Application method and system of intelligent electroscope in marketing operation

Abstract

The invention discloses an application method and system of an intelligent electroscope in marketing operation, and the system employs a non-contact electric field sensing module to detect the power-on state of an electric power line, avoids manual contact measurement, reduces the risk of electric shock of personnel, carries out the filtering and feature extraction (time domain and frequency domain features) of an electric field signal through a data processing unit, and improves the detection precision. A machine learning model (such as SVM and DNN) is combined to train historical data, real electrified signals and interference signals can be effectively distinguished, and detection errors are reduced; electricity testing data remote transmission is achieved by means of a wireless communication module, task issuing, automatic result uploading and abnormal alarm are completed in combination with a marketing operation system, manual recording and feedback are not needed, the problems that remote confirmation is difficult and information transmission lags behind in a traditional mode are solved, and intelligence and high efficiency of electricity marketing operation are improved; the positioning module records the geographic position of the electricity testing point and synchronizes the geographic position to the marketing operation system, thereby facilitating operation flow tracing and task overall scheduling, and optimizing the marketing operation flow.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric power safety detection, and particularly relates to an application method and system of an intelligent electric detector in marketing operation. BACKGROUND

[0002] In the process of electric power marketing operation, the staff often needs to accurately detect the power-on state of the line in the scenes of new installation, capacity increase, fault maintenance, metering device verification, etc. of the user power line, and needs to confirm whether the original line is powered off before performing wiring operation; when handling the power failure of user repair, it is necessary to first determine whether the fault line is live to develop a safe repair plan.

[0003] However, the electric detectors widely used in the industry at present are mostly traditional handheld devices, and their core detection method relies on the staff to directly contact the conductive part of the power line or equipment to complete the measurement. The contact operation requires the staff to approach the line at close range, especially in the scene of 10kV and above high-voltage user line. Once the insulation performance of the device decreases or the operation is wrong, it is easy to cause electric shock risk, which directly threatens the safety of the staff. In addition, in the actual scene of electric power marketing operation, the traditional electric detection method cannot meet the needs of remote and efficient operation. For the user lines distributed in remote mountainous areas and suburban areas, the staff needs to carry the device to the site for a long distance to complete the electric detection, which is time-consuming and laborious. For the line state investigation task of batch users, the traditional method needs to detect on site for each household, and it is difficult to realize the synchronous confirmation of multiple line states. Moreover, the detection results need to be fed back to the marketing operation system manually, and the information transmission is lagging, which makes it impossible for the background to master the line states in real time, affects the overall scheduling of operation tasks and the response speed of user service, and reduces the efficiency of electric power marketing operation as a whole. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides an application method and system of an intelligent electric detector in marketing operation to solve the problem that the existing electric detectors are mostly handheld devices and rely on manual contact measurement, which is inconvenient to operate and has high personnel safety risk. At the same time, the traditional electric detection method cannot efficiently complete the remote power state confirmation of user lines, which affects the efficiency of electric power marketing operation.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] The electric field signal is collected to generate time series data;

[0008] The time series data is filtered to convert the time series data into a direct current signal;

[0009] The pure electric field signal time series data is obtained by subtracting the interference signal of the time series data;

[0010] The necessary signal of the time series data is amplified to enhance the effective electric field signal time series data;

[0011] The electrification condition of the circuit line is judged by feature extraction and classification of the time series data;

[0012] The judgment result is sent to a remote terminal to trigger an audible and light alarm or push an alarm information to a remote terminal, and the geographic position of the point of the electric test is recorded and synchronized to a marketing operation system.

[0013] As a preferred scheme of the application method of the intelligent electric tester in the marketing operation, the time series data is generated by collecting electric field signals, including:

[0014] The electric field signals around the target line are collected by detecting the target power line to generate time series data.

[0015] As a preferred scheme of the application method of the intelligent electric tester in the marketing operation, the time series data is converted into a direct current signal by filtering the time series data, including:

[0016] The high-frequency noise interference and the periodic alternating component of the electric field signal are filtered out by filtering the time series data.

[0017] The dynamic time series data fluctuating with time is converted into a direct current signal reflecting the average electric field strength of the target line.

[0018] As a preferred scheme of the application method of the intelligent electric tester in the marketing operation, the pure electric field signal time series data is obtained by subtracting the interference signal of the time series data, including:

[0019] The pure electric field signal time series data of the electrification characteristics of the target line is obtained by constructing an interference model based on adjacent line structures to accurately subtract the interference components irrelevant to the target line from the signal.

[0020] As a preferred scheme of the application method of the intelligent electric tester in the marketing operation, the necessary signal of the time series data is amplified to enhance the effective electric field signal time series data, including:

[0021] The gain of the characteristic frequency of the effective signal is adjusted by amplifying the necessary signal in the time series data to enhance the amplitude and fluctuation characteristics, and highlight the time domain characteristics and frequency domain characteristics in the signal.

[0022] As a preferred scheme of the application method of the intelligent electroscope in marketing operation, wherein: the electrification condition of the circuit line is judged by feature extraction and classification on time series data, including:

[0023] The time domain features are obtained by feature extraction on the enhanced time series data, and the frequency domain features are obtained by Fourier transform;

[0024] The extracted features are input into the learning model for classification to determine the electrification condition of the target power line.

[0025] As a preferred scheme of the application method of the intelligent electroscope in marketing operation, wherein: the judgment result is sent to the remote terminal, triggering the sound and light alarm or the remote push alarm information, recording the geographic position of the electrification point, and synchronizing to the marketing operation system, including:

[0026] The judgment result is electrification or abnormal power state, by sending the electrification condition judgment result to the remote terminal or cloud platform, triggering the alarm module to sound and light alarm, and pushing the alarm information to the remote terminal;

[0027] By recording the geographic position information of the electrification point, and integrating the geographic position information, the geographic position information is synchronized to the remote terminal.

[0028] In a second aspect, the application provides an application system of an intelligent electroscope in marketing operation, comprising: a non-contact electric field sensing module for detecting the electric field intensity around the power line and outputting an electric signal;

[0029] A wireless communication module for data interaction with a remote terminal or a cloud platform;

[0030] A data processing unit connected to the electric field sensing module and the wireless communication module, for feature extraction on the electric signal, and judgment on the line electrification state based on a machine learning model;

[0031] An alarm module triggered by the output result of the data processing unit;

[0032] A positioning module for recording the geographic position of the electrification point and synchronizing to the marketing operation system.

[0033] In a third aspect, the application provides an electronic device, comprising:

[0034] A memory and a processor;

[0035] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions, which realizes the steps of the application method of the intelligent electroscope in marketing operation when the computer executable instructions are executed by the processor.

[0036] In a fourth aspect, the present application provides a computer readable storage medium storing computer executable instructions, which, when executed by a processor, implement the steps of the application method of the intelligent electricity tester in marketing operation.

[0037] Compared with the prior art, the present application has the following beneficial effects: the present application uses a non-contact electric field sensing module to detect the power line energized state, avoids manual contact measurement, reduces the risk of electric shock, filters the electric field signal through a data processing unit, extracts features (time domain and frequency domain features), and combines a machine learning model (such as SVM and DNN) to train historical data, which can effectively distinguish between real live signals and interference signals and reduce detection errors; the wireless communication module is used to realize remote transmission of electricity testing data, and the marketing operation system is combined to complete task issuing, result automatic uploading and abnormal alarm, without the need for manual recording and feedback, solving the problems of remote confirmation difficulty and information transmission lag in the traditional way, and improving the intelligence and efficiency of power marketing operation; the positioning module is used to record the geographic location of the electricity testing point and synchronize it to the marketing operation system, which is convenient for operation process tracing and task overall scheduling, and optimizes the marketing operation process. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of these drawings.

[0039] Figure 1 The overall flowchart of the application method of the intelligent electricity tester in marketing operation of an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings in the specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0041] Embodiment 1, refer to Figure 1 For an embodiment of the present application, an application method of an intelligent electricity tester in marketing operation is provided, which comprises:

[0042] S100: generating time series data by collecting electric field signals;

[0043] S200: converting the time series data into a direct current signal by filtering the time series data;

[0044] S300: obtaining pure electric field signal time series data by subtracting the interference signal of the time series data;

[0045] S400: amplifying the necessary signal of the time series data to enhance the effective electric field signal time series data;

[0046] S500: judging the electrification condition of the circuit line by feature extraction and classification of the time series data;

[0047] S600: sending the judgment result to a remote terminal, triggering an audible and light alarm or remotely pushing an alarm information, recording the geographic position of the electric testing point, and synchronizing to a marketing operation system.

[0048] It should be noted that the electric tester used in power marketing operation is mostly a handheld device, which relies on manual contact measurement and has three problems: first, the detection error is large, and the shaking of manual operation, the deviation of contact angle, etc. can easily lead to inaccurate data; second, the operation is inconvenient, and the results need to be read and recorded manually, which increases the labor intensity and the risk of recording errors; third, the personnel safety risk is high, and close contact with the line, especially high-voltage line, can easily cause electric shock accidents due to equipment insulation problems or operation errors. In addition, the traditional electric testing method cannot efficiently complete remote power state confirmation, and the line detection of users in remote areas requires long-distance travel of the staff, which is time-consuming for batch investigation and information transmission lags, seriously affecting the operation efficiency.

[0049] Therefore, in view of the above-mentioned operation monitoring and health prediction problems, through the steps of S100-S600, the electric field signal is collected by the non-contact electric field sensor to generate time series data; the detection accuracy is improved and the error is reduced through filtering and interference elimination of the data processing unit; the remote task issuing and automatic result uploading are realized by combining the wireless communication module, the problem of remote confirmation is solved, the manual recording error is reduced, and the operation scheduling and process tracing are optimized.

[0050] Embodiment 2, refer to Figure 1 For an embodiment of the present application, based on the above-mentioned embodiment, an application method of an intelligent electric tester in marketing operation is provided.

[0051] In the present application embodiment, in step S100, the target power line is detected by the electric field sensor, the electric field signal around the target line is collected, and time series data is generated.

[0052] Suppose the intensity of the electric field signal E(t) at time t is a continuous time series, and the signal is the output of the electric field sensor, and its expression is:

[0053] E(t) = Asin(2πft + φ) + ε(t)

[0054] where A is the amplitude of the electric field, f is the frequency of the electric field, φ is the phase, and ε(t) is the noise or interference signal. In addition, environmental factors such as temperature T(t) and humidity H(t) are also collected simultaneously, and their expressions are:

[0055] T(t) = T0 + δT(t), H(t) = H0 + δH(t)

[0056] where T0 and H0 are the reference temperature and humidity of the environment, and δT(t) and δH(t) are their changes over time. These real-time data are transmitted to the data processing unit.

[0057] In an alternative embodiment, the time series data in step S100 can also be detected by a capacitive coupling probe to detect the charge or voltage change induced by the electric field on the probe surface, and the time series data is collected, and its expression is:

[0058]

[0059] where ∈0: vacuum permittivity; ∈ r : relative permittivity; A: effective area of the probe; C f : feedback capacitance.

[0060] In another alternative embodiment, the time series data in step S100 can also be collected by a rotating electric field meter, which converts the direct current electric field into an alternating current signal by periodically shielding the electric field with rotating shielding blades.

[0061] where the modulation frequency is related to the rotation speed, and its expression is:

[0062]

[0063] where N: number of blades, ω: angular velocity of the blade (rad / s).

[0064] The amplitude-modulated signal output by the sensing electrode is:

[0065] V out (t) = k·E0·sin(2πf mod t)

[0066] where k: sensor sensitivity (V / (V / m)), E0: static electric field strength.

[0067] In the embodiments of the present application, step S200 converts the time series data into a direct current signal by filtering the time series data, including the following steps A1-A2:

[0068] A1: filtering the time series data to filter out the high-frequency noise interference and the periodic alternating components of the electric field signal;

[0069] A2: converting the dynamic time series data fluctuating over time into a direct current signal reflecting the average electric field strength of the target line.

[0070] In the embodiment of the present application, the interference signal of the time series data is subtracted by the subtracter in step S300 to obtain the pure electric field signal time series data. By establishing an interference model based on adjacent lines, the interference components irrelevant to the target line are accurately subtracted from the signal to obtain the pure electric field signal time series data of the charging characteristics of the target line.

[0071] In an alternative embodiment, the interference signal of the time series data can also be subtracted in step S300 by performing frequency domain feature extraction on the electric field signal, and using the difference in frequency between the electric field signals of the adjacent line and the target line. The interference can be removed by band-pass filtering.

[0072] The original electric field time series data of the target line signal and the adjacent line interference is E 原始 , which is expressed as:

[0073] E 原始 (t) = E 目标 (t) + E 干扰 (t) + ∈(t)

[0074] E 目标 (t) = Asin(2πf0t + φ)

[0075] E 干扰 (t) = Bsin(2πf1t + θ)

[0076] where E 目标 (t) is the effective signal of the target line, f0 is the characteristic frequency of the target line, E 干扰 (t) is the interference signal of the adjacent line, f1 is the characteristic frequency of the adjacent line, and ∈(t) is the noise.

[0077] The data processing unit performs Fourier transform on E 原始 (t) to obtain a frequency domain signal, which is expressed as:

[0078] E(f) = ∫E 原始 (t)e -i2πft dt

[0079] The frequency spectrum components corresponding to the target frequency f0 and the interference frequency f1 are separated, and the frequency domain signal is inversely Fourier transformed to obtain pure time series data containing only the target line signal.

[0080] In another alternative embodiment, the interference signal of the time series data is subtracted in step S300, which can also be achieved by dynamically adjusting the filtering parameters in combination with the environmental parameters to suppress the interference.

[0081] The environmental parameter-interference strength correlation model is established based on the time series data, which is expressed as:

[0082] E 下抗 (t) = k1 · δT(t) + k2 · δH(t) + C

[0083] wherein k1 and k2 are coefficients, and C is a constant.

[0084] According to the real-time environmental parameters δT(t) and δH(t), the real-time interference strength E(t) is calculated by the above model, and the interference signal is removed from the original signal, which is expressed as: 干扰

[0085] E 纯净 (t) = E 原始 (t) - E 干扰 (t) 环境计算

[0086] In the embodiment of the present application, the necessary signal in the time series data is amplified in step S400 by the amplifier, the gain of the characteristic frequency of the effective signal is adjusted, the amplitude and fluctuation characteristics are enhanced, and the time domain and frequency domain characteristics of the signal are highlighted.

[0087] In an alternative embodiment, the necessary signal in the time series data is amplified in step S400, which can be achieved by dynamically adjusting the gain coefficient through adaptive gain control, so that the weak signal is amplified and the strong signal gain is reduced, avoiding signal saturation while enhancing the relative strength of the effective signal, thereby highlighting the time domain fluctuation characteristics and frequency domain characteristics.

[0088] The instantaneous power of the real-time signal is calculated, the instantaneous power of the original time series data E(t) is calculated, the signal strength is reflected, and the instantaneous power is expressed as:

[0089] P(t) = |E(t)| 2

[0090] The target power threshold P0 is set, and the gain coefficient G(t) is dynamically adjusted, which is expressed as:

[0091]

[0092] wherein ∈ is a minimum value, avoiding the denominator P(t) < 0; when P(t) < P0, G(t) > 1, the signal is amplified; when P(t) ≥ P0, G(t) ≤ 1, to prevent signal overload.

[0093] ​The necessary signal is amplified, and the amplified signal is expressed as:

[0094] E 放大 (t) = G(t) · E 目标 (t)

[0095] The amplitude A' = G(t), A is dynamically adjusted with the gain, the instantaneous change rate in the time domain is enhanced, and the amplitude of the characteristic frequency f0 in the frequency domain is more prominent after Fourier transform. The instantaneous change rate is expressed as:

[0096]

[0097] In another optional embodiment, the necessary signal in the time series data in step S400 is amplified, which can also focus on the local characteristics of the signal in the time-frequency domain through wavelet transform. By amplifying the wavelet coefficients in the frequency band of the necessary signal, the time domain fluctuations and frequency domain characteristics of the frequency band are highlighted, and the interference of other frequency bands is suppressed.

[0098] The original time series data E(t) is wavelet transformed to obtain wavelet coefficients W j , k, where j is the scale, k is the time index, the characteristic frequency f0 of the necessary signal is determined, the wavelet coefficients W j0 , k of the scale j0 are amplified, and the other scale coefficients remain unchanged, which is expressed as:

[0099]

[0100] Wherein, k 放大 > 1 is the amplification coefficient.

[0101] The amplified coefficients and other scale coefficients are inverse wavelet transformed to obtain the amplified signal E 放大 (t). The signal is enhanced in the time domain with respect to the instantaneous fluctuation of f0; in the frequency domain, the spectral peak corresponding to f0 is more prominent through Fourier transform.

[0102] In the embodiments of the present application, the time series data is extracted and classified in step S500 to determine the live condition of the circuit line, including the following steps B1-B2.

[0103] B1: The enhanced time series data is extracted to obtain time domain features, and frequency domain features are obtained through Fourier transform;

[0104] B2: The extracted features are input into a learning model for classification to determine the live condition of the target power line.

[0105] Wherein, the time domain feature is expressed as:

[0106]

[0107] where N is the total number of signal samples, E(t i ) is the electric field signal at the i-th time point.

[0108] The degree of change in the electric field signal is reflected by the variance, which is expressed as:

[0109]

[0110] At the same time, the rate of change of the electric field signal at a certain time is used to capture the rapid fluctuations of the signal, which is expressed as

[0111] The time-domain signal is converted to the frequency-domain signal, which is expressed as:

[0112]

[0113] where E(f) is the frequency-domain signal, f is the frequency, and E(t) is the time-domain signal. Fourier transform can help us identify the frequency characteristics of the electric field signal, and further identify whether it is an interference signal.

[0114] Machine learning algorithms such as support vector machines (SVM) or deep neural networks (DNN) are used to classify and learn the electric field signal. The model will be trained through historical data to learn how to distinguish between normal charged signals and interference signals.

[0115] Support vector machines (SVM) is a supervised learning algorithm for classification, which finds an optimal hyperplane (decision boundary) to distinguish between different classes of signals. Assuming there are two classes of signals (charged and interference signals), SVM finds a hyperplane w·b = 0 that maximizes the separation between the two classes, which is expressed as:

[0116]

[0117] where w is the normal vector of the hyperplane, x i is the sample feature vector, and y i is the class of the sample.

[0118] Deep neural networks (DNN) are a type of multi-layer neural network that automatically learns high-order features of signals through multiple hidden layers. Assuming there are input layers, multiple hidden layers, and output layers, the network output can be represented as:

[0119] y = f(WL·f(WL-1……f(W1·x))

[0120] where x is the input feature vector, Wi is the weight matrix of the i-th layer, and f(x) is the activation function.

[0121] In an alternative embodiment, the amplitude feature of the time series data is calculated in step S500, and the line is directly determined to be live or not according to a set amplitude threshold.

[0122] The peak amplitude of the original electric field signal time series E(t) is calculated as:

[0123] A peak = max |E(t)|

[0124] A live threshold T h is set: when A peak > T h , the line is determined to be live; otherwise, it is determined to be not live.

[0125] In another alternative embodiment, the live condition is determined by detecting whether the characteristic frequency exists in the signal in step S500.

[0126] The electric field signal of the live power line has a fixed characteristic frequency, while the interference signal in the not live state usually has no such frequency component.

[0127] The standard characteristic frequency signal is defined: let the characteristic frequency of the target line be f0, and the standard reference signal be:

[0128] S(t) = sin(2πf0t)

[0129] The correlation coefficient of the original signal and the standard signal is calculated, and the original electric field signal E(t) is determined to contain the f0 component through correlation analysis. The correlation coefficient formula is:

[0130]

[0131] where T is the sampling time window, and the value range of R is [-1, 1]. The closer to 1, the higher the matching degree of the signal and f0.

[0132] A correlation threshold R h is set: when R > R h , it is indicated that E(t) contains a significant f0 frequency component, and the line is determined to be live; otherwise, it is determined to be not live.

[0133] In the embodiments of the present application, the judgment result is sent to the remote terminal in step S600, triggering the audible and light alarm or remotely pushing the alarm information, recording the geographic position of the live line detection point, and synchronizing to the marketing operation system.

[0134] LoRa or NB-IoT transmits the judgment result to the remote terminal, and the real-time acquired electric field signal is classified as "live signal" or "interference signal". When the live signal is detected, the microprocessor sends a control signal to trigger the alarm of the buzzer and the display screen, prompting the operator to pay attention to the live line.

[0135] The intelligent electricity tester is connected with the marketing operation system through the wireless communication module to realize functions such as electricity testing task management, result automatic uploading and abnormal situation alarm. After the staff complete the electricity testing task, the device automatically generates a detection report and uploads it to the background system, avoiding manual recording errors.

[0136] In summary, the application detects the target line through the non-contact electric field sensing module, acquires the time series data of the electric field signal (including the target line alternating current electric field signal and noise and interference signal) in real time, synchronously acquires environmental data such as temperature and humidity, the data processing unit filters the acquired time series data, removes high-frequency noise and periodic alternating components, and converts them into direct current signals reflecting the average electric field strength; further reduces the interference signals of adjacent lines to obtain pure electric field signal time series data; amplifies the necessary signals to enhance the time domain and frequency domain characteristics; extracts the above characteristics, inputs the machine learning model trained by historical data for classification, and judges whether the line is live.

[0137] Embodiment 3, the above is a schematic scheme of an application method and system of an intelligent electricity tester in marketing operation. It should be noted that the technical scheme of the high-temperature pipeline health online monitoring system belongs to the same concept as the technical scheme of the high-temperature pipeline health online monitoring method described above. The technical scheme of the high-temperature pipeline health online monitoring system in this embodiment is not described in detail, and the description of the technical scheme of the high-temperature pipeline health online monitoring method can be referred to.

[0138] The embodiment also provides a high-temperature pipeline health online monitoring system, comprising:

[0139] An acquisition module is configured to acquire pipeline parameters and construct a pipeline model;

[0140] A non-contact electric field sensing module is configured to detect the electric field strength around the power line and output an electric signal;

[0141] A wireless communication module is configured to interact with a remote terminal or a cloud platform;

[0142] A data processing unit is connected to the electric field sensing module and the wireless communication module, and is configured to extract features of the electric signal and judge the live state of the line based on a machine learning model;

[0143] An alarm module is configured to trigger an alarm according to the output result of the data processing unit;

[0144] A positioning module is configured to record the geographic position of the electricity testing point and synchronize to the marketing operation system.

[0145] The embodiment also provides an electronic device suitable for application of the smart electricity tester in the marketing operation, which comprises a memory and a processor.

[0146] The embodiment also provides a storage medium having a computer program stored thereon, and the computer program is executed by the processor to implement the method for applying the smart electricity tester in the marketing operation.

[0147] The storage medium proposed in the embodiment and the method for applying the smart electricity tester in the marketing operation proposed in the above embodiment belong to the same inventive concept, and the technical details not described in the embodiment can be referred to the above embodiment, and the embodiment and the above embodiment have the same beneficial effects.

[0148] From the above description about the embodiments, those skilled in the art can clearly understand that the present application can be realized by means of software and necessary universal hardware, and of course can also be realized by hardware. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, and the computer software product can be stored in a computer readable storage medium, such as a floppy disk, a ROM, a RAM, a FLASH, a hard disk or an optical disk, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute the methods of various embodiments of the present application.

[0149] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application but not limit the present application, and although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A method for applying an intelligent electroscope in marketing operations, characterized in that, include: Time series data is generated by collecting electric field signals; By filtering the time series data, the time series data is converted into a DC signal; By subtracting interference signals from the time series data, we obtain pure electric field signal time series data; Amplify the necessary signals of the time series data to enhance the effective electric field signal time series data; By extracting and classifying features from time series data, the electrical condition of circuit lines can be determined. The judgment result is sent to the remote terminal, triggering an audible and visual alarm or remotely pushing alarm information, recording the geographical location of the voltage testing point, and synchronizing it to the marketing operation system.

2. The method for applying the intelligent electroscope in marketing operations as described in claim 1, characterized in that, Time-series data is generated by acquiring electric field signals, including: By detecting the target power line, the electric field signal around the target line is collected, and time series data is generated.

3. The method for applying the intelligent electroscope in marketing operations as described in claim 2, characterized in that, By filtering the time series data, the time series data is converted into a DC signal, including: By filtering the time series data, high-frequency noise interference and periodic alternation components of the electric field signal are removed. The dynamic time series data that fluctuates over time is converted into a DC signal that reflects the average electric field strength of the target line.

4. The method for applying the intelligent electroscope in marketing operations as described in claim 3, characterized in that, By subtracting interference signals from the time series data, we obtain the pure electric field signal time series data, including: An interference model is constructed based on adjacent lines, and interference components unrelated to the target line are accurately subtracted from the signal to obtain time series data of the pure electric field signal with the charging characteristics of the target line.

5. The method for applying the intelligent electroscope in marketing operations as described in claim 4, characterized in that, Amplify the necessary signals from the time series data to enhance the effective electric field signal time series data, including: By amplifying the necessary signals in the time series data and adjusting the gain of the characteristic frequencies of the effective signals, the amplitude and fluctuation characteristics are enhanced, highlighting the time-domain and frequency-domain characteristics of the signals.

6. The method for applying the intelligent electroscope in marketing operations as described in claim 5, characterized in that, By extracting and classifying features from time-series data, the energization status of circuit lines can be determined, including: By extracting features from the enhanced time series data, time-domain features are obtained, and frequency-domain features are obtained through Fourier transform. The extracted features are input into the learning model for classification to determine the energization status of the target power line.

7. The method for applying the intelligent electroscope in marketing operations as described in claim 6, characterized in that, The judgment result is sent to a remote terminal, triggering an audible and visual alarm or remotely pushing alarm information. The geographical location of the voltage testing point is recorded and synchronized to the marketing operation system, including: If the judgment result is that the device is energized or has an abnormal power state, the judgment result of the energized status is sent to a remote terminal or cloud platform to trigger the alarm module to perform an audible and visual alarm, and at the same time push alarm information to the remote terminal. By recording the geographical location information of the voltage testing point and integrating the geographical location information, the geographical location information is synchronized to the remote terminal.

8. An application system for an intelligent electroscope in marketing operations, employing the method described in any one of claims 1-7, characterized in that, include: A non-contact electric field sensing module is used to detect the electric field strength around power lines and output an electrical signal; The wireless communication module is used for data interaction with remote terminals or cloud platforms; The data processing unit, connected to the electric field sensing module and the wireless communication module, is used to extract features from the electrical signal and determine the energized state of the line based on a machine learning model. The alarm module triggers an alarm based on the output of the data processing unit; The positioning module is used to record the geographical location of the testing point and synchronize it to the marketing operation system.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the application method of the intelligent electroscope in marketing operations according to any one of claims 1 to 7.

10. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the method for applying the intelligent electroscope in marketing operations as described in any one of claims 1 to 7.

Images