Electricity larceny prevention method and system based on intelligent electric meter

Abstract

The invention discloses an electricity larceny prevention method and system based on an intelligent ammeter, and the method comprises the steps: detecting whether an electricity larceny prevention analysis condition is satisfied or not according to the preset polling electricity larceny prevention detection time, the obtained state of a signal indicating lamp, a plurality of interval values, and a plurality of connection pressure values, the electricity larceny prevention analysis conditions comprise a first electricity larceny prevention analysis condition and a second electricity larceny prevention analysis condition; if the first electricity larceny prevention analysis condition is met, generating an electricity larceny prevention analysis result according to the collected electricity utilization information; if a second electricity larceny prevention analysis condition is met, the electricity utilization information, the collected position information and the environment information are uploaded to a cloud server, so that the cloud server performs electricity larceny prevention analysis through a hybrid model according to the electricity utilization information, the position information and the environment information to obtain an electricity larceny prevention analysis result, an electricity larceny prevention analysis result is issued to the intelligent electric meter; and carrying out grading alarm according to an electricity larceny prevention analysis result. According to the invention, the false alarm rate of electricity larceny prevention is reduced, and the accuracy of electricity larceny prevention is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of anti-stealing electricity, and particularly to an anti-stealing electricity method and system based on an intelligent electric meter. Background Art

[0002] With the continuous development of society and the progress of technology, electricity has become the basic energy source for modern social life and production. However, during the operation of the power system, it faces many challenges. Electricity theft not only causes economic losses to power enterprises, but also has a negative impact on the stable operation of the power system and the reasonable allocation of power resources. Therefore, how to effectively prevent electricity theft has become a key issue of concern to power enterprises and researchers.

[0003] Although existing anti-stealing electricity methods for intelligent electric meters have achieved physical protection and basic data monitoring, there are still the following problems: 1. Weak physical tampering protection: For example, only relying on mechanical locks, a single mechanical lock is easy to be cracked, and there is a lack of effective monitoring of high-tech electricity theft means (such as magnetic field interference, line tampering); 2. High false alarm rate: It is difficult to distinguish between maintenance operations and electricity theft behaviors, and manual verification is required; 3. Single data detection dimension, resulting in low accuracy of anti-stealing electricity. For example, only detecting current makes it difficult to identify electricity theft behaviors in complex electricity usage scenarios. Summary of the Invention

[0004] Embodiments of the present invention provide an anti-stealing electricity method and system based on an intelligent electric meter, aiming to solve the problem of low accuracy of existing anti-stealing electricity.

[0005] In a first aspect, the present invention provides an anti-stealing electricity method based on an intelligent electric meter. The intelligent electric meter includes a box door, and multiple groups of ultrasonic distance sensors are provided at the edge of the box door to collect the distances between the box door and the door frame to obtain multiple distance values. Multiple groups of pressure sensors are provided in the wiring terminal area inside the box door to collect the connection pressures of the wiring terminals to obtain multiple connection pressure values. The method includes: Detect whether the anti-stealing electricity analysis conditions are met according to the preset polling anti-stealing electricity detection time, the obtained signal indicator light state, the multiple distance values, and the multiple connection pressure values. Among them, the anti-stealing electricity analysis conditions include a first anti-stealing electricity analysis condition and a second anti-stealing electricity analysis condition; If the first anti-stealing electricity analysis condition is met, generate an anti-stealing electricity analysis result according to the collected electricity usage information; If the second anti-stealing electricity analysis condition is met, upload the electricity usage information, the collected location information, and the environmental information to the cloud server, so that the cloud server performs anti-stealing electricity analysis through a hybrid model according to the electricity usage information, the location information, and the environmental information to obtain the anti-stealing electricity analysis result, and send the anti-stealing electricity analysis result to the intelligent electric meter; Perform hierarchical alarming according to the anti-stealing electricity analysis result.

[0006] In a second aspect, the present invention further provides an anti-stealing electricity system based on a smart meter, including: A smart meter, which includes a box door. Multiple groups of ultrasonic distance sensors are provided at the edge of the box door to collect the distances between the box door and the door frame to obtain multiple distance values. Multiple groups of pressure sensors are provided in the wiring terminal area inside the box door to collect the connection pressures of the wiring terminals to obtain multiple connection pressure values. The smart meter further includes a detection module and a generation module. The detection module is used to detect whether the anti-stealing electricity analysis conditions are met according to the preset polling anti-stealing electricity detection time, the obtained signal indicator status, the multiple distance values, and the multiple connection pressure values. The generation module is used to generate an anti-stealing electricity analysis result according to the collected electricity consumption information; A cloud server, which includes an anti-stealing electricity analysis module and a sending module. The anti-stealing electricity analysis module is used to perform anti-stealing electricity analysis through a hybrid model according to the electricity consumption information uploaded by the smart meter, the collected location information, and the environmental information to obtain the anti-stealing electricity analysis result. The sending module is used to send the anti-stealing electricity analysis result to the smart meter; Wherein, the smart meter further includes an alarming module, and the alarming module is used to perform hierarchical alarming according to the anti-stealing electricity analysis result.

[0007] The present invention provides an anti-stealing electricity method and system based on an intelligent electric meter. The method includes: detecting whether anti-stealing electricity analysis conditions are met according to a preset polling anti-stealing electricity detection time, the obtained signal indicator status, a plurality of the spacing values, and a plurality of the connection pressure values, where the anti-stealing electricity analysis conditions include a first anti-stealing electricity analysis condition and a second anti-stealing electricity analysis condition; if the first anti-stealing electricity analysis condition is met, generating an anti-stealing electricity analysis result according to the collected electricity consumption information; if the second anti-stealing electricity analysis condition is met, uploading the electricity consumption information, the collected location information, and the environmental information to a cloud server, so that the cloud server performs anti-stealing electricity analysis through a hybrid model according to the electricity consumption information, the location information, and the environmental information to obtain the anti-stealing electricity analysis result, and sending the anti-stealing electricity analysis result to the intelligent electric meter; performing hierarchical alarm according to the anti-stealing electricity analysis result. This application first detects whether the anti-stealing electricity analysis conditions are met according to the preset polling anti-stealing electricity detection time, the signal indicator status, a plurality of spacing values, and a plurality of connection pressure values, and then when the first anti-stealing electricity analysis condition is met, generating an anti-stealing electricity analysis result according to the collected electricity consumption information; when the second anti-stealing electricity analysis condition is met, the cloud server performs anti-stealing electricity analysis through a hybrid model according to the electricity consumption information, the location information, and the environmental information to obtain the anti-stealing electricity analysis result; finally, performing hierarchical alarm according to the anti-stealing electricity analysis result. During the entire anti-stealing electricity analysis and alarm process, because it is detected whether the anti-stealing electricity analysis conditions are met according to multi-dimensional data, not only all-round and effective monitoring of electricity stealing is carried out, but also maintenance operations and electricity stealing behaviors can be distinguished, improving the accuracy of anti-stealing electricity; and when different anti-stealing electricity analysis conditions are met, the anti-stealing electricity analysis result is generated locally on the intelligent electric meter or on the cloud server according to multi-dimensional data, reducing the false alarm rate of anti-stealing electricity and improving the accuracy of anti-stealing electricity. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0009] Figure 1 Shows a block diagram of the anti-stealing electricity system based on an intelligent electric meter according to an embodiment of the present invention; Figure 2 Shows a flowchart of the anti-stealing electricity method based on an intelligent electric meter according to an embodiment of the present invention; Figure 3 Shows a sub-flowchart of the anti-stealing electricity method based on an intelligent electric meter according to an embodiment of the present invention; Figure 4Shows another sub - process schematic diagram of the anti - electricity - theft method based on an intelligent electric meter according to an embodiment of the present invention; Figure 5 Shows yet another sub - process schematic diagram of the anti - electricity - theft method based on an intelligent electric meter according to an embodiment of the present invention; Figure 6 Shows still another sub - process schematic diagram of the anti - electricity - theft method based on an intelligent electric meter according to an embodiment of the present invention; Reference numerals: 10. Anti - electricity - theft system based on an intelligent electric meter; 11. Intelligent electric meter; 111. Cabinet door; 112. Detection module; 113. Generation module; 114. Alarm module; 115. Electric meter body; 116. Voltage and current acquisition module; 117. Position monitoring module; 118. Environment monitoring module; 119. Communication module; 12. Cloud server; 121. Anti - electricity - theft analysis module; 122. Sending - down module. Detailed implementation manners

[0010] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0011] The directional terms mentioned in the present invention, such as "up", "down", "front", "back", "left", "right", "inside", "outside", "side", etc., are only references to the directions in the attached drawings. Therefore, the directional terms used are for explaining and understanding the present invention, rather than for limiting the present invention. In addition, in the drawings, structures that are similar or the same are denoted by the same reference numerals.

[0012] An embodiment of the present invention provides an anti-stealing electricity method and system based on an intelligent electricity meter, which solves the problem of low accuracy of existing anti-stealing electricity. First, it is detected whether the anti-stealing electricity analysis conditions are met according to the preset polling anti-stealing electricity detection time, signal indicator light status, multiple spacing values, and multiple connection pressure values. Then, when the first anti-stealing electricity analysis condition is met, an anti-stealing electricity analysis result is generated according to the collected electricity consumption information; when the second anti-stealing electricity analysis condition is met, the cloud server performs anti-stealing electricity analysis through a hybrid model according to the electricity consumption information, location information, and environmental information to obtain an anti-stealing electricity analysis result; finally, hierarchical alarms are made according to the anti-stealing electricity analysis result. During the entire anti-stealing electricity analysis and alarm process, because it is detected whether the anti-stealing electricity analysis conditions are met according to multi-dimensional data, not only the stealing of electricity is effectively monitored in all directions, but also the maintenance operation and stealing behavior can be distinguished, improving the accuracy of anti-stealing electricity; and when different anti-stealing electricity analysis conditions are met, the anti-stealing electricity analysis result is generated locally on the intelligent electricity meter or on the cloud server according to multi-dimensional data, reducing the false alarm rate of anti-stealing electricity and improving the accuracy of anti-stealing electricity.

[0013] To better understand the above technical solution, the following will describe the above technical solution in detail in conjunction with the specification drawings and specific embodiments.

[0014] Please refer to Figure 1 , Figure 1 which shows a block diagram of the anti-stealing electricity system based on an intelligent electricity meter according to an embodiment of the present invention. As Figure 1As shown, the anti-stealing electricity system 10 based on an intelligent electricity meter includes an intelligent electricity meter 11 and a cloud server 12. Among them, the intelligent electricity meter 11 includes a box door 111. Multiple groups of ultrasonic distance sensors are provided at the edge of the box door 111 to collect the distances between the box door 111 and the door frame to obtain multiple distance values. Multiple groups of pressure sensors are provided in the terminal block area inside the box door 111 to collect the connection pressures of the terminal blocks to obtain multiple connection pressure values; the intelligent electricity meter 11 further includes a detection module 112 and a generation module 113. The detection module 112 is used to detect whether the anti-stealing electricity analysis conditions are met according to a preset polling anti-stealing electricity detection time, the obtained signal indicator state, multiple of the distance values, and multiple of the connection pressure values; the generation module 113 is used to generate an anti-stealing electricity analysis result according to the collected electricity consumption information; the cloud server 12 includes an anti-stealing electricity analysis module 121 and a distribution module 122. The anti-stealing electricity analysis module 121 is used to perform anti-stealing electricity analysis on the electricity consumption information uploaded by the intelligent electricity meter 11, the collected location information, and environmental information through a hybrid model to obtain the anti-stealing electricity analysis result. The distribution module 122 is used to distribute the anti-stealing electricity analysis result to the intelligent electricity meter 11; the intelligent electricity meter 11 further includes an alarm module 114. The alarm module 114 is used to perform hierarchical alarms according to the anti-stealing electricity analysis result. It should be noted that in this embodiment, there are four groups of the ultrasonic distance sensors and six groups of the pressure sensors. The four groups of ultrasonic distance sensors are evenly arranged along the edge of the box door 111. The six groups of pressure sensors are distributed in a ring centered on the terminal block, covering the main stress areas of the terminal block plugging and unplugging operations. Understandably, in other embodiments, the number of groups of the ultrasonic distance sensors and the pressure sensors can be set according to actual needs. It should also be noted that in this embodiment, the intelligent electricity meter 11 further includes an electricity meter body 115, a voltage and current acquisition module 116, a position monitoring module 117, an environmental monitoring module 118, and a communication module 119. An electromagnetic shielding layer is provided on the electricity meter body 115 to prevent high-frequency magnetic field interference; the position monitoring module 117 is used to collect the position information; the environmental monitoring module 118 is used to collect the environmental information; the voltage and current acquisition module 116 is respectively connected to the phase wire and the neutral wire of the intelligent electricity meter 11 to simultaneously sample the electricity consumption information of the phase wire and the neutral wire respectively; the communication module 119 is used to upload the electricity consumption information, the position information, and the environmental information to the cloud server 12, and receive the anti-stealing electricity analysis result distributed by the cloud server 12. For the sake of simplicity of description, the method for generating the anti-stealing electricity analysis result in the cloud service, the detection method used by the detection module 112 in the intelligent electricity meter 11, the generation method used by the generation module 113, and the alarm method used by the alarm module 114 will be described in detail in the anti-stealing electricity based on the intelligent electricity meter 11 later and will not be elaborated here.

[0015] An embodiment of the present invention also provides an anti-stealing electricity method based on an intelligent electricity meter. This anti-stealing electricity method based on an intelligent electricity meter can be used in the anti-stealing electricity system based on an intelligent electricity meter in the above embodiment. The anti-stealing electricity system based on an intelligent electricity meter has been described in detail in the above embodiment. For the sake of simplicity of the specification, it will not be repeated here. To clearly illustrate the working process of the embodiment of the present invention, the anti-stealing electricity method based on an intelligent electricity meter will be described below in combination with the anti-stealing electricity system based on an intelligent electricity meter in the above embodiment. Referring to Figure 2 , the anti-stealing electricity method based on an intelligent electricity meter includes steps: S110 - S140.

[0016] S110. Detect whether the anti-stealing electricity analysis conditions are met according to the preset polling anti-stealing electricity detection time, the obtained signal indicator light state, multiple of the spacing values, and multiple of the connection pressure values. Among them, the anti-stealing electricity analysis conditions include a first anti-stealing electricity analysis condition and a second anti-stealing electricity analysis condition.

[0017] In this embodiment, a signal indicator light is provided in the intelligent electricity meter. When the signal indicator light is green, it indicates that the intelligent electricity meter is in a normal operating state. When it is yellow, it indicates that the intelligent electricity meter is in a maintenance state. When it is red, it indicates that the intelligent electricity meter is in an alarm state and there may be an electricity stealing behavior. Understandably, when the signal indicator light is green or red, that is, when the signal indicator light state is in a normal state or an alarm state, it is necessary to monitor for electricity stealing. Therefore, the signal indicator light state is obtained, and it is detected whether the anti-stealing electricity analysis conditions are met according to the signal indicator light state, the preset polling anti-stealing electricity detection time, multiple of the spacing values, and multiple of the connection pressure values. Among them, the anti-stealing electricity analysis conditions include a first anti-stealing electricity analysis condition and a second anti-stealing electricity analysis condition.

[0018] In one embodiment, for example, in this embodiment, as Figure 3 shown, step S110 specifically includes steps S111 - S114: S111. If the obtained signal indicator light state is not the preset indicator light state, then judge the preset polling anti-stealing electricity detection time, multiple of the spacing values, and multiple of the connection pressure values; S112. If the preset polling anti-stealing electricity detection time is reached, it is determined that the first anti-stealing electricity analysis condition is met; S113. If at least one of the multiple spacing values is greater than the preset reference spacing value, it is determined that the second anti-stealing electricity analysis condition is met; S114. If at least one of the multiple connection pressure values is greater than the preset connection upper limit pressure value or at least one of the multiple connection pressure values is less than the preset connection lower limit pressure value, it is determined that the second anti-stealing electricity analysis condition is met.

[0019] In this embodiment, the preset indicator light state is the maintenance state. That the signal indicator light state is not the preset indicator light state means that the signal indicator light state is not the maintenance state. Understandably, at this time, the signal indicator light state is the normal state or the alarm state, that is, the signal indicator light is green or red. When the preset indicator light state is not the maintenance state, the preset polling anti-stealing electricity detection time, the multiple spacing values, and the multiple connection pressure values are judged; if the preset polling anti-stealing electricity detection time is reached, it indicates that the fixed anti-stealing electricity detection time is reached, and only simple anti-stealing electricity detection of the local smart meter needs to be performed, then it is determined that the first anti-stealing electricity analysis condition is satisfied; if at least one of the multiple spacing values is greater than the preset reference spacing value, it indicates that the cabinet door may be abnormally opened, and more accurate anti-stealing electricity detection and analysis need to be performed through the cloud server, then it is determined that the second anti-stealing electricity analysis condition is satisfied; if at least one of the multiple connection pressure values is greater than the preset connection upper limit pressure value or at least one of the multiple connection pressure values is less than the preset connection lower limit pressure value, it indicates that there may be abnormal line operations or circuit short circuits, and more accurate anti-stealing electricity detection and analysis need to be performed through the cloud server, then it is determined that the second anti-stealing electricity analysis condition is satisfied. It should be noted that in this embodiment, The preset reference spacing value, the preset connection upper limit pressure value, and the preset connection lower limit pressure value can all be set according to actual needs, and no specific limitations are made here. It should also be noted that in this embodiment, by judging the signal indicator light state, the maintenance operation and the electricity stealing behavior can be clearly distinguished.

[0020] S120. If the first anti-stealing electricity analysis condition is satisfied, an anti-stealing electricity analysis result is generated according to the collected power consumption information.

[0021] In this embodiment, the electricity consumption information includes current data and voltage data. Generating an anti-stealing electricity analysis result based on the collected electricity consumption information includes: calculating a current balance degree according to the current data, and calculating power factor data according to the current data and the voltage data through a power calculation formula; generating the anti-stealing electricity analysis result according to the current balance degree and the power factor data. It should be noted that in this embodiment, the power calculation formula is P = UIcosφ, where P is power, U is the voltage data, I is the current data, and cosφ is the power factor data; the current balance degree is the difference between the voltage data of the phase line and the voltage data of the neutral line. It should also be noted that in this embodiment, if the current balance degree is greater than a preset current balance degree or the power factor data shows an abnormal jump, the anti-stealing electricity analysis result is set to suspected electricity stealing, and if the current balance degree is not greater than the preset current balance degree or the power factor data does not show an abnormal jump, the anti-stealing electricity analysis result is set to normal electricity consumption.

[0022] S130. If the second anti-stealing electricity analysis condition is satisfied, upload the electricity consumption information, the collected location information, and the environmental information to the cloud server, so that the cloud server performs anti-stealing electricity analysis through a hybrid model according to the electricity consumption information, the location information, and the environmental information to obtain the anti-stealing electricity analysis result, and send the anti-stealing electricity analysis result to the smart meter.

[0023] In this embodiment, the environmental information includes temperature and humidity and light intensity, such as Figure 4As shown, step S130 specifically includes steps S131 - S136: S131. The cloud server pre - processes the current data and the voltage data to obtain processed current data and processed voltage data, and performs feature enhancement on the processed current data and the processed voltage data to obtain enhanced current data and enhanced voltage data; S132. Calculate the power factor data according to the current data and the voltage data through the power calculation formula, and perform Fourier transform and normalization processing on the power factor data in sequence to obtain power normalized features; S133. Perform geographical hashing on the location information to generate geographical location codes; S134. Perform normalization processing on the temperature and humidity to obtain normalized temperature and humidity; S135. Perform logarithmic transformation on the light intensity to obtain transformed light intensity; S136. Perform anti - electricity - theft analysis through the hybrid model according to the enhanced current data, the enhanced voltage data, the power normalized features, the geographical location codes, the normalized temperature and humidity, and the transformed light intensity to obtain the anti - electricity - theft analysis result. It should be noted that in this embodiment, the pre - processing includes noise filtering, missing value repair, and normalization processing. Specifically, noise filtering is performed using a Butterworth band - pass filter to attenuate high - frequency harmonics and low - frequency drift and retain the effective signal components; missing value repair uses cubic spline interpolation to fill in the curve by fitting the data at adjacent times; feature enhancement is performed using a sliding window. The normalization processing in the pre - processing of the current data and the voltage data and the normalization processing of the temperature and humidity are both standardization processing, while the normalization processing of the power frequency - domain features is min - max normalization processing. It should also be noted that in this embodiment, the specific process of calculating the power factor data according to the current data and the voltage data through the power calculation formula is as described above and will not be elaborated here; performing Fourier transform and normalization processing on the power factor data in sequence to obtain power normalized features specifically means performing Fourier transform on the power factor data to obtain power frequency - domain features and performing normalization processing on the power frequency - domain features to obtain power normalized features; performing geographical hashing on the location information not only compresses the data dimension but also retains spatial proximity.

[0024] Further, as Figure 5As shown, step S136 specifically includes steps S1361 - S1365: S1361. Determine the behavior features based on the current enhancement data, the voltage enhancement data, the power normalization feature, the geographical location encoding, the normalized temperature and humidity, and the transformed light intensity; S1362. Concatenate the current enhancement data, the voltage enhancement data, and the power normalization feature based on time to generate a multi-dimensional time series feature; S1363. Concatenate the geographical location encoding, the normalized temperature and humidity, and the transformed light intensity based on time to generate a multi-dimensional spatial environment feature; S1364. Use the principal component analysis method to reduce the dimensions of the multi-dimensional time series feature and the multi-dimensional spatial environment feature to obtain a reduced-dimensional time series feature and a reduced-dimensional spatial environment feature; S1365. Input the behavior features, the reduced-dimensional time series feature, and the reduced-dimensional spatial environment feature into the hybrid model for anti-stealing electricity analysis to obtain the anti-stealing electricity analysis result. It should be noted that in this embodiment, the principal component analysis method is an unsupervised statistical method used to extract key features from high-dimensional data. By linearly transforming the original variables into a few mutually uncorrelated principal components, the maximum variance information in the data is retained at the same time.

[0025] Furthermore, step S1361 specifically includes: calculating the current balance degree and the proportion of night load according to the current enhancement data and the voltage enhancement data, and marking the load abnormal jump points according to the power normalization feature; calculating the correlation between the current enhancement data and the normalized temperature and humidity to obtain the temperature-humidity current correlation, and marking the abnormal light jump points according to the changed light intensity; determining the area where the user is located according to the geographical location code, and determining the area load deviation according to the average power consumption of other users in the area where the user is located; characterizing the behavior feature according to the current balance degree, the proportion of night load, the load abnormal jump points, the temperature-humidity current correlation, the abnormal light jump points, and the area load deviation. It should be noted that in this embodiment, the proportion of night load is calculated based on time according to the current enhancement data and the voltage enhancement data. Specifically, based on 24 hours a day, first calculate the total load, then calculate the night load, and finally calculate the proportion of night load according to the total load and the night load; marking the load abnormal jump points according to the power normalization feature. For example, if the power normalization feature suddenly drops from 0.9 to 0.5, the load at the current moment needs to be marked as a load abnormal jump point; calculating the correlation between the current enhancement data and the normalized temperature and humidity through an existing correlation algorithm; marking the abnormal light jump points according to the changed light intensity. It can be understood that when the changed light intensity suddenly increases at night, it indicates that the box door may be opened, so it is marked as an abnormal light jump point. Determining the area load deviation according to the average power consumption of other users in the area where the user is located. It can be understood that if the night load of users in a certain area is generally low, and if the night load of an individual user suddenly increases without a reasonable reason, there may be electricity theft. It should also be noted that in this embodiment, the calculation of the current balance degree according to the current enhancement data is as described above and will not be elaborated here. The reason for using the current balance degree, the proportion of night load, the load abnormal jump points, the temperature-humidity current correlation, the abnormal light jump points, and the area load deviation to characterize the behavior feature is that the current balance degree characterizes whether the line integrity is abnormal, the proportion of night load can identify the irregular power consumption behavior of users, the load abnormal jump points can capture the power consumption mutation mode, the temperature-humidity current correlation can characterize the relationship between the environment and power consumption, the abnormal light jump points can monitor the physical operation traces, and the area load deviation can locate the abnormal individuals in the group.

[0026] Further, the hybrid model includes a cross - domain attention model and a linear regression model. Step S1361 specifically includes: concatenating the behavioral features, the dimension - reduced time - series features, and the dimension - reduced spatial environment features to obtain a concatenated feature vector; inputting the concatenated feature vector into the cross - domain attention model to analyze the importance of different features for electricity theft and assign corresponding weight values to the behavioral features, the dimension - reduced time - series features, and the dimension - reduced spatial environment features to obtain a behavioral weight value, a time - series weight value, and a spatial environment weight value; performing weighted processing on the behavioral features, the dimension - reduced time - series features, and the dimension - reduced spatial environment features according to the behavioral weight value, the time - series weight value, and the spatial environment weight value to obtain weighted features; inputting the weighted features into the linear regression model to output the electricity theft probability, and generating the anti - electricity - theft analysis result according to the electricity theft probability. It should be noted that, in this embodiment, the cross - domain attention model includes a multi - head attention mechanism, that is, through multiple independent attention heads, to separately learn the feature associations in different sub - spaces of the concatenated feature vector and enhance the model's ability to capture complex relationships; the cross - domain attention model is constructed based on a deep learning framework (such as Transformer or BERT) and is optimized through a multi - stage training strategy and a specific task objective. Among them, the multi - stage training strategy includes a pre - training stage and a fine - tuning stage. The specific task objective optimization means that during the model training process, for a specific downstream task (such as classification, generation, etc.), the objective function (loss function) is designed and optimized to adjust the model parameters to the state most suitable for this task. Its core is to transform a general pre - trained model into a task - specific model. For example, the cross - domain attention model in this embodiment maximizes the task performance index by adjusting the loss function, the model structure, or the training strategy. It can be understood that when the cross - domain attention model performs weight assignment, the spatial environment weight value is the smallest, and the time - series weight value and the behavioral weight value are not limited. It should also be noted that, in this embodiment, generating the anti - electricity - theft analysis result according to the electricity theft probability specifically includes: if the electricity theft probability is in the first electricity theft probability interval, that is, if the electricity theft probability < the first preset electricity theft probability, then set the anti - electricity - theft analysis result to normal electricity consumption; if the electricity theft probability is in the second electricity theft probability interval, that is, if the first preset electricity theft probability ≤ the electricity theft probability < the second preset electricity theft probability, then set the anti - electricity - theft analysis result to suspected electricity theft; if the electricity theft probability is in the third electricity theft probability interval, that is, if the electricity theft probability ≥ the second preset electricity theft probability, then set the anti - electricity - theft analysis result to confirmed electricity theft. In this embodiment, the first preset electricity theft probability and the second preset electricity theft probability are 0.5 and 0.8 respectively. In other embodiments, the first preset electricity theft probability and the second preset electricity theft probability can be set according to actual needs.

[0027] S140. Perform hierarchical alarm according to the anti - electricity - theft analysis result.

[0028] In this embodiment, as Figure 6 shown, step S140 specifically includes steps S141 - S142: S141. If the anti - electricity - theft analysis result is suspected of electricity theft, trigger a primary alarm to control the buzzer to alarm, and control the camera to take multiple captured images of the smart meter; S142. If the anti - electricity - theft analysis result is confirmed electricity theft, trigger a high - level alarm to cut off the power supply. It should be noted that in this embodiment, after triggering the primary alarm to control the buzzer to alarm and controlling the camera to take multiple captured images of the smart meter, it further includes: uploading the multiple captured images to the cloud server, so that the cloud server uses the computer vision algorithm in the hybrid model to detect the appearance of the smart meter based on the multiple captured images to obtain a detection result, where the computer vision algorithm includes traditional computer vision algorithms and computer vision algorithms based on deep learning; and detecting the appearance of the smart meter is specifically to check whether the appearance of the smart meter is abnormal. For example, whether there are pry marks and whether the wires are exposed; if the detection result is abnormal appearance, that is, there are pry marks or the wires are exposed, then execute the step of triggering the high - level alarm to cut off the power supply. It should also be noted that in this embodiment, detecting the appearance of the smart meter through the computer vision algorithm in the hybrid model can further improve the accuracy of anti - electricity - theft.

[0029] Furthermore, after the step of triggering the high - level alarm to cut off the power supply, it may further include: uploading the anti - electricity - theft analysis result, multiple distance values, multiple connection pressure values, the signal indicator status, the electricity consumption information, the location information, and the environmental information to the blockchain evidence - storage platform to ensure non - tampering.

[0030] In summary, in this embodiment, it is first detected whether the anti-stealing electricity analysis conditions are met according to multi-dimensional data (preset polling anti-stealing electricity detection time, signal indicator light status, multiple spacing values, and multiple connection pressure values). Then, when the first anti-stealing electricity analysis condition is met, the generation module in the smart meter generates an anti-stealing electricity analysis result according to the collected electricity consumption information; when the second anti-stealing electricity analysis condition is met, the communication module uploads the electricity consumption information, location information, and environmental information to the cloud server, so that the cloud server performs anti-stealing electricity analysis through a hybrid model according to the electricity consumption information, location information, and environmental information to obtain an anti-stealing electricity analysis result, where the hybrid model includes a cross-domain attention model and a linear regression model; finally, hierarchical alarms are made according to the anti-stealing electricity analysis result. During the entire anti-stealing electricity analysis and alarm process, because it is detected whether the anti-stealing electricity analysis conditions are met according to multi-dimensional data, not only the anti-stealing electricity is effectively monitored in all aspects, but also the maintenance operations and anti-stealing electricity behaviors can be distinguished, improving the accuracy of anti-stealing electricity; and when different anti-stealing electricity analysis conditions are met, the anti-stealing electricity analysis result is generated locally in the smart meter or on the cloud server according to multi-dimensional data, not only improving the real-time performance and efficiency of anti-stealing electricity, but also reducing the false alarm rate of anti-stealing electricity and improving the accuracy of anti-stealing electricity.

[0031] As described above, the above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for preventing electricity theft based on a smart meter, characterized in that: The smart electric meter comprises a box door, the edge of the box door is provided with multiple groups of ultrasonic distance sensors to collect the distance between the box door and the door frame to obtain multiple distance values, and the terminal area inside the box door is provided with multiple groups of pressure sensors to collect the connection pressure of the terminal to obtain multiple connection pressure values. The method comprises: Detecting whether an anti-electricity theft analysis condition is met according to a preset polling anti-electricity theft detection time, the acquired signal indicator light state, a plurality of the spacing values, and a plurality of the connection pressure values, wherein the anti-electricity theft analysis condition includes a first anti-electricity theft analysis condition and a second anti-electricity theft analysis condition; If the first anti-electricity theft analysis condition is met, generating an anti-electricity theft analysis result according to the collected electricity usage information; If the second anti-electricity theft analysis condition is met, the electricity usage information, the collected location information and the environmental information are uploaded to the cloud server, so that the cloud server performs anti-electricity theft analysis based on the electricity usage information, the location information and the environmental information through a hybrid model to obtain the anti-electricity theft analysis result, and sends the anti-electricity theft analysis result to the smart meter; A graded alarm is issued according to the anti-electricity theft analysis result.

2. The method according to claim 1, characterized in that: The detecting whether the anti-electricity theft analysis condition is met according to the preset polling anti-electricity theft detection time, the acquired signal indicator light state, the plurality of the spacing values, and the plurality of the connection pressure values ​​comprises: If the obtained signal indicator light state is not the preset indicator light state, judging the preset polling anti-electricity theft detection time, the plurality of spacing values ​​and the plurality of connection pressure values; If the preset polling anti-electricity theft detection time is reached, it is determined that the first anti-electricity theft analysis condition is met; If at least one of the plurality of spacing values ​​is greater than a preset reference spacing value, it is determined that the second anti-electricity theft analysis condition is met; If at least one of the plurality of connection pressure values ​​is greater than a preset connection upper limit pressure value or at least one of the connection pressure values ​​is less than a preset connection lower limit pressure value, it is determined that the second anti-electricity theft analysis condition is met.

3. The method according to claim 1, characterized in that The electricity usage information includes current data and voltage data, and the generating of the anti-electricity theft analysis result according to the collected electricity usage information includes: Calculating the current balance according to the current data, and calculating the power factor data according to the current data and the voltage data by using a power calculation formula; The anti-electricity theft analysis result is generated according to the current balance and power factor data.

4. The method according to claim 3, characterized in that: The environmental information includes temperature, humidity and light intensity; The cloud server performs anti-electricity theft analysis based on the electricity usage information, the location information, and the environmental information through a hybrid model to obtain the anti-electricity theft analysis result, including: The cloud server pre-processes the current data and the voltage data to obtain current processed data and voltage processed data, and performs feature enhancement on the current processed data and the voltage processed data to obtain current enhanced data and voltage enhanced data; Calculating power factor data according to the current data and the voltage data using a power calculation formula, and performing Fourier transformation and normalization processing on the power factor data in sequence to obtain a power normalization feature; Performing geo-hashing on the location information to generate a geo-location code; Normalizing the temperature and humidity to obtain normalized temperature and humidity; Performing logarithmic transformation on the light intensity to obtain transformed light intensity; The anti-electricity theft analysis result is obtained by performing anti-electricity theft analysis through the hybrid model according to the current enhancement data, the voltage enhancement data, the power normalization feature, the geographic location code, the normalized temperature and humidity, and the transformed light intensity.

5. The method according to claim 4, characterized in that The anti-electricity theft analysis is performed through the hybrid model according to the current enhancement data, the voltage enhancement data, the power normalization feature, the geographic location code, the normalized temperature and humidity, and the transformed light intensity to obtain the anti-electricity theft analysis result, including: Determine a behavior feature according to the current enhancement data, the voltage enhancement data, the power normalization feature, the geographic location code, the normalized temperature and humidity, and the transformed light intensity; The current enhancement data, the voltage enhancement data and the power normalization feature are spliced ​​based on time to generate a multi-dimensional time series feature; The geographic location code, the normalized temperature and humidity, and the transformed light intensity are spliced ​​based on time to generate a multi-dimensional spatial environmental feature; Using a principal component analysis method to reduce the dimensions of the multidimensional time series features and the multidimensional space environment features to obtain reduced-dimensional time series features and reduced-dimensional space environment features; The behavior feature, the dimension-reduced time series feature, and the dimension-reduced space environment feature are input into the hybrid model to perform anti-electricity theft analysis to obtain the anti-electricity theft analysis result.

6. The method according to claim 5, characterized in that The determining of the behavior characteristics according to the current enhancement data, the voltage enhancement data, the power normalization characteristics, the geographic location code, the normalized temperature and humidity, and the transformed light intensity includes: Calculating the current balance degree according to the current enhancement data, calculating the night load proportion according to the current enhancement data and the voltage enhancement data, and marking the load abnormality jump point according to the power normalization feature; Calculating the correlation between the current enhancement data and the normalized temperature and humidity to obtain the temperature-humidity-current correlation, and marking the abnormal illumination jump point according to the transformed illumination intensity; Determine the area where the user is located according to the geographic location code, and determine the regional load deviation according to the average power consumption of other users in the area where the user is located; The behavior characteristics are characterized according to the current balance, the nighttime load proportion, the load abnormality jump point, the temperature-humidity-current correlation, the illumination abnormality jump point and the regional load deviation.

7. The method according to claim 5, characterized in that The hybrid model includes a cross-domain attention model and a linear regression model, and the behavior features, the reduced-dimensionality time series features, and the reduced-dimensionality space environment features are input into the hybrid model for anti-electricity theft analysis to obtain the anti-electricity theft analysis result, including: The behavior feature, the reduced-dimensionality time series feature, and the reduced-dimensionality space environment feature are concatenated to obtain a concatenated feature vector; Input the concatenated feature vector into the cross-domain attention model to analyze the importance of different features to electricity theft, and assign corresponding weight values ​​to the behavior feature, the reduced-dimensionality temporal feature, and the reduced-dimensionality spatial environment feature to obtain a behavior weight value, a temporal weight value, and a spatial environment weight value; The behavior feature, the reduced-dimensionality time series feature, and the reduced-dimensionality space environment feature are weighted according to the behavior weight value, the time series weight value, and the space environment weight value to obtain a weighted feature; The weighted features are input into the linear regression model to output the probability of electricity theft, and the anti-electricity theft analysis result is generated according to the probability of electricity theft.

8. The method according to any one of claims 1 to 7, characterized in that: The step of providing a graded alarm according to the anti-electricity theft analysis result includes: If the anti-electricity theft analysis result is suspected electricity theft, a primary alarm is triggered to control a buzzer to sound an alarm, and a camera is controlled to take a picture of the smart meter to obtain a plurality of pictures; If the anti-electricity theft analysis result confirms electricity theft, a high-level alarm is triggered to cut off the power supply.

9. The method according to claim 8, characterized in that After the primary alarm is triggered to control the buzzer to sound an alarm and the camera is controlled to photograph the smart meter to obtain a plurality of photographed images, the method further includes: Uploading the plurality of photographed images to the cloud server, so that the cloud server detects the appearance of the smart meter according to the plurality of photographed images through the computer vision algorithm in the hybrid model to obtain a detection result; If the detection result is that the appearance is abnormal, the step of triggering a high-level alarm to cut off the power supply is performed. 10.An anti-electricity theft system based on a smart meter, characterized in that: include: A smart electric meter, comprising a box door, wherein the edge of the box door is provided with a plurality of groups of ultrasonic distance sensors to collect the distance between the box door and the door frame to obtain a plurality of distance values, and a plurality of groups of pressure sensors are provided in the terminal area inside the box door to collect the connection pressure of the terminal to obtain a plurality of connection pressure values; the smart electric meter also comprises a detection module and a generation module, wherein the detection module is used to detect whether an anti-electricity theft analysis condition is met according to a preset polling anti-electricity theft detection time, an acquired signal indicator light state, a plurality of the distance values, and a plurality of the connection pressure values; and the generation module is used to generate an anti-electricity theft analysis result according to the collected electricity usage information; The cloud server comprises an anti-electricity theft analysis module and a sending module, wherein the anti-electricity theft analysis module is used to perform anti-electricity theft analysis through a hybrid model according to the electricity consumption information uploaded by the smart meter, the collected location information and the environmental information to obtain the anti-electricity theft analysis result, and the sending module is used to send the anti-electricity theft analysis result to the smart meter; The smart electric meter further comprises an alarm module, and the alarm module is used to issue graded alarms according to the anti-electricity theft analysis results.

Images