Training method and detection method of electric vehicle charging detection model, equipment and medium

Abstract

The invention discloses a training method, a detection method, equipment and a medium for an electric vehicle charging detection model, and relates to the field of electric vehicle charging detection, and the training method comprises the steps: obtaining a plurality of first current data according to a preset sampling frequency and preset sampling time; wherein the first current data is current data corresponding to the power utilization object; obtaining a first higher harmonic characteristic according to the first current data, and establishing a data set according to the first higher harmonic characteristic; training a preset classification model according to the data set to obtain an electric bicycle charging detection model; wherein the electric bicycle charging detection model is used for detecting whether the electric bicycle charging behavior exists in the power utilization object within the corresponding preset sampling time. The charging behavior of the electric vehicle can be effectively detected, and potential safety hazards caused by illegal charging of the electric vehicle indoors are avoided.

Description

Technical Field

[0001] The present application relates to the field of electric vehicle detection, and in particular to a training method, detection method, equipment and medium for an electric vehicle charging detection model. Background Art

[0002] With the increasing global awareness of environmental protection and the pursuit of sustainable development, electric bicycles, as a green travel mode, can effectively reduce carbon emissions and air pollution, and are therefore favored by more and more consumers.

[0003] However, the popularity of electric bicycles also brings with it a series of safety risks. Because electric bicycles can cause fires due to battery overheating, short circuits, or other malfunctions, many local governments have already or are in the process of enacting regulations explicitly prohibiting the charging of electric bicycles indoors (particularly in residential spaces, including private charging in hallways and corridors).

[0004] At present, there is a lack of regulatory measures for indoor electric bicycle charging, which can easily lead to fire accidents. Summary of the Invention

[0005] The purpose of this application is to provide a training method, detection method, equipment and medium for an electric vehicle charging detection model, which can effectively detect the charging behavior of electric vehicles and avoid the safety hazards caused by illegal charging of electric vehicles indoors.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a method for training an electric vehicle charging detection model, comprising:

[0008] Acquire a plurality of first current data according to a preset sampling frequency and a preset sampling time; wherein the first current data is current data corresponding to the power consumption object;

[0009] Acquire a first high-order harmonic feature according to the first current data, and establish a data set according to the first high-order harmonic feature;

[0010] The preset classification model is trained according to the data set to obtain the electric bicycle charging detection model; wherein, the electric bicycle charging detection model is used to detect whether the power-consuming object has electric bicycle charging behavior within the corresponding preset sampling time.

[0011] Optionally, obtaining a first high-order harmonic feature according to the first current data specifically includes:

[0012] Performing fast Fourier transform processing on the first current data to obtain first frequency domain data;

[0013] The first high-order harmonic feature is obtained according to the absolute amplitude corresponding to the 2i-1th harmonic in the first frequency domain data; wherein i represents the i-th data in the first high-order harmonic feature, i={1,2,...n}.

[0014] Optionally, obtaining the first high-order harmonic feature according to the absolute amplitude corresponding to the 2i-1th harmonic in the first frequency domain data specifically includes:

[0015] For each i, obtaining a first relative amplitude corresponding to the 2i-1th harmonic in the first frequency domain data;

[0016] Obtaining an i-th first actual amplitude according to the i-th first relative amplitude;

[0017] The first high-order harmonic feature is obtained according to the vector composed of the first actual amplitudes.

[0018] Optionally, the data set includes multiple sub-data, each of the sub-data includes the first high-order harmonic feature and a label, and the label is used to indicate whether the power user corresponding to the first high-order harmonic feature has an electric bicycle charging behavior within a corresponding preset sampling time.

[0019] Optionally, the data set includes a training set and a test set, and the training of a preset classification model according to the data set to obtain the electric bicycle charging detection model includes:

[0020] Training the preset classification model according to the training set to obtain an initial detection model;

[0021] The initial detection model is verified and updated according to the test set until the accuracy of the initial detection model is not less than a preset ratio, and the initial detection model is used as the electric bicycle charging detection model.

[0022] In a second aspect, the present application provides an electric vehicle charging detection method, comprising:

[0023] Acquire second current data to be detected according to a preset sampling frequency and a preset sampling time;

[0024] acquiring a second high-order harmonic characteristic according to the second current data;

[0025] An electric vehicle charging detection is performed on the second high-order harmonic according to a pre-trained classification model to obtain a detection result; wherein, the pre-trained classification model is an electric bicycle charging detection model obtained according to the training method of the above-mentioned electric bicycle charging detection model, and the detection result is used to indicate whether the power user corresponding to the second current data has an electric bicycle charging behavior.

[0026] In a third aspect, the present application provides a training device for an electric vehicle charging detection model, comprising:

[0027] A first acquisition module is configured to acquire a plurality of first current data according to a preset sampling frequency and a preset sampling time; wherein the first current data is current data corresponding to the power consumption object;

[0028] a first feature module, configured to obtain a first high-order harmonic feature according to the first current data, and establish a data set according to the first high-order harmonic feature;

[0029] A training module is used to train a preset classification model according to the data set to obtain the electric bicycle charging detection model; wherein, the electric bicycle charging detection model is used to detect whether the power user has electric bicycle charging behavior within the corresponding preset sampling time.

[0030] In a fourth aspect, the present application provides an electric vehicle charging detection device, comprising:

[0031] A second acquisition module, configured to acquire second current data to be detected according to a preset sampling frequency and a preset sampling time;

[0032] A second feature module, configured to obtain a second high-order harmonic feature based on the second current data;

[0033] A detection module is used to perform electric vehicle charging detection on the second high-order harmonic according to a pre-trained classification model to obtain a detection result; wherein, the pre-trained classification model is an electric bicycle charging detection model obtained according to the training method of the above-mentioned electric bicycle charging detection model, and the detection result is used to indicate whether the power user corresponding to the second current data has electric bicycle charging behavior.

[0034] In a fifth aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the training method of the electric vehicle charging detection model or the steps of the electric vehicle charging detection method described above.

[0035] In a sixth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the training method of the electric vehicle charging detection model or the steps of the electric vehicle charging detection method described above.

[0036] In a seventh aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the training method of the electric vehicle charging detection model or the electric vehicle charging detection method described above.

[0037] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0038] The present application provides a training method, detection method, device, and medium for an electric vehicle charging detection model. The training method obtains an electric bicycle charging detection model by acquiring the first harmonic signature corresponding to the current data of the power user, and then training a preset classification model based on a data set established using the first harmonic signature. The first harmonic signature can effectively reflect the characteristics of the electric vehicle during charging, allowing electric vehicle charging to be distinguished from other loads to a certain extent. The electric bicycle charging detection model can detect whether the power user is charging an electric bicycle, providing an effective means for indoor monitoring of electric vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0040] Figure 1 This is a flow chart of a method for training an electric vehicle charging detection model in one embodiment of the present application;

[0041] Figure 2 for Figure 1 Detailed flow diagram of step 102;

[0042] Figure 3 for Figure 2 Detailed flow diagram of step 202;

[0043] Figure 4 A comparison chart of current frequency domain data corresponding to different power loads;

[0044] Figure 5 A flow chart of an electric vehicle charging detection method provided in one embodiment of the present application Figure 1 ;

[0045] Figure 6 A flow chart of an electric vehicle charging detection method provided in one embodiment of the present application Figure 2 ;

[0046] Figure 7 A schematic diagram of the functional modules of a training device for an electric vehicle charging detection model provided by another embodiment of the present application;

[0047] Figure 8A schematic diagram of the functional modules of an electric vehicle charging detection device provided in another embodiment of the present application;

[0048] Figure 9 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0050] The terms "first," "second," "third," "fourth," and so forth (if any) in the description and claims of the present invention and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or sequential sequence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the present invention described herein can, for example, be implemented in sequences other than those illustrated or described herein.

[0051] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0052] The training method of the electric vehicle charging detection model or the electric vehicle charging detection method provided in the embodiment of the present application can be applied to the application environment of indoor electric bicycle supervision. It can conduct real-time supervision of electricity users on a household basis, determine whether there is electric bicycle charging behavior in the user's home, and provide strong technical support for standardizing charging behavior and preventing fire accidents, thereby ensuring public safety and promoting the healthy development of the electric bicycle industry.

[0053] In an exemplary embodiment, Figure 1 As shown, a method for training an electric vehicle charging detection model is provided, comprising the following steps 101 to 103. In which:

[0054] Step 101: acquiring a plurality of first current data according to a preset sampling frequency and a preset sampling time; wherein the first current data is current data corresponding to an electric object;

[0055] Specifically, taking users as units, current data of different users in different power usage states are collected as first current data.

[0056] Specifically, the first current data is current data when at least one load is consuming electricity, and the electricity-consuming loads include one or more of an electric bicycle charger, a washing machine, a refrigerator, an induction cooker, a computer, a laptop computer, and the like.

[0057] Specifically, the current data I of the user's main line is collected through the mutual inductor, and the preset sampling frequency is f s , the unit is Hz, the preset sampling time is t, and the preset current scaling factor is λ.

[0058] Step 102: Acquire a first high-order harmonic feature according to the first current data, and establish a data set according to the first high-order harmonic feature.

[0059] Specifically, for each first current data, frequency domain analysis is performed to obtain the first high-order harmonic characteristics;

[0060] Specifically, the data set includes multiple sub-data, each sub-data includes a first high-order harmonic feature and a corresponding label, wherein the label is used to indicate whether the first high-order harmonic feature corresponds to an electric bicycle charging behavior in the corresponding preset sampling time.

[0061] For example, 0 or 1 is used as a label, 0 indicates that no electric vehicle is being charged, and 1 indicates that an electric vehicle is being charged.

[0062] Step 103 , training a preset classification model according to the data set to obtain an electric bicycle charging detection model; wherein the electric bicycle charging detection model is used to detect whether the electricity user has an electric bicycle charging behavior within a preset sampling time.

[0063] As a specific implementation, step 103 specifically includes:

[0064] Step 1031: The data set includes a training set and a test set. The preset classification model is trained according to the training set to obtain an initial detection model.

[0065] For example, the data is divided into a training set and a test set, where the training set accounts for 70% and the test set accounts for 30%;

[0066] Optionally, the preset classification model may be a classification model based on machine learning, such as a neural network model, a decision tree, a random forest model, or a support vector machine.

[0067] Step 1032 : Verify and update the initial detection model according to the test set until the accuracy of the initial detection model is not less than a preset ratio, and use the initial detection model as the electric bicycle charging detection model.

[0068] For example, a decision tree model is trained. After the training is completed, the test set data is input into the initial detection model to obtain output label data. The output label is compared with the test set label. If the accuracy is above 95%, the model training is successful, and the initial detection model is used as the electric bicycle charging detection model.

[0069] Correspondingly, if it is lower than 95%, the model can be optimized by adjusting the decision tree depth, pruning, etc., adjusting the model parameters, regenerating the test set and training set in proportion, repeating the training and verification until the accuracy is above 95%, and using this initial detection model as the electric bicycle charging detection model.

[0070] By implementing steps 101 to 103, the first harmonic signature effectively reflects the characteristics of electric vehicle charging, allowing it to be distinguished from other loads to a certain extent. Using the first harmonic signature as a dataset, a pre-set classification model is trained to effectively identify whether an electric bicycle is charging among electricity users, providing an effective means for indoor monitoring of electric vehicles.

[0071] In another exemplary embodiment of the present application, in order to more accurately detect the charging behavior of an electric bicycle, a method for obtaining first current data is provided. The first current data obtained according to this method can more clearly reflect the charging characteristics of the electric bicycle. Figure 2 As shown, the above step 102 is replaced by the following steps:

[0072] Step 201, performing fast Fourier transform processing on first current data to obtain first frequency domain data;

[0073] Specifically, the first current data I within the preset sampling time t is processed using the fast Fourier transform FFT. t Processing is performed to obtain the first frequency domain data I of the first current data f .

[0074] Furthermore, in order to reduce frequency leakage, the first current data is first windowed and then subjected to fast Fourier transform to obtain the first frequency domain data I f .

[0075] For example, a Hanning window is used to perform windowing to prevent frequency leakage. The calculation process of step 201 is as follows:

[0076] I f =FFT(Hanning·I t )

[0077] Step 202 : Obtain a first higher harmonic feature according to the absolute amplitude corresponding to the 2i-1th harmonic in the first frequency domain data; wherein, i represents the i-th data in the first higher harmonic feature, i={1, 2, ...n}.

[0078] Specifically, we analyze the current frequency domain data to obtain the current's higher harmonic characteristics. The main frequency of household AC current is 50Hz. When current passes through a rectifier, it generates current components with higher frequencies, such as 150Hz, 250Hz, and 350Hz. These high-frequency currents are called harmonics, and multiples of 50Hz are called harmonics.

[0079] Specifically, the absolute amplitude sequence corresponding to the odd-order harmonics from 1 to 2n-1 is obtained as the first high-order harmonic feature.

[0080] As a specific implementation method, Figure 3 , step 202 specifically includes:

[0081] Step 2021: for each i, obtain a first relative amplitude corresponding to the 2i-1th harmonic in the first frequency domain data;

[0082] Specifically, for each i, determine its corresponding frequency size as (2i-1)f s / N, in the first frequency domain data, (2i-1)f s The corresponding amplitude of the amplitude corresponding to / N is the first relative amplitude of the i-th data I fi , N is the current data I t length.

[0083] Step 2022: Obtain the i-th first actual amplitude according to the i-th first relative amplitude;

[0084] Specifically, according to the amplitude calculation formula, the i-th actual amplitude is obtained by the following formula:

[0085] x i =4|I fi | / λN

[0086] Step 2023: Acquire the first high-order harmonic feature according to the vector composed of the first actual amplitude.

[0087] Specifically, a vector obtained by sorting the first actual amplitude from small to large is used as the first high-order harmonic feature.

[0088] In one embodiment, n is an integer between 10 and 15.

[0089] In another embodiment, the sampling frequency is 50 Hz, the sampling time is 5 s, and n is 12. Then, the absolute amplitudes corresponding to 50 Hz, 150 Hz, ..., 1050 Hz, and 1150 Hz obtained according to the above steps are x1, x2, ..., x 11 ,x 12 , then the first harmonic characteristic composed of these absolute amplitudes is X=[x1 x2…x 11 x 12 ].

[0090] Further, Figure 4 The first current data sampled for different load devices are the current frequency domain data obtained according to the above steps, where (a), (b), (c) and (d) are the current frequency domain data corresponding to the electric bicycle, kettle, laptop computer and washing machine respectively. For the convenience of comparison, their amplitudes are normalized. Figure 4 Compared with other current frequency domain data, the odd harmonics of electric bicycles in Figure a have their own particularity. The first high-order harmonic features obtained according to the above steps 201-202 have obvious distinguishability for the power consumption behavior of electric bicycles and non-electric bicycles, and are insensitive to noise, outliers and input disturbances. The electric bicycle charging detection model obtained by training the preset classification model through the first high-order harmonic features can realize the detection of battery vehicle charging behavior and can effectively distinguish it from other electrical equipment, providing an effective means for indoor monitoring of electric vehicles.

[0091] Based on the same inventive concept, Figure 5 and Figure 6 As shown, the embodiment of the present application also provides an electric vehicle charging detection method, such as Figure 6 , the specific steps include:

[0092] Step 601, obtaining second current data to be detected according to a preset sampling frequency and a preset sampling time;

[0093] Specifically, the preset sampling frequency and the preset sampling time are the same as the preset values during model training, and the current data of the main line of the user to be tested is collected through the mutual inductor.

[0094] Step 602, obtaining a second high-order harmonic characteristic according to the second current data;

[0095] Specifically, the method for obtaining the second high-order harmonic characteristics in this step is similar to the above-mentioned method for obtaining the first high-order harmonic characteristics (steps 201 to 202), and will not be described in detail here.

[0096] Step 603 : Perform an electric vehicle charging detection on the second higher harmonic according to the pre-trained classification model to obtain a detection result, where the detection result is used to indicate whether the power user corresponding to the second current data has an electric bicycle charging behavior.

[0097] Specifically, the pre-trained classification model is an electric bicycle charging detection model obtained according to the training method of the above-mentioned electric vehicle charging detection model.

[0098] This application achieves efficient monitoring through current data analysis, eliminating the need for complex modules like power calculations, significantly reducing data acquisition costs and equipment complexity. Non-invasive testing can be performed simply by collecting current data through a transformer, ensuring safety and reliability while minimizing interference or damage to the circuit.

[0099] In terms of data analysis, this application combines machine learning technology, which can identify complex patterns in current signals more accurately and flexibly than traditional threshold judgment methods. By training the machine learning model, the system can automatically adapt to different power consumption environments and monitor the circuit status in real time with a response time of less than 10 seconds. This method of combining harmonic analysis and machine learning not only improves the accuracy of monitoring, but also enhances the real-time and adaptability of the system, providing strong technical support for the accurate monitoring of the charging status of electric bicycles, which can ensure public safety and promote the healthy development of the electric bicycle industry.

[0100] Based on the same inventive concept, embodiments of the present application also provide an electric vehicle charging detection model training device for implementing the aforementioned electric vehicle charging detection model training method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of the one or more electric vehicle charging detection model training device embodiments provided below can be found in the limitations of the electric vehicle charging detection model training method described above and will not be repeated here.

[0101] The present application also provides an application scenario, which applies the above-mentioned electric vehicle charging detection method.

[0102] Specifically: The electric vehicle charging detection method provided in this embodiment can be applied to indoor monitoring scenarios of electric vehicle charging behavior. It can perform real-time monitoring of the user to be tested according to the monitoring cycle. If it is determined that electric vehicle charging behavior exists, an alarm reminder can be sent to the monitoring terminal through wireless transmission equipment, thereby realizing real-time supervision of indoor charging behavior.

[0103] In an exemplary embodiment, Figure 7 A training device for an electric vehicle charging detection model is provided, comprising:

[0104] A first acquisition module is configured to acquire a plurality of first current data according to a preset sampling frequency and a preset sampling time; wherein the first current data is current data corresponding to the power consumption object;

[0105] A first feature module, configured to obtain a first high-order harmonic feature based on the first current data, and establish a data set based on the first high-order harmonic feature;

[0106] The training module is used to train the preset classification model according to the data set to obtain an electric bicycle charging detection model; wherein the electric bicycle charging detection model is used to detect whether the electricity user has electric bicycle charging behavior within the corresponding preset sampling time.

[0107] As an optional implementation manner, the first feature module is further configured to:

[0108] Performing fast Fourier transform processing on the first current data to obtain first frequency domain data;

[0109] The first high-order harmonic feature is obtained according to the absolute amplitude corresponding to the 2i-1th harmonic in the first frequency domain data; wherein i represents the i-th data in the first high-order harmonic feature, i={1,2,...n}.

[0110] As an optional implementation manner, the first feature module is further configured to:

[0111] For each i, obtain the first relative amplitude corresponding to the 2i-1th harmonic in the first frequency domain data;

[0112] Obtaining the i-th first actual amplitude according to the i-th first relative amplitude;

[0113] A first high-order harmonic feature is obtained according to a vector composed of the first actual amplitudes.

[0114] As an optional implementation, the data set includes multiple sub-data, each sub-data includes a first high-order harmonic feature and a label, and the label is used to indicate whether the electricity user corresponding to the first high-order harmonic feature has an electric bicycle charging behavior within the corresponding preset sampling time.

[0115] As an optional implementation, the training module is further configured to: train a preset classification model according to the training set to obtain an initial detection model;

[0116] The initial detection model is verified and updated according to the test set until the accuracy of the initial detection model is not less than the preset ratio, and the initial detection model is used as the electric bicycle charging detection model.

[0117] Based on the same inventive concept, the present application also provides an electric vehicle charging detection device for implementing the above-mentioned electric vehicle charging detection method. The solution provided by this device is similar to the solution described in the above-mentioned method. Therefore, the specific limitations of one or more electric vehicle charging detection device embodiments provided below can be found in the above-mentioned limitations of the electric vehicle charging detection method and will not be repeated here.

[0118] In an exemplary embodiment, Figure 8 Provided is an electric vehicle charging detection device, comprising:

[0119] A second acquisition module, configured to acquire second current data to be detected according to a preset sampling frequency and a preset sampling time;

[0120] A second feature module, configured to obtain a second high-order harmonic feature based on the second current data;

[0121] A detection module is used to perform electric vehicle charging detection on the second higher harmonic according to a pre-trained classification model to obtain a detection result; wherein the pre-trained classification model is an electric bicycle charging detection model obtained according to the training method of the above-mentioned electric bicycle charging detection model, and the detection result is used to indicate whether the power user corresponding to the second current data has electric bicycle charging behavior.

[0122] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device 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 computer device is used to store processing data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements the above-mentioned electric vehicle charging detection model training method or electric vehicle charging detection method.

[0123] Those skilled in the art will understand that Figure 9The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0124] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0125] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0126] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0127] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0128] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0129] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0130] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0131] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of this application. In summary, the content of this specification should not be construed as limiting this application.

Claims

1. A training method for an electric vehicle charging detection model, characterized in that: The training method of the electric bicycle charging detection model includes: Acquire a plurality of first current data according to a preset sampling frequency and a preset sampling time; wherein the first current data is current data corresponding to the power consumption object; Acquire a first high-order harmonic feature according to the first current data, and establish a data set according to the first high-order harmonic feature; The preset classification model is trained according to the data set to obtain the electric bicycle charging detection model; wherein, the electric bicycle charging detection model is used to detect whether the power-consuming object has electric bicycle charging behavior within the corresponding preset sampling time.

2. The training method of the electric bicycle charging detection model according to claim 1, characterized in that: The acquiring a first high-order harmonic characteristic according to the first current data includes: Performing fast Fourier transform processing on the first current data to obtain first frequency domain data; The first high-order harmonic feature is obtained according to the absolute amplitude corresponding to the 2i-1th harmonic in the first frequency domain data; wherein i represents the i-th data in the first high-order harmonic feature, i={1,2,...n}.

3. The training method of the electric bicycle charging detection model according to claim 2, characterized in that: The obtaining the first high-order harmonic feature according to the absolute amplitude corresponding to the 2i-1th harmonic in the first frequency domain data includes: For each i, obtaining a first relative amplitude corresponding to the 2i-1th harmonic in the first frequency domain data; Obtaining an i-th first actual amplitude according to the i-th first relative amplitude; The first high-order harmonic feature is obtained according to the vector composed of the first actual amplitudes.

4. The training method for the electric bicycle charging detection model according to claim 1, characterized in that: The data set includes multiple sub-data, each of which includes the first high-order harmonic feature and a label, and the label is used to indicate whether the power consumer corresponding to the first high-order harmonic feature has an electric bicycle charging behavior within a corresponding preset sampling time.

5. The training method for the electric bicycle charging detection model according to claim 1, characterized in that: The data set includes a training set and a test set, and the method of training a preset classification model according to the data set to obtain the electric bicycle charging detection model includes: Training the preset classification model according to the training set to obtain an initial detection model; The initial detection model is verified and updated according to the test set until the accuracy of the initial detection model is not less than a preset ratio, and the initial detection model is used as the electric bicycle charging detection model.

6. A method for detecting charging of an electric bicycle, characterized in that: The electric bicycle charging detection method comprises: Acquire second current data to be detected according to a preset sampling frequency and a preset sampling time; acquiring a second high-order harmonic characteristic according to the second current data; An electric vehicle charging detection is performed on the second high-order harmonic according to a pre-trained classification model to obtain a detection result; wherein, the pre-trained classification model is an electric bicycle charging detection model obtained according to the training method of the electric bicycle charging detection model according to any one of claims 1-5, and the detection result is used to indicate whether the power user corresponding to the second current data has an electric bicycle charging behavior.

7. A training device for an electric vehicle charging detection model, characterized in that: include: A first acquisition module is configured to acquire a plurality of first current data according to a preset sampling frequency and a preset sampling time; wherein the first current data is current data corresponding to the power consumption object; a first feature module, configured to obtain a first high-order harmonic feature according to the first current data, and establish a data set according to the first high-order harmonic feature; A training module is used to train a preset classification model according to the data set to obtain the electric bicycle charging detection model; wherein, the electric bicycle charging detection model is used to detect whether the power user has electric bicycle charging behavior within the corresponding preset sampling time.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and runnable on the processor, characterized in that the processor executes the computer program to implement the training method of the electric bicycle charging detection model described in any one of claims 1 to 5 or the steps of the electric bicycle charging detection method described in claim 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the training method of the electric bicycle charging detection model according to any one of claims 1 to 5 or the steps of the electric bicycle charging detection method according to claim 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the training method of the electric bicycle charging detection model according to any one of claims 1 to 5 or the steps of the electric bicycle charging detection method according to claim 6 are implemented.

Images