Default power consumption behavior identification method, electronic device and storage medium

Abstract

The application provides a defaulting electricity behavior identification method, an electronic device and a storage medium. By obtaining user profile data and electricity information, basic data is provided for subsequent risk judgment. According to the user profile data, a high-risk community is determined, and the high-risk community is screened based on multi-dimensional profile data to avoid resource waste of indiscriminate investigation. According to the user profile data and the high-risk community, a risk user is determined to further lock the risk user in the high-risk community; according to the user profile data and the risk user, a high-risk user is determined to further determine the high-risk user in the risk user; three-level screening greatly reduces the target range of subsequent behavior identification, reduces invalid processing amount, and significantly improves the identification efficiency. According to the electricity information, the electricity behavior of the high-risk user is identified, and the electricity behavior of the high-risk user is accurately distinguished based on multi-dimensional electricity information through multi-layer verification.

Description

Technical Field

[0001] This application relates to the field of electricity consumption behavior identification technology, and in particular to a method, electronic device and storage medium for identifying defaulted electricity consumption behavior. Background Technology

[0002] With the global energy structure transformation and the rapid development of the electric vehicle industry, the penetration rate of electric vehicles in the automotive market is increasing. Some older residential areas lack the public environment for building charging facilities, leading some users to illegally install charging piles under their household electricity meters or even use extension cords. Such behavior not only constitutes illegal electricity use but also poses significant safety hazards. Current technologies for detecting illegal charging typically rely on manual analysis and investigation, which is inefficient. Installing monitoring equipment for identifying illegal charging is costly. Therefore, a more efficient and low-cost investigation method is needed. Summary of the Invention

[0003] In view of this, the purpose of this application is to propose a method, electronic device and storage medium for identifying illegal electricity use, so as to solve some or all of the problems existing in the background art.

[0004] To achieve the above objectives, this application provides a method for identifying violations of electricity usage regulations, comprising:

[0005] Obtain user profile data and the corresponding electricity consumption information; Based on the user profile data, high-risk residential areas were identified; Based on the user profile data and the high-risk communities, risky users are identified; Based on the user profile data and the risky users, high-risk users are identified; Based on the electricity consumption information, the electricity consumption behavior of the high-risk users is identified.

[0006] Optionally, the user profile data includes residential community information, charging resource information around the residential community, travel demand information corresponding to the residential community, and user charging demand information within the residential community; Based on the user profile data and the electricity consumption information, high-risk residential areas are identified, including: The score of the residential community is determined based on the information on the residential community, the charging resources around the residential community, the travel demand information corresponding to the residential community, the charging demand information of users in the residential community, and the conditions of illegal electricity use. If the score of the residential community is less than a preset risk assessment threshold, the residential community corresponding to the user profile data is determined to be a high-risk community.

[0007] Optionally, a score for the residential community is determined based on the information about the residential community, the charging resources around the residential community, the travel demand information corresponding to the residential community, the charging demand information of users within the residential community, and the conditions of illegal electricity use. This score includes: Based on the residential community information and the conditions of illegal electricity use, a first score is determined; The second score is determined based on the information on charging resources around the residential community and the conditions of illegal electricity use; The third score is determined based on the travel demand information corresponding to the residential community and the illegal electricity use conditions. Based on the charging demand information of users in the residential community and the conditions of illegal electricity use, a fourth score is determined; The score of the residential community is determined based on the first score, the second score, the third score, and the fourth score.

[0008] Optionally, the user profile data includes the user's location; Based on the user profile data and the high-risk residential areas, risky users are identified, including: Users whose location matches the location of their residential community in the high-risk community are defined as high-risk users.

[0009] Optionally, the user profile data includes the status of the independent electricity meter for the applied charging pile; Based on the user profile data and the risky users, high-risk users are identified, including: Users other than those whose independent electricity meter for charging piles is in the "application already applied" status are considered high-risk users.

[0010] Optionally, the electricity consumption information includes electricity load information, electricity current information, and electricity consumption information; Based on the electricity consumption information, identify the electricity consumption behavior of the high-risk users, including: Within a preset time period, a set of time periods for illegal electricity use is determined based on the electricity load information, the electricity current information, and the electricity consumption information; Based on the set of time periods of illegal electricity use, the level of suspicion is determined; In response to the suspicion level being greater than a preset suspicion threshold, the high-risk user is determined to be a user violating electricity regulations; In response to the suspicion level being less than or equal to a preset suspicion threshold, the high-risk user is determined to be a regular electricity user.

[0011] Optionally, within a preset time period, a set of time periods for illegal electricity use is determined based on the electricity load information, the electricity current information, and the electricity consumption information, including: Within a preset time period, a set of time periods for electricity load is determined based on the electricity load information; Within a preset time period, a set of time periods for electricity consumption is determined based on the electricity consumption information; Within a preset time period, a set of time periods for electricity consumption is determined based on the electricity consumption information; Calculate the similarity between any two or three of the set of electricity load time periods, the set of electricity current time periods, and the set of electricity consumption time periods; In response to the similarity being greater than a preset similarity threshold, the time periods corresponding to the similarity are merged into a set of time periods for illegal electricity use.

[0012] Optionally, calculating the similarity between any two or three of the set of electricity load time periods, the set of electricity current time periods, and the set of electricity consumption time periods includes: Calculate the first overlap duration between the set of electricity load time periods and the set of electricity current time periods; In response to the first overlap duration being greater than or equal to a preset overlap duration threshold, a first proportion of the first overlap duration within the set of electricity load time periods is calculated; a second proportion of the first overlap duration within the set of electricity current time periods is calculated; and the average of the first proportion and the second proportion is taken as the similarity. In response to the first overlap duration being less than a preset overlap duration threshold, a second overlap duration is calculated for the electricity load time period set and the electricity consumption time period set; In response to the second overlap duration being greater than or equal to a preset overlap duration threshold, a third proportion of the second overlap duration within the set of electricity load time periods is calculated; a fourth proportion of the second overlap duration within the set of electricity consumption time periods is calculated; and the average of the third proportion and the fourth proportion is taken as the similarity. In response to the second overlap duration being less than a preset overlap duration threshold, the third overlap duration of the set of electricity load time periods, the set of electricity current time periods, and the set of electricity consumption time periods is calculated; the fifth proportion of the third overlap duration within the set of electricity load time periods is calculated; the sixth proportion of the third overlap duration within the set of electricity current time periods is calculated; the seventh proportion of the third overlap duration within the set of electricity consumption time periods is calculated; and the average of the fifth, sixth, and seventh proportions is used as the similarity.

[0013] Based on the same inventive concept, this disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method described above when executing the computer program.

[0014] Based on the same inventive concept, this disclosure also provides a non-transitory computer-readable storage medium that stores computer instructions for causing a computer to perform the method described above.

[0015] As can be seen from the above, the method, electronic device, and storage medium for identifying defaulted electricity use provided in this application offer complete and relevant basic data for subsequent risk assessment by acquiring user profile data and electricity usage information. Based on user profile data, high-risk communities are identified. High-risk communities are screened based on multi-dimensional profile data, shifting the focus of supervision from "all communities" to "high-risk concentrated communities," avoiding the waste of resources from indiscriminate screening. Based on user profile data and high-risk communities, risky users are identified, further locking down risky users within high-risk communities, completing the initial downward shift from "community level" to "user level." Based on user profile data and risky users, high-risk users are identified, further identifying high-risk users among risky users, completing the action of locking down high-risk users. This three-level screening significantly reduces the target scope of subsequent behavior identification, reduces invalid processing, and significantly improves identification efficiency. Based on electricity usage information, electricity use behavior of high-risk users is identified. Based on multi-dimensional electricity usage information, through layer-by-layer verification of time period set construction, similarity calculation, and suspicion determination, accurate differentiation of the electricity use behavior of high-risk users is achieved. This approach effectively avoids the limitations of relying on a single data dimension for identification, reduces the probability of misjudgments and omissions, and ensures accurate differentiation between users who violate electricity regulations and those who use electricity normally. Based on existing user profiles and electricity monitoring data, it eliminates the need for additional monitoring equipment and reliance on manual on-site inspections. Identification is completed in a data-driven, intelligent manner, significantly reducing regulatory costs such as equipment investment and manpower consumption while ensuring identification effectiveness. This solves the technical problems of low efficiency and high cost associated with traditional inspection methods. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic flowchart of a method for identifying illegal electricity use according to an embodiment of this application; Figure 2 This is a schematic diagram illustrating the process for determining high-risk cells according to an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a device for identifying illegal electricity use according to an embodiment of this application; Figure 4 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0019] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0020] As described in the background, according to relevant industry data, the annual growth rate of electric vehicle ownership in some first-tier cities has exceeded 30%, with households becoming the core consumer group for electric vehicles. However, the contradiction between the explosive growth in electric vehicle charging demand and the lagging development of charging infrastructure is becoming increasingly prominent, especially in older residential areas and urban villages. Older residential areas generally suffer from outdated construction and planning, lacking dedicated space and power capacity for charging facilities. On the one hand, parking spaces are scarce, making it difficult to establish centralized charging stations in public areas; on the other hand, some residential power grids are aging, and large-scale installation of charging piles may exceed the existing power load capacity, posing safety risks such as circuit overload and short circuits, making it difficult for property management and power departments to approve applications for new charging facilities. Faced with this predicament, some electric vehicle users choose to illegally use electricity to meet their charging needs, leading to various dangerous behaviors. For example, some users directly run wires under their own residential meters, bypassing the power department's standardized approval process to install private charging piles. These privately installed charging stations often lack professional safety inspections, have non-standard wiring connections, and are not equipped with necessary safety devices such as overcurrent protection and leakage protection. Long-term use can easily lead to overheating and short circuits, potentially causing fires. Even worse, some resort to the extreme method of "flying wire charging"—illegally hanging wires from the windows and balconies of high-rise residential buildings to connect to charging stations. These wires are constantly exposed to outdoor wind, rain, and sun, causing the insulation layer to age and break down. This not only poses a risk of electric shock, but the fallen wires can also threaten the safety of pedestrians and vehicles in the community. A typical case occurred in a certain city: a resident of an old residential area hung a temporary wire from the 15th-floor window to charge an electric vehicle below. Because the insulation layer of the wire was corroded and damaged by rainwater, a short circuit occurred, igniting nearby debris. The fire quickly spread to the residential building, causing serious property damage. Besides directly threatening personal and property safety, this kind of illegal electricity use has multiple negative impacts. From a power management perspective, the unauthorized installation of charging piles and the use of extension cords for charging fall under the category of illegal electricity use. Users bypass the dedicated meters for charging piles, potentially leading to electricity theft and resulting in power losses and revenue losses for the national grid. Furthermore, the unstable load caused by such illegal electricity use can interfere with the overall power supply quality of the community, affecting the normal electricity use of other residents. From a management efficiency perspective, existing methods for monitoring such illegal charging activities have significant shortcomings: traditional manual inspections rely on staff patrolling each community and building, which is not only costly in terms of manpower and resources but also inefficient, making it difficult to achieve 24 / 7, comprehensive monitoring. While installing large-scale monitoring equipment and sensors in communities for real-time monitoring could improve accuracy, the high costs of equipment procurement, installation, and maintenance place a heavy burden on both property management and power companies, making widespread application difficult.

[0021] To solve the above technical problems, such as Figure 1 As shown, this application provides a method for identifying violations of electricity usage regulations, including the following steps: Step 101: Obtain user profile data and the electricity consumption information corresponding to the user profile data.

[0022] In this step, for example, the user profile data needs to cover core information such as residential community information, surrounding charging resources information, travel demand information corresponding to the residential community, user charging demand information within the residential community, user location, and the status of the independent electricity meter for the applied charging pile. Electricity usage information includes electricity load information, electricity current information, and electricity consumption information, ensuring a one-to-one correspondence between the acquired data and the user profile data, comprehensively covering the key dimensions required for subsequent risk assessment and behavior identification. This provides complete and corresponding basic data for subsequent high-risk community identification, high-risk user screening, high-risk user determination, and electricity behavior identification, avoiding logical breaks in identification due to missing or mismatched data, and ensuring the smooth progress of the entire identification process.

[0023] Step 102: Based on the user profile data, identify high-risk communities.

[0024] In this step, based on the residential community information, surrounding charging resource information, travel demand information, and user charging demand information within the residential community from the user profile data, and combined with the conditions of illegal electricity use, a first score, a second score, a third score, and a fourth score are determined respectively. These four scores are then integrated through a reasonable calculation method to obtain a score for the residential community. This score is compared with a preset risk assessment threshold. If the score is lower than the preset risk assessment threshold, the residential community is determined to be a high-risk community. By comparing multi-dimensional data scores with thresholds, communities with concentrated illegal electricity use risks are accurately screened, focusing the risk scope from "all communities" to "high-risk communities," reducing the scope of subsequent user screening and improving identification efficiency.

[0025] Step 103: Identify high-risk users based on the user profile data and the high-risk communities.

[0026] In this step, user location information is extracted from user profile data and matched with the residential locations of identified high-risk communities. Users whose locations match those of high-risk communities are classified as high-risk users, thus filtering out all users residing in high-risk communities. Based on high-risk communities, potential risk targets are further identified, completing the initial downward delineation of risk from the "community level" to the "user level," narrowing the scope of subsequent high-risk user identification and improving the targeting of risk screening.

[0027] Step 104: Based on the user profile data and the risky users, identify high-risk users.

[0028] In this step, the status of independent electricity meters for charging piles applied for in the user profile data of risky users is checked. Users whose independent electricity meters for charging piles are already applied for are excluded, and the remaining risky users are high-risk users. By eliminating the group of risky users with a very high probability of compliant electricity use, the focus is precisely shifted from "risky users" to "high-risk users," significantly narrowing the target scope for subsequent electricity behavior identification and reducing the cost of ineffective identification.

[0029] Step 105: Identify the electricity consumption behavior of the high-risk users based on the electricity consumption information.

[0030] In this step, within a preset time period, sets of time periods for electricity load, electricity current, and electricity consumption are determined based on electricity load information, electricity current information, and electricity consumption information, respectively. The similarity between any two or three of these time periods is calculated. If the similarity is greater than a preset similarity threshold, the corresponding time periods are merged to form a set of illegal electricity consumption time periods. Based on this set of illegal electricity consumption time periods, a suspicion level is determined. If the suspicion level is greater than a preset suspicion threshold, the user is identified as a high-risk user for illegal electricity consumption; if the suspicion level is less than or equal to the preset suspicion threshold, the user is identified as a regular user. Through cross-validation and similarity calculation of multi-dimensional electricity consumption data, and suspicion level determination, accurate differentiation of high-risk user electricity consumption behavior is achieved, effectively identifying illegal and regular users, ensuring the accuracy of the identification results, and reducing identification costs by eliminating the need for manual investigation or additional monitoring equipment.

[0031] In steps 101-105, step 101 provides complete and relevant basic data for all subsequent risk assessment stages by comprehensively collecting user profile data (including residential community information, surrounding charging resources, travel and charging needs, user location, application status of independent electricity meters for charging piles, etc.) and corresponding electricity information (including electricity load, current, and electricity consumption information). This completely solves the identification bias problem caused by data missing or mismatch, ensuring that the entire identification process has reliable data support. Steps 102-104 employ a three-tiered screening mechanism of "community-user-high-risk user" to achieve a gradual and precise narrowing of the risk scope. Step 102, based on multi-dimensional archive data, identifies high-risk communities, shifting the regulatory focus from "all communities" to "high-risk concentrated communities," avoiding the waste of resources from indiscriminate screening. Step 103 further identifies high-risk users within these communities, completing the initial downward shift from "community level" to "user level." Step 104 removes compliant users who have applied for independent charging pile meters, ultimately focusing on the core high-risk user group. This three-tiered screening significantly reduces the target scope for subsequent behavior identification, decreases invalid processing, and significantly improves identification efficiency. Step 105, based on multi-dimensional electricity consumption information, achieves precise differentiation of high-risk user electricity consumption behavior through layered verification including time period set construction, similarity calculation, and suspicion determination. This is achieved through data analysis of electricity load, current, and electricity consumption. The cross-comparison and fusion analysis of three types of data effectively avoids the one-sidedness of identification based on a single data dimension, reduces the probability of misjudgment and omission, and ensures accurate identification of users who violate electricity regulations and those who use electricity normally. Relying on existing user profile data and electricity monitoring data, it eliminates the need for additional monitoring equipment and reliance on manual on-site inspections. Identification is completed in a data-driven, intelligent manner, significantly reducing regulatory costs such as equipment investment and manpower consumption while ensuring identification effectiveness. This solves the core pain points of traditional inspection methods, namely low efficiency and high cost. Through steps 101-105, a closed-loop system of "data support - scope focus - accurate identification" is formed, achieving both efficient and accurate identification of illegal electricity use and effective control of inspection costs. This provides a scientific and feasible solution for electricity safety supervision, and can specifically address the safety hazards and management challenges caused by illegal electricity use such as unauthorized charging of electric vehicles.

[0032] In some embodiments, such as Figure 2 As shown, for step 102, the user profile data includes residential community information, charging resource information around the residential community, travel demand information corresponding to the residential community, and user charging demand information within the residential community. Based on the user profile data and the electricity consumption information, high-risk residential areas are identified, including the following steps: Step 1021: Determine the score of the residential community based on the information on the residential community, the charging resources around the residential community, the travel demand information corresponding to the residential community, the charging demand information of users in the residential community, and the conditions of illegal electricity use.

[0033] In this step, based on the residential community information, surrounding charging resource information, travel demand information corresponding to the residential community, user charging demand information within the residential community, and illegal electricity use conditions, a score for the residential community is determined, including the following steps: Step 10211: Determine the first score based on the residential community information and the illegal electricity use conditions.

[0034] In this step, the residential community information includes the year the residential community was built and the number of public charging piles within the residential community. In response to the residential community's year of construction being greater than or equal to a preset year and / or the number of public charging piles within the residential community being zero, i.e., the residential community information meets the conditions for illegal electricity use, a first score is determined for the residential community information. In this embodiment, the illegal electricity use conditions include two conditions corresponding to the residential community information. Multiple illegal electricity use conditions can be set according to actual circumstances, and the score is the average of the number of conditions. No specific limitations are made here. For example, a residential community is 15 years or older and has not been equipped with public charging piles (the planning and construction conditions for charging piles in older school areas are usually poor). The residential community information is assigned a weight of 0.4. When the residential community's year of construction is greater than or equal to a preset year or the number of public charging piles within the residential community is zero, i.e., the residential community information only meets one of the illegal electricity use conditions, it can only obtain 0.2 points (half the score). If a residential community's construction year is greater than or equal to a preset age and the number of public charging piles within the community is zero, meaning the community meets both conditions for illegal electricity use, then the score is 0.4 points (out of 100). By focusing on the two core attributes of a residential community—its construction year and the number of public charging piles—and combining these with the conditions for illegal electricity use to establish quantitative scoring rules, the high-risk characteristics of older communities and communities without internal charging facilities are accurately captured. The design of weight allocation and the calculation of the average score for multiple conditions not only highlights the impact of the community's basic attributes on the risk of illegal electricity use, but also achieves a refined distinction of risk level through situational scoring (different scores for meeting one or more conditions), avoiding the bias of a "one-size-fits-all" judgment and providing a basic dimension support for the comprehensive scoring of communities that fits the actual scenario.

[0035] Step 10212: Determine the second score based on the charging resource information around the residential community and the illegal electricity use conditions.

[0036] In this step, the charging resource information around the residential community includes the number of public charging piles within a preset distance from the residential community and the vacancy rate of these public charging piles. In response to the number of public charging piles within the preset distance from the residential community being less than or equal to a preset charging pile number threshold and / or the vacancy rate of these public charging piles being lower than a preset vacancy rate threshold, a second score is determined corresponding to the charging resource information around the residential community. That is, when the charging resource information around the residential community meets the conditions for illegal electricity use, the second score is determined. In this embodiment, the illegal electricity use conditions include two illegal electricity use conditions corresponding to the charging resource information around the residential community. Multiple illegal electricity use conditions can also be set according to the actual situation, and the score is the average of the number of conditions. No specific limitation is made here. For example, if the number of public charging piles within a 3km radius of the residential community is less than two, and the average vacancy rate of these public charging piles is low, for example, below 30%, it indicates a shortage of charging resources. The charging resource information around residential communities is assigned a weight of 0.25. If the number of public charging piles within a preset distance from the residential community is less than or equal to a preset threshold, or if the idle rate of these public charging piles is lower than a preset idle rate threshold, it indicates that the charging resource information around the residential community meets one condition for illegal electricity use, and the second score is 0.12 points (half the score). If the number of public charging piles within a preset distance from the residential community is less than or equal to a preset threshold and the idle rate of these public charging piles is lower than a preset idle rate threshold, it indicates that the charging resource information around the residential community meets two conditions for illegal electricity use, and the second score is 0.25 points (full score). Based on the two key indicators of the number of charging piles within a preset distance and the idle rate, the accessibility and sufficiency of external charging resources are quantitatively assessed. By setting thresholds and scoring according to different situations, communities with scarce external charging resources and intense competition for use are accurately identified—users in these communities have a significantly increased probability of illegal electricity use due to the inconvenience of external charging. This step supplements the external risk dimension beyond the internal charging resources of the community, making the scoring system more comprehensive and further improving the accuracy of subsequent comprehensive risk assessments.

[0037] Step 10213: Determine the third score based on the travel demand information corresponding to the residential community and the illegal electricity use conditions.

[0038] In this step, the travel demand information corresponding to the residential community includes the occupancy rate of the residential community and the number of users whose average monthly electricity consumption exceeds a preset electricity threshold. In response to the residential community occupancy rate being less than the preset occupancy rate threshold and / or the number of users whose average monthly electricity consumption exceeds the preset electricity threshold exceeding a preset user number threshold, i.e., the travel demand information corresponding to the residential community meets the illegal electricity use conditions, a third score corresponding to the user charging demand information of the residential community is determined. In this embodiment, the illegal electricity use conditions include two illegal electricity use conditions corresponding to the travel demand information of the residential community. Multiple illegal electricity use conditions can also be set according to the actual situation, and the score is the average of the number of conditions. No specific limitation is made here. For example, if the occupancy rate of the residential community is less than 20% (which can be determined based on the user's average monthly electricity consumption being less than 10 kWh, i.e., the proportion of vacant users), and the number of users whose average monthly electricity consumption exceeds 800 kWh exceeds 15%, the travel demand information corresponding to the residential community is assigned a weight of 0.2. When the occupancy rate of a residential community is less than a preset occupancy rate threshold, or the number of users whose average monthly electricity consumption exceeds a preset electricity consumption threshold exceeds a preset user number threshold, it indicates that the travel demand information corresponding to the residential community meets one of the illegal electricity use conditions, and the third score is 0.1 points (half the score). When the occupancy rate of a residential community is less than a preset occupancy rate threshold, and the number of users whose average monthly electricity consumption exceeds a preset electricity consumption threshold exceeds a preset user number threshold, it indicates that the travel demand information corresponding to the residential community meets both illegal electricity use conditions, and the third score is 0.2 points (full score). Taking occupancy rate and the proportion of high-electricity-consumption users as starting points, this indirectly reflects the travel dependence of community users and the intensity of potential charging demand. Low occupancy rate means high vacancy rate, which may indicate hidden spaces for private illegal charging; high proportion of high-electricity-consumption users suggests that the number of electric vehicles may be high, and the charging demand is strong. Through the quantitative scoring in this step, the characteristics of communities that breed illegal electricity use risks due to the mismatch between travel demand and charging demand are effectively discovered, adding a demand-side risk assessment dimension to the comprehensive score, making risk judgment more targeted.

[0039] Step 10214: Determine the fourth score based on the user charging demand information in the residential community and the illegal electricity use conditions.

[0040] In this step, the user charging demand information within the residential community includes: the location of the residential community; in response to the residential community being located in a first environment without charging conditions and / or having no means of transportation nearby, a fourth score is determined corresponding to the user charging demand information within the residential community. In this embodiment, the illegal electricity use conditions include two illegal electricity use conditions corresponding to the user charging demand information within the residential community. Multiple illegal electricity use conditions can also be set according to actual circumstances, and their scores are averaged based on the number of conditions. No specific limitations are made here. For example, if the residential community is located in the suburbs / next to a main road, and there are no subway, bus, or other modes of transportation within 3km of the residential community, a fourth score is determined corresponding to the user charging demand information within the residential community. A weight of 0.15 is assigned to the user charging demand information within the residential community. When the residential community is located in a first environment without charging conditions or has no means of transportation nearby, it indicates that the user charging demand information within the residential community meets one of the illegal electricity use conditions, and the fourth score is determined to be 0.07 points (half the score). When a residential community is located in an environment without charging facilities and there are no other means of transportation nearby, it indicates that the user's charging needs meet two conditions for illegal electricity use, and the fourth score is determined to be 0.15 points (out of 100). Focusing on the community's geographical location (e.g., near a main road) and surrounding public transportation facilities, this approach accurately identifies high-demand scenarios where "there are no alternative charging options"—users in such communities have a high dependence on electric vehicles due to a lack of convenient public transportation, and the absence of charging facilities nearby makes illegal electric vehicle use the strongest. This step, starting from the urgency of users' actual charging needs, supplements the scenario-based risk assessment dimension, complementing other scoring dimensions and further improving the comprehensiveness of community risk quantification.

[0041] Step 10215: Determine the score of the residential community based on the first score, the second score, the third score, and the fourth score.

[0042] Specifically, the residential community's score is a comprehensive score based on the aforementioned information about the residential community, surrounding charging resources, travel demand, and user charging needs within the community. In other words, the first, second, third, and fourth scores are added together to obtain the community's overall score. By directly adding the scores from these four dimensions, a comprehensive quantitative integration of multi-dimensional risk factors is achieved. This method is logically clear and computationally simple, preserving the risk contribution of each dimension while providing a clear overall reflection of the community's illegal electricity use risk level through the total score, avoiding the bias of a single-dimensional assessment. The resulting comprehensive community score provides a unified and objective quantitative standard for subsequent screening of high-risk communities, ensuring that risk assessment is based on evidence.

[0043] Step 1022: In response to the fact that the score of the residential community is less than the preset risk assessment threshold, the residential community corresponding to the user profile data is determined to be a high-risk community.

[0044] In this step, for example, the preset risk assessment threshold can be 0.6 points. When the score of a residential community is less than the preset risk assessment threshold, it indicates that there is a large amount of information in the community that meets the conditions for illegal electricity use, and it is judged as a high-risk community. That is, it means that the residential community is an old community lacking public environments for building charging facilities, and is a high-risk community for illegal electricity use. By using the preset risk assessment threshold as the judgment threshold, the screening and locking of high-risk communities can be completed quickly. This step is based on the comprehensive score in step 1021, transforming the abstract risk quantification indicators into clear community risk level judgments, effectively separating areas with concentrated illegal electricity use risks from all communities in the region. Its core effect is to narrow the scope of supervision, avoid the waste of resources caused by indiscriminate screening, and focus the subsequent identification of risky users and high-risk users on high-risk areas, laying the foundation for improving the efficiency and targeting of the entire illegal electricity use identification process.

[0045] In some embodiments, for step 103, the user profile data includes the user's location; Based on the user profile data and the high-risk residential areas, risky users are identified, including: Users whose location matches the location of their residential community in the high-risk community are defined as high-risk users.

[0046] In this step, user profile data stores user locations. The user location information is extracted from the user profile data and matched with the residential locations of the identified high-risk communities. Users whose locations match the high-risk community locations are classified as high-risk users, thus filtering out all users residing in high-risk communities. Based on the high-risk communities, potential risk targets are further identified, completing the initial risk assessment from the "community level" to the "user level," narrowing the scope of subsequent high-risk user identification and improving the targeting of risk screening.

[0047] In some embodiments, for step 104, the user profile data includes the status of the independent electricity meter for the applied charging pile; Based on the user profile data and the risky users, high-risk users are identified, including: Users other than those whose independent electricity meter for charging piles is in the "application already applied" status are considered high-risk users.

[0048] Specifically, this embodiment first clarifies the core judgment criteria for the "application status of independent charging meter" in the user profile data. This status needs to be distinguished into three categories: "application completed, non-application completed, and application in progress." The "application completed" status specifically refers to the user having passed the standardized approval of the power department and completed the application and installation of the independent charging meter. Their charging behavior falls within the scope of compliant metering and supervision, and the probability of illegal electricity use is extremely low. The "non-application completed" and "application in progress" statuses are both considered non-compliant approval statuses. Based on the screened risk users (i.e., users living in high-risk communities), the user profile data corresponding to each risk user is checked one by one to extract their specific status information for applying for an independent charging meter. Risk users whose status is clearly "application completed" are directly eliminated. The remaining risk users who have not completed the compliant application (including non-application completed and application in progress) are classified as high-risk users because they live in high-risk communities (where there is a shortage of charging resources and a contradiction between demand and supply) and lack legal charging channels. Their motivation and probability of violating electricity use regulations such as illegally installing charging piles and charging with extension cords are significantly higher than other users. By using the key compliance indicator of the independent electricity meter status of charging piles, compliant users among the risk users are accurately screened and excluded. This avoids including users who have already compliantly charged their devices in the subsequent monitoring scope, significantly reducing the base for identifying high-risk users. This ensures that subsequent electricity behavior identification only targets users with genuine potential for violation, improving the accuracy and efficiency of the identification process. Combining the environmental risks of high-risk communities (insufficient charging resources, high demand) with the user's personal compliance status (not having applied for an independent electricity meter), a dual judgment logic of "environmental risk + personal behavioral risk" is formed. This ensures that the identified high-risk users possess both the objective conditions for violation and the subjective motivation for violation, making the identification of high-risk users more closely aligned with actual scenarios and avoiding misjudgments caused by a single dimension. After excluding compliant users, subsequent monitoring and data analysis of the electricity behavior of high-risk users do not require resources to be spent on low-risk individuals, reducing ineffective data processing and monitoring costs. This allows regulatory resources to be concentrated on core risk users, significantly improving the return on investment in identifying illegal electricity behavior.

[0049] In some embodiments, for step 105, the electricity consumption information includes electricity load information, electricity current information, and electricity consumption information; Based on the electricity consumption information, the electricity consumption behavior of the high-risk users is identified, including the following steps: Step 1051: Within a preset time period, determine the set of time periods for illegal electricity use based on the electricity load information, the electricity current information, and the electricity consumption information.

[0050] In this step, the set of illegal charging time periods can be determined based on preset illegal charging power consumption parameters. For example, the preset illegal charging power consumption parameters are shown in Table 1. Table 1. Preset power consumption parameters for unauthorized charging

[0051] Specifically, within a preset time period, based on the electricity load information, the electricity current information, and the electricity consumption information, a set of time periods for illegal electricity use is determined, including the following steps: Step 10511: Within a preset time period, determine the set of time periods for electricity load based on the electricity load information.

[0052] In this step, the electricity load information includes the electricity load and load fluctuation range. The preset time period needs to cover scenarios with high incidence of illegal electricity use. For example, electricity usage data is collected over a 24-hour period (including consecutive overnight periods), with a data collection frequency of 15 minutes / time (96 data points per day). Based on the load characteristics of illegal charging, a preset threshold standard is established: the electricity load value is stable at 3.5kW (portable charging pile) or 7kW (conventional home charging pile), lasting for ≥3 hours, and the load fluctuation range is ≤±0.5kW. Within the preset time period, all consecutive time periods that meet this threshold standard are selected and integrated in chronological order to form the electricity load time period set P{p1,…,pf}. Assuming the preset time period is January 1st-2nd, 2024, a high-risk user's electricity load is stable at 7kW from 23:00 on January 1st to 7:00 on January 2nd, with a fluctuation range of ±0.3kW; and stable at 3.5kW from 8:00 to 18:00 on January 2nd, with a fluctuation range of ±0.2kW. Both of these consecutive time periods meet the load threshold standard. For example, p1 is the time period from 00:00 to 00:15, p2 is the time period from 00:15 to 00:30, p3 is the time period from 00:30 to 00:45, and so on. Therefore, the set of electricity load time periods is P{p1,…,pf}. Based on this, time periods that meet the characteristics of illegal charging loads can be accurately identified, excluding the periodic load fluctuations caused by the start-stop and temperature control of common high-power household appliances (such as air conditioners and electric heaters). This provides a core load dimension basis for subsequent multi-dimensional data cross-validation, ensuring the targeted selection of illegal time periods.

[0053] Step 10512: Within a preset time period, determine the set of time periods for electricity consumption based on the electricity consumption information.

[0054] In this step, the electricity consumption information includes the current consumption and the current fluctuation range. Based on the above embodiment, the preset time period and data acquisition frequency are the same as those in the above steps. Based on the correspondence between power and current in a single-phase 220V circuit, the preset current threshold standard is: the electricity consumption current value is stable at 16A (corresponding to 3.5kW power) or 32A (corresponding to 7kW power), the duration is ≥3 hours, and the current fluctuation range is ≤±1A. Within the preset time period, all continuous time periods that meet this threshold standard are extracted and arranged in chronological order to form a set of electricity consumption time periods. Assuming the preset time period is January 1st-January 2nd, 2024, a high-risk user's electricity consumption current is stable at 32A from 23:00 on January 1st to 7:00 on January 2nd, with a fluctuation range of ±0.8A; and the electricity consumption current is stable at 16A from 8:00 to 18:00 on January 2nd, with a current fluctuation range of ±0.5A. Both of these continuous time periods meet the load threshold standard. For example, I1 represents the time period from 00:00 to 00:15, I2 represents the time period from 00:15 to 00:30, I3 represents the time period from 00:30 to 00:45, and so on. Therefore, the set of electricity load time periods is I{i1,…,im}. Based on this, time periods that meet the characteristics of illegal charging are filtered from the current dimension, which corresponds to the verification from the load dimension. Since the current of common household appliances fluctuates greatly and has a limited duration, this step can further filter out interference from non-charging high-current loads, improving the accuracy of subsequent similarity calculations.

[0055] Step 10513: Within a preset time period, determine the set of time periods for electricity consumption based on the electricity consumption information.

[0056] In this step, the electricity consumption information includes the electricity consumption. Based on the above embodiment, the preset time period and data collection frequency are the same as those in the above steps. The preset electricity consumption threshold standard is: the electricity consumption in a single continuous electricity consumption period is ≥10kWh, and the sum of the electricity consumption of 4 consecutive data points (i.e., 1 hour) is ≥2.5kWh (to avoid misjudgment caused by low standby power). Within the preset time period, all continuous time periods that meet this threshold standard are selected and integrated in chronological order to form the electricity consumption time period set Q{q1,…,qL}. Assuming the preset time period is January 1-2, 2024, a high-risk user's cumulative electricity consumption from 23:00 on January 1 to 7:00 on January 2 is 12.25kWh, with an average of 3.5kWh per hour, which meets the electricity consumption threshold standard. For example, q1 is the time period from 00:00 to 00:15, q2 is the time period from 00:15 to 00:30, q3 is the time period from 00:30 to 00:45, and so on. Therefore, the set of electricity load time periods is Q{q1,…,qL}. Based on the electricity consumption within the preset time periods, the scope of suspected violations is further narrowed down, providing electricity consumption dimension support for cross-validation of multi-dimensional data and reducing the one-sidedness of single-dimensional judgment.

[0057] Step 10514: Calculate the similarity between any two or three of the set of electricity load time periods, the set of electricity current time periods, and the set of electricity consumption time periods.

[0058] In this step, similarity is calculated following the logic of "first comparing pairs, then comparing all three": First, the first overlap duration between the electricity load time period set and the electricity current time period set is calculated. If the first overlap duration is greater than or equal to a preset overlap duration threshold (e.g., 2 hours), the proportion of the first overlap duration in both sets is calculated, and the average is taken as the similarity. If the first overlap duration is less than the preset threshold, the second overlap duration between the electricity load time period set and the electricity consumption time period set is calculated, and the similarity is calculated using the same logic. If the second overlap duration is still less than the preset threshold, the third overlap duration of all three is calculated, and its proportion in the three sets is calculated, and the average is taken as the similarity. The preset similarity threshold is 60%. (Example provided.) The time periods [2024-01-05 00:00, 2024-01-05 04:30] in the three time sets of electricity load, electricity current, and electricity consumption completely overlap, with the first overlap duration being 4.5 hours (≥ 2 hours). The proportion of this first overlap duration in both the load and current sets is 100%, resulting in a similarity of (100% + 100%) / 2 = 100%. Another time period [2024-01-10 23:15, 2024-01-11 02:45] also completely overlaps, with a similarity of 100%. By calculating the overlap of multiple time periods, cross-validation of potentially illegal time periods is achieved, avoiding misjudgments caused by anomalies in single-dimensional data. The similarity metric provides an objective basis for subsequent time period fusion, ensuring that the selected time periods possess multi-dimensional correlations of illegal characteristics.

[0059] Step 10515: In response to the similarity being greater than a preset similarity threshold, the time periods corresponding to the similarity are merged as the set of illegal electricity use time periods.

[0060] In this step, when the similarity is greater than the similarity threshold, the corresponding time period is determined to be a highly correlated suspected violation time period. All time periods that meet the criteria are deduplicated and merged (if there is partial overlap, they are merged into consecutive time periods), ultimately forming a set of illegal electricity usage time periods. For example, the similarity between the two time periods is 100% > 60%, and there is no repetition or partial overlap. Therefore, the set of time periods for illegal electricity use is {[2024-01-05 00:00, 2024-01-05 04:30], [2024-01-10 23:15, 2024-01-11 02:45]}. If a user's electricity load time period [2024-01-15 22:30, 2024-01-16 01:30] partially overlaps with the electricity current time period [2024-01-15 23:00, 2024-01-16 02:00], with an overlap duration of 2 hours and a similarity of 75% > 60%, then these two periods are merged into the set [2024-01-15 22:30, 2024-01-16 02:00]. This completes the integration of multi-dimensional suspected violation time periods, forming a unified and accurate set of violation electricity usage time periods, providing core data support for subsequent suspicion calculations. This step, through similarity threshold screening and time period fusion, significantly improves the accuracy and completeness of violation time period identification, avoiding the omission of violations verified across dimensions.

[0061] Step 1052: Determine the suspicion level based on the set of illegal electricity usage time periods.

[0062] In this step, based on the above embodiments, a set of time periods of illegal electricity use is obtained. To verify violations of electricity usage time, since electric vehicle charging and residential electricity consumption typically differ in their time periods, different weightings are assigned to different time windows: 1) During off-peak electricity pricing periods for residential users (such as the common 11:00 PM to 7:00 AM the next day), electric vehicle charging usually accounts for a higher proportion, while the frequency of use of regular high-power household appliances is relatively low (generally only refrigerators, routers, and other devices with low total power consumption; air conditioners, electric heaters, and other appliances have higher usage rates in specific seasons, but their high-power operation time is short). This is defined as the main window, and a weight is set to [value missing]. =1.4; 2) During non-residential regular electricity consumption periods (such as 8:00-18:00 on weekdays), residential users typically exhibit fewer charging characteristics during this period, which is defined as an auxiliary window and set with a weight of 1.4. =1.2; 3) Other time periods (weekdays 7:00-8:00, 18:00-23:00, non-weekdays 7:00-23:00), during which residents may intensively use high-power appliances such as electric water heaters and induction cookers, are defined as exclusion windows to avoid misjudgment, and a weight is set to 1.2; =1. Based on the set of illegal electricity usage time periods. and the preset weight set ,pass Calculate the degree of suspicion; For each time point The corresponding weights are assigned, where each time point corresponds to the time period in the example above, and the weight corresponding to that time period is used as the assigned weight. By weighted summing the weights of the above dimensions, the final suspicion score of the high-risk user is obtained. The higher the score, the greater the likelihood of illegal electricity use.

[0063] Step 1053: In response to the suspicion level being greater than a preset suspicion level threshold, determine the high-risk user as a user who violates electricity regulations.

[0064] In this step, the preset suspicion threshold needs to be determined through statistical analysis of a large amount of historical data on illegal electricity use and regular household electricity consumption data to ensure that the threshold can accurately distinguish between illegal electricity use and regular electricity use behavior (e.g., after empirical verification, the suspicion threshold is set to 8 points). When the suspicion of a high-risk user is greater than the preset suspicion threshold (e.g., score > 8 points), it indicates that the user has had multiple and prolonged periods of abnormal electricity use within the preset time period, and all dimensions of electricity use data show illegal characteristics, thus the user is determined to be an illegal electricity user.

[0065] In this embodiment, if the suspicion level is greater than a preset suspicion threshold for two consecutive days, the device can be added to the suspicion list for electricity usage investigation. This avoids false positives.

[0066] Step 1054: In response to the suspicion level being less than or equal to a preset suspicion level threshold, determine that the high-risk user is a regular electricity user.

[0067] In this step, when the suspicion level of a high-risk user is less than or equal to the preset suspicion level threshold (e.g., score ≤ 8 points), it indicates that the number of abnormal electricity usage periods is small, the duration is short, or there is only a slight abnormality in a single dimension of data, which is in line with the fluctuation range of normal household electricity usage, and the user is determined to be a normal electricity user.

[0068] In this embodiment, it can also be determined that the suspicion level is less than or equal to a preset suspicion level threshold for two consecutive days, thus identifying high-risk users as regular electricity users. By eliminating users based on the suspicion level for two consecutive days, the problem of misjudgment can be avoided.

[0069] Through steps 1051-1054, a multi-dimensional cross-validation system was constructed based on three core electricity consumption information categories: electricity load, current, and electricity consumption. This effectively avoids the one-sidedness of identification based on a single data dimension. By capturing the unique characteristics of illegal charging behavior, such as "fixed power / current, long-term stable operation, and high power consumption during specific periods," the system accurately distinguishes between regular household electricity consumption and illegal charging, significantly reducing the probability of false positives and false negatives, and ensuring the objectivity and accuracy of the identification results. Using a preset time period as the analysis cycle, and combining the temporal distribution patterns of illegal electricity consumption behavior (such as concentrated charging during off-peak hours at night), the system dynamically and comprehensively captures illegal behavior by filtering sets of illegal electricity consumption time periods and quantifying the degree of suspicion. This covers complex charging scenarios such as overnight charging and charging over multiple consecutive days, and highlights the behavioral characteristics of high-risk periods through weighted calculation of suspicion levels, making the identification logic more aligned with actual electricity consumption scenarios. Without relying on manual investigation or additional monitoring equipment, this system uses existing electricity monitoring data and user profiles to identify violations in a data-driven, intelligent manner. While ensuring accuracy, it significantly reduces regulatory costs such as equipment investment and manpower consumption, addressing the core pain points of traditional investigation methods: low efficiency and high cost. Through a progressive process of "identifying the set of violation time periods—calculating suspicion—threshold comparison and judgment," a standardized and replicable identification mechanism is formed. This mechanism is applicable to older communities with mostly ordinary smart meters and can quickly adapt to different regional electricity policies and violation characteristics, demonstrating broad applicability and providing efficient and feasible technical support for electricity safety supervision.

[0070] In some embodiments, for step 10514, calculating the similarity between any two or three of the set of electricity load time periods, the set of electricity current time periods, and the set of electricity consumption time periods includes the following steps: Step 105141: Calculate the first overlap duration between the set of electricity load time periods and the set of electricity current time periods.

[0071] In this step, the electricity load time period set is a continuous set of time periods that meet the characteristics of illegal charging loads, filtered based on electricity load information. The electricity current time period set is a continuous set of time periods that meet the characteristics of illegal charging currents, filtered based on electricity current information. The first overlap duration refers to the cumulative duration of the overlapping portion of all time periods in the two sets. During calculation, the time periods in the two sets need to be compared one by one to determine the overlap interval between individual time periods (if the time periods have no intersection, the overlap duration is 0). Then, the durations of all overlapping intervals are summed to obtain the first overlap duration. The preset overlap duration threshold needs to be set in conjunction with the typical duration of illegal charging; an example value of 2 hours is used. Assume the set of electricity load time periods P = {[2024-05-01 23:00, 2024-05-02 03:30], [2024-05-03 00:15, 2024-05-03 02:45]}, and the set of electricity current time periods I = {[2024-05-01 23:30, 2024-05-02 03:30], [2024-05-03 00:00, 2024-05-03 02:30]}. Segment-by-segment comparison: The first overlapping segment is [2024-05-01 23:30, 2024-05-02 03:30], lasting 4 hours; the second overlapping segment is [2024-05-03 00:15, 2024-05-03 02:30], lasting 2.25 hours. The first overlap duration = 4 + 2.25 = 6.25 hours, which is greater than the preset overlap duration threshold of 2 hours. By accurately calculating the overlap duration of the two core electricity consumption dimensions, basic data is provided for subsequent similarity determination. Load and current dimensions are compared first because they directly reflect the operating status of electrical equipment, and their overlap can quickly and preliminarily determine whether there is any illegal charging behavior, laying the foundation for subsequent similarity calculations by scenario.

[0072] Step 105142: In response to the first overlap duration being greater than or equal to a preset overlap duration threshold, calculate the first proportion of the first overlap duration within the set of electricity load time periods; calculate the second proportion of the first overlap duration within the set of electricity current time periods; and use the average of the first proportion and the second proportion as the similarity.

[0073] In this step, when the first overlap duration meets the preset threshold, it indicates a strong correlation between the abnormal time periods in the load and current dimensions, requiring further quantification of similarity. The first percentage = first overlap duration ÷ total duration of the electricity load time period set × 100%, the second percentage = first overlap duration ÷ total duration of the electricity current time period set × 100%, and the similarity is the arithmetic mean of the two. An example preset similarity threshold is 60%. For instance, the total duration of the electricity load time period set = 4.5 (first segment 4.5 hours) + 2.5 (second segment 2.5 hours) = 7 hours; the total duration of the electricity current time period set = 4 (first segment 4 hours) + 2.5 (second segment 2.5 hours) = 6.5 hours. The first percentage = 6.25 ÷ 7 × 100% ≈ 89.29%, the second percentage = 6.25 ÷ 6.5 × 100% ≈ 96.15%, and the similarity = (89.29% + 96.15%) ÷ 2 ≈ 92.72%, which is greater than the preset similarity threshold of 60%. Calculating the similarity using the average percentage objectively reflects the degree of matching between the two abnormal time periods, avoiding judgment bias caused by the percentage of duration in a single dimension. In this scenario, the load and current highly overlap, directly corroborating the consistency of abnormal electricity consumption behavior and providing a reliable quantitative basis for subsequent fusion of violation time periods.

[0074] Step 105143: In response to the first overlap duration being less than a preset overlap duration threshold, calculate the second overlap duration of the electricity load time period set and the electricity consumption time period set.

[0075] In this step, if the first overlap duration does not reach the threshold, it indicates a weak correlation between load and current dimensions, requiring further verification using the electricity consumption dimension. The electricity consumption time period set is a continuous set of time periods that meet the characteristics of illegal charging based on electricity consumption information. The calculation logic for the second overlap duration is consistent with that of the first overlap duration, i.e., comparing the time periods of the electricity load time period set and the electricity consumption time period set segment by segment, accumulating the total duration of the overlapping intervals, thereby determining the abnormal correlation between load and electricity consumption dimensions. Assume the set of electricity load time periods P = {[2024-05-05 22:00, 2024-05-05 23:30], [2024-05-06 01:00, 2024-05-06 02:00]} (total duration 2.5 hours), and the set of electricity current time periods I = {[2024-05-05 23:00, 2024-05-05 23:15], [2024-05-06 01:30, 2024-05-06 01:45]} (total duration 0.5 hours). The first overlap duration = 0.25 + 0.25 = 0.5 hours, which is less than the preset threshold of 2 hours. The set of electricity consumption time periods Q = {[2024-05-05 21:45, 2024-05-05 23:45], [2024-05-06 00:45, 2024-05-06 02:15]} is compared segment by segment with P and Q: the first overlapping interval [2024-05-05 22:00, 2024-05-05 23:30] (1.5 hours), the second overlapping interval [2024-05-06 01:00, 2024-05-06 02:00] (1 hour), the second overlap duration = 1.5 + 1 = 2.5 hours, which is greater than the preset threshold of 2 hours. When the correlation between load and current is insufficient, the electricity consumption dimension is introduced for secondary verification to avoid missing violations that are abnormal in a single dimension but correlated in multiple dimensions. Electricity consumption is the ultimate manifestation of electricity use behavior. The degree of overlap with the load can corroborate the authenticity of abnormal behavior from the perspective of energy consumption, ensuring the comprehensiveness of similarity calculation.

[0076] Step 105144: In response to the second overlap duration being greater than or equal to a preset overlap duration threshold, calculate the third proportion of the second overlap duration within the set of electricity load time periods; calculate the fourth proportion of the second overlap duration within the set of electricity consumption time periods; and use the average of the third proportion and the fourth proportion as the similarity.

[0077] In this step, when the second overlap duration meets the threshold, it indicates a strong correlation between abnormal time periods in the load and electricity consumption dimensions. The similarity is calculated using the percentage-average method consistent with step 105142. The third percentage = second overlap duration ÷ total duration of the electricity load time period set × 100%, and the fourth percentage = second overlap duration ÷ total duration of the electricity consumption time period set × 100%. The similarity is the average of the two, ensuring consistency and coherence in the calculation logic. For example, if the total duration of the electricity load time period set is 2.5 hours, the total duration of the electricity consumption time period set = 2 (first segment 2 hours) + 1.5 (second segment 1.5 hours) = 3.5 hours. The third percentage = 2.5 ÷ 2.5 × 100% = 100%, and the fourth percentage = 2.5 ÷ 3.5 × 100% ≈ 71.43%. The similarity = (100% + 71.43%) ÷ 2 ≈ 85.71%, which is greater than the preset similarity threshold of 60%. Similarity is calculated by using the average proportion of load and power consumption, which compensates for the insufficient correlation between load and current. In this scenario, the two highly overlap, verifying the consistency of abnormal behavior from the perspectives of power operation and energy consumption, further improving the accuracy of similarity determination and avoiding misjudgments caused by bias in a single dimension.

[0078] Step 105145: In response to the second overlap duration being less than a preset overlap duration threshold, calculate the third overlap duration of the set of electricity load time periods, the set of electricity current time periods, and the set of electricity consumption time periods; calculate the fifth proportion of the third overlap duration within the set of electricity load time periods; calculate the sixth proportion of the third overlap duration within the set of electricity current time periods; calculate the seventh proportion of the third overlap duration within the set of electricity consumption time periods; and use the average of the fifth, sixth, and seventh proportions as the similarity.

[0079] In this step, if the second overlap duration still does not reach the threshold, it indicates that the correlation between any two dimensions is weak, and verification is needed through the overlapping time periods of all three dimensions. The third overlap duration refers to the cumulative duration of the common overlapping intervals of all time periods in the three sets. It is necessary to compare the time periods of the three sets segment by segment, extract the intersection, and accumulate the duration. Subsequently, the proportion of the third overlap duration in the total duration of the three sets is calculated, and the average of the three is taken as the similarity to ensure the comprehensiveness of multi-dimensional cross-validation. Assume the set of electricity load time periods P = {[2024-05-08 20:00, 2024-05-08 22:00], [2024-05-09 03:00, 2024-05-09 04:30]} (total duration 3.5 hours), the set of electricity current time periods I = {[2024-05-08 20:30, 2024-05-08 21:30], [2024-05-09 03:30, 2024-05-09 04:15]} (total duration 1.5 hours), and the set of electricity consumption time periods Q = {[2024-05-08 20:15, 2024-05-08 21:45], [2024-05-09 04:15]} (total duration 1.5 hours). [03:15, 2024-05-09 04:20] (Total duration 2.5 hours). First overlapping duration = 0.5 + 0.75 = 1.25 hours (less than 2 hours), second overlapping duration = 1.5 + 1 = 2.5 hours (assuming the second overlapping duration is calculated to be 1.8 hours, less than 2 hours). The three overlapping intervals are: first segment [2024-05-08 20:30, 2024-05-08 21:30] (1 hour), second segment [2024-05-09 03:30, 2024-05-09 04:15] (0.75 hours), third overlapping duration = 1 + 0.75 = 1.75 hours. The fifth percentage is calculated as 1.75 ÷ 3.5 × 100% = 50%, the sixth percentage as 1.75 ÷ 1.5 × 100% ≈ 116.67% (percentages exceeding 100% are rounded up to 100%), and the seventh percentage as 1.75 ÷ 2.5 × 100% = 70%. The similarity is calculated as (50% + 100% + 70%) ÷ 3 ≈ 73.33%, which is greater than the preset similarity threshold of 60%. In cases where the correlation between any two dimensions is insufficient, the similarity is calculated by measuring the duration of overlap among the three dimensions, achieving deep cross-validation across multiple dimensions and preventing the omission of highly concealed violations of electricity usage regulations. The calculation method of the average percentage of the three dimensions integrates the characteristics of the three core electricity usage dimensions: power, current, and energy, ensuring the comprehensiveness and objectivity of the similarity judgment and minimizing the probability of missed detections.

[0080] Based on the aforementioned technical solutions, this application addresses the problem of residents illegally connecting and using electricity in older residential areas due to insufficient charging facilities. Traditional investigation and analysis methods are inefficient, while installing monitoring equipment is costly. Mainstream machine learning and deep learning methods have high data acquisition costs and are unsuitable for older residential areas with mostly ordinary smart meters. This application constructs an electricity consumption identification system through data analysis technology. By analyzing business patterns, high-risk areas are located. Based on a comparison of the differences between residents' regular electricity consumption and charging behavior, combined with user regular electricity consumption data and electricity usage time distribution, illegal charging behavior is identified to accurately combat violations and prevent safety risks at the source.

[0081] It should be noted that the method in this embodiment can be executed by a single device, such as a computer or server. The method can also be applied in a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method in this embodiment, and the multiple devices will interact with each other to complete the method described.

[0082] It should be noted that the above description describes some embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0083] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides a device for identifying illegal electricity use behavior.

[0084] refer to Figure 3 The aforementioned device for identifying violations of electricity usage regulations includes: The acquisition module 301 is configured to acquire user profile data and the electricity consumption information corresponding to the user profile data; The first determining module 302 is configured to determine high-risk cells based on the user profile data; The second determining module 303 is configured to determine risky users based on the user profile data and the high-risk cell. The third determination module 304 is configured to determine high-risk users based on the user profile data and the risky users; The identification module 305 is configured to identify the electricity consumption behavior of the high-risk user based on the electricity consumption information.

[0085] In some embodiments, the first determining module 302 is further configured such that the user profile data includes residential community information, charging resource information around the residential community, travel demand information corresponding to the residential community, and user charging demand information within the residential community; determining high-risk communities based on the user profile data and the electricity consumption information includes: determining a score for the residential community based on the residential community information, charging resource information around the residential community, travel demand information corresponding to the residential community, user charging demand information within the residential community, and illegal electricity consumption conditions; and determining the residential community corresponding to the user profile data as a high-risk community in response to the score of the residential community being less than a preset risk assessment threshold.

[0086] In some embodiments, the first determining module 302 is further configured to determine a score for the residential community based on the residential community information, surrounding charging resource information, travel demand information corresponding to the residential community, user charging demand information within the residential community, and illegal electricity use conditions, including: determining a first score based on the residential community information and the illegal electricity use conditions; determining a second score based on the surrounding charging resource information and the illegal electricity use conditions; determining a third score based on the travel demand information corresponding to the residential community and the illegal electricity use conditions; determining a fourth score based on the user charging demand information within the residential community and the illegal electricity use conditions; and determining the overall score for the residential community based on the first score, the second score, the third score, and the fourth score.

[0087] In some embodiments, the second determining module 303 is further configured such that the user profile data includes the user's location; and that, based on the user profile data and the high-risk community, determining risky users includes: identifying users whose user location matches the residential community location of the high-risk community as the risky users.

[0088] In some embodiments, the first determining module 304 is further configured such that the user profile data includes the status of the independent electricity meter for applying for a charging pile; and that, based on the user profile data and the risk users, the high-risk users are determined, including: identifying users other than those whose independent electricity meter for applying for a charging pile is in the "applied for" status among the risk users as the high-risk users.

[0089] In some embodiments, the identification module 305 is further configured such that the electricity consumption information includes electricity load information, electricity current information, and electricity consumption information; and to identify the electricity consumption behavior of the high-risk user based on the electricity consumption information, including: determining a set of illegal electricity consumption time periods based on the electricity load information, the electricity current information, and the electricity consumption information within a preset time period; determining a suspicion level based on the set of illegal electricity consumption time periods; determining the high-risk user as an illegal electricity user in response to the suspicion level being greater than a preset suspicion level threshold; and determining the high-risk user as a regular electricity user in response to the suspicion level being less than or equal to the preset suspicion level threshold.

[0090] In some embodiments, the identification module 305 is further configured to determine a set of illegal electricity use time periods within a preset time period based on the electricity load information, the electricity current information, and the electricity consumption information, including: determining a set of electricity load time periods based on the electricity load information within the preset time period; determining a set of electricity current time periods based on the electricity current information within the preset time period; determining a set of electricity consumption time periods based on the electricity consumption information within the preset time period; calculating the similarity between any two or three of the set of electricity load time periods, the set of electricity current time periods, and the set of electricity consumption time periods; and, in response to the similarity being greater than a preset similarity threshold, merging the time periods corresponding to the similarity as the set of illegal electricity use time periods.

[0091] In some embodiments, the identification module 305 is further configured to calculate the similarity between any two or three of the set of electricity load time periods, the set of electricity current time periods, and the set of electricity consumption time periods, including: calculating a first overlap duration between the set of electricity load time periods and the set of electricity current time periods; in response to the first overlap duration being greater than or equal to a preset overlap duration threshold, calculating a first proportion of the first overlap duration within the set of electricity load time periods; calculating a second proportion of the first overlap duration within the set of electricity current time periods; using the average of the first proportion and the second proportion as the similarity; in response to the first overlap duration being less than the preset overlap duration threshold, calculating a second overlap duration between the set of electricity load time periods and the set of electricity consumption time periods; in response to the second overlap duration... If the duration is greater than or equal to a preset overlap duration threshold, calculate the third proportion of the second overlap duration within the set of electricity load time periods; calculate the fourth proportion of the second overlap duration within the set of electricity consumption time periods; use the average of the third and fourth proportions as the similarity; if the second overlap duration is less than the preset overlap duration threshold, calculate the third overlap duration of the set of electricity load time periods, the set of electricity consumption time periods, and the set of electricity consumption time periods; calculate the fifth proportion of the third overlap duration within the set of electricity load time periods; calculate the sixth proportion of the third overlap duration within the set of electricity consumption time periods; calculate the seventh proportion of the third overlap duration within the set of electricity consumption time periods; use the average of the fifth, sixth, and seventh proportions as the similarity.

[0092] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing this application, the functions of each module can be implemented in one or more software and / or hardware.

[0093] The apparatus described above is used to implement a corresponding method for identifying illegal electricity use in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0094] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a method for identifying illegal electricity use behavior as described in any of the above embodiments.

[0095] Figure 4This embodiment illustrates a more specific hardware structure of an electronic device. The device may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0096] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0097] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0098] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0099] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0100] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0101] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0102] The electronic devices described above are used to implement a corresponding method for identifying illegal electricity use in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0103] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute a method for identifying illegal electricity use as described in any of the above embodiments.

[0104] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0105] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute a method for identifying illegal electricity use as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0106] It is understood that before using the technical solutions of the various embodiments in this disclosure, users will be informed of the type, scope of use, and usage scenarios of the personal information involved in an appropriate manner, and user authorization will be obtained.

[0107] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose, based on the prompt message, whether to provide personal information to the software or hardware such as electronic devices, applications, servers, or storage media performing the operations of this disclosed technical solution.

[0108] As an optional but not limited implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0109] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0110] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application is limited to these examples; under the concept of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in detail for the sake of brevity.

[0111] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0112] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0113] Any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application shall be included within the protection scope of this application.

Claims

1. A method for identifying violations of electricity usage regulations, characterized in that, include: Obtain user profile data and the corresponding electricity consumption information; Based on the user profile data, high-risk residential areas were identified; Based on the user profile data and the high-risk communities, risky users are identified; Based on the user profile data and the risky users, high-risk users are identified; Based on the electricity consumption information, the electricity consumption behavior of the high-risk users is identified.

2. The method according to claim 1, characterized in that, The user profile data includes information on residential communities, charging resources around residential communities, travel needs corresponding to residential communities, and charging needs of users within residential communities. Based on the user profile data and the electricity consumption information, high-risk residential areas are identified, including: The score of the residential community is determined based on the information on the residential community, the charging resources around the residential community, the travel demand information corresponding to the residential community, the charging demand information of users in the residential community, and the conditions of illegal electricity use. If the score of the residential community is less than a preset risk assessment threshold, the residential community corresponding to the user profile data is determined to be a high-risk community.

3. The method according to claim 2, characterized in that, Based on the residential community information, surrounding charging resource information, corresponding travel demand information, user charging demand information within the residential community, and illegal electricity use conditions, a score for the residential community is determined, including: Based on the residential community information and the conditions of illegal electricity use, a first score is determined; The second score is determined based on the information on charging resources around the residential community and the conditions of illegal electricity use; The third score is determined based on the travel demand information corresponding to the residential community and the illegal electricity use conditions. Based on the charging demand information of users in the residential community and the conditions of illegal electricity use, a fourth score is determined; The score of the residential community is determined based on the first score, the second score, the third score, and the fourth score.

4. The method according to claim 1, characterized in that, The user profile data includes the user's location; Based on the user profile data and the high-risk residential areas, risky users are identified, including: Users whose location matches the location of their residential community in the high-risk community are defined as high-risk users.

5. The method according to claim 1, characterized in that, The user profile data includes the status of the independent electricity meter for the applied charging pile; Based on the user profile data and the risky users, high-risk users are identified, including: Users other than those whose independent electricity meter for charging piles is in the "application already applied" status are considered high-risk users.

6. The method according to claim 1, characterized in that, The electricity consumption information includes electricity load information, electricity current information, and electricity consumption information; Based on the electricity consumption information, identify the electricity consumption behavior of the high-risk users, including: Within a preset time period, a set of time periods for illegal electricity use is determined based on the electricity load information, the electricity current information, and the electricity consumption information; Based on the set of time periods of illegal electricity use, the degree of suspicion is determined; In response to the suspicion level being greater than a preset suspicion threshold, the high-risk user is determined to be a user violating electricity regulations; In response to the suspicion level being less than or equal to a preset suspicion threshold, the high-risk user is determined to be a regular electricity user.

7. The method according to claim 6, characterized in that, Within a preset time period, based on the electricity load information, the electricity current information, and the electricity consumption information, a set of time periods for illegal electricity use is determined, including: Within a preset time period, a set of time periods for electricity load is determined based on the electricity load information; Within a preset time period, a set of time periods for electricity consumption is determined based on the electricity consumption information; Within a preset time period, a set of time periods for electricity consumption is determined based on the electricity consumption information; Calculate the similarity between any two or three of the set of electricity load time periods, the set of electricity current time periods, and the set of electricity consumption time periods; In response to the similarity being greater than a preset similarity threshold, the time periods corresponding to the similarity are merged into a set of time periods for illegal electricity use.

8. The method according to claim 7, characterized in that, Calculating the similarity between any two or three of the set of electricity load time periods, the set of electricity current time periods, and the set of electricity consumption time periods includes: Calculate the first overlap duration between the set of electricity load time periods and the set of electricity current time periods; In response to the first overlap duration being greater than or equal to a preset overlap duration threshold, a first proportion of the first overlap duration within the set of electricity load time periods is calculated; a second proportion of the first overlap duration within the set of electricity current time periods is calculated; and the average of the first proportion and the second proportion is taken as the similarity. In response to the first overlap duration being less than a preset overlap duration threshold, a second overlap duration is calculated for the electricity load time period set and the electricity consumption time period set; In response to the second overlap duration being greater than or equal to a preset overlap duration threshold, a third proportion of the second overlap duration within the set of electricity load time periods is calculated; a fourth proportion of the second overlap duration within the set of electricity consumption time periods is calculated; and the average of the third proportion and the fourth proportion is taken as the similarity. In response to the second overlap duration being less than a preset overlap duration threshold, the third overlap duration of the set of electricity load time periods, the set of electricity current time periods, and the set of electricity consumption time periods is calculated; the fifth proportion of the third overlap duration within the set of electricity load time periods is calculated; the sixth proportion of the third overlap duration within the set of electricity current time periods is calculated; the seventh proportion of the third overlap duration within the set of electricity consumption time periods is calculated; and the average of the fifth, sixth, and seventh proportions is used as the similarity.

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 program, it implements the method as described in any one of claims 1 to 8.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method described in any one of claims 1 to 8.

Images