Current fingerprint feature library updating method and device, equipment and storage medium

Abstract

According to the current fingerprint feature library updating method and device, the equipment and the storage medium provided by the invention, the equipment model and the working state of the new equipment are acquired under the condition that the edge equipment and the new equipment are networked for the first time; under the condition that the working state is that the new equipment is working, acquiring a first current time domain waveform of the new equipment; determining a first harmonic characteristic based on the first current time domain waveform; outputting the first harmonic characteristic to a pre-established neural network model to determine a first current fingerprint characteristic of the new equipment; and establishing a corresponding relationship between the first current fingerprint feature and the equipment model of the new equipment, and updating the current fingerprint feature library based on the corresponding relationship, so that the current fingerprint feature library can be automatically updated at the edge equipment, and the updating process of the current fingerprint feature library is simplified.

Description

Technical Field

[0001] This application belongs to the technical field of device identification, and particularly relates to a method, device, equipment and storage medium for updating a current fingerprint feature library. Background Art

[0002] Current fingerprints are widely used in the identification of electrical appliances in various fields. However, the existing identification capabilities are often limited to specific models of devices. When expanding to new models of devices, it is necessary to establish the correspondence between the new models and the current fingerprints for identification. In related technologies, when establishing the correspondence between a new model of device and a current fingerprint, the common process is: collecting data, preprocessing the data, calibrating the data, training a model on the server side, updating the model of the current fingerprint identification device, and identifying the current fingerprint according to the updated model. Finally, the correspondence between the current fingerprint feature and the device model is established. It can be seen that in the process of establishing the correspondence between the current fingerprint feature and the device model in related technologies, there is a lot of human participation and the update is relatively cumbersome. Summary of the Invention

[0003] In view of the above problems, the embodiments of this application provide a method, device, equipment and storage medium for updating a current fingerprint feature library, which can automatically update the current fingerprint feature library and simplify the update process of the current fingerprint feature library.

[0004] In a first aspect, the embodiments of this application provide a method for updating a current fingerprint feature library, which is applied to an edge device and includes:

[0005] When the edge device and a new device are first networked, obtain the device model and working status of the new device;

[0006] When the working status is that the new device is working, obtain the first current time-domain waveform of the new device;

[0007] Determine the first harmonic feature based on the first current time-domain waveform;

[0008] Output the first harmonic feature to a pre-established neural network model to determine the first current fingerprint feature of the new device;

[0009] Establish the correspondence between the first current fingerprint feature and the device model of the new device, and update the current fingerprint feature library based on the correspondence.

[0010] In some embodiments, the obtaining of the first current time-domain waveform of the new device includes:

[0011] Collect the second current time-domain waveform of the current device, where the device at least includes: the new device;

[0012] In the case where there are multiple devices, an independent component analysis method is used to separate the second current time-domain waveform to obtain a separated current time-domain waveform;

[0013] Based on the separated current time-domain waveform, the first current time-domain waveform of the new device is determined.

[0014] In some embodiments, the determining the first current time-domain waveform of the new device based on the separated current time-domain waveform includes:

[0015] Obtain the current time-domain waveform corresponding to the device stored in advance;

[0016] Match the current time-domain waveform corresponding to the device stored in advance with each of the separated current time-domain waveforms, and determine the unmatched separated current time-domain waveforms;

[0017] Determine the unmatched separated current time-domain waveform as the first current time-domain waveform of the new device.

[0018] In some embodiments, the determining the first harmonic feature based on the first current time-domain waveform includes:

[0019] Use the fast Fourier transform algorithm to convert the first current time-domain waveform into a first frequency-domain waveform;

[0020] Extract the first harmonic feature of the first frequency-domain waveform based on the frequency-domain signal amplitude spectrum formula.

[0021] In some embodiments, the method further includes:

[0022] Obtain the neural network model sent by the server;

[0023] Store the neural network model, where the loss function of the neural network model is a triplet loss function.

[0024] In some embodiments, the method further includes:

[0025] Send the updated current fingerprint feature library to the server, so that the server sends the updated current fingerprint feature library to other edge devices.

[0026] In some embodiments, the method further includes:

[0027] Obtain the third current time-domain waveform of the device to be recognized;

[0028] Convert the third current time-domain waveform into a second frequency-domain waveform;

[0029] Determine the second harmonic feature based on the second frequency-domain waveform, and output the second harmonic feature to a pre-established neural network model to determine the second current fingerprint feature of the device to be identified;

[0030] Determine the device model of the device to be identified based on the second current fingerprint feature and the current fingerprint feature library.

[0031] In a second aspect, an embodiment of the present application provides an update device for a current fingerprint feature library, including:

[0032] A first acquisition module, configured to acquire the device model and working status of the new device when the edge device is first connected to the new device;

[0033] A second acquisition module, configured to acquire the first current time-domain waveform of the new device when the working status is that the new device is working;

[0034] A first determination module, configured to determine the first harmonic feature based on the first current time-domain waveform;

[0035] A second determination module, configured to output the first harmonic feature to a pre-established neural network model to determine the first current fingerprint feature of the new device;

[0036] An update module, configured to establish a correspondence between the first current fingerprint feature and the device model of the new device, and update the current fingerprint feature library based on the correspondence.

[0037] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the method provided in the first aspect is implemented.

[0038] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method provided in the first aspect is implemented.

[0039] In a fifth aspect, an embodiment of the present application provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, it is at least used to implement the method in any item of the first aspect.

[0040] The beneficial effects of the embodiments of the present application compared with the prior art are:

[0041] The method for updating the current fingerprint feature library provided by the embodiments of the present application obtains the device model and working status of the new device when the edge device is first networked with the new device; when the working status is that the new device is working, obtains the first current time-domain waveform of the new device; determines the first harmonic feature based on the first current time-domain waveform; outputs the first harmonic feature to a pre-established neural network model to determine the first current fingerprint feature of the new device; establishes a correspondence relationship between the first current fingerprint feature and the device model of the new device, and updates the current fingerprint feature library based on the correspondence relationship, which can automatically update the current fingerprint feature library on the edge device and simplify the update process of the current fingerprint feature library.

[0042] It can be understood that the beneficial effects of the second to fifth aspects above can refer to the relevant descriptions in the first aspect above, and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0044] Figure 1 It is a schematic structural diagram of an update system for a current fingerprint feature library provided by the embodiments of the present application;

[0045] Figure 2 It is a schematic flow diagram of a method for updating a current fingerprint feature library provided by the embodiments of the present application;

[0046] Figure 3 It is a schematic implementation flow diagram of a method for updating a current fingerprint feature library provided by the embodiments of the present application;

[0047] Figure 4 It is a schematic structural diagram of an update device for a current fingerprint feature library provided by the embodiments of the present application;

[0048] Figure 5 It is a schematic structural diagram of an electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] In the following description, specific details such as specific system architectures and technologies are presented for purposes of illustration and not limitation, so as to provide a thorough understanding of the embodiments of the present application. However, those skilled in the art should understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from obscuring the description of the present application.

[0050] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0051] It should also be understood that the term "and / or" as used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0052] As used in the specification of the present application and the appended claims, the term "if" can be interpreted as "when" or "once" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrases "if determined" or "if detected" can be interpreted as meaning "once determined" or "in response to determining" or "once detected" or "in response to detecting" depending on the context.

[0053] In addition, in the description of the specification of the present application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0054] The reference to "one embodiment" or "some embodiments" etc. described in the specification of the present application means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of the present application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways.

[0055] Based on the technical problems of the related art, an embodiment of the present application provides an update method for a current fingerprint feature library that can be applied to an electronic device. The electronic device may include: a smart meter, a smart air switch, a smart socket, etc. The embodiment of the present application does not impose any restrictions on the specific type of the electronic device, and the electronic device can be used as an edge device.

[0056] In the embodiments of the present application, an edge device is a device that can extract the current fingerprint vector of electrical appliances in its downstream circuit and has AI computing power.

[0057] Figure 1 FIG. is a schematic structural diagram of an update system for a current fingerprint feature library provided by an embodiment of the present application. As Figure 1 shown, the edge device can be referred to as the edge side. The edge device can be any edge side, for example, any one of edge side A, edge side B, or edge side N. The edge side is communicatively connected to the home appliance device. For example, edge side A is communicatively connected to home appliance devices A1, A2, and A3. Each edge side is also communicatively connected to the server side.

[0058] Based on the foregoing update system for the current fingerprint feature library, an embodiment of the present application provides a method for updating the current fingerprint feature library. Figure 2 FIG. is a schematic flowchart of a method for updating a current fingerprint feature library provided by an embodiment of the present application. As Figure 2 shown, the method includes:

[0059] Step S101, when the edge device and the new device are first networked, obtain the device model and working state of the new device.

[0060] In the embodiments of the present application, an edge device refers to a device located at the edge of the network, which is usually used for data processing and storage to reduce the dependence on the server and improve the response speed and efficiency. A new device refers to a device that is first networked with the edge device, and it may be any type of Internet of Things device, such as a household appliance. The device model is the unique identifier assigned by the manufacturer to distinguish different devices, and the working state refers to whether the device is currently in an operating state.

[0061] In the embodiments of the present application, when the edge device and the new device are first networked, the new device will send information including its model and working state to the edge device, so that the edge device can obtain the device signal and working state of the new device.

[0062] Step S102, when the working state is that the new device is working, obtain the first current time-domain waveform of the new device.

[0063] In the embodiments of the present application, the current time-domain waveform is a graphical representation of the current change with time generated by the device during operation, which reflects the electrical characteristics and operating state of the device.

[0064] In the embodiments of the present application, the edge device can determine whether the new device is in a normal use state through the working state. If it is not in a normal working state, it needs to wait. If it is in a normal working state, the first current time-domain waveform of the new device is obtained.

[0065] In the embodiments of the present application, the edge device can sample at a preset frequency, and the preset frequency can be configured. Exemplarily, a frequency of 8KHz can be configured for current sampling, so as to obtain the first current time-domain waveform of the new device.

[0066] Step S103, determine the first harmonic feature based on the first current time-domain waveform.

[0067] In the embodiments of the present application, the first harmonic feature refers to the performance of the current time-domain waveform in the frequency domain, especially the specific frequency components related to the electrical characteristics of the device.

[0068] In the embodiments of the present application, the first current time-domain waveform can be converted into a frequency-domain waveform through the Fast Fourier Transform (FFT) algorithm, and then the first harmonic components in the frequency-domain waveform are extracted.

[0069] Step S104, output the first harmonic feature to a pre-established neural network model to determine the first current fingerprint feature of the new device.

[0070] In the embodiments of the present application, the neural network model is a machine learning algorithm, and the neural network model is used to extract the current fingerprint feature from the current harmonic feature. The current fingerprint feature is the unique electrical feature of the device, which is extracted based on the current harmonic feature of the device and is used for device identification. In the embodiments of the present application, the neural network model can be a CNN model, and this model can be obtained from the server and sent to the edge device after being trained on the server.

[0071] In the embodiments of the present application, the extracted first harmonic feature is used as input data and passed to the neural network model, and the model will output the corresponding current fingerprint feature.

[0072] Step S105, establish a correspondence between the first current fingerprint feature and the device model of the new device, and update the current fingerprint feature library based on the correspondence.

[0073] In the embodiments of the present application, the current feature fingerprint library stores the correspondence between the current fingerprint feature and the device model, and there can be multiple groups of correspondences in the current feature fingerprint library.

[0074] In the embodiments of the present application, a new record can be created in the local database or memory of the edge device to store the correspondence between the current fingerprint feature and the device model. This record can be a structure, a dictionary (key-value pair) or a row in a database table. The first current fingerprint feature can be stored as part of the record, and then the device model of the new device is associated with the first current fingerprint feature, so as to establish this correspondence.

[0075] In the embodiments of the present application, the created record can be added to the feature library to update the current feature fingerprint library.

[0076] The method for updating the current fingerprint feature library provided by the embodiments of the present application includes, when the edge device is first connected to the new device to the network, obtaining the device model and working status of the new device; when the working status is that the new device is working, obtaining the first current time-domain waveform of the new device; determining the first harmonic feature based on the first current time-domain waveform; outputting the first harmonic feature to a pre-established neural network model to determine the first current fingerprint feature of the new device; establishing a correspondence relationship between the first current fingerprint feature and the device model of the new device, and updating the current fingerprint feature library based on the correspondence relationship, which can automatically update the current fingerprint feature library on the edge device and simplify the update process of the current fingerprint feature library.

[0077] In some embodiments, step S102 can be implemented through the following steps:

[0078] Step S1021, collecting the current second current time-domain waveform of the device, where the device at least includes: the new device.

[0079] In the embodiments of the present application, the second current time-domain waveform can be a single current time-domain waveform or a composite waveform. When multiple devices work simultaneously, their current time-domain waveforms will be superimposed on each other to form a composite waveform.

[0080] In the embodiments of the present application, current monitoring points can be set at appropriate positions in the power system, so as to capture the current signals of all relevant devices.

[0081] Step S1022, when there are multiple devices, using the independent component analysis method to separate the second current time-domain waveform to obtain the separated current time-domain waveform.

[0082] In the embodiments of the present application, when there is only one device, the collected current time-domain waveform is directly determined as the first current time-domain waveform of the new device. If there are multiple devices, the independent component analysis method needs to be used for separation.

[0083] In the embodiments of the present application, the collected composite current time-domain waveform can be denoised to eliminate the influence of environmental noise and measurement errors. Before performing the independent component analysis method, the data is normalized to ensure the comparability of the current signals of different devices in terms of amplitude and phase.

[0084] In the embodiments of the present application, according to the characteristics of the collected data and the analysis requirements, a suitable ICA model is selected. Common ICA models include FastICA, JADE, etc. The preprocessed second current time-domain waveform is input into the ICA algorithm to extract independent components. The ICA algorithm decomposes the second current time-domain waveform into multiple independent current time-domain waveforms by maximizing the independence between the components, thereby obtaining the separated current time-domain waveforms.

[0085] Step S1023, determine the first current time-domain waveform of the new device based on the separated current time-domain waveforms.

[0086] In the embodiments of the present application, the current time-domain waveform corresponding to the new device can be identified from the separated current time-domain waveforms obtained by decomposition.

[0087] The method provided by the embodiments of the present application can separate the current time-domain waveform of the new device from the composite current time-domain waveform, providing accurate data support for subsequent applications such as device identification and fault diagnosis.

[0088] In some embodiments, in step S1023, the determining the first current time-domain waveform of the new device based on the separated current time-domain waveforms includes:

[0089] Step S1, obtain the current time-domain waveform corresponding to the device stored in advance.

[0090] In the embodiments of the present application, a waveform library containing the current time-domain waveforms of known devices can be established. The current time-domain waveform corresponding to the device stored in advance can be obtained from the waveform library.

[0091] Step S2, match the current time-domain waveform corresponding to the device stored in advance with each of the separated current time-domain waveforms, and determine the unmatched separated current time-domain waveforms.

[0092] In the embodiments of the present application, before matching, in order to ensure the accuracy of the matching process, each waveform in the waveform library can be preprocessed, such as denoising, normalization, etc. And preprocess the separated current time-domain waveforms. Each separated current time-domain waveform can be matched with the waveforms in the waveform library. The matching process can be based on the comparison of waveform features or more complex pattern recognition algorithms can also be used.

[0093] In the embodiments of the present application, if waveform features are used, then compare the features of the separated waveforms with the features of the waveforms in the waveform library to find the closest match. If pattern recognition algorithms (such as neural networks, support vector machines, etc.) are used, then input the separated waveforms into the algorithm, and the algorithm will output the matched waveforms and the unmatched waveforms.

[0094] Step S3, determine the unmatched separated current time-domain waveform as the first current time-domain waveform of the new device.

[0095] In the embodiments of the present application, during the matching process, if the separated current time-domain waveform does not match any current time-domain waveform in the waveform library, the unmatched current time-domain waveform is the first current time-domain waveform of the new device.

[0096] In some embodiments, after determining the unmatched current time-domain waveform as the first current time-domain waveform of the new device, the waveform library can be updated based on the unmatched current time-domain waveform.

[0097] In some embodiments, step S103 can be implemented through the following steps:

[0098] Step S1031, convert the first current time-domain waveform into a first frequency-domain waveform by using the fast Fourier transform algorithm.

[0099] In the embodiments of the present application, the fast Fourier transform (FFT) is an algorithm for efficiently calculating the discrete Fourier transform (DFT) and its inverse transform. It can convert a signal from the time domain to the frequency domain. Input the data of the first current time-domain waveform into the FFT algorithm to obtain the first frequency-domain waveform.

[0100] Step S1032, extract the first harmonic feature of the first frequency-domain waveform based on the frequency-domain signal amplitude spectrum formula.

[0101] In the embodiments of the present application, the amplitude spectrum of the frequency-domain signal is a set of amplitudes of the signal at each frequency component. It can be calculated by taking the modulus of the complex number array output by the FFT.

[0102] In the embodiments of the present application, the harmonic components can be extracted using the frequency-domain signal amplitude spectrum formula to obtain the first harmonic feature, where the frequency-domain signal amplitude spectrum formula is expressed as:

[0103] Where:

[0104] |X(k)| is the amplitude of the Fourier transform result at the k-th frequency point, which is the first harmonic feature. The amplitude spectrum shows the energy distribution of the signal at different frequencies.

[0105] X(k) is the complex result of the signal at the k-th frequency point after Fourier transform. Each X(k) can be expressed as X(k) = ak + jbk, where ak is the real part, bk is the imaginary part, and j is the imaginary unit;

[0106] Re(X(k)) is the real part of X(k), that is, ak. In signal processing, the real part represents the cosine component of the signal;

[0107] Im(X(k)) is the imaginary part of X(k), which is bk. In signal processing, the imaginary part represents the sine component of the signal;

[0108] Re(X(k)) 2 is the square of the real part, that is

[0109] Im(X(k)) 2 is the square of the imaginary part, that is

[0110] is the square root of the sum of the square of the real part and the square of the imaginary part. It calculates the modulus length, i.e., the amplitude, of the complex number X(k). This value is positive because it represents the energy magnitude of the signal at a specific frequency.

[0111] Through the above formula, the first harmonic feature can be calculated.

[0112] The method provided by the embodiments of this application can convert the time-domain waveform of the current into a frequency-domain waveform, so as to extract useful harmonic features.

[0113] In some embodiments, before step S101, the method further includes:

[0114] Step S1011, obtaining the neural network model sent by the server.

[0115] In the embodiments of this application, the server can establish a communication connection with the edge device and can use network protocols such as HTTP / HTTPS / CoAP / MQTT / WEBSOCKETS for requests and responses.

[0116] In the embodiments of this application, the server can store the neural network model as a compressed file or a specified binary file. Then the file is sent to the edge device, so that the edge device can obtain the neural network model sent by the server.

[0117] Step S1012, storing the neural network model, where the loss function of the neural network model is a triplet loss function.

[0118] In the embodiments of this application, the edge device can determine a storage location to save the received neural network model. The storage location can be a local file system, a cloud storage service, a database, etc. Then the received model data is saved to the selected storage location. If the model data is compressed, it needs to be decompressed before saving.

[0119] In the embodiments of the present application, the Triplet Loss function is generally used to train a deep learning model to learn an embedding space, such that in this space, similar samples (i.e., positive sample pairs) are closer than dissimilar samples (i.e., negative sample pairs).

[0120] In the embodiments of the present application, a triplet is defined as:

[0121] Anchor: Harmonic sample;

[0122] Positive: Harmonic sample belonging to the same class as the Anchor;

[0123] Negative: Harmonic sample belonging to a different class from the Anchor.

[0124] In the embodiments of the present application, the server can train a neural network model with sample data and send the neural network model to an edge device after training is completed.

[0125] In some embodiments, after step S105, the method further includes:

[0126] Step S106, sending the updated current fingerprint feature library to the server, so that the server sends the updated current fingerprint feature library to other edge devices.

[0127] In the embodiments of the present application, the edge device can package the updated current fingerprint feature library into a file or data packet for sending the updated current fingerprint feature library to the server.

[0128] In the embodiments of the present application, the server sends the updated current fingerprint feature library to other edge devices after obtaining it, thereby realizing data synchronization and update.

[0129] In some embodiments, the method further includes:

[0130] Step S201, obtaining the third current time-domain waveform of the device to be identified.

[0131] The current time-domain waveform of the device can be collected; in the case where there are multiple devices, the independent component analysis method is used to separate the current time-domain waveform to obtain the separated current time-domain waveform; the third current time-domain waveform of each device to be identified is determined based on the separated current time-domain waveform.

[0132] Step S202, converting the third current time-domain waveform into a second frequency-domain waveform.

[0133] In the embodiments of the present application, the fast Fourier transform algorithm can be used to convert the third current time-domain waveform into a second frequency-domain waveform.

[0134] Step S203: Determine the second harmonic feature based on the second frequency-domain waveform, and output the second harmonic feature to a pre-established neural network model to determine the second current fingerprint feature of the device to be identified.

[0135] In the embodiment of the present application, the second harmonic feature of the second frequency-domain waveform is extracted based on the frequency-domain signal amplitude spectrum formula, and then a pre-established neural network model is loaded. This model has been trained and can output the current fingerprint feature of the device according to the input harmonic feature. The extracted second harmonic feature is input into the neural network model, and the model will output the second current fingerprint feature of the device to be identified.

[0136] Step S204: Determine the device model of the device to be identified based on the second current fingerprint feature and the current fingerprint feature library.

[0137] In the embodiment of the present application, the second current fingerprint feature of the device to be identified is matched with the features in the current fingerprint feature library. Matching algorithms (such as Euclidean distance, cosine similarity, etc.) are used to calculate the similarity between the second current fingerprint feature and the features in the library. The device model corresponding to the feature with the highest similarity is selected as the model of the device to be identified.

[0138] The method provided in the embodiment of the present application can identify the device by obtaining the current waveform of the device to be identified, extracting the harmonic feature, and using the neural network model and the current fingerprint feature library.

[0139] Based on the foregoing embodiments, the embodiment of the present application further provides an update method for the current fingerprint feature library. Figure 3 It is a schematic flowchart of the implementation process of an update method for the current fingerprint feature library provided in the embodiment of the present application. As Figure 3 shown, it includes:

[0140] Step S301: Record the model and working state of the new model device.

[0141] In the embodiment of the present application, it can be integrated and interacted with the smart home system to obtain the model and working state of the new model device in real time.

[0142] Step S302: High-frequency collect current parameters.

[0143] Step S303: Time-domain signal separation.

[0144] In the embodiment of the present application, the ICA method can be used to analyze the current time-domain waveform of the new model device.

[0145] Step S304: Time-domain to frequency-domain conversion.

[0146] In the embodiments of the present application, the time-domain waveform can be converted into a frequency-domain waveform using the fast Fourier transform.

[0147] Step S305: Obtain harmonic features.

[0148] In the embodiments of the present application, the amplitude of the frequency-domain waveform can be calculated to obtain harmonic features.

[0149] Step S306: Extract the current fingerprint feature vector.

[0150] In the embodiments of the present application, a CNN model can be used to extract the feature vector.

[0151] Step S307: Associate the device model and update the current fingerprint feature library.

[0152] Step S308: Upload the current fingerprint feature library to the server.

[0153] The method provided in the embodiments of the present application can uniformly control smart home devices through edge devices and can obtain their model and working status information in real time; the edge device can independently iterate and update the current fingerprint feature library to support the identification of new model devices.

[0154] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0155] According to the foregoing embodiments, the embodiments of the present application provide an update device for a current fingerprint feature library. Each module included in the device, as well as each unit included in each module, can be implemented by a processor in a computer device; of course, it can also be implemented by specific logic circuits; in the implementation process, the processor can be a central processing unit (CPU, Central Processing Unit), a microprocessor (MPU, Microprocessor Unit), a digital signal processor (DSP, Digital Signal Processing), or a field programmable gate array (FPGA, Field Programmable Gate Array), etc.

[0156] The embodiments of the present application provide an update device for a current fingerprint feature library. Figure 4 As shown in the structural schematic diagram of an update device for a current fingerprint feature library provided in the embodiments of the present application, Figure 4 as shown, the update device 400 for the current fingerprint feature library includes:

[0157] The first acquisition module 401 is configured to acquire the device model and working status of the new device when the edge device is first networked with the new device;

[0158] The second acquisition module 402 is configured to acquire the first current time-domain waveform of the new device when the working status indicates that the new device is working;

[0159] The first determination module 403 is configured to determine the first harmonic feature based on the first current time-domain waveform;

[0160] The second determination module 404 is configured to output the first harmonic feature to a pre-established neural network model to determine the first current fingerprint feature of the new device;

[0161] The update module 405 is configured to establish a correspondence between the first current fingerprint feature and the device model of the new device, and update the current fingerprint feature library based on the correspondence.

[0162] In some embodiments, the second acquisition module includes:

[0163] The acquisition unit is configured to acquire the current second current time-domain waveform of the device, where the device at least includes: the new device;

[0164] The separation unit is configured to, when there are multiple devices, use the independent component analysis method to separate the second current time-domain waveform to obtain a separated current time-domain waveform;

[0165] The first determination unit is configured to determine the first current time-domain waveform of the new device based on the separated current time-domain waveform.

[0166] In some embodiments, the first determination unit includes:

[0167] The acquisition subunit is configured to acquire the current time-domain waveform corresponding to the device stored in advance;

[0168] The matching subunit is configured to match the current time-domain waveform corresponding to the device stored in advance with each of the separated current time-domain waveforms, and determine the unmatched separated current time-domain waveforms;

[0169] The determination subunit is configured to determine the unmatched separated current time-domain waveforms as the first current time-domain waveform of the new device.

[0170] In some embodiments, the first determination module includes:

[0171] The conversion unit is configured to convert the first current time-domain waveform into a first frequency-domain waveform by using the fast Fourier transform algorithm;

[0172] An extraction unit, configured to extract the first harmonic feature of the first frequency-domain waveform based on the frequency-domain signal amplitude spectrum formula.

[0173] In some embodiments, the updating device 400 of the current fingerprint feature library further includes:

[0174] A third acquisition module, configured to acquire a neural network model sent by a server.

[0175] A storage module, configured to store the neural network model, where a loss function of the neural network model is a triplet loss function.

[0176] In some embodiments, the updating device 400 of the current fingerprint feature library further includes:

[0177] A sending module, configured to send the updated current fingerprint feature library to a server, so that the server sends the updated current fingerprint feature library to other edge devices.

[0178] In some embodiments, the updating device 400 of the current fingerprint feature library further includes:

[0179] A fourth acquisition module, configured to acquire a third current time-domain waveform of a device to be recognized.

[0180] A conversion module, configured to convert the third current time-domain waveform into a second frequency-domain waveform.

[0181] A third determination module, configured to determine a second harmonic feature based on the second frequency-domain waveform, and output the second harmonic feature to a pre-established neural network model to determine a second current fingerprint feature of the device to be recognized.

[0182] An identification module, configured to determine a device model of the device to be recognized based on the second current fingerprint feature and the current fingerprint feature library.

[0183] In addition, Figure 4 The updating device of the current fingerprint feature library shown may be a software unit, a hardware unit, or a unit combining software and hardware built into an existing electronic device, may also be integrated into the electronic device as an independent pendant, or may exist as an independent terminal device.

[0184] It should be noted that for the information interaction, execution process, etc. between the above-mentioned device / unit, since it is based on the same concept as the method embodiment of the present application, its specific functions and the technical effects brought can be specifically referred to in the method embodiment part, and will not be elaborated here.

[0185] Those skilled in the art can clearly understand that, for the convenience and conciseness of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated here.

[0186] Figure 5 The following is a schematic structural diagram of the electronic device provided by the embodiment of the present application. As Figure 5 shown, the electronic device 3 in this embodiment may include: at least one processor 30 ( Figure 5 only one processor 30 is shown in the figure), a memory 31, and a computer program 32 stored in the memory 31 and executable on at least one processor 30. When the processor 30 executes the computer program 32, it implements the steps in any of the foregoing method embodiments, or when the processor 30 executes the computer program 32, it implements the functions of each module / unit in each of the foregoing device embodiments.

[0187] Exemplarily, the computer program 32 can be divided into one or more modules / units. One or more modules / units are stored in the memory 31 and executed by the processor 30 to complete this application. One or more modules / units can be a series of computer program 32 instruction segments capable of completing specific functions, and these instruction segments are used to describe the execution process of the computer program 32 in the electronic device 3.

[0188] The embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program 32, and when the computer program 32 is executed by the processor 30, it can implement the steps in each of the foregoing method embodiments.

[0189] The embodiment of the present application provides a computer program product. When the computer program product runs on an electronic device, it enables the electronic device to execute and implement the steps in each of the foregoing method embodiments.

[0190] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-described embodiment methods of this application, a computer program 32 can be used to instruct relevant hardware to complete. The computer program 32 can be stored in a computer-readable storage medium. When the computer program 32 is executed by a processor 30, the steps of the above-described method embodiments can be implemented. Among them, the computer program 32 includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the terminal, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium. For example, USB flash drive, mobile hard disk, magnetic disk, or optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0191] In the above embodiments, the descriptions of each embodiment have their own focuses. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0192] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0193] In the embodiments provided in this application, it should be understood that the disclosed device / network device and method can be implemented in other ways. For example, the device / network device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in an electrical, mechanical, or other forms.

[0194] The unit described as a separation component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0195] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

[0196] In each embodiment of the present application, the relevant user personal information that may be involved is strictly in accordance with the requirements of laws and regulations, following the principles of legality, legitimacy, and necessity, and for reasonable purposes based on business scenarios, to process the personal information actively provided by the user during the use of the product / service or generated due to the use of the product / service, as well as the personal information obtained with the user's authorization.

[0197] The user personal information processed by the applicant will vary depending on the specific product / service scenario, and it is subject to the specific scenario of the user's use of the product / service. It may involve the user's account information, device information, driving information, vehicle information, or other relevant information. The applicant will treat the user's personal information and its processing with a high degree of diligence.

[0198] The applicant attaches great importance to the security of user personal information and has taken security protection measures that meet industry standards and are reasonable and feasible to protect the user's information and prevent personal information from being accessed, publicly disclosed, used, modified, damaged, or lost without authorization.

Claims

1. A method for updating a current fingerprint feature library, characterized in that: Applied to edge devices, including; When the edge device is connected to a new device for the first time, obtaining a device model and a working status of the new device; When the working state is that the new device is working, obtaining a first current time domain waveform of the new device; determining a first harmonic characteristic based on the first current time domain waveform; Outputting the first harmonic feature to a pre-established neural network model to determine a first current fingerprint feature of the new device; A correspondence between the first current fingerprint feature and the device model of the new device is established, and a current fingerprint feature library is updated based on the correspondence.

2. The method according to claim 1, characterized in that The obtaining of a first current time domain waveform of the new device includes: Acquiring a current second current time domain waveform of a device, wherein the device at least includes: the new device; In the case where there are multiple devices, an independent component analysis method is used to separate the second current time domain waveform to obtain a separated current time domain waveform; A first current time-domain waveform of the new device is determined based on the separated current time-domain waveform.

3. The method according to claim 2, characterized in that The determining of a first current time-domain waveform of the new device based on the separated current time-domain waveform comprises: Obtain a current time domain waveform corresponding to a pre-stored device; Matching the pre-stored current time domain waveform corresponding to the device with each of the separated current time domain waveforms, and determining the unmatched separated current time domain waveform; The unmatched separated current time-domain waveform is determined as the first current time-domain waveform of the new device.

4. The method according to claim 1, characterized in that: The determining of a first harmonic characteristic based on the first current time domain waveform comprises: Converting the first current time domain waveform into a first frequency domain waveform using a fast Fourier transform algorithm; A first harmonic feature of the first frequency domain waveform is extracted based on a frequency domain signal amplitude spectrum formula.

5. The method according to claim 1, characterized in that The method further comprises: Get the neural network model sent by the server; The neural network model is stored, wherein the loss function of the neural network model is a triple loss function.

6. The method according to claim 1, characterized in that The method further comprises: The updated current fingerprint feature library is sent to the server, so that the server sends the updated current fingerprint feature library to other edge devices.

7. The method according to claim 1, characterized in that The method further comprises: Acquire a third current time domain waveform of the device to be identified; Converting the third current time domain waveform into a second frequency domain waveform; Determine a second harmonic feature based on the second frequency domain waveform, and output the second harmonic feature to a pre-established neural network model to determine a second current fingerprint feature of the device to be identified; The device model of the device to be identified is determined based on the second current fingerprint feature and the current fingerprint feature library.

8. A device for updating a current fingerprint feature library, characterized in that: include: A first acquisition module is used to acquire a device model and a working status of a new device when the edge device is connected to the new device for the first time; A second acquisition module is used to acquire a first current time domain waveform of the new device when the working state is that the new device is working; A first determining module, configured to determine a first harmonic feature based on the first current time domain waveform; A second determination module is used to output the first harmonic feature to a pre-established neural network model to determine a first current fingerprint feature of the new device; The updating module is used to establish a corresponding relationship between the first current fingerprint feature and the device model of the new device, and update the current fingerprint feature library based on the corresponding relationship.

9. An electronic device, characterized in that: include: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images