methods to calculate statistics such as the mean, variance, and standard deviation for the basic operation data provided by the data acquisition module, and uses this to determine whether the data is within the normal fluctuation range, completing preliminary screening and anomaly detection; the middle layer uses the device's historical operation data and the analysis results of the base layer, and uses machine learning algorithms to build a prediction model to predict the change trend of the device's future operation parameters and gain insight into potential changes in the device in advance. The core layer comprehensively combines the results of the base layer and the middle layer, and combines the device design specifications and performance indicators to comprehensively evaluate the health status of the device and obtain a comprehensive judgment. Through the hierarchical evaluation structure advancing layer by layer, the base layer initially identifies anomalies, the middle layer predicts trends, and the core layer makes a comprehensive determination, greatly improving the accuracy and reliability of the evaluation. It can discover potential fault hazards in the device in advance, provide a strong basis for device maintenance, reduce the probability of sudden device failures, and ensure the stable operation of the smart home system.

[0066] The formula used by the base layer to determine whether the data is within the normal fluctuation range using statistical analysis methods is:

[0067]

[0068] Among them, Z is the standard score, x is the original data value collected, μ is the mean of the historical data, σ is the standard deviation of the historical data, and when Z exceeds the preset threshold, the data is determined to be abnormal.

[0069] Specifically, by calculating statistics such as the mean, variance, and standard deviation of the data, establish a standard for the normal fluctuation range of the data, and compare the collected real-time data with this standard. If the data exceeds the normal fluctuation range, it is determined to be abnormal. It can quickly screen out abnormal data, discover potential problems in the initial stage of device operation in a timely manner, provide clues for subsequent in-depth analysis, help maintenance personnel intervene early, avoid small problems from evolving into major failures, reduce the device repair cost, and increase the service life of the device.

[0070] The machine learning algorithms used by the middle layer to build a prediction model include:

[0071] Adopt the time series analysis algorithm, and its formula is:

[0072]

[0073] where y t is the predicted value of time t, is the autoregressive coefficient, θ j is the moving average coefficient, ∈ t is white noise, p is the autoregressive order, and q is the moving average order;

[0074] By training on historical operation data, the model parameters are determined to achieve the prediction of equipment operation parameters.

[0075] Specifically, a time series analysis algorithm is adopted to train using the historical operation data of the equipment, determine the model parameters, and construct a prediction model. This model can predict the change trend of equipment operation parameters in a future period according to the past operation data of the equipment, such as the change trends of parameters such as equipment voltage, current, and temperature, so as to predict in advance the change trend of equipment operation parameters, enabling maintenance personnel to make preparations in advance. For example, if it is predicted that the equipment temperature will rise and may cause a failure, maintenance can be arranged in advance to avoid damage to the equipment due to excessive temperature, improve the initiative and pertinence of equipment maintenance, and reduce the impact of equipment failures on user use.

[0076] The core layer comprehensively evaluates the equipment health status in combination with the design specifications and performance indicators of the equipment, including:

[0077] Establish an equipment health status evaluation matrix, and the matrix elements include the deviation degree between the actual value and the design value of each performance indicator of the equipment, and the deviation degree between the prediction result of the intermediate layer and the actual value;

[0078] Use the analytic hierarchy process to determine the weights of each element in the matrix, and obtain the comprehensive health status score of the equipment through weighted calculation, and determine the equipment health status according to the score.

[0079] Specifically, establish an equipment health status evaluation matrix, and the matrix elements include the deviation degree between the actual value and the design value of each performance indicator of the equipment, and the deviation degree between the prediction result of the intermediate layer and the actual value; use the analytic hierarchy process to determine the weights of each element in the matrix, and obtain the comprehensive health status score of the equipment through weighted calculation, and determine the equipment health status according to the score. Considering the equipment design specifications, performance indicators and actual operation conditions comprehensively, a comprehensive and accurate equipment health evaluation result is obtained, making the equipment health status evaluation more scientific and reasonable, providing a precise basis for equipment maintenance decision-making, helping to achieve precise equipment maintenance, reducing maintenance costs, and improving equipment operation efficiency.

[0080] The formula for the comprehensive health status score is:

[0081]

[0082] Among them, S represents the comprehensive score of the final device health status, and w 1i represents the weight coefficient of the deviation degree between the actual value and the design value of the i-th performance index in the weight vector w1, and w 2i is the weight coefficient of the deviation degree between the intermediate layer prediction result and the actual value of the i-th performance index in the weight vector w2. represents the actual value x of the i-th performance index i and the design value y i of the deviation degree, z i that is, the deviation degree between the prediction result of the intermediate layer for the i-th performance index and the actual value.

[0083] Specifically, by assigning different weights to the deviation degree between the actual value and the design value of each performance index of the device and the deviation degree between the intermediate layer prediction result and the actual value, and then performing weighted calculation, a score that comprehensively reflects the device health status is obtained. This score comprehensively considers the influence of multiple key factors of the device on the health status, accurately presents the device health status in a quantitative manner, and is convenient for intuitively judging the device health degree. The scoring result can be used as the basis for ranking the device maintenance priorities. Priority is given to maintaining the devices with low scores, reasonably allocating maintenance resources, and improving maintenance efficiency.

[0084] The rule for the health status determination module to determine the device health status is as follows:

[0085] When the comprehensive score output by the hierarchical evaluation model module is higher than the preset normal threshold, it is determined that the device is in a normal state;

[0086] When the comprehensive score is between the warning threshold and the normal threshold, it is determined that the device is in a warning state;

[0087] When the comprehensive score is lower than the warning threshold, it is determined that the device is in a failure state.

[0088] Specifically, the clear and definite determination rule makes the device health status clear at a glance, enabling users or maintenance personnel to quickly understand the device situation and take corresponding measures. For example, timely check for hidden dangers in the warning state and quickly repair in the failure state, improving the timeliness of device maintenance and ensuring the stable operation of the smart home system.

[0089] The feedback control methods of the feedback and control module include:

[0090] When the device is in a warning state, send an adjustment instruction to the smart home device to adjust the device operation parameters to reduce the device failure risk. The instruction sending rule is based on the preset device status and the instruction mapping table;

[0091] When the device is in a fault state, immediately send a notice containing information such as the device fault type and fault location to the user terminal, and the notice methods include text messages and APP push.

[0092] Specifically, when the device is in a warning state, the feedback and control module sends adjustment instructions to the device according to the preset device state and instruction mapping table, such as adjusting the power of smart home appliances and changing the brightness of smart lighting, etc., to reduce the device fault risk; when the device is in a fault state, immediately send a notice containing information such as the device fault type and fault location to the user terminal by means of text messages, APP push, etc. Actively adjust the device operation parameters during warning to prevent faults from occurring and extend the service life of the device. When a fault occurs, notify the user in time, which is convenient for the user to quickly understand the situation and arrange maintenance, reduce the inconvenience caused by device faults to life, and improve the user's satisfaction with the smart home system.

[0093] When the feedback and control module sends a notice message to the user terminal, the method for generating the content of the fault diagnosis suggestion attached is as follows:

[0094] According to the fault type, match the corresponding fault causes and solutions from the fault diagnosis knowledge base;

[0095] Organize the matched fault causes and solutions into a text format and send them to the user.

[0096] Specifically, when the user receives a device fault notice, they can simultaneously obtain professional fault diagnosis suggestions, understand the fault causes and solutions, which helps the user take some simple measures before the arrival of professional maintenance personnel, reduce the impact of the fault, and at the same time improve the user's participation and awareness in device fault handling, and enhance the user's trust in the smart home system.

[0097] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed.

Claims

1. A smart home device health monitoring system based on a hierarchical evaluation model, characterized in that, Including: Data acquisition module: used to collect various operating data of smart home devices in real time, including but not limited to the voltage, current, temperature, operating frequency of the device, and specific state parameters of the device; Hierarchical evaluation model module: electrically connected to the data acquisition module, the hierarchical evaluation model module analyzes and evaluates the collected data layer by layer based on a preset hierarchical structure, and gradually judges the health status of the device from the basic layer, intermediate layer to the core layer; Health status determination module: determines the current health status of the smart home device according to the analysis results of the hierarchical evaluation model module, and divides it into three states: normal, warning, and failure; Feedback and control module: electrically connected to the health status determination module, when the device is in a warning or failure state, this module sends adjustment instructions to the smart home device and sends notification information to the user terminal according to preset rules.

2. The smart home device health monitoring system based on a hierarchical evaluation model according to claim 1, wherein The data acquisition module includes: Multi-parameter sensor unit: includes a voltage sensor for monitoring the operating voltage of the device, a current sensor for measuring the operating current of the device, a temperature sensor for sensing the operating temperature of the device, and a frequency sensor for obtaining the operating frequency of the device; Device status acquisition unit: for different types of smart home devices, corresponding status acquisition devices are set, including but not limited to the collection of the opening and closing times of smart locks and the recognition of the operating modes of smart home appliances; Data preprocessing unit: filters, denoises, and normalizes the collected raw data to improve the data quality for subsequent analysis.

3. The smart home device health monitoring system based on the hierarchical evaluation model according to claim 1, characterized in that, The hierarchical structure of the hierarchical evaluation model module includes: Basic layer: uses statistical analysis methods to preliminarily analyze the basic operating data collected by the data acquisition module, calculates the mean, variance, and standard deviation of the data, and judges whether the data is within the normal fluctuation range; Intermediate layer: based on the historical operating data of the device and the analysis results of the basic layer, uses machine learning algorithms to construct a prediction model to predict the change trend of the device's operating parameters in the future for a period of time; Core layer: comprehensively combines the analysis results of the basic layer and the intermediate layer, and combines the design specifications and performance indicators of the device to comprehensively evaluate the health status of the device.

4. The health monitoring system for smart home devices based on the hierarchical evaluation model according to claim 3, wherein, The formula for the basic layer to judge whether the data is within the normal fluctuation range using statistical analysis methods is: Where Z is the standard score, x is the collected raw data value, μ is the historical data mean, and σ is the historical data standard deviation. When Z exceeds the preset threshold, the data is judged to be abnormal.

5. The health monitoring system for smart home devices based on the hierarchical evaluation model according to claim 3, characterized in that The intermediate layer uses machine learning algorithms to construct a prediction model including: Adopts a time series analysis algorithm, and its formula is: where y t is the predicted value of time t, is the autoregressive coefficient, θ j is the moving average coefficient, ∈ t is white noise, p is the autoregressive order, and q is the moving average order; Through the training of historical operating data, the model parameters are determined to realize the prediction of the device's operating parameters.

6. The health monitoring system for smart home devices based on a hierarchical evaluation model according to claim 3, characterized in that, The core layer comprehensively evaluates the health status of the device by combining the design specifications and performance indicators of the device including: Establish a device health status evaluation matrix, and the matrix elements include the deviation degree between the actual value and the design value of each performance indicator of the device, and the deviation degree between the intermediate layer prediction result and the actual value; Use the analytic hierarchy process to determine the weights of each element in the matrix, and obtain the comprehensive health status score of the device through weighted calculation, and determine the health status of the device according to the score.

7. The health monitoring system for smart home devices based on the hierarchical evaluation model according to claim 6, wherein, The formula for the comprehensive health status score is: Among them, S represents the comprehensive score of the device health status finally obtained, w 1i represents the weight coefficient of the deviation degree between the actual value and the design value of the i-th performance index in the weight vector w1, w 2i is the weight coefficient of the deviation degree between the prediction result of the intermediate layer and the actual value of the i-th performance index in the weight vector w2, represents the actual value x of the i-th performance index i and the deviation degree from the design value y i , z i that is, the deviation degree between the prediction result of the intermediate layer for the i-th performance index and the actual value.

8. The smart home device health monitoring system based on a hierarchical evaluation model according to claim 1, characterized in that, The rules for the health status determination module to determine the health status of the device are as follows: When the comprehensive score output by the hierarchical evaluation model module is higher than the preset normal threshold, it is determined that the device is in a normal state; When the comprehensive score is between the warning threshold and the normal threshold, it is determined that the device is in a warning state; When the comprehensive score is lower than the warning threshold, it is determined that the device is in a failure state.

9. The smart home device health monitoring system based on a hierarchical evaluation model according to claim 1, characterized in that, The feedback control methods of the feedback and control module include: When the device is in a warning state, send an adjustment instruction to the smart home device to adjust the device operation parameters to reduce the device failure risk, and the instruction sending rule is based on the preset device state and the instruction mapping table; When the device is in a failure state, immediately send a notice containing information such as the device failure type and failure location to the user terminal, and the notice methods include text messages and APP push.

10. The smart home device health monitoring system based on a hierarchical evaluation model according to claim 1, characterized in that, When sending a notice message to the user terminal in the feedback and control module, the method for generating the content of the fault diagnosis suggestion attached is: According to the fault type, match the corresponding fault causes and solutions from the fault diagnosis knowledge base; Organize the matched fault causes and solutions into a text format and send them to the user.

Images