Fault data analysis method and device for smoke alarm and smoke alarm

Abstract

The present invention provides a method and device for analyzing fault data of a smoke alarm, as well as a smoke alarm, comprising: obtaining the original data collected by the smoke alarm, extracting multi-dimensional features of the original data; inputting the multi-dimensional features into a pre-trained deep neural network, and processing them to obtain multi-dimensional restored features; wherein the deep neural network encodes and compresses the multi-dimensional features through an autoencoder architecture, and then decodes and restores them to obtain multi-dimensional restored features; calculating the difference between the multi-dimensional restored features and the standard features to obtain a difference result; and obtaining the fault data in the original data collected by the smoke alarm based on the difference result. In the present invention, the collected data is deeply analyzed by comprehensively considering multiple factors, and the fault data is accurately identified, thereby improving the reliability of the smoke alarm and the efficiency of troubleshooting, thereby ensuring the stable operation of the fire safety monitoring system.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and device for analyzing fault data of a smoke alarm, and a smoke alarm. Background Art

[0002] During the long-term operation of smoke alarms, due to the influence of various factors, failures may occur, resulting in false alarms or missed alarms, which seriously affect their reliability and effectiveness.

[0003] On the one hand, smoke alarms operate in complex and ever-changing environments. Environmental factors such as temperature, humidity, dust, and electromagnetic interference can interfere with sensor performance, leading to deviations in collected data. On the other hand, over time, issues such as aging and damage to electronic components within smoke alarms can gradually surface, which can also be reflected in anomalies in collected data.

[0004] Traditional smoke alarm fault detection methods are often relatively simple and limited, usually based on a single threshold judgment. This simple threshold judgment method has difficulty distinguishing between real fire danger signals and erroneous data caused by the alarm itself. It is easy to cause misjudgment. In actual applications, it may cause unnecessary panic or fail to provide timely warning when a fire occurs.

[0005] That is, the current smoke alarms are unable to identify fault data caused by their own faults. Summary of the Invention

[0006] The main purpose of the present invention is to provide a method and device for analyzing fault data of a smoke alarm, and a smoke alarm, in order to overcome the defect that the current smoke alarm cannot identify fault data.

[0007] To achieve the above object, the present invention provides a method for analyzing fault data of a smoke alarm, comprising the following steps:

[0008] Obtaining raw data collected by the smoke alarm and extracting multi-dimensional features of the raw data;

[0009] Inputting the multi-dimensional features into a pre-trained deep neural network to process and obtain multi-dimensional restored features; wherein the deep neural network encodes and compresses the multi-dimensional features through an autoencoder architecture, and then decodes and restores the multi-dimensional restored features;

[0010] Calculating the difference between the multi-dimensional restored features and the standard features to obtain a difference result;

[0011] According to the difference result, the fault data in the original data collected by the smoke alarm is obtained.

[0012] Furthermore, the raw data includes smoke concentration data, data acquisition timestamp data, temperature and humidity data, and sensor status data.

[0013] Furthermore, the multi-dimensional features are input into a pre-trained deep neural network to obtain multi-dimensional restored features, including:

[0014] The multi-dimensional features are input into the encoding layer of the autoencoder architecture. The encoding layer adopts a multi-layer fully connected neural network structure with the number of neurons in each layer decreasing in sequence. The features are transformed by a nonlinear activation function, and the high-dimensional multi-dimensional features are mapped to a low-dimensional encoding space to obtain encoded data;

[0015] The encoded data is input into the decoding layer of the autoencoder architecture. The decoding layer adopts a multi-layer fully connected neural network structure. The number of neurons in each layer increases successively and is symmetrical with the structure of the encoding layer. The encoded data is transformed by a nonlinear activation function opposite to that of the encoding layer, and the low-dimensional encoded data is restored to high-dimensional multi-dimensional restored features.

[0016] Furthermore, the difference between the multi-dimensional restored features and the standard features is calculated to obtain a difference result, including:

[0017] Performing principal component analysis on the multidimensional restored features and the standard features respectively, extracting their respective principal component eigenvectors, and obtaining a principal component matrix of the multidimensional restored features and a principal component matrix of the standard features;

[0018] The cosine similarity between the multi-dimensional restored feature principal component matrix and the standard feature principal component matrix is calculated to obtain a similarity value sequence of each dimension as the difference result.

[0019] Furthermore, extracting multi-dimensional features of the original data includes:

[0020] Based on wavelet packet decomposition, the original data is decomposed into multi-layer wavelet packet subspaces, and the energy entropy of the signal in each subspace is calculated as the energy entropy feature, and the correlation coefficient between the signal in each subspace and the original data is calculated as the correlation coefficient feature;

[0021] Performing nonlinear dimensionality reduction on the original data based on a local linear embedding algorithm, calculating the distance features between data points in the low-dimensional space after dimensionality reduction, and combining the Euclidean distance features of the original data in the high-dimensional space to obtain a distance feature combination;

[0022] Using the original data as an observation sequence, based on a hidden Markov model, the hidden state transition probability matrix characteristics and the observation probability distribution characteristics under each hidden state are obtained;

[0023] The energy entropy feature, correlation coefficient feature, distance feature combination, hidden state transition probability matrix feature and observation probability distribution feature are used as multi-dimensional features of the original data.

[0024] Furthermore, after obtaining the fault data in the original data collected by the smoke alarm according to the difference result, the method further includes:

[0025] Based on the fault data, obtaining a faulty component of the smoke alarm;

[0026] Obtaining characteristic information of a supplier of the faulty component;

[0027] Obtaining product information of the faulty component and manufacturer information of the smoke alarm;

[0028] Generate an after-sales authorization code based on the feature information, product information, and manufacturer information;

[0029] After-sales maintenance information is sent to the supplier; the after-sales maintenance information carries the after-sales authority code, which is used by the supplier to authenticate the authority of the after-sales maintenance information.

[0030] Furthermore, based on the feature information, product information and manufacturer information, an after-sales authorization code is generated, including:

[0031] Converting the characteristic information, product information, and manufacturer information into preset matrix forms respectively; wherein the characteristic information is constructed into a multidimensional sparse matrix, the product information is constructed into a triangular matrix, and the manufacturer information is constructed into a symmetric matrix;

[0032] Performing a matrix multiplication operation on the transformed matrix to obtain a composite matrix, and calculating the eigenvalues and eigenvectors of the composite matrix;

[0033] With the eigenvalue as the horizontal coordinate and the modulus of the eigenvector as the vertical coordinate, a plurality of plane coordinate points are constructed, and each plane coordinate point is connected to form a continuous smooth curve;

[0034] Performing Fourier series expansion on the curve, and arranging the coefficients of the preset items in order into a digital sequence;

[0035] The after-sales authorization code is generated based on the digital sequence.

[0036] The present invention also provides a smoke alarm fault data analysis device, comprising:

[0037] An acquisition unit, configured to acquire raw data collected by the smoke alarm and extract multi-dimensional features of the raw data;

[0038] A processing unit is configured to input the multi-dimensional features into a pre-trained deep neural network to obtain multi-dimensional restored features; wherein the deep neural network encodes and compresses the multi-dimensional features through an autoencoder architecture, and then decodes and restores the multi-dimensional restored features;

[0039] a calculation unit, configured to calculate the difference between the multi-dimensional restored features and the standard features to obtain a difference result;

[0040] The analyzing unit is used to obtain the fault data in the original data collected by the smoke alarm according to the difference result.

[0041] The present invention also provides a smoke alarm, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0042] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0043] The present invention provides a method and device for analyzing fault data of a smoke alarm, as well as a smoke alarm, comprising: obtaining the raw data collected by the smoke alarm, extracting multi-dimensional features of the raw data; inputting the multi-dimensional features into a pre-trained deep neural network, and processing them to obtain multi-dimensional restored features; wherein the deep neural network encodes and compresses the multi-dimensional features through an autoencoder architecture, and then decodes and restores them to obtain multi-dimensional restored features; calculating the difference between the multi-dimensional restored features and the standard features to obtain a difference result; and obtaining the fault data in the raw data collected by the smoke alarm based on the difference result. In the present invention, the collected data is deeply analyzed by comprehensively considering multiple factors, and the fault data is accurately identified, thereby improving the reliability of the smoke alarm and the efficiency of troubleshooting, thereby ensuring the stable operation of the fire safety monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a schematic diagram of the steps of a method for analyzing fault data of a smoke alarm according to one embodiment of the present invention;

[0045] Figure 2 This is a structural block diagram of a fault data analysis device for a smoke alarm according to an embodiment of the present invention;

[0046] Figure 3 It is a schematic block diagram of the structure of a smoke alarm according to an embodiment of the present invention.

[0047] The implementation, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0049] Reference Figure 1 In one embodiment of the present invention, a method for analyzing fault data of a smoke alarm is provided, comprising the following steps:

[0050] Step S1, obtaining raw data collected by the smoke alarm and extracting multi-dimensional features of the raw data;

[0051] Step S2: inputting the multi-dimensional features into a pre-trained deep neural network to process and obtain multi-dimensional restored features; wherein the deep neural network encodes and compresses the multi-dimensional features through an autoencoder architecture, and then decodes and restores the multi-dimensional restored features;

[0052] Step S3, calculating the difference between the multi-dimensional restored features and the standard features to obtain a difference result;

[0053] Step S4: obtaining fault data from the original data collected by the smoke alarm according to the difference result.

[0054] In this embodiment, as described in step S1 above, the smoke alarm continuously collects relevant raw data during operation. This raw data serves as the basis for subsequent analysis. For example, the raw data may include a numerical sequence of smoke concentration changes over time, ambient temperature and humidity data, and the sensor's own operating state parameters (such as voltage and current).

[0055] The purpose of extracting multi-dimensional features is to more comprehensively characterize the characteristics of the original data. In one embodiment, for smoke concentration data, the features that can be extracted include the concentration change rate (such as the increase or decrease in smoke concentration per unit time), the fluctuation frequency of concentration data (reflecting the stability of smoke concentration or the frequency of change), the concentration mean and variance in different time periods and other statistical features. For environmental data, extreme values, mean values, and change trends of temperature and humidity can also be used as features. The extraction of the above multi-dimensional features helps to examine the data collected by smoke alarms from multiple angles, so as to more accurately discover potential fault information.

[0056] As described in step S2 above, the pre-trained deep neural network autoencoder has a unique architecture and functionality. The autoencoder consists of an encoding layer and a decoding layer. During the encoding process, high-dimensional, multi-dimensional feature data is input into the encoding layer. The encoding layer, through multiple layers of neurons and a specific activation function, gradually maps the data into a low-dimensional encoding space, achieving data compression. This process extracts key information or underlying patterns from the data while removing some redundant information.

[0057] The resulting low-dimensional encoded data is then fed into the decoding layer. The decoding layer's structure mirrors that of the encoding layer, but in reverse order. Through a series of transformations, the low-dimensional encoded data is gradually restored back to a high-dimensional data space, yielding multi-dimensional restored features. Through this encoding, compression, and decoding-restoration process, the neural network learns the inherent structure and feature representation of the data. Ideally, the restored multi-dimensional features should be highly similar to the original multi-dimensional features. Significant differences between the two indicate anomalies or fault-related information in the original data.

[0058] As described in step S3 above, the standard features are determined based on a multi-dimensional feature statistical model of the data collected by the smoke alarm under normal working conditions. The above standard features can be obtained by analyzing and summarizing a large amount of normal operating data, such as the reasonable range of the smoke concentration change rate under normal circumstances, the normal correlation pattern between environmental data and smoke concentration data, and other standard values or standard ranges of multi-dimensional features. When calculating the difference between the multi-dimensional restored features and the standard features, the difference measure can be calculated for each dimension separately, such as the absolute value of the difference, the relative proportion difference, etc. The overall degree of difference can also be calculated by using a specific algorithm or model based on the differences in multiple dimensions. For example, different weights are assigned to different important dimensions by weighted summation to obtain a difference result that comprehensively reflects the degree to which the multi-dimensional restored features deviate from the standard features. This difference result will serve as the key basis for determining whether there is a fault in the original data.

[0059] As described in step S4 above, when the difference exceeds a pre-set threshold or meets specific fault judgment rules, it can be determined that the corresponding raw data contains fault information. For example, if the difference in the rate of change of smoke concentration exceeds a certain threshold, it indicates that there is an abnormality in the smoke sensor, such as sensitivity change, obstruction, or damage. If the correlation characteristics between the environmental data and the smoke concentration data differ significantly, it indicates that environmental factors have caused abnormal interference with the smoke alarm or that the internal data processing module has failed. In this way, fault data can be accurately identified from the raw data, providing an important basis for subsequent fault location, alarm, and repair, thereby improving the reliability and stability of the smoke alarm system.

[0060] In this embodiment, the collected data is deeply analyzed by comprehensively considering various factors, fault data is accurately identified, the reliability of the smoke alarm and the troubleshooting efficiency are improved, and the stable operation of the fire safety monitoring system is guaranteed.

[0061] In one embodiment, the raw data includes smoke concentration data, data acquisition timestamp data, temperature and humidity data, and sensor status data.

[0062] In one embodiment, the multi-dimensional features are input into a pre-trained deep neural network, and the multi-dimensional restored features are obtained by processing the multi-dimensional features, including:

[0063] The multi-dimensional features are input into the encoding layer of the autoencoder architecture. The encoding layer adopts a multi-layer fully connected neural network structure with the number of neurons in each layer decreasing in sequence. The features are transformed by a nonlinear activation function, and the high-dimensional multi-dimensional features are mapped to a low-dimensional encoding space to obtain encoded data;

[0064] The encoded data is input into the decoding layer of the autoencoder architecture. The decoding layer adopts a multi-layer fully connected neural network structure. The number of neurons in each layer increases successively and is symmetrical with the structure of the encoding layer. The encoded data is transformed by a nonlinear activation function opposite to that of the encoding layer, and the low-dimensional encoded data is restored to high-dimensional multi-dimensional restored features.

[0065] In this embodiment, the neurons in each layer of the fully connected neural network are interconnected with all neurons in the next layer. This structure can fully capture the complex relationships between different dimensions of the input data. By adopting a multi-layer structure in the encoding layer, as the number of layers increases, it is possible to gradually perform in-depth feature extraction and information integration on multi-dimensional features. For example, for multi-dimensional features such as smoke concentration changes and environmental parameters extracted from data collected by a smoke alarm, the first layer of neurons can receive and preliminarily process these features before passing them to the next layer. Each layer will learn more abstract feature representations based on the output of the previous layer.

[0066] The multi-dimensional features initially input are at a higher dimensionality, containing relatively rich but also redundant information. As the number of neurons gradually decreases, the data is mapped to a lower-dimensional space, the so-called encoding space. For example, the initial multi-dimensional features input may correspond to hundreds of neurons. After multiple layers of reduction, they are ultimately compressed to low-dimensional encoded data represented by only a dozen neurons. This process refines the raw data, retaining key, representative information while removing minor details that are less important to the overall feature expression. This facilitates more efficient mining of the data's underlying structure and characteristic patterns.

[0067] Without activation functions, a multi-layer, fully connected neural network is equivalent to the superposition of multiple linear transformations. Ultimately, it can only represent linear relationships and cannot handle the complex nonlinear data relationships in reality. Commonly used nonlinear activation functions, such as ReLU (Rectified Linear Unit), Sigmoid, or Tanh, can introduce nonlinear factors into neural networks. Taking ReLU as an example, it will change input values less than 0 to 0 and input values greater than 0 to remain unchanged, thus making the neuron output nonlinear. In the encoding layer, when multi-dimensional feature data passes through each layer of neurons, these nonlinear activation functions can be used to transform the data nonlinearly, thereby learning more complex and realistic feature representations. This enables the neural network to model the nonlinear relationships contained in multi-dimensional features, better complete the task of mapping high-dimensional features to a low-dimensional coding space, and obtain effective encoded data.

[0068] The decoding layer also employs a multi-layer, fully connected neural network structure to process the encoded data in a gradual manner. This symmetrical design, symmetrical with the encoding layer, means that the number of neurons in each layer of the decoding layer changes in the opposite direction to that of the encoding layer, decreasing gradually in the encoding layer while increasing in the decoding layer. This symmetric structure helps ensure that data can be properly restored from its low-dimensional encoded state to its high-dimensional state, consistent with the overall operating logic and data processing flow of the autoencoder.

[0069] The process of reducing data from low dimensions to high dimensions requires a gradual increase in the amount of information and dimensional representation of the data. The increasing number of neurons in each layer continuously supplements and enriches the data features, making the restored features as close as possible to the multi-dimensional features of the original input. For example, the decoding layer begins with the initial low-dimensional encoded data. As the number of layers and neurons increases, it continuously adds more detail and dimensional information to the data, ultimately restoring it to the original high-dimensional feature space. During the decoding process, a nonlinear activation function opposite to that used in the encoding layer is used. This allows the restored data to be reversed to restore features that match the distribution characteristics of the original data. Because the encoding layer transforms and compresses the multi-dimensional features using a specific nonlinear activation function, the decoding layer uses a corresponding, inverse nonlinear activation function, which helps to more accurately restore the encoded data to a state close to the original input features.

[0070] By using the collaborative work of the above-mentioned encoding and decoding layers and utilizing the deep neural network autoencoder architecture, multi-dimensional features can be encoded, compressed, and then decoded and restored to obtain multi-dimensional restored features, providing a key data foundation for further fault data analysis.

[0071] In one embodiment, calculating the difference between the multi-dimensional restored features and the standard features to obtain a difference result includes:

[0072] Performing principal component analysis on the multidimensional restored features and the standard features respectively, extracting their respective principal component eigenvectors, and obtaining a principal component matrix of the multidimensional restored features and a principal component matrix of the standard features;

[0073] The cosine similarity between the multi-dimensional restored feature principal component matrix and the standard feature principal component matrix is calculated to obtain a similarity value sequence of each dimension as the difference result.

[0074] In this embodiment, principal component analysis (PCA) is a commonly used data dimensionality reduction and feature extraction method. It transforms multiple variables in the original data into a set of new, uncorrelated variables, called principal components, through linear transformation. The principal components are arranged from largest to smallest in terms of variance: the first principal component explains the most variance in the original data, the second the second, and so on. When processing multidimensional data, the first few principal components often contain the majority of the original data's information.

[0075] For multidimensional reduced features and standard features, the first step is to calculate their covariance matrix. The covariance matrix reflects the correlations between the dimensions. The principal components are then determined by solving for the eigenvalues and eigenvectors of the covariance matrix. The eigenvalue represents the variance explained by the corresponding eigenvector, while the eigenvector represents the direction of the principal component. The corresponding eigenvectors are sorted from largest to smallest by eigenvalue, and the first few eigenvectors with the largest eigenvalues are selected as the principal component eigenvectors. These principal component eigenvectors form the principal component matrix.

[0076] Cosine similarity measures the cosine of the angle between two vectors. In vector space, it effectively reflects the degree of directional consistency between two vectors. Cosine similarity values range from -1 to 1. Values closer to 1 indicate greater similarity and alignment between the two vectors; values closer to -1 indicate more opposite directions; and values closer to 0 indicate little to no linear correlation between the two vectors.

[0077] Each pair of corresponding principal component vectors in the multidimensional restored feature principal component matrix and the standard feature principal component matrix (column or row, depending on the matrix organization) is treated as two vectors, and the cosine similarity between them is calculated. For example, if both the multidimensional restored feature principal component matrix and the standard feature principal component matrix are 3×10 matrices, then the cosine similarity is calculated for the two vectors in each column (representing a principal component dimension). This results in a sequence of 10 similarity values (assuming the original data has 10 dimensions). This sequence of similarity values serves as the difference between the multidimensional restored feature and the standard feature. If the cosine similarity for a particular dimension is low, it means that there is a significant difference between the multidimensional restored feature and the standard feature in the feature direction represented by that principal component. This indicates that a fault or anomaly may exist in the portion of the original data related to that dimension. This method, combining principal component analysis with cosine similarity, effectively quantifies the difference between the multidimensional restored feature and the standard feature while considering the correlation between the data dimensions, providing an important basis for subsequent fault diagnosis.

[0078] In one embodiment, extracting multi-dimensional features of the original data includes:

[0079] Based on wavelet packet decomposition, the original data is decomposed into multi-layer wavelet packet subspaces, and the energy entropy of the signal in each subspace is calculated as the energy entropy feature, and the correlation coefficient between the signal in each subspace and the original data is calculated as the correlation coefficient feature;

[0080] Performing nonlinear dimensionality reduction on the original data based on a local linear embedding algorithm, calculating the distance features between data points in the low-dimensional space after dimensionality reduction, and combining the Euclidean distance features of the original data in the high-dimensional space to obtain a distance feature combination;

[0081] Using the original data as an observation sequence, based on a hidden Markov model, the hidden state transition probability matrix characteristics and the observation probability distribution characteristics under each hidden state are obtained;

[0082] The energy entropy feature, correlation coefficient feature, distance feature combination, hidden state transition probability matrix feature and observation probability distribution feature are used as multi-dimensional features of the original data.

[0083] In this embodiment, wavelet packet decomposition is a multi-resolution analysis of the signal, which is a further extension of the wavelet transform. It is based on wavelet decomposition and continues to decompose the high-frequency part that is not subdivided by the wavelet decomposition, so that the characteristics of the signal in different frequency bands can be analyzed more finely. For the original data collected by the smoke alarm (such as data on smoke concentration changes over time, etc.), by selecting appropriate wavelet basis functions (such as Haar wavelet, Daubechies wavelet, etc.), according to a certain number of decomposition layers, the original data is gradually decomposed into multi-layer wavelet packet subspaces. Each layer of decomposition will further divide a certain frequency band of the previous layer into narrower sub-bands, so that subspaces of different frequency ranges can be obtained, which can more finely present the performance of the original data in each frequency component.

[0084] The energy entropy of the signal is calculated within each wavelet packet subspace. The energy entropy reflects the complexity and uncertainty of the signal's energy distribution within that subspace. Specifically, the energy of the signal within that subspace is first calculated, usually by summing the squares of the signal amplitudes to determine its energy value. Then, based on the information entropy calculation principle, the energy value is normalized, and the energy entropy is calculated using the information entropy calculation formula (e.g., the Shannon entropy formula). The energy entropy characteristics of different subspaces can reflect the differences in disorder or regularity of the energy distribution of the original data in different frequency bands. These differences are very helpful in determining whether the original data has undergone abnormal frequency characteristic changes due to a fault.

[0085] The correlation coefficient between the signal in each subspace and the original data is calculated. Here, the statistical calculation method of the correlation coefficient is generally used, such as the commonly used Pearson correlation coefficient. It measures the degree of linear correlation between two variables (i.e., the signal in the subspace and the original data as a whole), and the value range is between -1 and 1. By calculating this correlation coefficient, we can understand the degree of correlation between the signal in each subspace and the original complete data, reflecting the relative importance and changes of different frequency components in the overall structure of the original data. If the correlation between the signal in a subspace and the original data shows obvious abnormal changes, it indicates that the original data has been affected by the fault factor in the corresponding frequency part.

[0086] The above-mentioned local linear embedding algorithm is a nonlinear dimensionality reduction method based on the idea of manifold learning, which believes that high-dimensional data is often distributed on a low-dimensional manifold. For the raw data of the smoke alarm (which may contain multiple dimensions of environmental and sensor-related data, etc.), the local linear relationship between each data point and its neighboring points in the high-dimensional data space is found. Then, by maintaining these local linear relationships, the high-dimensional data is mapped to the low-dimensional space, so that the local geometric structure characteristics of the original data can still be well preserved in the low-dimensional space. The advantage of this is that while reducing the data dimension, it avoids the loss of nonlinear information in the data like some linear dimensionality reduction methods, which is more consistent with the complex distribution of actual data.

[0087] After nonlinear dimensionality reduction of the original data to a low-dimensional space, the distance features between data points in this low-dimensional space are calculated. Various distance metrics can be used, such as Euclidean distance (the straight-line distance between two points) and Manhattan distance. Furthermore, the Euclidean distance features of the original data in the high-dimensional space must also be considered. The Euclidean distance in the original high-dimensional space reflects the spatial distance of the data under the combined effects of all dimensions before dimensionality reduction. This distance can be combined with the distance features in the low-dimensional space to form a distance feature combination. For example, the Euclidean distance between two data points in the high-dimensional space and their corresponding Euclidean distance in the low-dimensional space can be combined to form a new feature vector. By comparing the changes and differences in distances in the high- and low-dimensional spaces, we can more comprehensively understand the characteristic changes of the original data during the dimensionality transformation process and identify spatial structural anomalies that may be caused by faults. Under normal circumstances, there should be a reasonable correlation between the distances in the high- and low-dimensional spaces, but faults can disrupt this correlation.

[0088] A hidden Markov model (HMM) is a statistical model used to describe a Markov process with hidden unknown parameters. The raw data from a smoke alarm can be viewed as a sequence of observations, with underlying hidden states (for example, these states can represent different operating states of the smoke alarm, such as normal operation, slightly disturbed, or impending failure). These hidden states have a certain transition probability relationship, and the probability of generating observation data (i.e., raw data) in each hidden state is also different. By training on a large amount of raw data under known normal and possible failure conditions, the hidden Markov model can learn the transition patterns between these hidden states and the probability distribution of observation data under each hidden state.

[0089] The hidden state transition probability matrix represents the probability of transitioning from one hidden state to another. After model training is complete, analyzing this matrix can reveal the probability of transitions between different hidden operating states of the smoke alarm. For example, if the probability of transitioning from a normal state to a faulty state suddenly increases at a certain moment, this indicates an impending fault. The values of each element in this matrix are the hidden state transition probability matrix features, reflecting the dynamic trends and probability characteristics of internal state changes.

[0090] Each hidden state has a corresponding observation probability distribution, which is the probability of different observation data (such as different smoke concentration values, environmental parameter values, etc.) appearing under a specific hidden working state. By obtaining the observation probability distribution characteristics under each hidden state, we can understand the probability distribution pattern of the original data under different working conditions. For example, the smoke concentration value under normal conditions may follow a certain normal distribution, while under fault conditions it may show other different distribution forms. By comparing the actual observation data with the observation probability distribution characteristics under these hidden states, we can determine which hidden state the current original data is more consistent with, and then assist in determining whether there is a fault and the possible type of fault.

[0091] The energy entropy features, correlation coefficient features, distance feature combinations, hidden state transition probability matrix features, and observation probability distribution features extracted by the above-mentioned different technical means, each feature characterizes a certain aspect of the original data from a unique perspective. Integrating them together forms a rich and comprehensive multi-dimensional feature set of the original data. The above-mentioned multi-dimensional features can more comprehensively reflect the overall situation of the data collected by the smoke alarm, covering both the frequency characteristics of the data, the spatial structure relationship, and the hidden working status associations. This provides a more sufficient and in-depth feature foundation for subsequent input into deep neural networks for further fault data analysis, helps to more accurately determine whether the original data is abnormal due to a fault, and improves the accuracy and reliability of fault detection.

[0092] In one embodiment, after obtaining the fault data in the original data collected by the smoke alarm according to the difference result, the method includes:

[0093] Based on the fault data, obtaining a faulty component of the smoke alarm;

[0094] Obtaining characteristic information of a supplier of the faulty component;

[0095] Obtaining product information of the faulty component and manufacturer information of the smoke alarm;

[0096] Generate an after-sales authorization code based on the feature information, product information, and manufacturer information;

[0097] After-sales maintenance information is sent to the supplier; the after-sales maintenance information carries the after-sales authority code, which is used by the supplier to authenticate the authority of the after-sales maintenance information.

[0098] In this embodiment, the smoke alarm is a complex device composed of multiple different components, such as a smoke sensor, a signal processing module, a power module, a communication module, etc. Failures of different components will manifest themselves in different characteristics in the collected raw data. For example, if the smoke concentration data is always abnormal and does not conform to normal environmental correlation conditions, it may be that the smoke sensor itself has failed, such as sensor aging, damage, or being blocked by foreign objects; if there is an abnormal interruption or error in data transmission, it may be that there is a problem with the communication module. By analyzing and matching the specific abnormal patterns presented by the fault data, combining the internal structure of the smoke alarm and the functional characteristics of each component, and using pre-established fault models or empirical knowledge, etc., it is possible to accurately determine which specific component has failed, providing a clear target for subsequent targeted repairs, replacements, and other after-sales processing.

[0099] The supplier profile of a faulty component covers a wide range of aspects, including basic business information such as the supplier's name, address, and contact information. Obtaining this information helps provide a more comprehensive understanding of the supplier's background and facilitates subsequent communication and coordination with them regarding after-sales matters.

[0100] The product information for a faulty component includes the component model, specifications, batch number, and production date. The model and specifications determine the component's specific performance parameters and applicable range. Components of different models and specifications will vary in their functional performance and the types of faults they may experience. The batch number and production date are crucial for tracing the component's production process and identifying any quality issues arising from the production process. For example, if multiple similar failures occur within the same batch of components, it's likely that systemic issues exist within the raw materials, process, or other aspects of the production process.

[0101] The smoke alarm manufacturer's information is equally important, including the manufacturer's name, address, contact information, qualifications, market reputation, etc. Knowing the manufacturer's information makes it easier to communicate and collaborate with the manufacturer to solve complex faults or problems involving multiple parties.

[0102] The generation of after-sales authorization codes is to ensure the security and standardization of after-sales maintenance information transmission and processing. By comprehensively utilizing the characteristic information of the supplier, the product information of the faulty component, and the manufacturer information of the smoke alarm, a unique authorization code is generated using a preset algorithm or coding rule. For example, the information from these different sources can be formatted and organized first, and key data items can be extracted. Then, the organized information can be encrypted using an encryption algorithm (such as a combination of hash encryption, symmetric encryption, or asymmetric encryption), and the encrypted result can be used as the after-sales authorization code. Such an authorization code is unique and confidential. Only authorized suppliers who have mastered the corresponding decryption or verification rules can authenticate its authorization, ensuring that after-sales maintenance information is accurately delivered to the correct supplier, and preventing the information from being tampered with or misused, thereby ensuring the reliability and security of the entire after-sales process.

[0103] After determining the faulty component, collecting relevant information and generating the after-sales authorization code, it is necessary to send after-sales maintenance information to the corresponding supplier. The maintenance information describes in detail the fault condition of the smoke alarm, the relevant information of the faulty component and the expected after-sales processing method (such as repair, replacement, etc.), and carries the generated after-sales authorization code. After receiving the after-sales maintenance information, the supplier will first use the pre-set authentication mechanism to verify the authorization code, such as by matching its own saved encryption key or verification algorithm rules, etc., to determine whether the information comes from a legally authorized channel and whether the information content is complete and has not been tampered with. Only after the authorization authentication is passed, the supplier will initiate the corresponding after-sales process based on the specific content of the after-sales maintenance information, such as arranging technicians to perform repairs, prepare replacement components, etc., so as to achieve efficient, safe and standardized after-sales maintenance docking.

[0104] Through the above steps, after detecting a smoke alarm failure, subsequent after-sales processing work can be carried out in an orderly manner to ensure that the equipment can resume normal operation as soon as possible, while maintaining the rights and interests of all parties in the after-sales link and the safety and standardization of the entire process.

[0105] In one embodiment, generating an after-sales authorization code based on the feature information, product information, and manufacturer information includes:

[0106] Converting the characteristic information, product information, and manufacturer information into preset matrix forms respectively; wherein the characteristic information is constructed into a multidimensional sparse matrix, the product information is constructed into a triangular matrix, and the manufacturer information is constructed into a symmetric matrix;

[0107] Performing a matrix multiplication operation on the transformed matrix to obtain a composite matrix, and calculating the eigenvalues and eigenvectors of the composite matrix;

[0108] With the eigenvalue as the horizontal coordinate and the modulus of the eigenvector as the vertical coordinate, a plurality of plane coordinate points are constructed, and each plane coordinate point is connected to form a continuous smooth curve;

[0109] Performing Fourier series expansion on the curve, and arranging the coefficients of the preset items in order into a digital sequence;

[0110] The after-sales authorization code is generated based on the digital sequence.

[0111] In this embodiment, the characteristic information usually includes descriptions of many aspects of the supplier, such as attributes of different dimensions, and these attributes may not all exist densely, and some attributes may be vacant or have very few values for specific situations. Constructing it into a multidimensional sparse matrix means using different attributes as the dimensions of the matrix, such as the supplier's credit rating, the number of major quality accidents in the past, the number of cooperative customers, etc. as element indicators of different rows or columns. Since there are a large number of zero values or vacant values in these elements (corresponding to certain attributes, the supplier has no relevant records, etc.), the formed matrix is sparse. The above representation method is convenient for clearly reflecting the relationship between the attributes and the overall characteristic distribution from a mathematical structure. At the same time, the sparse matrix can use its special storage and calculation methods to improve efficiency in subsequent mathematical operations.

[0112] Product information includes components such as model, specifications, batch number, production date, etc. Constructing this information into a triangular matrix is based on its inherent data structure and logical relationship considerations. For example, the different elements of product information can be arranged in order, and the more important and basic information (such as model) can be placed on the main diagonal of the matrix. Then, according to the strength of the association or logical dependency between the elements, the other elements can be placed in the upper or lower triangular area of the matrix to form a triangular matrix. Triangular matrices have some special mathematical properties, such as the relatively simple evaluation of determinants, which facilitates subsequent operations such as calculations with other matrices and feature extraction. In addition, this construction method can well reflect the hierarchy and association characteristics between the various parts of product information.

[0113] Manufacturer information includes various aspects such as the manufacturer's name, address, contact information, and qualification level. Because this information often corresponds to each other, for example, there's a certain correlation between a manufacturer's reputation and its qualification level. Furthermore, from a mathematical perspective, many relationships between attributes are symmetrical (for example, the degree of correlation between attribute A and attribute B is the same as the degree of correlation between attribute B and attribute A), it is constructed as a symmetric matrix. Different manufacturer information attributes are used as the rows and columns of the matrix, and the elements in corresponding positions represent the strength of the correlation or quantitative relationship between the two attributes. This symmetric matrix can concisely and accurately reflect the inherent connections between the various components of manufacturer information, and the properties of symmetric matrices can be leveraged for efficient processing in subsequent matrix operations.

[0114] Matrix multiplication is performed on the multidimensional sparse, triangular, and symmetric matrices constructed above. Matrix multiplication follows clear mathematical rules and comprehensively considers the corresponding relationships between matrix elements. This process effectively combines three different but interrelated sources of information through mathematical operations. The composite matrix embodies the comprehensive mathematical characteristics of feature information, product information, and manufacturer information. It no longer simply reflects a single type of information, but rather interweaves the relationships and characteristics of all three.

[0115] The calculation of the eigenvalues and eigenvectors of a composite matrix is based on relevant theories and methods in linear algebra. Eigenvalues and eigenvectors reflect some essential characteristics of the linear transformation represented by the matrix. For this composite matrix that integrates multiple aspects of information, the eigenvalues are obtained by solving its characteristic equation (generally in the form of a determinant), and the non-zero vector corresponding to each eigenvalue is the eigenvector. The size of the eigenvalue represents the degree of "stretching" or "compression" in the direction of the corresponding eigenvector, while the eigenvector represents the invariance characteristics of the composite matrix in a specific direction. By obtaining these eigenvalues and eigenvectors, the key mathematical features of the fused information can be extracted from a deeper level. The above features are more representative and abstract than the original information, which facilitates the subsequent generation of unique and secure after-sales authorization codes.

[0116] The calculated eigenvalues are used as the horizontal coordinates, and the modulus of the eigenvector (i.e., the length of the eigenvector, calculated by taking the square root of the sum of the squares of the vector elements) is used as the vertical coordinate. In this way, each set of eigenvalues and the corresponding eigenvector modulus can determine a plane coordinate point. Since a composite matrix has multiple eigenvalues and corresponding eigenvectors, multiple such plane coordinate points can be constructed. These coordinate points are distributed on the plane, intuitively reflecting the relationship between the eigenvalues and eigenvectors of the composite matrix from a geometric perspective. Moreover, each point contains the key features extracted after the previous fusion of information. These abstract mathematical features are visualized in the form of coordinate points, facilitating subsequent operations such as curve construction.

[0117] Connect the various plane coordinate points in order (for example, in order of eigenvalue from small to large) to form a continuous and smooth curve. Geometrically, the above curve is an integrated and continuous expression of the information contained in the previous coordinate points. It is no longer a discrete point, but has overall geometric characteristics such as shape and trend. The shape of the curve will vary greatly depending on the original feature information, product information, and manufacturer information. It actually becomes a unique graphical representation generated based on this information. Due to its continuity and smoothness, it is easier to further extract the inherent laws and characteristics through subsequent mathematical analysis methods (such as Fourier series expansion).

[0118] The Fourier series expansion is a mathematical method that decomposes a periodic function (a continuous smooth curve here can be considered a special form of periodic function representation, or processed by periodic extension within a certain interval) into a series of linear combinations of sine and cosine functions. Through this expansion, the complex shape and changing patterns contained in the curve can be represented by the coefficients of a series of trigonometric functions of different frequencies. Specifically, for a given curve, according to the formula of the Fourier series expansion, the coefficients of the sine and cosine functions of the corresponding frequency components can be calculated. These coefficients reflect the energy distribution or characteristic contribution of the curve at different frequencies, providing an in-depth mathematical analysis and quantitative representation of the curve.

[0119] The coefficients of the preset items in the Fourier series expansion are selected and arranged into a digital sequence in a certain order (for example, according to the order of coefficients corresponding to low to high frequency). The above digital sequence integrates the main frequency characteristic information of the curve. Since the curve itself is connected based on the coordinate points constructed by integrating multiple aspects of information, this digital sequence is actually a concise and orderly digital representation of the original characteristic information, product information, and manufacturer information after multiple layers of mathematical transformation and refinement. It is unique and deterministic (given the same information input and the same processing steps, the same digital sequence will be obtained), providing a suitable data foundation for generating after-sales authorization codes.

[0120] In this embodiment, this digital sequence can be directly used as the after-sales authorization code, or the digital sequence can be further subjected to simple encoding processing, such as using a specific base conversion (such as decimal to hexadecimal, etc.), adding a check digit (for verifying the accuracy and completeness of the authorization code), etc. to generate the final after-sales authorization code. The after-sales authorization code generated by the above-mentioned unique mathematical processing process has high security and uniqueness. It not only integrates key information closely related to the faulty component and related subjects, but also presents it in a way that is difficult to crack and forge. In the process of after-sales maintenance information transmission, it can effectively ensure the security of information and the supplier's accurate authorization authentication of after-sales maintenance information, ensuring the standardized and reliable operation of the entire after-sales process.

[0121] Through the closely coordinated and interlocking mathematical processing of the above steps, information of different dimensions is cleverly converted into after-sales authorization codes, providing an innovative and effective guarantee mechanism for the after-sales management link after the smoke alarm fails.

[0122] In one embodiment, the step of generating an after-sales authorization code based on the feature information, product information, and manufacturer information includes:

[0123] Convert the feature information, product information, and manufacturer information into binary data strings respectively, and then concatenate these binary data strings end to end to form a long binary sequence;

[0124] Using the long binary sequence as initial data, an iterative process is performed using a chaotic mapping function to obtain a set of chaotic sequence values; wherein the parameters of the chaotic mapping function are dynamically adjusted according to the unique identification code of the smoke alarm to increase the randomness and uniqueness of the sequence;

[0125] Perform fractal geometry transformation on the chaotic sequence value to construct a fractal graph and extract the boundary contour coordinate point sequence of the fractal graph;

[0126] Calculate the Fourier descriptor based on the boundary contour coordinate point sequence, quantize the Fourier descriptor, and obtain a quantized numerical sequence;

[0127] Perform polynomial fitting on the quantized numerical sequence, take the coefficients of the fitted polynomial as the core data, and use the information diffusion principle to diffuse and encrypt the core data to obtain the encrypted after-sales permission code.

[0128] In this embodiment, by combining and transforming various technical means such as information conversion, chaos mapping, fractal geometry, Fourier descriptors and information diffusion encryption in an innovative way, a simple combination of existing technologies is avoided, and after-sales permission codes are generated from a unique mathematical and graphic processing perspective, which greatly improves the creativity and security of permission code generation, making after-sales permission management more reliable and difficult to crack.

[0129] In one embodiment, the step of generating an after-sales authorization code based on the feature information, product information, and manufacturer information includes:

[0130] Encoding the characteristic information, product information, and manufacturer information to obtain an encoded character string;

[0131] Performing feature extraction on the feature information, product information, and manufacturer information, and extracting a plurality of numbers from the corresponding features;

[0132] Based on the extracted numbers, a simulation graph is generated;

[0133] The encoded character string is discretely distributed on the simulation graphic, and a plurality of target characters are found on the simulation graphic, and characters other than the target characters are used as characters to be selected;

[0134] Calculate the positional relationship between the candidate character and each target character, and when the candidate character and any target character meet the preset positional relationship, use it as the permission character;

[0135] The various authority characters are combined to obtain the after-sales authority code.

[0136] In this embodiment, the feature information, product information, and manufacturer information often contain data in various formats and semantics. To facilitate subsequent unified mathematical processing and integration of this diverse information, it is necessary to encode it. A common encoding method, such as the common ASCII code, can be used. Through encoding, this originally diverse information is converted into a unified coded string consisting of numbers and specific symbols, enabling subsequent computer systems or corresponding algorithms to efficiently process and calculate it, while also achieving digital representation of the information.

[0137] In the complex information mentioned above, numbers often carry key quantitative features, and numbers are more convenient for mathematical operations and the construction of regular logical relationships. For characteristic information, such as the number of past service times of the supplier and the year of quality certification obtained, they can be extracted as numbers; in product information, the digital part of the production batch number of the component and the key values in the specification parameters (such as the rated power value, etc.) are all extractable objects; in manufacturer information, such as the year of establishment of the manufacturer and the number of employees, numbers can also be extracted. By carefully selecting and extracting these numbers from the corresponding features of each information, it is to further explore the valuable key elements that can reflect the essence of the information and facilitate the subsequent construction of graphics and generation of permission codes, focusing the information from a broader descriptive form to a more operational set of numbers, and using the uniqueness and certainty of numbers to create conditions for the generation of permission codes.

[0138] There are many ways to use these extracted numbers to construct simulated graphics. For example, the numbers can be used as coordinate parameters of the graphic. If a large number of numbers are extracted, a two-dimensional coordinate system can be used, with some of the numbers used as the horizontal and vertical coordinate values to determine the coordinate points one by one. Then, lines can be drawn in a certain order (such as connecting adjacent coordinate points in sequence or according to specific drawing algorithm rules), thereby forming a polygon or a more complex curved graphic. Alternatively, the shape, color, fill method and other visual features of the graphic can be determined based on the size relationship, parity and other properties of the numbers (for example, even numbers correspond to filling a certain area, odd numbers correspond to not filling, etc.), to construct complex simulated graphics such as rectangles, circles, and irregular shapes. The purpose of generating this simulated graphic is to present the digital information in a visual, spatially structured form, providing an intuitive and unique carrier for subsequent operations such as distributing characters on the graphic and filtering permission characters based on graphic features. This allows the generation process of the permission code to be combined with the structural characteristics of the graphic, increasing the complexity and uniqueness of the permission code generation.

[0139] The previously obtained coded string is discretely distributed onto the simulated graphic. Various mapping rules can be used, such as dividing the graphic into equal intervals according to its perimeter, area, etc., and placing the characters in the coded string in these divided positions in sequence; or assigning characters to different sub-regions in sequence according to the sub-regions within the graphic (if the graphic is complex, there are multiple divided regions). When determining the target characters, some clear rules can be set in advance. For example, characters located at special positions such as the vertex position of the graphic, the intersection position of the graphic's symmetry axis, and within a specific color area are defined as target characters. These target characters are usually selected based on the key geometric features of the graphic or positional attributes with obvious differentiation. They are in relatively important and iconic positions in the entire graphic. The remaining characters not in these special positions are selected as candidate characters so that the positional relationship between the candidate characters and the target characters can be used to screen out the permission characters that meet specific conditions. Through this character classification based on graphic position, the graphic structure characteristics are further introduced to participate in the permission code generation process, increasing the complexity and uniqueness of the permission code generation logic.

[0140] Calculating positional relationships can be considered from multiple dimensions. For example, the distance between the candidate character and the target character on the graph can be calculated (using metrics such as Euclidean distance and Manhattan distance, depending on the nature of the graph and specific requirements) to determine whether the candidate character falls within a specific radius with the target character as the center. Alternatively, the angle relationship can be considered to determine whether the angle formed by the line connecting the candidate character and the target character and a baseline of the graph (such as a coordinate axis or symmetry axis) is within a preset angle range. Alternatively, from the perspective of regional attribution, it can be determined whether the subregion where the candidate character is located satisfies a preset regional relationship such as adjacent to or containing the subregion where the target character is located. When the candidate character meets these pre-set positional relationship conditions with any target character, it is marked as an authorized character. By using this screening method based on the spatial structure and layout characteristics of the simulated graph, the final selected authorization characters are both related to the original information encoding and closely dependent on the unique structure of the graph. This makes the authorization code more secure and unpredictable because only authorized parties who know the entire graph construction, character distribution, and positional relationship setting rules can accurately generate and verify the authorization code.

[0141] The filtered permission characters are combined in sequence, either in the order in which they were filtered on the simulated graphic or according to their position in the original encoded string. This combination ultimately forms a complete after-sales permission code. The generated after-sales permission code integrates the results of multiple steps, including encoding of feature information, product information, and manufacturer information, feature extraction, and complex screening based on simulated graphics. It is highly unique and confidential, serving as a valid permission authentication identifier during the transmission of after-sales maintenance information. This ensures that only legitimate suppliers, relying on the correct permission authentication mechanism, can process after-sales maintenance information, thus safeguarding the information security and standardization of the entire after-sales process.

[0142] Reference Figure 2 In one embodiment of the present invention, a device for analyzing fault data of a smoke alarm is provided, comprising:

[0143] An acquisition unit, configured to acquire raw data collected by the smoke alarm and extract multi-dimensional features of the raw data;

[0144] A processing unit is configured to input the multi-dimensional features into a pre-trained deep neural network to obtain multi-dimensional restored features; wherein the deep neural network encodes and compresses the multi-dimensional features through an autoencoder architecture, and then decodes and restores the multi-dimensional restored features;

[0145] a calculation unit, configured to calculate the difference between the multi-dimensional restored features and the standard features to obtain a difference result;

[0146] The analyzing unit is used to obtain the fault data in the original data collected by the smoke alarm according to the difference result.

[0147] In this embodiment, for the specific implementation of each unit in the above device embodiment, please refer to the above method embodiment, which will not be repeated here.

[0148] Reference Figure 3 In the embodiment of the present invention, a smoke alarm is also provided. The internal structure of the smoke alarm can be as follows: Figure 3As shown. The smoke alarm includes a processor, memory, display screen, input device, network interface and database connected via a system bus. The computer-designed processor is used to provide computing and control capabilities. The memory of the smoke alarm includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the smoke alarm is used to store the corresponding data in this embodiment. The network interface of the smoke alarm is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0149] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the smoke alarm to which the solution of the present invention is applied.

[0150] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-described method when executed by a processor. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0151] In summary, the fault data analysis method, device, and smoke alarm provided in the embodiments of the present invention include: obtaining the original data collected by the smoke alarm, extracting the multi-dimensional features of the original data; inputting the multi-dimensional features into a pre-trained deep neural network, and processing to obtain multi-dimensional restored features; wherein the deep neural network encodes and compresses the multi-dimensional features through an autoencoder architecture, and then decodes and restores them to obtain multi-dimensional restored features; calculating the difference between the multi-dimensional restored features and the standard features to obtain a difference result; and obtaining the fault data in the original data collected by the smoke alarm based on the difference result. In the present invention, the collected data is deeply analyzed by comprehensively considering various factors, and the fault data is accurately identified to improve the reliability of the smoke alarm and the efficiency of troubleshooting, so as to ensure the stable operation of the fire safety monitoring system.

[0152] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Among them, any reference to memory, storage, database, or other media provided by the present invention and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAM bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM.

[0153] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, article, or method comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, apparatus, article, or method. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, apparatus, article, or method comprising the element.

[0154] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for analyzing fault data of a smoke alarm, characterized in that: The following steps are involved: Obtaining raw data collected by the smoke alarm and extracting multi-dimensional features of the raw data; the raw data includes smoke concentration data, data collection timestamp data, temperature and humidity data, and sensor status data; The extracting of multi-dimensional features of the original data includes: decomposing the original data into multi-layer wavelet packet subspaces based on wavelet packet decomposition, calculating the energy entropy of the signal in each subspace as the energy entropy feature, and the correlation coefficient between the signal in each subspace and the original data as the correlation coefficient feature; performing nonlinear dimensionality reduction on the original data based on a local linear embedding algorithm, calculating the distance feature between data points in the low-dimensional space after dimensionality reduction, and combining the Euclidean distance feature of the original data in the high-dimensional space to obtain a distance feature combination; using the original data as an observation sequence, obtaining the hidden state transition probability matrix feature and the observation probability distribution feature under each hidden state based on a hidden Markov model; using the energy entropy feature, correlation coefficient feature, distance feature combination, hidden state transition probability matrix feature and observation probability distribution feature as the multi-dimensional features of the original data; Inputting the multi-dimensional features into a pre-trained deep neural network to process and obtain multi-dimensional restored features; wherein the deep neural network encodes and compresses the multi-dimensional features through an autoencoder architecture, and then decodes and restores the multi-dimensional restored features; Calculating the difference between the multi-dimensional restored features and the standard features to obtain a difference result; According to the difference result, the fault data in the original data collected by the smoke alarm is obtained.

2. The method for analyzing fault data of a smoke alarm according to claim 1, characterized in that: Inputting the multi-dimensional features into a pre-trained deep neural network to process and obtain multi-dimensional restored features includes: The multi-dimensional features are input into the encoding layer of the autoencoder architecture. The encoding layer adopts a multi-layer fully connected neural network structure with the number of neurons in each layer decreasing in sequence. The features are transformed by a nonlinear activation function, and the high-dimensional multi-dimensional features are mapped to a low-dimensional encoding space to obtain encoded data; The encoded data is input into the decoding layer of the autoencoder architecture. The decoding layer adopts a multi-layer fully connected neural network structure. The number of neurons in each layer increases successively and is symmetrical with the structure of the encoding layer. The encoded data is transformed by a nonlinear activation function opposite to that of the encoding layer, and the low-dimensional encoded data is restored to high-dimensional multi-dimensional restored features.

3. The method for analyzing fault data of a smoke alarm according to claim 1, characterized in that: Calculating the difference between the multi-dimensional restored features and the standard features to obtain a difference result includes: Performing principal component analysis on the multidimensional restored features and the standard features respectively, extracting their respective principal component eigenvectors, and obtaining a principal component matrix of the multidimensional restored features and a principal component matrix of the standard features; The cosine similarity between the multi-dimensional restored feature principal component matrix and the standard feature principal component matrix is calculated to obtain a similarity value sequence of each dimension as the difference result.

4. The method for analyzing fault data of a smoke alarm according to claim 1, characterized in that: After obtaining the fault data in the original data collected by the smoke alarm according to the difference result, the method includes: Based on the fault data, obtaining a faulty component of the smoke alarm; Obtaining characteristic information of a supplier of the faulty component; Obtaining product information of the faulty component and manufacturer information of the smoke alarm; Generate an after-sales authorization code based on the feature information, product information, and manufacturer information; After-sales maintenance information is sent to the supplier; the after-sales maintenance information carries the after-sales authority code, which is used by the supplier to authenticate the authority of the after-sales maintenance information.

5. The method for analyzing fault data of a smoke alarm according to claim 4, characterized in that: Based on the feature information, product information, and manufacturer information, an after-sales authorization code is generated, including: Converting the characteristic information, product information, and manufacturer information into preset matrix forms respectively; wherein the characteristic information is constructed into a multidimensional sparse matrix, the product information is constructed into a triangular matrix, and the manufacturer information is constructed into a symmetric matrix; Performing a matrix multiplication operation on the transformed matrix to obtain a composite matrix, and calculating the eigenvalues and eigenvectors of the composite matrix; With the eigenvalue as the horizontal coordinate and the modulus of the eigenvector as the vertical coordinate, a plurality of plane coordinate points are constructed, and each plane coordinate point is connected to form a continuous smooth curve; Performing Fourier series expansion on the curve, and arranging the coefficients of the preset items in order into a digital sequence; The after-sales authorization code is generated based on the digital sequence.

6. A smoke alarm fault data analysis device, characterized in that: include: An acquisition unit is used to acquire raw data collected by the smoke alarm and extract multi-dimensional features of the raw data; the raw data includes smoke concentration data, data collection timestamp data, temperature and humidity data, and sensor status data; The extracting of multi-dimensional features of the original data includes: decomposing the original data into multi-layer wavelet packet subspaces based on wavelet packet decomposition, calculating the energy entropy of the signal in each subspace as the energy entropy feature, and the correlation coefficient between the signal in each subspace and the original data as the correlation coefficient feature; performing nonlinear dimensionality reduction on the original data based on a local linear embedding algorithm, calculating the distance feature between data points in the low-dimensional space after dimensionality reduction, and combining the Euclidean distance feature of the original data in the high-dimensional space to obtain a distance feature combination; using the original data as an observation sequence, obtaining the hidden state transition probability matrix feature and the observation probability distribution feature under each hidden state based on a hidden Markov model; using the energy entropy feature, correlation coefficient feature, distance feature combination, hidden state transition probability matrix feature and observation probability distribution feature as the multi-dimensional features of the original data; A processing unit is configured to input the multi-dimensional features into a pre-trained deep neural network to obtain multi-dimensional restored features; wherein the deep neural network encodes and compresses the multi-dimensional features through an autoencoder architecture, and then decodes and restores the multi-dimensional restored features; a calculation unit, configured to calculate the difference between the multi-dimensional restored features and the standard features to obtain a difference result; The analyzing unit is used to obtain the fault data in the original data collected by the smoke alarm according to the difference result.

7. A smoke alarm comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images