Intelligent furniture state analysis method and system based on Internet of Things, and storage medium

Abstract

The invention relates to the technical field of electronic module detection, and discloses an intelligent furniture state analysis method and system based on the Internet of Things, and a storage medium, and the method comprises the steps: collecting first sound data of an electronic module in a set time period, and carrying out the frequency spectrum conversion of the first sound data to obtain first frequency spectrum data; meanwhile, a background sound library of the environment where the electronic module is located is obtained, and background sound data and corresponding background spectrum data exist in the library; filtering the first spectrum data according to the background spectrum data to obtain second spectrum data; calculating incremental frequencies, incremental energy, an average value and a discrete value of the incremental frequencies, and an accumulated value and a fluctuation value of the incremental energy of the plurality of second frequency spectrum data; and a frequency confidence value and an energy confidence value are calculated through the numerical values, so that a comprehensive confidence value is obtained. And if the comprehensive confidence value is greater than a preset reference confidence value, state abnormity prompting is carried out, so that effective monitoring and early warning of the operation state of the intelligent furniture electronic module can be realized.

Description

Technical Field

[0001] The present application relates to the technical field of electronic module detection, and in particular to a method, system and storage medium for analyzing the state of smart furniture based on the Internet of Things. Background Art

[0002] The development of smart furniture relies on the deep integration of the Internet of Things and energy management technology, and the core lies in the innovative integration of electronic modules. Sensor technology is used to achieve basic environmental perception. With the advancement of microprocessor and wireless communication technology, electronic modules support device interconnection and remote control.

[0003] Electronic modules have evolved from single functions to multi-technology integration. They have functions such as wireless charging and electrical appliance control. The circuit in the electronic module has an independent power supply and control unit. The power supply is used to charge or power the control unit. There is also a status indicator in the circuit to indicate the working status of the electronic module. For example, when the electronic module is dormant, the status indicator goes out, and when the electronic module is working, the status indicator flashes.

[0004] The circuits in electronic modules have a variety of components, such as resistors, capacitors, inductors, integrated circuit chips, etc. After the electronic modules are used for a period of time, the components will age, causing the electronic modules to produce current whistling sounds when working. The reasons for the current whistling sounds include excessive power ripple, capacitor leakage, or large dielectric loss. The current whistling sounds emitted by electronic modules become louder over time, and the frequency of the current whistling sounds also changes over time. Users cannot perceive the current whistling sounds in the early stages. When they can perceive the current whistling sounds, they have already spent a long time in the current whistling sounds. The user experience needs to be improved. Summary of the invention

[0005] In order to let users know the current howling status of electronic modules as early as possible, the present application provides a smart furniture status analysis method, system and storage medium based on the Internet of Things.

[0006] In the first aspect, the present application provides a method for analyzing the state of smart furniture based on the Internet of Things, which adopts the following technical solutions: A method for analyzing the state of smart furniture based on the Internet of Things comprises the following steps: Within a set time period, regularly collect first sound data of the electronic module; Performing spectrum conversion on the first sound data to obtain first spectrum data; Acquire a background sound library of the environment where the electronic module is located, wherein the background sound library includes background sound data and background spectrum data corresponding to the background sound data; Filtering the first spectrum data according to the background spectrum data to obtain second spectrum data; Calculate the incremental frequency of multiple pieces of the second spectral data and the incremental energy corresponding to the incremental frequency; Calculate the average value and the discrete value of the incremental frequency, and calculate the cumulative value and the fluctuation value of the incremental energy; Calculate the frequency confidence value according to the average value and the discrete value, and calculate the energy confidence value according to the cumulative value and the fluctuation value; Calculate the comprehensive confidence value according to the frequency confidence value and the energy confidence value; If the comprehensive confidence value is greater than a preset reference confidence value, perform a status anomaly prompt.

[0007] By adopting the above technical solution, with the help of sound wave and spectrum analysis technology, the sound signal can be accurately analyzed. Through spectrum conversion, the sound data is converted into spectral data to analyze the frequency composition, so as to sensitively identify the current whistling caused by component failures such as capacitors. Because of its unique spectral characteristics, it can be compared with the normal state. It can achieve effective early warning and greatly improve the user experience. By regularly collecting and continuously analyzing the sound data, when the current whistling is difficult to detect by the human ear in the very early stage, various confidence values are calculated based on key parameters. Once the comprehensive confidence value exceeds the preset value, an anomaly is prompted, enabling the user to handle the problem in the initial stage of the failure, reducing noise interference, and improving the accuracy and reliability of the analysis.

[0008] Optionally, the method further includes the following steps: Calculate the first time-domain waveform diagram of the comprehensive confidence value, and extract the first change node sequence from the first time-domain waveform diagram; Calculate the fluctuation degree value in the first change node sequence; If the fluctuation degree value is greater than a preset first classification value, perform a non-continuous whistling warning.

[0009] By adopting the above technical solution, for smart furniture, non-continuous whistling may mean that the component failure is in the initial unstable stage or is subject to intermittent interference. Timely warning can enable users or maintenance personnel to pay attention in advance and take targeted measures to reduce the degree of problem deterioration, further improving the accuracy and comprehensiveness of the operation status monitoring of smart furniture.

[0010] Optionally, the method further includes the following steps: Based on the non-continuous whistling warning, obtain the indication parameter of the electronic module while calculating the frequency confidence value; Calculate the second time-domain waveform diagram of the indication parameter, and extract the second change node sequence from the second time-domain waveform diagram; Calculate the node matching value between the first change node sequence and the second change node sequence; If the node matching value is greater than a preset first reference matching value, non - continuous whistling warning is performed.

[0011] By adopting the above - mentioned technical solution, the current whistling characteristics are correlated and analyzed with other working state parameters (such as indication parameters) of the electronic module. Taking the change of light as an example, if changes such as light flickering match the change nodes of current whistling, it is very likely that there is a systematic problem in the circuit rather than a single component failure. Through the matching analysis of various types of parameters, the root cause of the failure of the smart furniture can be judged more accurately, providing more valuable information for precise maintenance, reducing unnecessary troubleshooting work, improving the maintenance efficiency, and at the same time providing more targeted and reliable warnings for users to ensure the stable operation of the smart furniture.

[0012] Optionally, the method further includes the following steps: Based on the non - continuous whistling warning, adjust the working state of the electronic module according to a preset change strategy so that the indication parameter changes to obtain an adjustment parameter; Calculate the third time - domain waveform diagram of the adjustment parameter, and extract a third change node sequence from the third time - domain waveform diagram; Calculate the second time - domain waveform diagram of the latest comprehensive confidence value, and extract the latest second change node sequence from the second time - domain waveform diagram; Calculate the adjustment matching value between the third change node sequence and the second change node sequence; If the adjustment matching value is greater than a preset adjustment reference matching value, non - continuous whistling anomaly prompt is performed.

[0013] By adopting the above - mentioned technical solution, it is possible to further accurately determine whether there is a real anomaly in the smart furniture. Traditional judgment methods may produce misjudgments due to factors such as environmental interference, while this method actively changes the working state of the electronic module and observes the changes of relevant parameters, just like conducting a "stress test". For example, in the light change scenario, if the matching degree between the light change and the change nodes of the comprehensive confidence value is high after adjusting the working state and exceeds the preset reference value, then the reliability of determining the anomaly is greatly improved. It reduces misjudgments and can more accurately locate the root cause of the problem when determining the anomaly, providing a clear direction for maintenance personnel, greatly optimizing the maintenance process of smart furniture, ensuring the long - term stable operation of the equipment, and improving the user experience.

[0014] Optionally, the method further includes the following steps: Calculate the first time - domain waveform diagram of the comprehensive confidence value, and extract a continuous state sequence from the first time - domain waveform diagram; Calculate the ratio of the continuous state duration in the continuous state sequence; If the ratio of the duration of the continuous state is greater than a preset second classification value, an abnormal prompt for continuous whistling sound is given.

[0015] By adopting the above technical solution, the determination dimension of current whistling faults is enriched and refined. In the complex operating environment of smart furniture, different types of current whistling correspond to electronic module faults of different degrees and natures. Continuous whistling often means that there are relatively serious and continuous problems inside the electronic module, such as short circuits or severe aging of key components. By specifically analyzing the continuous whistling state, it can be effectively distinguished from non - continuous whistling situations, making the fault judgment more accurate, improving the user experience. It also helps maintenance personnel quickly lock in the problem, formulate targeted maintenance plans, improve maintenance efficiency, and extend the service life of the equipment.

[0016] Optionally, the method further includes the following steps: When the fluctuation degree value is less than the first classification value, the second classification value is adjusted positively according to the fluctuation degree value; the larger the fluctuation degree value, the larger the second classification value; the smaller the fluctuation degree value, the smaller the second classification value.

[0017] By adopting the above technical solution, in the complex and changeable operating environment of smart furniture, the characteristics of current whistling are different in different scenarios. When the fluctuation degree value is less than the first classification value, it indicates that the current current whistling mode is different from the common non - continuous whistling situation and may be in a relatively mild or special state. At this time, adjusting the second classification value positively according to the fluctuation degree value can flexibly adjust the threshold for judging continuous whistling sounds. This adjustment mechanism improves the adaptability of the system judgment, makes the fault judgment more in line with the actual operating state, enhances the accuracy of smart furniture state analysis, and thus provides users with more reliable equipment state monitoring and early warning services.

[0018] Optionally, the process of establishing the background sound library includes the following steps: Create the background sound library; Collect the background sound when the electronic module is not powered on to obtain the background sound data, and collect the background sound when the electronic module without whistling is powered on to obtain the background sound data; Perform spectrum conversion on the background sound data to obtain background spectrum data; Save the frequency data and energy data corresponding to the background spectrum data to the background sound library.

[0019] By adopting the above technical solutions, a background sound library is created to build an infrastructure for sound data analysis. The background sounds when the electronic module is not powered on and when it is powered on but without whistling are collected, comprehensively covering the ambient sounds in different states of the device to ensure the accuracy of the background sound data. After the spectrum conversion of the background sound data, the frequency and energy data are stored, providing key support for accurately filtering out background noise. This greatly improves the recognition accuracy of current whistling, ensures the reliability of the intelligent furniture status analysis, and helps to timely detect faults in the electronic module.

[0020] Optionally, the optimization process of the background sound library includes the following steps: Collect the whistling sounds when other electronic modules that generate whistling are powered on to obtain whistling data; Perform spectrum conversion on the whistling data to obtain whistling spectrum data; Delete the background spectrum data corresponding to the whistling spectrum data in the background sound library.

[0021] By adopting the above technical solutions, the corresponding background spectrum data in the background sound library is deleted to prevent misjudging the whistling of other electronic modules as background sounds, improving the purity of the background sound library, enabling the intelligent furniture status analysis to more accurately focus on current whistling anomalies, and enhancing the reliability of fault warning.

[0022] In a second aspect, the present application provides an intelligent furniture status analysis system based on the Internet of Things, adopting the following technical solutions: An intelligent furniture status analysis system based on the Internet of Things, including a processor, and the processor executes the steps of the intelligent furniture status analysis method based on the Internet of Things described in any one of the above.

[0023] In a third aspect, the present application provides a storage medium, adopting the following technical solutions: A storage medium, in which a program is stored, and when the program is executed by a processor, it realizes the steps of the intelligent furniture status analysis method based on the Internet of Things described in any one of the above.

[0024] In summary, the present application includes at least one of the following beneficial technical effects: Through comprehensive and detailed sound data collection, spectrum conversion, and multi-dimensional analysis, such as calculating incremental frequency, incremental energy, various confidence values, etc., it is possible to accurately identify current whistling caused by aging and faults of components such as capacitors in the electronic modules of intelligent furniture, distinguish between continuous and non-continuous whistling situations, accurately judge the type and severity of faults, and provide a reliable basis for maintenance.

[0025] In the very early stage of current whistling when it is hardly perceptible to the human ear, status anomaly alerts can be given based on data analysis, greatly improving the user experience of using smart furniture. At the same time, for the warning and alert mechanisms for non - continuous whistling and continuous whistling, users can be informed of the device status in a timely manner and take measures in advance to deal with potential faults.

[0026] The establishment and optimization of the background sound library comprehensively collect background sound data under different states, effectively filter out environmental noise interference, accurately extract current whistling signals, and can flexibly adjust the judgment threshold according to the fluctuation degree value, improving the adaptability and analysis accuracy of the system in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a step diagram of a method for analyzing the status of smart furniture based on the Internet of Things.

[0028] Figure 2 It is a step diagram for judging whether to give a non - continuous whistling warning.

[0029] Figure 3 It is a step diagram for judging whether to give a non - continuous whistling alert. SPECIFIC IMPLEMENTATION MANNER

[0030] The following details the implementation manners of the present application, and examples of the implementation manners are shown in the drawings.

[0031] In the description of this specification, the description with reference to the terms "certain implementation manners", "one implementation manner", "some implementation manners", "illustrative implementation manners", "examples", "specific examples" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the implementation manner or example are included in at least one implementation manner or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same implementation manner or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more implementation manners or examples.

[0032] An embodiment of the present application discloses a method for analyzing the status of smart furniture based on the Internet of Things, referring to Figure 1 , including the following steps: Within a set duration, the first sound data of the electronic module is periodically collected through a microphone sensor. The first sound data is all the sound data in the surrounding environment where the smart device is located. The collected first sound data is transmitted through an Internet of Things communication module. The Internet of Things communication module can be Wi-Fi, Bluetooth, ZigBee, etc. It converts the analog sound signal collected by the microphone sensor into a digital signal and transmits the data to a cloud server or a local data analysis device according to a specific communication protocol. During the transmission process, an encryption algorithm is used to encrypt the data to ensure the security and integrity of the data. At the same time, the data is stored in a large-capacity data storage device, such as a hard disk array or cloud storage, for subsequent spectrum conversion and analysis.

[0033] The fast Fourier transform (FFT) algorithm is used to perform spectrum conversion on the first sound data to obtain the first spectrum data. In practical applications, the collected first sound data is segmented according to a certain time window, and the fast Fourier transform algorithm is applied to each segment of data to calculate the frequency components and corresponding energy distributions of the sound signal within that time period. In this way, the complex sound signal is decomposed into a series of sine waves of different frequencies superimposed, intuitively showing the frequency characteristics of the sound signal, providing a key basis for subsequent filtering and analysis.

[0034] Obtain the background sound library of the environment where the electronic module is located. The background sound library includes background sound data and background spectrum data corresponding to the background sound data.

[0035] According to the background spectrum data, an adaptive filtering algorithm is used to filter the first spectrum data. The algorithm continuously compares the first spectrum data and the background spectrum data, identifies the frequency components belonging to background noise, and removes them from the first spectrum data to obtain the second spectrum data; the second spectrum data is the spectrum data corresponding to the current whistling sound.

[0036] Calculate the incremental frequency of multiple second spectrum data and the incremental energy corresponding to the incremental frequency; the incremental frequency is calculated by the difference between the same frequency components in the second spectrum data at two adjacent time points, reflecting the change of frequency over time. The incremental energy is obtained by calculating the energy difference of the same frequency components at adjacent time points, reflecting the dynamic change of energy. During the calculation process, a sliding window method is used to process the second spectrum data to ensure that the calculation results can timely reflect the real-time operation status of the electronic module.

[0037] Calculate the average value and discrete value of the incremental frequency, and calculate the cumulative value and fluctuation value of the incremental energy. The average value is obtained by summing the incremental frequency data over a period of time and dividing by the number of data points, which reflects the overall level of the incremental frequency. The discrete value is calculated using the standard deviation, which measures the degree of dispersion of the incremental frequency data relative to the average value and reflects the stability of the frequency change. The cumulative value of the incremental energy is the sum of the incremental energy over a period of time, which reflects the overall accumulation of energy. The fluctuation value is obtained by calculating the variance of the incremental energy, which shows the degree of fluctuation of the energy over time. These statistics provide important input parameters for the subsequent calculation of the confidence value.

[0038] Calculate the frequency confidence value based on the average value and discrete value, and calculate the energy confidence value based on the cumulative value and fluctuation value. When calculating the frequency confidence value and energy confidence value, a weighted fusion algorithm is used. This algorithm assigns corresponding weights according to the importance of different parameters, and combines parameters such as the average value, discrete value, cumulative value, and fluctuation value through weighting to obtain the frequency confidence value and energy confidence value. The determination of the weights is optimized through a large amount of experimental data and machine learning algorithms to ensure that the confidence value can accurately reflect the operating state of the electronic module.

[0039] Calculate the comprehensive confidence value based on the frequency confidence value and energy confidence value; similarly, use the weighted fusion method to perform a weighted sum of the frequency confidence value and energy confidence value to obtain a comprehensive index to evaluate the overall operating state of the electronic module.

[0040] If the comprehensive confidence value is greater than the preset reference confidence value, an abnormal state prompt is issued. The reference confidence value is an empirical value obtained through long-term monitoring and data analysis of a large number of smart furniture in normal operating states. In practical applications, the real-time calculated comprehensive confidence value is compared with the reference confidence value. When the comprehensive confidence value exceeds the reference confidence value, the system determines that the electronic module may be in an abnormal state and immediately triggers the abnormal prompt mechanism. The abnormal prompt can be achieved in various ways, such as displaying a warning message on the control panel of the smart furniture, pushing a notification through the mobile phone APP, or sending a text message to the user to remind the user to take timely measures for inspection and maintenance.

[0041] With the help of sound wave and spectrum analysis technology, sound signals can be accurately analyzed. Through spectrum conversion, sound data is transformed into spectrum data, and then the frequency composition is analyzed. By virtue of the unique spectrum characteristics of the current whistling caused by component failures such as capacitors, compared with the normal state, faults can be sensitively identified. This technology collects and continuously analyzes sound data at regular intervals. In the very early stage of current whistling when the human ear can hardly detect it, various confidence values are calculated based on key parameters. Once the comprehensive confidence value exceeds the preset value, an anomaly is immediately prompted. In this way, effective early warning can be achieved, enabling users to handle problems in a timely manner at the initial stage of the fault, reducing noise interference, greatly improving the accuracy and reliability of the intelligent furniture status analysis, and significantly enhancing the user experience.

[0042] Refer to Figure 2 , the method further includes the following steps: Calculate the first time-domain waveform diagram of the comprehensive confidence value, and extract the first change node sequence from the first time-domain waveform diagram; the comprehensive confidence value is a comprehensive evaluation index of the operating state of the electronic module, which integrates information on multiple key parameters such as frequency confidence value and energy confidence value. By presenting the change of the comprehensive confidence value over time in the form of a waveform diagram, its dynamic change trend can be intuitively observed. During the calculation process, the system samples the comprehensive confidence value at regular time intervals according to the collected sound data and various characteristic values calculated previously, and then connects these sampling points to form the first time-domain waveform diagram. A change node refers to a point where the slope of the waveform diagram changes significantly. These points often represent large fluctuations in the comprehensive confidence value, which may be related to changes in the operating state of the electronic module. The system will use specialized algorithms, such as the slope detection algorithm, to analyze the waveform diagram point by point, identify the points where the slope change exceeds a certain threshold, and extract these points as the first change node sequence. This sequence records the significant changes in the comprehensive confidence value at different time points, providing an important data basis for subsequent analysis of the fluctuation degree.

[0043] Calculate the fluctuation degree value in the first change node sequence; the fluctuation degree value is used to measure the severity of the fluctuation of the comprehensive confidence value at these change nodes, which reflects the instability of the operating state of the electronic module. The system will use a variety of statistical methods to calculate the fluctuation degree value, such as calculating the absolute value of the difference in the comprehensive confidence value between adjacent change nodes and performing statistical analysis on these differences to obtain a value that can represent the fluctuation degree.

[0044] If the fluctuation value is greater than the preset first classification value, a non-continuous howling warning is issued. The first classification value is an empirical threshold obtained through experiments and data analysis on a large number of smart furniture in normal and faulty operation states. It serves as an important basis for judging whether there is non-continuous howling. When the fluctuation value exceeds this threshold, it means that the fluctuation of the comprehensive confidence value is more drastic, and non-continuous howling may exist.

[0045] For smart furniture, non-continuous howling is of great significance. It may indicate that the component failure is in the initial unstable stage, such as a slight leakage of the capacitor causing abnormal current fluctuations, causing non-continuous howling; it may also be caused by intermittent interference to the electronic module, such as nearby electromagnetic interference and instantaneous fluctuations in power supply voltage. Timely non-continuous howling warnings can allow users and maintenance personnel to pay attention to equipment operation in advance. Users can pay attention to subtle abnormalities in furniture, such as flickering lights and temporary functional failures; maintenance personnel can prepare detection equipment and maintenance tools based on this, and conduct a comprehensive inspection and diagnosis of electronic modules. Taking targeted measures in advance can reduce the degree of deterioration of the problem and avoid the escalation of faults that make the furniture unusable. This early warning mechanism improves the accuracy and comprehensiveness of operating status monitoring, which can not only detect obvious faults, but also capture potential initial problems, providing more reliable protection for the stable operation of smart furniture.

[0046] Reference Figure 3 , the method further comprises the following steps: Based on the non-continuous howling warning, the frequency confidence value is calculated and the indication parameters of the electronic module are obtained. Once the system triggers the non-continuous howling warning, a new round of in-depth analysis process will be started. On the one hand, the system will recalculate the frequency confidence value. As a key indicator reflecting the stability of the frequency characteristics of the current howling of the electronic module, the accurate calculation of the frequency confidence value at this stage will help to further analyze the details of the changes in the frequency dimension of the current howling. By re-sorting the previously collected sound data, using a more sophisticated spectrum analysis algorithm and combining the current warning situation, the system can derive a more accurate frequency confidence value, providing solid data support for subsequent comprehensive judgments. At the same time, the system will fully obtain the indication parameters of the electronic module. The indication parameters cover the working status information of the electronic module in many aspects, such as the motor speed controlled by the electronic module, the values ​​fed back by various sensors, and the working status parameters of devices such as lights and display screens in smart furniture. These indication parameters reflect the real-time operating status of the electronic module from different angles. Taking the smart lighting system as an example, the brightness adjustment value, flickering frequency, and color temperature changes of the light all belong to the category of indication parameters, and the changes in these parameters may be closely related to the operating status of the electronic module.

[0047] Calculate the second time-domain waveform diagram of the indication parameter, and extract the second change node sequence from the second time-domain waveform diagram. Similar to the first time-domain waveform diagram of the comprehensive confidence value, the second time-domain waveform diagram uses time as the horizontal axis and visually presents the change of the indication parameter over time. By continuously sampling the indication parameter and plotting it in the coordinate system in chronological order, a curve that can reflect its dynamic change is formed. By detecting the mutation points of features such as slope or curvature in the waveform, these mutation points are extracted as change nodes to form the second change node sequence. These change nodes represent the significant change moments of the indication parameter on the time axis, which may correspond to the state transition inside the electronic module or the interference effect of external environmental factors.

[0048] Calculate the node matching value between the first change node sequence and the second change node sequence; the calculation of the node matching value aims to measure the synchronization degree and similarity between the change nodes of the comprehensive confidence value related to current whistling and the change nodes of the indication parameter of the electronic module. The system will adopt various matching algorithms, such as the dynamic time warping algorithm (DTW). This algorithm can find the most similar corresponding relationship between the two sequences considering the difference in the length of the time series and calculate a quantified matching value. For example, if the time point representing the mutation of the current whistling frequency in the first change node sequence is relatively close to the time point of the sudden change in the light brightness in the second change node sequence on the time axis and the change trends have a certain similarity, then the node matching value will be relatively high.

[0049] If the node matching value is greater than the preset first reference matching value, a non-continuous whistling warning is given. The first reference matching value is a threshold determined through a large amount of experimental data and actual case analysis, combined with the node matching situations in the normal operation and fault states of the smart furniture. When the node matching value exceeds this threshold, it indicates that there is a strong correlation between the current whistling characteristics and the other working state parameters of the electronic module, and there is likely a deep-seated systematic problem.

[0050] Associating the current whistling characteristics with other operating state parameters of the electronic module for correlation analysis has great practical value. Taking the change of lighting as an example, if the flashing of the light matches the change node of the current whistling, it is very likely to be a systematic circuit problem. For example, the voltage of the power supply line is unstable, which causes the electronic module to control the lighting abnormally and trigger the current whistling. This cross-parameter analysis breaks through the limitation of judging faults by a single parameter and can consider the operating state of the electronic module from multiple dimensions. In this way, the root cause of the failure of the smart furniture can be judged more accurately. Different from the traditional troubleshooting of each component one by one, it can quickly lock the problem area and provide a precise repair direction for the maintenance personnel. For example, when receiving a non-continuous whistling warning, if the lighting indication parameter is strongly correlated with the current whistling, the maintenance personnel can give priority to checking the lighting control circuit and the power supply system, reducing unnecessary troubleshooting and greatly improving the maintenance efficiency. In addition, it can also provide more targeted and reliable warnings for users. When users receive a warning, they can understand which parameters are abnormal and their correlation with the current whistling, better understand the nature of the fault, and then take temporary measures during the waiting for repair to avoid the deterioration of the fault. This comprehensively ensures the stable operation of the smart furniture and improves the use safety and user experience.

[0051] The method further includes the following steps: Based on the non-continuous whistling warning, adjust the working state of the electronic module according to a preset change strategy so that the indication parameter changes to obtain an adjustment parameter. The preset change strategy is formulated through a large number of experiments and data analyses, considering different usage scenarios of the smart furniture and possible fault situations. For example, for a smart lighting system, if a non-continuous whistling warning occurs, the system may gradually reduce the brightness of the light or change the flashing frequency of the light according to the preset strategy to observe the reaction of the electronic module in different working states. By adjusting the working state of the electronic module, the indication parameter will change accordingly, thereby obtaining the adjustment parameter. The indication parameter reflects various state information of the electronic module during normal operation, such as voltage, current, power, etc., while the adjustment parameter is the new value of these parameters after changing the working state. Taking a smart air conditioner as an example, when the system issues a non-continuous whistling warning, adjust the rotation speed of the air conditioner compressor. At this time, the indication parameters such as the current and cooling capacity of the air conditioner will change, and these changed values are the adjustment parameters.

[0052] Calculate the third time-domain waveform diagram of the adjustment parameter, and extract the third change node sequence from the third time-domain waveform diagram. The time-domain waveform diagram can intuitively display the change of the adjustment parameter over time. It uses time as the horizontal axis and the value of the adjustment parameter as the vertical axis, presenting the dynamic change of the parameter during the adjustment process in the form of a graph. The system will continuously sample the adjustment parameter, record the parameter values at a certain time interval, and connect these values into a curve to form the third time-domain waveform diagram.

[0053] Calculate the second time-domain waveform diagram of the latest comprehensive confidence value, and extract the latest second change node sequence from the second time-domain waveform diagram. Extract the third change node sequence from the third time-domain waveform diagram. The change node is the point where the slope in the waveform diagram changes significantly. These points represent the sudden changes of the adjustment parameters over time and may be related to internal faults or external interferences of the electronic module. The system will use a special algorithm, such as the differential algorithm, to analyze the waveform diagram point by point, find the points where the slope change exceeds a certain threshold, and extract these points as the third change node to form a sequence. At the same time, the system will calculate the second time-domain waveform diagram of the latest comprehensive confidence value. The comprehensive confidence value is a comprehensive evaluation index of the overall operating state of the electronic module, which combines multiple key parameters such as frequency confidence value and energy confidence value. By calculating the change of the latest comprehensive confidence value over time, the second time-domain waveform diagram is obtained. Then, extract the latest second change node sequence from the second time-domain waveform diagram, and the method is similar to that of extracting the third change node sequence.

[0054] Calculate the adjustment matching value between the third change node sequence and the second change node sequence. The adjustment matching value is used to measure the correlation and synchronization degree between the change of the adjustment parameter and the change of the comprehensive confidence value. The system will adopt a correlation analysis algorithm, such as the Pearson correlation coefficient calculation method, to compare the two sequences and obtain a quantified matching value. The higher this matching value, the more synchronous the change of the adjustment parameter and the change of the comprehensive confidence value are, which may mean a more serious abnormal situation.

[0055] If the adjustment matching value is greater than the preset adjustment reference matching value, a non-continuous whistling abnormal prompt will be given. The adjustment reference matching value is a threshold determined through a large number of experiments and actual cases, and it is an important basis for judging whether there is a real abnormality. When the adjustment matching value exceeds this threshold, it indicates that after adjusting the working state of the electronic module, the change of the adjustment parameter is highly correlated with the change of the comprehensive confidence value, and it is very likely that there is a real abnormal situation in the smart furniture. This method can accurately determine whether there is a real abnormality in the smart furniture. Traditional judgments rely on single time points or fixed-condition data and are easily misjudged by environmental interferences. This method actively changes the working state of the electronic module, similar to doing a "stress test" on the furniture, allowing hidden problems to be exposed. For example, in a lighting scenario, after detecting a non-continuous whistling warning, adjust the lighting brightness or flashing frequency. If the matching degree between the lighting change and the change node of the comprehensive confidence value exceeds the preset value, the abnormality can be more determined. The multi-parameter matching judgment greatly improves the reliability of the abnormality determination. Moreover, it not only reduces misjudgments, but also can accurately locate the root cause of the problem when determining the abnormality. When the maintenance personnel receive the abnormal prompt and based on the changes of the adjustment parameter and the comprehensive confidence value, they can quickly narrow down the troubleshooting scope. For example, if the current and the comprehensive confidence value are abnormal after adjusting the lighting brightness, they can focus on checking the lighting power supply and control circuit, greatly optimizing the maintenance process, reducing the maintenance time and cost, ensuring the long-term stable operation of the equipment, reducing the inconvenience of users, and improving the experience and satisfaction.

[0056] The method further includes the following steps: Calculate the first time-domain waveform diagram of the comprehensive confidence value, and extract the continuous state sequence from the first time-domain waveform diagram. The comprehensive confidence value is obtained by fusing key information in multiple aspects such as frequency confidence value and energy confidence value, and it is a comprehensive index that can comprehensively reflect the operating state of the electronic module. When calculating the first time-domain waveform diagram, the system samples the comprehensive confidence value at a certain time interval, and connects these sampling points in chronological order to form a curve that intuitively shows the change of the comprehensive confidence value over time, which can clearly present its state fluctuations at different moments. The continuous state refers to the state where the comprehensive confidence value remains relatively stable within a period of time, and it may correspond to the electronic module being in normal operation, abnormal whistling, or other specific working states. The system will use advanced signal processing algorithms to analyze the waveform diagram segment by segment. By detecting features such as the slope and amplitude change of the waveform, identify those time periods where the change amplitude of the comprehensive confidence value is less than a certain threshold, define these time periods as continuous states, and extract them to form a continuous state sequence. For example, when the electronic module of the smart furniture has continuous whistling, the comprehensive confidence value may remain at a relatively high and stable level for a long time, and the system will extract this period as a continuous state.

[0057] Calculate the ratio of the duration of the continuous state in the continuous state sequence; this ratio refers to the proportion of the total duration of all continuous states in the entire analysis time period. The calculation process is relatively intuitive. The system accumulates the duration of each continuous state in the continuous state sequence to obtain the total duration of the continuous state, and then divides it by the duration of the entire analysis time period to obtain the ratio of the duration of the continuous state. This ratio can quantify the importance of the continuous state in the entire operation process and provide a clear quantitative index for subsequent fault judgment.

[0058] If the ratio of the duration of the continuous state is greater than the preset second classification value, an abnormal prompt for continuous whistling sound will be given. The second classification value is an empirical threshold obtained by analyzing and statistically processing a large amount of experimental data of smart furniture in normal operation and fault states. It is the key boundary for distinguishing normal operation and continuous whistling faults. When the ratio of the duration of the continuous state exceeds this threshold, it indicates that the electronic module has been in an abnormal state for a long time, and there is likely a problem with continuous whistling. The system will give an abnormal prompt for continuous whistling in various ways, such as displaying a prominent warning message on the control panel of the smart furniture, pushing a notification to the user through the mobile phone APP, and even triggering the voice prompt function to timely inform the user that there are potential serious problems with the smart furniture.

[0059] This analysis method has significant advantages in the complex operating environment of smart furniture. Different current howling corresponds to different electronic module faults. Continuous howling is mostly caused by serious and continuous hardware problems inside the electronic module, such as short circuit and severe aging of key components. If not handled in time, it is easy to cause complete damage to the module and affect the normal use of the furniture. This method can specifically analyze the state of continuous howling and effectively distinguish between continuous and non-continuous howling. Traditional methods are difficult to distinguish accurately and are prone to misjudgment and omission. This method deeply analyzes the continuous state of the comprehensive confidence value, accurately identifies the characteristics of continuous howling from the time dimension, and improves the accuracy of fault judgment. For users, timely abnormal prompts of continuous howling can improve the experience, allowing users to contact maintenance in time to avoid long-term noise interference. For maintenance personnel, after receiving the prompt, they can quickly lock the key points of investigation, focus on key components, formulate targeted maintenance plans, reduce troubleshooting time, improve maintenance efficiency, repair faults in time, extend equipment life, and ensure the long-term stable operation of smart furniture.

[0060] The method further comprises the steps of: When the fluctuation degree value is less than the first classification value, it indicates that the current howling pattern generated by the current smart furniture electronic module is significantly different from the common non-continuous howling situation. Common non-continuous howling is often accompanied by large fluctuations, and the small fluctuation degree at this time may mean that the electronic module is in a relatively mild or special state. For example, it may be that a component in the electronic module begins to show a slight performance degradation, but has not yet reached the level of causing violent fluctuations; or it may be affected by some intermittent and relatively weak interference factors.

[0061] The second classification value is adjusted according to the positive correlation of the fluctuation degree value; the larger the fluctuation degree value, the larger the second classification value; the smaller the fluctuation degree value, the smaller the second classification value. The first classification value is an important threshold for distinguishing different current howling modes, and the second classification value is an important reference threshold for judging whether a continuous howling sound occurs.

[0062] Suppose there is an intelligent desk lamp, and its electronic module controls the brightness and color temperature adjustment of the light. During normal use, the light is stable, and the degree of current whistling fluctuation value remains at a low level. For example, in a quiet study environment, when the user uses the desk lamp to read for a long time, the degree of current whistling fluctuation value monitored at this time is calculated to be 5 (assumed unit value). Since this value is less than the first classification value of 10, the system starts the adjustment mechanism. Due to the small degree of fluctuation, the second classification value is adjusted downward from the initial 30 (assumed unit value) to 25. This means that even if the duration ratio of the continuous current whistling state of the desk lamp does not reach the initially set 30, as long as it exceeds 25, the system will determine that there may be a continuous whistling anomaly and then issue a prompt. If one day, the power adapter of the desk lamp shows slight aging, resulting in a certain fluctuation in the current, and the degree of fluctuation value rises to 8. At this time, the system, according to the positive correlation adjustment mechanism, adjusts the second classification value upward from 25 to 28. This enables the system to dynamically adjust the standard basis according to the current fluctuation situation when judging whether there is a continuous whistling problem with the desk lamp, avoiding misjudgment or missed judgment due to a fixed threshold.

[0063] In the complex operating environment of smart furniture, different scenarios and external conditions will make the current whistling characteristics vary significantly. Environments such as high temperature or strong electromagnetic interference will change the current whistling frequency and the degree of fluctuation. This system can adjust the second classification value according to the degree of fluctuation value and automatically adapt to the changes. When the fluctuation is small, it reduces this value to sensitively capture potential continuous whistling; when the fluctuation is large, it increases this value to prevent normal fluctuations from being misjudged. The traditional fixed-threshold fault judgment method is difficult to adapt to complex situations and is prone to misjudgment and missed judgment. However, this adjustment mechanism can combine the real-time degree of fluctuation value to dynamically adjust the judgment standard, making the fault judgment more in line with the actual operating state. For example, when the fluctuation is small but the duration ratio of the continuous state is high, the traditional threshold cannot determine the anomaly, and the adjustment mechanism reduces the second classification value to accurately identify and prompt in a timely manner. This adjustment mechanism significantly enhances the accuracy of the smart furniture state analysis, provides reliable monitoring and early warning for users, helps them respond to faults in a timely manner; and also helps maintenance personnel quickly locate problems, formulate efficient maintenance plans, and extend the service life of smart furniture.

[0064] The process of establishing the background sound library includes the following steps: Create a background sound library; the database structure can efficiently store and manage a large amount of sound data, including background sound data, background spectrum data, and corresponding frequency data and energy data, etc. At the same time, considering the scalability and compatibility of the data, so as to facilitate the addition of new data types and analysis functions in the future.

[0065] Collect the background sound data when the acquisition electronic module is powered off, and collect the background sound data when the electronic module without whistling is powered on. When the electronic module is powered off, there are still various sounds in the environment, such as the running sounds of surrounding electrical equipment, environmental noise, etc. These sounds constitute the basic noise background of the environment where the smart furniture is located. In order to collect accurate background sound data when powered off, it is necessary to select a suitable sound collection device, such as a high-sensitivity microphone. Place the microphone near the smart furniture to ensure that it can clearly capture the surrounding sound signals. The collection process needs to last for a period of time to obtain enough sample data. When the electronic module is powered on but without whistling, it will generate some normal operating sounds by itself, and at the same time, it will also be affected by the surrounding environment. These sounds contain the sound characteristics of the electronic module during normal operation and the superposition of environmental noise.

[0066] Use the Fast Fourier Transform (FFT) algorithm to perform spectrum conversion on the background sound data to obtain background spectrum data. When performing spectrum conversion, first, it is necessary to preprocess the collected background sound data, including operations such as noise removal and filtering, to improve the quality of the data. Then, segment the preprocessed sound data according to a certain time window, apply the FFT algorithm to each segment of data, and calculate the frequency components and corresponding energy distributions of the sound signals within that time period. The finally obtained background spectrum data, with the corresponding data of frequency and energy, clearly shows the energy distribution of the background sound at different frequencies.

[0067] Save the frequency data and energy data corresponding to the background spectrum data to the background sound library. Store the frequency data and energy data in the database in the form of a table. Each row represents a frequency point, including the frequency value of that frequency point and the corresponding energy value. At the same time, add information such as timestamps and environmental parameters to each data record to facilitate data screening and comparison in subsequent analysis.

[0068] The background sound library established through a series of steps strongly supports the state analysis of smart furniture. It can greatly improve the recognition accuracy of current whistling. By comparing the sound data of the collected electronic module with the spectrum data in the library, it can accurately identify and filter out the frequency components of background noise, highlight the current whistling signal, avoid interference, and make the recognition more accurate and reliable. The background sound library also ensures the reliability of state analysis. It accurately filters background noise, enables the system to focus on the actual operating state of the electronic module, and promptly detect potential faults. For example, when there is a current whistling in the electronic module, the system can quickly determine whether the whistling is abnormal based on the background spectrum data, give an early warning in time, and help users and maintenance personnel take measures to prevent the deterioration of the fault and ensure the stable operation of the smart furniture. The optimization process of the background sound library includes the following steps: Collect the whistling sound data when other electronic modules that produce whistling are powered on; widely collect the whistling sound data when other electronic modules that produce whistling are powered on through a microphone, so as to obtain comprehensive whistling sound data. In actual operation, it is necessary to collect for a variety of intelligent furniture electronic modules of different types, brands, and service life. These electronic modules cover various common components such as the drive module in the intelligent lighting system, the compressor control module of the intelligent air conditioner, and the power amplifier module of the intelligent speaker.

[0069] Use the Fast Fourier Transform (FFT) algorithm to perform spectral conversion on the whistling sound data to obtain whistling sound spectrum data, decompose the complex time-domain whistling signal into a series of sine waves with different frequency components superimposed, and clearly present the energy distribution of the whistling sound at each frequency.

[0070] Carefully compare the whistling sound spectrum data obtained through spectral conversion with the background spectrum data stored in the background sound library, and delete the background spectrum data corresponding to the whistling sound spectrum data in the background sound library.

[0071] In the operating environment of intelligent furniture, if there is data in the background sound library that is similar to the whistling sound spectrum of other electronic modules, it is easy to misjudge the abnormal current whistling as normal background sound during state analysis, seriously affecting the accuracy. Deleting such interfering data can significantly improve the purity of the background sound library. During subsequent analysis, the system can focus more on and precisely focus on the abnormal current whistling, effectively avoiding misjudgment caused by background noise interference, and greatly enhancing the reliability of fault warning. This strongly supports the timely discovery of potential faults, ensures the stable operation of furniture, and improves the overall performance and practicality of the state analysis system.

[0072] The embodiment of the present application also discloses an intelligent furniture state analysis system based on the Internet of Things, including a processor, and the processor executes the steps of the intelligent furniture state analysis method based on the Internet of Things as described in any one of the above.

[0073] The embodiment of the present application also discloses a storage medium, in which a program is stored, and when the program is executed by the processor, the steps of the intelligent furniture state analysis method based on the Internet of Things as described in any one of the above are realized.

[0074] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. An intelligent furniture status analysis method based on the Internet of Things, characterized in that, It includes the following steps: During a set time period, regularly collect the first sound data of the electronic module; Perform spectrum conversion on the first sound data to obtain first spectrum data; Obtain the background sound library of the environment where the electronic module is located, and the background sound library includes background sound data and background spectrum data corresponding to the background sound data; Filter the first spectrum data according to the background spectrum data to obtain second spectrum data; Calculate the incremental frequency of multiple pieces of the second spectrum data and the incremental energy corresponding to the incremental frequency; Calculate the average value and discrete value of the incremental frequency, and calculate the cumulative value and fluctuation value of the incremental energy; Calculate the frequency confidence value according to the average value and the discrete value, and calculate the energy confidence value according to the cumulative value and the fluctuation value; Calculate the comprehensive confidence value according to the frequency confidence value and the energy confidence value; If the comprehensive confidence value is greater than a preset reference confidence value, perform a status anomaly prompt.

2. The method for analyzing the state of intelligent furniture based on the Internet of Things according to claim 1, wherein The method further includes the following steps: Calculate the first time-domain waveform diagram of the comprehensive confidence value, and extract the first change node sequence from the first time-domain waveform diagram; Calculate the fluctuation degree value in the first change node sequence; If the fluctuation degree value is greater than a preset first classification value, perform a non-continuous whistling warning.

3. The method for analyzing the status of intelligent furniture based on the Internet of Things according to claim 2, wherein The method further includes the following steps: Based on the non-continuous whistling warning, while calculating the frequency confidence value, obtain the indication parameter of the electronic module; Calculate the second time-domain waveform diagram of the indication parameter, and extract the second change node sequence from the second time-domain waveform diagram; Calculate the node matching value between the first change node sequence and the second change node sequence; If the node matching value is greater than a preset first reference matching value, perform a non-continuous whistling warning.

4. The method for analyzing the state of intelligent furniture based on the Internet of Things according to claim 3, wherein, The method further includes the following steps: Based on the non-continuous whistling warning, adjust the working state of the electronic module according to a preset change strategy so that the indication parameter changes to obtain an adjustment parameter; Calculate the third time-domain waveform diagram of the adjustment parameter, and extract the third change node sequence from the third time-domain waveform diagram; Calculate the second time-domain waveform diagram of the latest comprehensive confidence value, and extract the latest second change node sequence from the second time-domain waveform diagram; Calculate the adjustment matching value between the third change node sequence and the second change node sequence; If the adjustment matching value is greater than a preset adjustment reference matching value, perform a non-continuous whistling anomaly prompt.

5. The method for analyzing the status of intelligent furniture based on the Internet of Things according to claim 3, wherein The method further includes the following steps: Calculate the first time-domain waveform diagram of the comprehensive confidence value, and extract the continuous state sequence from the first time-domain waveform diagram; Calculate the ratio of the continuous state duration in the continuous state sequence; If the ratio of the continuous state duration is greater than a preset second classification value, perform a continuous whistling sound anomaly prompt.

6. The method for analyzing the state of intelligent furniture based on the Internet of Things according to claim 5, wherein The method further includes the following steps: When the fluctuation degree value is less than the first classification value, adjust the second classification value in positive correlation with the fluctuation degree value; the greater the fluctuation degree value, the greater the second classification value; The smaller the fluctuation degree value, the smaller the second classification value.

7. The method for analyzing the state of intelligent furniture based on the Internet of Things according to claim 1, characterized in that The establishment process of the background sound library includes the following steps: Create the background sound library; Collect the background sound data by collecting the background sound when the electronic module is not powered on, and collect the background sound data by collecting the background sound when the electronic module without whistling is powered on; Perform spectral conversion on the background sound data to obtain background spectral data; Save the frequency data and energy data corresponding to the background spectral data to the background sound library.

8. The method for analyzing the state of intelligent furniture based on the Internet of Things according to claim 1, wherein The optimization process of the background sound library includes the following steps: Collect the whistling sound data by collecting the whistling sound when other electronic modules that whistle are powered on; Perform spectral conversion on the whistling sound data to obtain whistling spectral data; Delete the background spectral data corresponding to the whistling spectral data in the background sound library.

9. An intelligent furniture status analysis system based on the Internet of Things, characterized in that, It includes a processor, and the steps of the method for analyzing the status of intelligent furniture based on the Internet of Things according to any one of claims 1-8 are executed in the processor.

10. A storage medium, characterized in that, A program is stored in the medium, and when the program is executed by the processor, the steps of the method for analyzing the status of intelligent furniture based on the Internet of Things according to any one of claims 1-8 are implemented.

Images