A method, device, and electronic device for identifying electricity theft based on electricity usage scenarios.
By constructing a feature library of electricity theft through weighted fusion of electrical parameters and visual frames, and dynamically adjusting the weights and recombining them, the adaptability and accuracy problems of existing electricity theft identification methods are solved, achieving efficient electricity theft identification and control, and reducing operation and maintenance costs and power consumption.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HEXING ELECTRICAL CO LTD
- Filing Date
- 2026-03-05
- Publication Date
- 2026-06-30
AI Technical Summary
Existing methods for identifying electricity theft using electricity meters are ill-suited to new methods of theft, have a high false positive rate, lack iterative capabilities, and are unable to effectively address complex electricity theft environments.
By collecting electrical parameters and visual frames and weighting them together, a database of electricity theft features is constructed. The weight groups are dynamically adjusted based on the update cycle and the number of samples to achieve accurate identification and control of electricity theft, adapting to the differentiated needs of different electricity consumption scenarios.
It improves the accuracy and response speed of electricity theft detection, reduces operation and maintenance costs, enhances the model's anti-interference ability and robustness of electricity theft detection, reduces invalid investigations, and lowers power consumption.
Smart Images
Figure CN122307171A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of electricity meter anti-theft technology, and in particular to an electricity theft identification method, device, electronic device and storage medium based on electricity usage scenarios. Background Technology
[0002] In the development of smart grids, electricity theft methods are becoming increasingly sophisticated, and dual-modal monitoring linking electricity meters and cameras has become the mainstream approach to combating electricity theft. Existing linkage solutions fall into two categories: one is centralized cloud processing, with all data uploaded to the cloud for identification; the other is preliminary local processing, where abnormal electrical parameters trigger image capture and upload to the cloud for judgment. Both solutions use fixed models and lack iterative capabilities, making them difficult to adapt to the ever-evolving new electricity theft methods and prone to misjudgment. Summary of the Invention
[0003] To address the problems existing in the prior art, this specification describes one or more embodiments of a method, apparatus, electronic device, and storage medium for identifying electricity theft based on electricity consumption scenarios.
[0004] According to the first aspect, a method for identifying electricity theft based on electricity consumption scenarios is provided, the method comprising:
[0005] The electrical parameters of the electricity meter to be identified in the electricity consumption scenario are collected. When the electrical parameters are greater than the set electrical parameter threshold, the visual frame of the electricity meter to be identified in the electricity consumption scenario is collected. The electrical parameters and the visual frame are weighted and fused to obtain the fused feature.
[0006] The fused features are compared with a set electricity theft feature database, and the electricity theft behavior with the highest matching degree with the fused features in the electricity theft feature database corresponding to the electricity meter to be identified is output. Electricity theft control is carried out based on the electricity theft behavior.
[0007] The update cycle and sample number are set based on the electricity consumption scenario. The weighted reassembly of the electrical parameters and the visual frame is updated based on the update cycle and the sample number.
[0008] Preferably, the electrical parameters include current imbalance and power fluctuation coefficient, the electricity usage scenario includes a first electricity usage scenario, a second electricity usage scenario, and a third electricity usage scenario with different weightings, the visual frame includes the percentage of damaged seals and the outline of foreign objects in the wiring, and the weighted fusion of the electrical parameters and the visual frame to obtain the fusion feature includes: selecting the weighting set corresponding to the electricity usage scenario where the meter to be identified is located, and weighted fusion of the selected weighting set, the electrical parameters, and the visual frame to obtain the fusion feature.
[0009] Preferably, updating the weighted reassembly of the electrical parameters and the visual frame based on the update period and the number of samples includes:
[0010] Electricity theft samples are collected based on the number of samples and the update period. Factors that change when electricity theft occurs are selected based on the electricity theft samples. The weights of the electrical parameters and the visual frame are updated based on the factors that change when electricity theft occurs.
[0011] Preferably, the output is the electricity theft behavior in the electricity theft feature database that has the highest matching degree with the fused feature corresponding to the electricity meter to be identified, and the electricity theft control based on the electricity theft behavior includes:
[0012] A first confidence interval and a second confidence interval are set. The matching degree between each electricity theft behavior in the electricity theft feature database and the fused feature is calculated. The electricity theft feature corresponding to the highest matching degree is selected. If the highest matching degree is in the first confidence interval, an electricity theft alarm is triggered and the location of the electricity meter to be identified is uploaded. If the highest matching degree is in the second confidence interval, the visual frame of the electricity meter to be identified in the electricity consumption scenario is collected for secondary identification.
[0013] Preferably, the step of collecting visual frames of the meter to be identified in the power consumption scenario when the electrical parameter is greater than a set electrical parameter threshold includes: setting an abnormality duration threshold; if the time when the electrical parameter is greater than the set electrical parameter threshold is longer than the abnormality duration threshold, collecting visual frames of the meter to be identified in the power consumption scenario.
[0014] Preferably, the update cycle and the number of samples are different for each of the described electricity consumption scenarios.
[0015] Preferably, the ratio of the number of updated weights to the total number of weights is less than a set update threshold.
[0016] According to a second aspect, a target detection apparatus is provided, the apparatus comprising:
[0017] The feature acquisition and fusion module is used to acquire electrical parameters in the power consumption scenario. When the electrical parameters are greater than the set electrical parameter threshold, visual frames in the power consumption scenario are acquired, and the electrical parameters and the visual frames are weighted and fused to obtain fused features.
[0018] The electricity theft detection module is used to compare the fused features with a set electricity theft feature library and output the electricity theft behavior in the electricity theft feature library that has the highest matching degree with the fused features;
[0019] The model update module is used to set the update cycle and sample number based on the electricity consumption scenario, and to update the weights of the electrical parameters and the visual frame during weighted fusion based on the update cycle and the sample number.
[0020] According to a third aspect, an electronic device is provided, including a processor and a memory;
[0021] The processor is connected to the memory;
[0022] The memory is used to store executable program code;
[0023] The processor runs a program corresponding to the executable program code stored in the memory to perform the steps of the method provided as in the first aspect or any possible implementation thereof.
[0024] According to a fourth aspect, a computer-readable storage medium is provided having a computer program stored thereon, the computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform the method provided as in the first aspect or any possible implementation thereof.
[0025] The beneficial effects of this invention are as follows:
[0026] 1. The method and apparatus provided in the embodiments of this specification update the weighted recombination of electrical parameters and visual frames by periodically collecting samples, and perform periodic iterations to adapt to various new types of electricity theft behaviors, thereby improving the accuracy of electricity theft judgment;
[0027] 2. The methods and apparatus provided in the embodiments of this specification have different update cycles and sample numbers for each electricity consumption scenario. When a new type of electricity theft technology becomes popular in a specific field (such as a commercial complex), the model for that scenario can be iterated and sample injected at high frequency to quickly form a defense capability without waiting for the update cycle of the entire large system. This improves the response speed to new types of electricity theft. Furthermore, the differentiated sample strategy allows the model to introduce relevant external variables in a targeted manner during training (such as inputting temperature into the residential model and operating rate into the industrial and commercial model), so that the model remains robust when the environment changes and will not fail due to the drift of the overall data distribution, thereby improving the anti-interference capability of the electricity theft judgment model.
[0028] 3. The method and apparatus provided in the embodiments of this specification determine whether to directly upload electricity theft behavior by calculating the confidence level. The system can concentrate limited inspection manpower and material resources on suspicious users with high confidence, avoid ineffective investigation of low-risk users, greatly improve the success rate of on-site detection of electricity theft, and reduce operation and maintenance costs.
[0029] 4. The method and apparatus provided in the embodiments of this specification have a ratio of the number of updated weights to the total number of weights that is less than a set update threshold, thereby improving the accuracy of the model in judging new types of electricity theft while ensuring that the accuracy of the model in judging old types of electricity theft does not decrease.
[0030] 5. The method and apparatus provided in the embodiments of this specification acquire visual frames by setting an abnormal persistence threshold, thereby reducing the number of times the camera device is activated due to sudden changes in electrical parameters caused by environmental factors, and thus reducing the power consumption of the entire electricity theft identification system. Attached Figure Description
[0031] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0032] Figure 1 This is a flowchart illustrating a method for identifying electricity theft based on an electricity consumption scenario, as specifically implemented in this manual.
[0033] Figure 2 This is a schematic diagram of the structure of an electricity theft detection device based on an electricity consumption scenario in a specific implementation of this specification;
[0034] Figure 3 This is a schematic diagram of the structure of an electronic device used in a specific implementation of this specification. Detailed Implementation
[0035] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.
[0036] In the following description, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. The following description provides multiple embodiments of this application, which can be substituted or combined with each other. Therefore, this application can also be considered to include all possible combinations of the same and / or different embodiments described. Thus, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then this application should also be considered to include embodiments containing one or more other possible combinations of A, B, C, and D, even if such embodiments are not explicitly described in the following text.
[0037] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes may be made to the function and arrangement of the described elements without departing from the scope of this application. Various processes or components may be appropriately omitted, substituted, or added to the examples. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Furthermore, features described with respect to some examples may be combined into other examples.
[0038] See Figure 1 , Figure 1 This is a flowchart illustrating a method for identifying electricity theft based on electricity consumption scenarios provided in an embodiment of this application. In this embodiment, the method includes:
[0039] S101. Collect electrical parameters of the electricity meter to be identified in the electricity consumption scenario. When the electrical parameters are greater than the set electrical parameter threshold, collect the visual frame of the electricity meter to be identified in the electricity consumption scenario. Weightedly fuse the electrical parameters and the visual frame to obtain the fusion feature.
[0040] S102. Compare the fused features with the set electricity theft feature database, output the electricity theft behavior in the electricity theft feature database that has the highest matching degree with the fused features corresponding to the electricity meter to be identified, and carry out electricity theft control based on the electricity theft behavior;
[0041] S103. Based on the electricity consumption scenario, set the update cycle and sample number, and update the weighted reassembly when the electrical parameters and the visual frame are weighted and fused based on the update cycle and the sample number.
[0042] The entity executing this application may be a cloud server.
[0043] In the embodiments of this specification, electricity usage scenarios are categorized according to the methods of electricity theft. These scenarios are divided into residential electricity usage scenarios, industrial and commercial electricity usage scenarios, and old meter electricity usage scenarios. Residential electricity usage scenarios are designated as the first electricity usage scenario, industrial and commercial electricity usage scenarios as the second electricity usage scenario, and old meter electricity usage scenarios as the third electricity usage scenario. Electrical parameters of the meters to be identified within each electricity usage scenario are periodically collected according to a set collection cycle. These electrical parameters include current, voltage, power factor, current imbalance, and power fluctuation coefficient. Current imbalance is the ratio of the negative-sequence current component to the positive-sequence current component. The power fluctuation coefficient is the amplitude or frequency of change of active power (or reactive power) within a certain time window. A threshold value for these electrical parameters is set, which can be equal to the average value of the historical electrical parameters of the meters to be identified. When the electrical parameters exceed the threshold, visual frames of the meter to be identified within the power consumption scenario are acquired. The acquisition process of the visual frames is as follows: three consecutive frames are acquired through a camera device. The difference between the first two frames and the difference between the last two frames are calculated. The intersection of the two (logical AND operation) is taken as the motion region mask, i.e., the visual frame. The visual frame includes the proportion of damaged seals, the outline of foreign objects in the wiring, etc. The proportion of damaged seals is the ratio of the pixel area of cracks, gaps, and breaks to the total pixel area of the complete area of the seal. The outline of foreign objects in the wiring is the geometry of the external boundary of unexpected objects appearing in electrical terminals, busbars, or cable trenches. The electrical parameters and visual frames are weighted and fused according to the timestamp to obtain the fused features. Data from an electricity theft feature database is acquired. This database stores multiple electricity theft behavior tags and corresponding fusion features. The fusion features are compared with the data in the database, and the electricity theft behavior with the highest similarity to the fusion features of the meter to be identified is selected. For example, if the fusion features of the meter to be identified are most similar to the fusion features corresponding to the electricity theft behavior of tampering with the seal, then the meter to be identified is determined to have engaged in electricity theft related to tampering with the seal. Then, electricity theft control is implemented for the meter to be identified based on the electricity theft behavior. An update cycle and sample number are set, and the weighted fusion of electrical parameters and visual frames is updated according to the update cycle and sample number. In this application, the weighted fusion of electrical parameters and visual frames is updated by periodically collecting samples to iterate and adapt to various new types of electricity theft behaviors, thereby improving the accuracy of electricity theft detection.
[0044] In the embodiments of this specification, the update cycle and sample number are different for each electricity consumption scenario. For example, for the first electricity consumption scenario, the methods of electricity theft in the residential electricity consumption scenario are relatively simple, so the update cycle can be set to one week and the sample number to 20, that is, 20 electricity theft samples are sent to the electricity meters in the residential electricity consumption scenario every week. For the second electricity consumption scenario, the methods of electricity theft in the industrial and commercial electricity consumption scenario are more complex, so the update cycle can be set to three days and the sample number to 50, that is, 50 electricity theft samples are sent to the electricity meters in the industrial and commercial electricity consumption scenario every three days. For the third electricity consumption scenario, there are fewer cases of electricity theft in the old electricity meter electricity consumption scenario, so the update cycle can be set to one month and the sample number to 15, that is, 15 electricity theft samples are sent to the electricity meters in the old electricity meter electricity consumption scenario every month. The samples are generated by the power operation and maintenance system based on actual electricity theft cases: in residential, industrial and commercial scenarios, when electricity theft is detected on-site, the corresponding electrical parameters (such as current fluctuations and magnetic field strength) and visual frames (such as damaged seals and abnormal wiring) are collected simultaneously. After manual labeling of the electricity theft type, these are processed into "electrical parameter-visual paired samples" and then uniformly stored in the electricity theft feature database. In this application, the update cycle and sample number are different for each electricity consumption scenario. When a new type of electricity theft technology becomes popular in a specific field (such as commercial complexes), the model for that scenario can be iterated and sampled at high frequency to quickly form a defense capability without waiting for the update cycle of the entire system. This improves the response speed to new types of electricity theft. Furthermore, the differentiated sample strategy allows the model to selectively introduce relevant external variables during training (such as inputting temperature for the residential model and operating rate for the industrial and commercial model), so that the model remains robust when the environment changes and will not fail due to the drift of the overall data distribution, thus improving the anti-interference capability of the electricity theft judgment model.
[0045] In the embodiments of this specification, the ratio of the number of updated weights to the total number of weights is less than a set update threshold, i.e., an update threshold is set, such as 10%. When updating the weighted reassembly during the weighted fusion of electrical parameters and visual frames, the ratio of updated parameters to total parameters is less than 10% (for example, if there are 100 total parameters, only 10 or fewer parameters are updated). This improves the model's accuracy in judging new types of electricity theft while ensuring that the model's accuracy in judging old types of electricity theft does not decrease.
[0046] In the embodiments of this specification, the process of obtaining fused features by weighted fusion of electrical parameters and visual frames is as follows: First, extract features from electrical parameters and visual frames, namely, features such as current imbalance and power fluctuation coefficient in electrical parameters, and features such as the proportion of damaged seals and the outline of foreign objects in wiring in visual frames. Then, according to the weighted reorganization corresponding to each power consumption scenario (e.g., the weight of electrical parameters is 0.5 and the weight of visual frames is 0.5 in the first power consumption scenario, and the weight of electrical parameters is 0.3 and the weight of visual frames is 0.7 in the second power consumption scenario), weight the electrical parameters and visual frames to obtain fused features.
[0047] In the embodiments of this specification, the process of updating the weighted fusion of electrical parameters and visual frames based on the update cycle and sample number is as follows: Obtain the electricity theft samples generated by the power operation and maintenance system based on actual electricity theft cases. Adjust the weights of the electrical parameters and visual frames during the weighted fusion according to the changing factors at the time of electricity theft for each sample. For example, for the first electricity consumption scenario, the current weight of the electrical parameters is 0.6, and the weight of the visual frame is 0.4. When a new electricity theft sample is received (e.g., "a household secretly connected a branch line, and the current fluctuation was particularly obvious, but the seal in the image was not broken"), it is found that the electricity theft was caused by factors affecting the electrical parameters (the whole process can be seen by comparing the difference between the sub-feature corresponding to the electricity theft and the sub-feature when the meter is running normally; the larger the difference between the sub-feature corresponding to the electricity theft and the sub-feature when the meter is running normally, the more likely the electricity theft was caused by factors affecting that sub-feature). At this time, the weight of the electrical parameters is adjusted to 0.7, and the weight of the visual frame is adjusted to 0.3.
[0048] In the embodiments of this specification, the output is the electricity theft behavior with the highest matching degree with the fused feature in the electricity theft feature database corresponding to the electricity meter to be identified. The process of electricity theft control based on electricity theft behavior is as follows: The fused feature is matched with the data in the electricity theft feature database (the fused feature corresponding to each electricity theft behavior label) to obtain multiple matching degrees. The electricity theft behavior with the highest matching degree is selected. The highest matching degree is multiplied by the quality score of the fused feature to obtain the confidence level. The quality of the fused feature is the completeness of the fused feature data. The confidence level and the electricity theft behavior are output. A first confidence interval (e.g., ≥90%), a second confidence interval (e.g., 70%-90%), and a third confidence interval (e.g., ≤70%) are set. If the confidence level is in the first confidence interval, electricity theft is confirmed and an electricity theft alarm is triggered. The encrypted evidence packet is uploaded via power line carrier and the location of the electricity meter is also uploaded. If the confidence level is in the second confidence interval, electricity theft is suspected. The camera device collects visual frames a second time for verification. If the confidence level is in the third confidence interval, it is judged as normal fluctuation. In this application, by calculating the confidence level to determine whether to directly upload electricity theft behavior, the system can concentrate limited inspection manpower and material resources on suspicious users with high confidence, avoid ineffective investigation of low-risk users, greatly improve the success rate of on-site detection of electricity theft, and reduce operation and maintenance costs.
[0049] In the embodiments of this specification, an abnormal duration threshold is set. If the duration for which the electrical parameter exceeds the set threshold is longer than the abnormal duration threshold, a visual frame of the meter to be identified in the electricity consumption scenario is acquired. For example, if the current in the acquired electrical parameters exceeds the threshold calculated from historical data, a timer is started. If the duration for which the current exceeds the threshold is longer than the abnormal duration threshold, a visual frame of the meter to be identified in the electricity consumption scenario is acquired. In this application, by setting an abnormal duration threshold to acquire visual frames, the number of times the camera device is activated due to sudden changes in environmental factors causing electrical parameters to change is reduced, thereby reducing the power consumption of the entire electricity theft identification system.
[0050] The following will be combined with the appendix Figure 2 This application provides a detailed description of the electricity theft detection device based on electricity consumption scenarios provided in its embodiments. It should be noted that the appendix... Figure 2 The electricity theft detection device shown is based on an electricity consumption scenario and is used to perform the functions described in this application. Figure 1 The methods shown in the embodiments are for illustrative purposes only, illustrating the parts relevant to the embodiments of this application. For specific technical details not disclosed, please refer to this application. Figure 1 The example shown.
[0051] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of an electricity theft detection device based on an electricity consumption scenario provided in an embodiment of this application. For example... Figure 2 As shown, the device includes:
[0052] The feature acquisition and fusion module 201 is used to acquire electrical parameters in the power consumption scenario. When the electrical parameters are greater than the set electrical parameter threshold, visual frames in the power consumption scenario are acquired, and the electrical parameters and the visual frames are weighted and fused to obtain fused features.
[0053] The electricity theft detection module 202 is used to compare the fused features with a set electricity theft feature library and output the electricity theft behavior in the electricity theft feature library that has the highest matching degree with the fused features;
[0054] The model update module 203 is used to set the update cycle and sample number based on the electricity consumption scenario, and update the weights of the electricity parameters and the visual frame during weighted fusion based on the update cycle and the sample number.
[0055] In one possible implementation, the feature acquisition and fusion module 201 is specifically used for:
[0056] If an abnormality duration threshold is set, and the duration of the electrical parameter being greater than the set electrical parameter threshold is longer than the abnormality duration threshold, visual frames of the meter to be identified in the electricity consumption scenario are collected.
[0057] In one possible implementation, the feature acquisition and fusion module 201 is specifically used for:
[0058] The update cycle and the number of samples are different for each of the described electricity consumption scenarios.
[0059] In one possible implementation, the feature acquisition and fusion module 201 is specifically used for:
[0060] The electrical parameters include current imbalance and power fluctuation coefficient. The electricity usage scenarios include a first electricity usage scenario, a second electricity usage scenario, and a third electricity usage scenario with different weightings. The visual frames include the percentage of damaged seals and the outline of foreign objects in the wiring. The weighted fusion of the electrical parameters and the visual frames to obtain fusion features includes: selecting the weighting set corresponding to the electricity usage scenario where the meter to be identified is located, and weighted fusion of the selected weighting set, the electrical parameters, and the visual frames to obtain fusion features.
[0061] In one possible implementation, the electricity theft detection module 202 is specifically used for:
[0062] The output corresponds to the electricity theft behavior in the electricity theft feature database that has the highest matching degree with the fused feature, and the electricity theft control based on the electricity theft behavior includes:
[0063] A first confidence interval and a second confidence interval are set. The matching degree between each electricity theft behavior in the electricity theft feature database and the fused feature is calculated. The electricity theft feature corresponding to the highest matching degree is selected. If the highest matching degree is in the first confidence interval, an electricity theft alarm is triggered and the location of the electricity meter to be identified is uploaded. If the highest matching degree is in the second confidence interval, the visual frame of the electricity meter to be identified in the electricity consumption scenario is collected for secondary identification.
[0064] In one possible implementation, the model update module 203 is specifically used for:
[0065] The step of updating the weighted fusion of the electrical parameters and the visual frame based on the update period and the number of samples includes:
[0066] Electricity theft samples are collected based on the number of samples and the update period. Factors that change when electricity theft occurs are selected based on the electricity theft samples. The weights of the electrical parameters and the visual frame are updated based on the factors that change when electricity theft occurs.
[0067] In one possible implementation, the model update module 203 is specifically used for:
[0068] The ratio of the number of updated weights to the total number of weights is less than a set update threshold.
[0069] Those skilled in the art will clearly understand that the technical solutions of the embodiments of this application can be implemented by means of software and / or hardware. In this specification, "unit" and "module" refer to software and / or hardware that can independently complete or cooperate with other components to complete a specific function, wherein the hardware may be, for example, a field-programmable gate array (FPGA), an integrated circuit (IC), etc.
[0070] Each processing unit and / or module in the embodiments of this application can be implemented by an analog circuit that implements the functions described in the embodiments of this application, or by software that executes the functions described in the embodiments of this application.
[0071] See Figure 3 It shows a schematic diagram of the structure of an electronic device according to an embodiment of this application, which can be used to implement... Figure 1 The method in the illustrated embodiment. (As shown) Figure 3 As shown, the electronic device 300 may include: at least one central processing unit 301, at least one network interface 304, user interface 303, memory 305, and at least one communication bus 302.
[0072] The communication bus 302 is used to enable communication between these components.
[0073] The user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.
[0074] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).
[0075] The central processing unit 301 may include one or more processing cores. The central processing unit 301 connects to various parts within the electronic device 300 using various interfaces and lines. It executes various functions of the terminal 300 and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305. Optionally, the central processing unit 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The central processing unit 301 may integrate one or more of the following: a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip without being integrated into the central processing unit 301.
[0076] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory 305 may include a non-transitory computer-readable storage medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned central processing unit 301. Figure 3 As shown, the memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and program instructions.
[0077] exist Figure 3In the illustrated electronic device 300, the user interface 303 is mainly used to provide an input interface for the user and to acquire user input data; while the central processing unit 301 can be used to call the application program stored in the memory 305 and specifically perform the following operations:
[0078] S101. Collect electrical parameters of the electricity meter to be identified in the electricity consumption scenario. When the electrical parameters are greater than the set electrical parameter threshold, collect the visual frame of the electricity meter to be identified in the electricity consumption scenario. Weightedly fuse the electrical parameters and the visual frame to obtain the fusion feature.
[0079] S102. Compare the fused features with the set electricity theft feature database, output the electricity theft behavior in the electricity theft feature database that has the highest matching degree with the fused features corresponding to the electricity meter to be identified, and carry out electricity theft control based on the electricity theft behavior;
[0080] S103. Based on the electricity consumption scenario, set the update cycle and sample number, and update the weighted reassembly when the electrical parameters and the visual frame are weighted and fused based on the update cycle and the sample number.
[0081] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, as well as magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.
[0082] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.
[0083] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.
[0084] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between devices or units may be electrical or other forms.
[0085] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0086] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0087] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0088] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.
[0089] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of embodiments of this disclosure upon considering the specification and practicing the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described herein. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.
Claims
1. A method for identifying electricity theft based on electricity usage scenarios, characterized in that, The method includes: The electrical parameters of the electricity meter to be identified in the electricity consumption scenario are collected. When the electrical parameters are greater than the set electrical parameter threshold, the visual frame of the electricity meter to be identified in the electricity consumption scenario is collected. The electrical parameters and the visual frame are weighted and fused to obtain the fused feature. The fused features are compared with a set electricity theft feature database, and the electricity theft behavior with the highest matching degree with the fused features in the electricity theft feature database corresponding to the electricity meter to be identified is output. Electricity theft control is carried out based on the electricity theft behavior. The update cycle and sample number are set based on the electricity consumption scenario. The weighted reassembly of the electrical parameters and the visual frame is updated based on the update cycle and the sample number.
2. The method for identifying electricity theft based on electricity consumption scenarios according to claim 1, characterized in that, The electrical parameters include current imbalance and power fluctuation coefficient. The electricity usage scenarios include a first electricity usage scenario, a second electricity usage scenario, and a third electricity usage scenario with different weightings. The visual frames include the percentage of damaged seals and the outline of foreign objects in the wiring. The weighted fusion of the electrical parameters and the visual frames to obtain fusion features includes: selecting the weighting set corresponding to the electricity usage scenario where the meter to be identified is located, and weighted fusion of the selected weighting set, the electrical parameters, and the visual frames to obtain fusion features.
3. The method for identifying electricity theft based on electricity consumption scenarios according to claim 2, characterized in that, The step of updating the weighted fusion of the electrical parameters and the visual frame based on the update period and the number of samples includes: Electricity theft samples are collected based on the number of samples and the update period. Factors that change when electricity theft occurs are selected based on the electricity theft samples. The weights of the electrical parameters and the visual frame are updated based on the factors that change when electricity theft occurs.
4. The method for identifying electricity theft based on electricity consumption scenarios according to claim 2, characterized in that, The output corresponds to the electricity theft behavior in the electricity theft feature database that has the highest matching degree with the fused feature, and the electricity theft control based on the electricity theft behavior includes: A first confidence interval and a second confidence interval are set. The matching degree between each electricity theft behavior in the electricity theft feature database and the fused feature is calculated. The electricity theft feature corresponding to the highest matching degree is selected. If the highest matching degree is in the first confidence interval, an electricity theft alarm is triggered and the location of the electricity meter to be identified is uploaded. If the highest matching degree is in the second confidence interval, the visual frame of the electricity meter to be identified in the electricity consumption scenario is collected for secondary identification.
5. The method for identifying electricity theft based on electricity usage scenarios according to claim 1, characterized in that, The step of collecting visual frames of the meter to be identified in the power consumption scenario when the electrical parameter is greater than the set electrical parameter threshold includes: setting an abnormality duration threshold; if the time when the electrical parameter is greater than the set electrical parameter threshold is longer than the abnormality duration threshold, collecting visual frames of the meter to be identified in the power consumption scenario.
6. The method for identifying electricity theft based on electricity consumption scenarios according to claim 1, characterized in that, The update cycle and the number of samples are different for each of the described electricity consumption scenarios.
7. The method for identifying electricity theft based on electricity usage scenarios according to claim 1, characterized in that, The ratio of the number of updated weights to the total number of weights is less than a set update threshold.
8. A device for detecting electricity theft based on electricity usage scenarios, characterized in that, The apparatus implements the steps of the method as described in any one of claims 1-7, the apparatus comprising: The feature acquisition and fusion module is used to acquire electrical parameters in the power consumption scenario. When the electrical parameters are greater than the set electrical parameter threshold, visual frames in the power consumption scenario are acquired, and the electrical parameters and the visual frames are weighted and fused to obtain fused features. The electricity theft detection module is used to compare the fused features with a set electricity theft feature library and output the electricity theft behavior in the electricity theft feature library that has the highest matching degree with the fused features; The model update module is used to set the update cycle and sample number based on the electricity consumption scenario, and to update the weights of the electrical parameters and the visual frame during weighted fusion based on the update cycle and the sample number.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-7.
10. A computer-readable storage medium having a computer program stored thereon, the computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform the steps of the method as claimed in any one of claims 1-7.