An electric power consumption anomaly analysis method and device, electronic equipment and readable storage medium

Abstract

The application provides a power consumption anomaly analysis method and device, electronic equipment and readable storage medium, wherein the method comprises: acquiring household power consumption data of different households in a plurality of residential areas in real time; dividing residential areas in a target area into different types of residential areas according to attribute information of the residential areas and road connection conditions between different residential areas; for each type of residential area, classifying different households in the type of residential area according to life information of the households in the type of residential area; for each type of household in each type of residential area, performing preliminary power consumption anomaly analysis on the type of household according to household power consumption data of the type of household; calling meter detection data of a preliminary anomaly household; and determining whether the preliminary anomaly household in the preliminary power consumption anomaly analysis result is a final anomaly household according to the meter detection data. Through the method, power consumption anomaly analysis can be more accurately performed without door-to-door inspection.

Description

Technical Field

[0001] This application relates to the field of electricity meter technology, and in particular to a method, apparatus, electronic device, and readable storage medium for analyzing abnormal electricity consumption. Background Technology

[0002] Household electricity meters are the core devices for recording household electricity consumption and calculating electricity bills. Their operating status directly affects the accuracy of electricity metering and electricity safety. Sometimes, the electricity meter may show abnormal data when recording household electricity consumption. This could be due to reasons such as electricity theft, meter malfunction, wiring problems, signal transmission issues, or problems with the electrical equipment. To address this issue, manual on-site inspection or regular replacement with the latest model of electricity meter is usually adopted.

[0003] However, with the increasing awareness of privacy rights, there is growing resistance to on-site inspections, and replacing the electricity meter with the latest model would be too costly. Therefore, there is a need to find a way to more accurately analyze abnormal electricity usage without on-site inspections. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method, apparatus, electronic device and readable storage medium for analyzing power consumption anomalies, so as to perform more accurate power consumption anomaly analysis without on-site inspection.

[0005] In a first aspect, embodiments of this application provide a method for analyzing abnormal electricity consumption, including:

[0006] Real-time acquisition of residential electricity consumption data from different households in multiple residential communities;

[0007] Based on the attribute information of residential communities and the road connectivity between different residential communities, the residential communities within the target area are divided into different types of residential communities;

[0008] For each type of residential community, the different households in that type of community are classified according to their living information;

[0009] For each type of household in each type of residential community, a preliminary analysis of abnormal electricity consumption is conducted based on the household electricity consumption data of that type of household.

[0010] Retrieve the electricity meter detection data of the households with preliminary abnormal electricity consumption from the preliminary electricity consumption anomaly analysis results; the electricity meter detection data includes the brightness value detected by the photosensitive sensor installed on the electricity meter and the infrared value detected by the infrared sensor installed on the electricity meter.

[0011] Based on the electricity meter readings, determine whether the initially abnormal households in the preliminary electricity consumption anomaly analysis results are ultimately abnormal households.

[0012] In conjunction with the first aspect, this application provides a first possible implementation of the first aspect, wherein the attribute information of the residential community is determined based on the following information: the density of bus stops within a preset range of the residential community, the density and price of restaurants within a preset range of the residential community, and the density and price of infant and toddler service units.

[0013] In conjunction with the first aspect, this application provides a second possible implementation of the first aspect, wherein the road connectivity is determined based on the following information: the correlation between the two residential communities is measured by the length of the road connecting them, the consistency of road specifications, and the number of short-distance routes that can connect the two residential communities.

[0014] In conjunction with the first aspect, this application provides a third possible implementation of the first aspect, wherein the preliminary electricity consumption anomaly analysis for each type of household in each type of residential community, based on the household electricity consumption data of that type of household, includes:

[0015] Households are clustered based on time period-based electricity consumption data, and preliminary analysis of electricity consumption anomalies is conducted based on the clustering results.

[0016] or,

[0017] For each household, a preliminary analysis of abnormal electricity usage is conducted based on the similarity between the household's first historical electricity usage habits and its electricity usage habits during a specified time period.

[0018] or,

[0019] The system determines residents' second historical electricity consumption habits in each time period in real time and performs preliminary electricity consumption anomaly analysis based on the similarity between multiple second historical electricity consumption habits.

[0020] In conjunction with the third possible implementation of the first aspect, this application provides a fourth possible implementation of the first aspect, wherein the step of determining the second historical electricity consumption habits of residents in each time period in real time and performing preliminary electricity consumption anomaly analysis based on the similarity between multiple second historical electricity consumption habits includes:

[0021] For each household, the household's historical electricity consumption data is segmented according to a reference time unit to obtain historical electricity consumption data for multiple different target time periods;

[0022] For each household, the household's historical living information is segmented according to a reference time unit to obtain historical living information for multiple different time periods;

[0023] For each household and each time period, determine the electricity usage habits for that time period based on historical electricity consumption data and historical living information.

[0024] For each household, based on the relative values ​​between electricity usage habits at different time periods, abnormal electricity usage habits that conform to the preset jump pattern are identified from multiple electricity usage habits, and the household is identified as a household with preliminary abnormal electricity usage.

[0025] For each household, the initial abnormal electricity usage period is determined based on the target time period corresponding to the household's abnormal electricity usage habits.

[0026] In conjunction with the first aspect, this application provides a fifth possible implementation of the first aspect, wherein determining whether a preliminarily abnormal household in the preliminary electricity consumption anomaly analysis result is a final abnormal household based on the electricity meter detection data includes:

[0027] For each household with preliminary abnormalities, the degree of correlation between the individual electricity meter data and the group electricity meter data is determined based on the group electricity meter data of the household type to which the household with preliminary abnormalities belongs and the individual electricity meter data of the household with preliminary abnormalities.

[0028] Based on the degree of abnormality, determine whether the initially abnormal household is the final abnormal household.

[0029] In conjunction with the first aspect, this application provides a sixth possible implementation of the first aspect, wherein the method further includes:

[0030] If the household with the initial abnormal electricity consumption is determined to have a physical abnormality, and is determined to be the final abnormal household, then the voltage value, current value, temperature value and image of the electricity meter of the final abnormal household are obtained by the voltage detector, current detector, temperature sensor and image sensor installed in the electricity meter, respectively.

[0031] The electricity meter of the resident with the final abnormality sends the meter's voltage, current, and temperature values, along with an image of the meter's display area, to the backend server via the corresponding concentrator. The backend server then generates a correlation curve analysis graph based on the meter's voltage, current, and temperature values, and determines whether the meter is physically damaged based on the correlation curve analysis graph and the meter's display area image.

[0032] Secondly, embodiments of this application also provide an electricity consumption anomaly analysis device, comprising:

[0033] The first acquisition module is used to acquire residential electricity data of different households in multiple residential communities in real time.

[0034] The segmentation module is used to divide residential communities within a target area into different types of residential communities based on the attribute information of the residential communities and the road connectivity between different residential communities.

[0035] The classification module is used to categorize different households in each type of residential community based on their living information.

[0036] The analysis module is used to perform preliminary analysis of abnormal electricity consumption for each type of household in each type of residential community, based on the household electricity consumption data of that type of household.

[0037] The retrieval module is used to retrieve the electricity meter detection data of the households with preliminary abnormal electricity consumption analysis results; the electricity meter detection data includes the brightness value detected by the photosensitive sensor installed on the electricity meter and the infrared value detected by the infrared sensor installed on the electricity meter.

[0038] The determination module is used to determine, based on the electricity meter detection data, whether the initially abnormal households in the preliminary electricity consumption anomaly analysis results are ultimately abnormal households.

[0039] Thirdly, embodiments of this application also provide an electronic device, including: a processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and when the machine-readable instructions are executed by the processor, the steps in any of the possible implementations of the first aspect described above are performed.

[0040] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps in any of the possible implementations of the first aspect described above.

[0041] This application provides a method, apparatus, electronic device, and readable storage medium for analyzing abnormal electricity consumption. Without conducting on-site inspections, and considering that the electricity consumption of similar residential communities is roughly the same, the communities are first categorized. Furthermore, considering the differences in occupations and other lifestyle information among residents, residents are further categorized based on this lifestyle information. This two-level categorization ensures accuracy. Then, based on the residential electricity consumption data of each category, a preliminary analysis of abnormal electricity consumption is performed to identify residents with preliminary abnormalities. A verification process is then conducted on these residents to ensure the accuracy of the analysis results.

[0042] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0043] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 A flowchart of a power consumption anomaly analysis method provided in an embodiment of this application is shown;

[0045] Figure 2 This illustration shows a topology diagram of an energy meter, concentrator, and backend server provided in an embodiment of this application.

[0046] Figure 3 This paper shows a schematic diagram of the structure of an electricity consumption anomaly analysis device provided in an embodiment of this application;

[0047] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0049] In related technologies, various reasons can lead to abnormal electricity meter readings, such as electricity theft by residents, physical structural faults in the meter, wiring faults, signal transmission problems between the meter and concentrator, and signal transmission problems between the concentrator and the central server. Generally, to address physical structural problems with the meter, distance or pressure sensors are typically installed inside the meter box or meter itself to detect if anyone has opened the meter. After the sensor activates, an alarm is triggered, and a manual on-site inspection is conducted to verify whether the meter has been tampered with.

[0050] However, this method can only prevent abnormal records caused by physical modification of the electricity meter to a certain extent, and cannot perform overall anomaly analysis.

[0051] Based on this, embodiments of this application provide a method, apparatus, electronic device, and readable storage medium for analyzing power consumption anomalies, which are described below through embodiments.

[0052] To facilitate understanding of this embodiment, a detailed description of the electricity consumption anomaly analysis method disclosed in this application embodiment will be provided first. For example... Figure 1 As shown, the process includes the following steps S101-S106:

[0053] S101: Real-time acquisition of residential electricity consumption data from different households in multiple residential communities.

[0054] S102: Based on the attribute information of residential communities and the road connectivity between different residential communities, the residential communities within the target area are divided into different types of residential communities.

[0055] S103: For each type of residential community, classify the different households in that type of residential community based on their living information.

[0056] S104: For each type of household in each type of residential community, conduct a preliminary analysis of abnormal electricity usage based on the household electricity consumption data of that type of household.

[0057] S105: Retrieve the electricity meter detection data of the households with preliminary abnormal electricity consumption from the preliminary electricity consumption anomaly analysis results; the electricity meter detection data includes the brightness value detected by the photosensitive sensor installed on the electricity meter and the infrared value detected by the infrared sensor installed on the electricity meter.

[0058] S106: Determine whether the initially abnormal households in the preliminary electricity consumption anomaly analysis results are the final abnormal households based on the electricity meter detection data.

[0059] In step S101, a residential community refers to multiple residential communities that are physically close to each other. These communities are all located in the same city and are close to each other, so the living and working conditions among them will not differ significantly (housing prices in the same community are roughly the same, residents' economic levels will not vary greatly, and electricity usage can be compared with each other). Step S101 is generally executed in real time, rather than being executed an hour or a short period of time before step S102.

[0060] Step S102 primarily involves classifying residential communities. The attribute information of a residential community refers to information that reflects its economic or living standards. This attribute information can typically be obtained in various ways. For example, it can be determined based on the following information: the density of bus stops within a pre-defined area of ​​the community, the density and prices of restaurants within that area, and the density and prices of infant and toddler service providers. In reality, the density and prices of private service providers around most residential communities have some reference value. However, due to the accuracy and difficulty of data acquisition, only bus stops, restaurants, and infant and toddler service providers offer the most valuable reference. For instance, small supermarkets and markets exist around every residential community, but their prices fluctuate greatly, heavily influenced by individual consumers and random consumption, thus offering little reference value (they cannot distinguish between different residential communities). Similarly, sports venues like gyms and swimming pools are not attached to any single residential community but are shared by multiple communities. Their proximity to certain communities may simply be due to lower prices, also failing to provide effective reference. Similarly, other entertainment venues such as cinemas and KTVs do not belong to a single residential community, so their information is not very relevant. In other words, the attribute information of a residential community is mainly determined by the density and price of service establishments belonging solely to that community. Specifically, this includes the density of bus stops, the density and price of restaurants, and the density and price of infant and toddler service establishments within the pre-defined area of ​​the community.

[0061] Road connectivity mainly refers to three aspects. The first aspect is how many distances of roads connect different residential communities. In other words, the relevance between two residential communities is measured by the length of the road connecting them (specifically, it can be the length of the shortest road or the average length of the shortest roads). The shorter the distance, the higher the similarity between the two residential communities, and the more likely they should be classified into the same category.

[0062] The second aspect refers to road specifications or the consistency of road specifications, that is, what level of road connects two residential communities, or what levels of roads constitute them. Specifically, different residential communities in a city will not be connected by highways or national roads, but they can be distinguished based on road attribute information (such as width, number of lanes, and speed limits) and the degree of road variation (how many roads with different attribute information are on a connecting route). The less variation in road attribute information and the more consistent the attribute information, the greater the similarity between the two residential communities, and they should be classified into the same category.

[0063] The third aspect is the number of short-distance routes connecting the two residential communities. This number is generally determined by first identifying the center points of the two communities and then forming an acute angle between the driving direction and the line connecting these center points. The number of routes connecting the two communities (a single route typically includes multiple roads; here, "roads" refers to straight urban roads) is the total number of short-distance routes connecting the two communities. Generally, the more short-distance routes there are, the greater the similarity between the two communities, and they should be grouped into the same category.

[0064] In practice, you can preset the number of residential community categories as needed, and then set the core number or density threshold for clustering based on this number. Alternatively, you can set different core numbers and density thresholds, conduct multiple trials, and select one of these clustering results as the residential community classification result based on the reasonableness of each result.

[0065] Step S103 primarily involves classifying residents. Specifically, this classification is based on available lifestyle data. There are two main objectives: one is simply determining the resident's work and lifestyle type, and the other is using a large-scale model for classification. Generally, due to limitations in information availability, it's difficult to accurately collect lifestyle information for every resident. Commonly used lifestyle information includes: travel information (such as taxi bookings, travel locations, information reflecting work locations, and travel times), resume information (descriptions of education and work experience), and consumption information. Without dedicated data interfaces, it's difficult to guarantee that all types of information for each resident can be obtained. Therefore, using a large-scale model for analysis can aid in classification. Generally, residents in similar residential communities tend to have similar lifestyles, and therefore similar electricity usage habits, making them relatively valuable for comparison.

[0066] In step S104, the preliminary electricity consumption anomaly analysis mainly involves identifying households with potential electricity consumption anomalies. Simply put, this means selecting households with anomalies from those of the same type. Whether a household is abnormal can be determined in three ways. The first method is through clustering (the parameter used for clustering is the electricity consumption data of each household for each time period). This step requires pre-setting a cluster density threshold, which means finding individuals whose electricity consumption habits deviate significantly from those of other households of this type. The cluster cores are typically 3-5 (the number of cores is slightly larger than the number of similar residential communities). This is mainly because within the same type of residential community, differences in geographical location may lead to differences in living habits. For example, the lifestyles of residents living on the street and those living far from the street may differ (due to noise), or there may be other unforeseen reasons. Therefore, in practice, it may be necessary to try different numbers of cluster cores, but the density threshold should not be significantly adjusted. In other words, households can be clustered based on time period-electricity consumption data, and preliminary electricity consumption anomaly analysis can be performed based on the clustering results.

[0067] The second method involves verification through historical electricity usage information. For an individual household, their historical electricity usage data can be further analyzed. This historical data primarily refers to the electricity consumption data during the initial period after occupancy. This is because electricity meters and wiring are typically not damaged during this initial period, and electricity theft is unlikely. Therefore, using this initial period as a reference value for historical verification is relatively reliable. In other words, for each household, preliminary analysis of electricity usage anomalies can be conducted based on the similarity between their initial historical electricity usage habits (during the initial period after occupancy) and their electricity usage habits over a specified time period.

[0068] The third approach involves using lifestyle information for consistency verification. This verification method is time-segmented, such as by day or week. For a given household, firstly, based on their historical electricity usage data and the corresponding lifestyle information for that time period, their primary electricity usage habit is determined. Then, based on real-time lifestyle information and current electricity usage data, their secondary electricity usage habit is determined. Finally, a comparison is made between the primary and secondary habits to confirm whether they have changed. In other words, if a household's electricity usage habit changes significantly, they may be considered a preliminary case of abnormal electricity usage. Essentially, a household's secondary historical electricity usage habit (determined based on electricity data and lifestyle information) can be determined in real-time for each time period, and preliminary abnormal electricity usage analysis can be performed based on the similarity between multiple secondary historical electricity usage habits.

[0069] Further, more accurate judgments can be made, specifically as follows:

[0070] For each household, the household's historical electricity consumption data is segmented by a reference time unit (usually a day, week, or month) to obtain historical electricity consumption data for multiple different target time periods.

[0071] For each household, the household's historical living information is segmented according to a reference time unit to obtain historical living information for multiple different time periods;

[0072] For each household and each time period, determine the electricity usage habits for that time period based on historical electricity consumption data and historical living information.

[0073] For each household, based on the relative values ​​between electricity usage habits at different time periods, abnormal electricity usage habits that conform to the preset jump pattern are identified from multiple electricity usage habits, and the household is identified as a household with preliminary abnormal electricity usage.

[0074] For each household, the initial abnormal electricity usage period is determined based on the target time period corresponding to the household's abnormal electricity usage habits (generally, this target time period can be directly used as the initial abnormal electricity usage period).

[0075] Among these, abnormal electricity usage habits that conform to a preset jump pattern, if both positive and negative jumps are large and frequent, usually indicate a physical abnormality in the electricity meter or a problem with signal transmission between the meter and the concentrator, meaning the abnormality is caused by physical damage to the meter. If the abnormal electricity usage habits that conform to a preset jump pattern are characterized by large negative jumps, with no positive jumps occurring in a short period or at a low frequency, it usually indicates electricity theft, meaning the abnormality is caused by the user stealing electricity. Therefore, the type of abnormal electricity usage can be determined using this third method.

[0076] These three methods can be used simultaneously. The final preliminary abnormal electricity consumption households can be determined by weighted calculation based on the results of the three methods. Alternatively, only one method can be used.

[0077] In step S105, the main purpose is to perform a verification on the households with abnormal electricity consumption. This is mainly because the incomplete information obtained about their living conditions may lead to a misjudgment in step S104. However, if the previous steps are skipped and only step S105 is used for judgment, the probability of misjudgment may be greater (based on actual usage, relying solely on the sensors on the electricity meter for detection results has poor predictability).

[0078] In other words, before step S105 is executed, a photosensitive sensor and an infrared sensor need to be pre-installed on the electricity meter. When recording household electricity consumption data, brightness and infrared values ​​are simultaneously acquired through these two sensors. Then, in step S106, the changes in brightness and infrared values ​​are used to verify whether the electricity meter data of the previously acquired households with preliminary abnormal electricity consumption (i.e., households with preliminary abnormal electricity consumption) are synchronized with the changes in brightness and infrared values. Specifically, some verification strategies can be pre-set. These strategies can be divided into short-term (verifying using values ​​within a short period) and long-term (verifying using values ​​over a longer period). For example, in summer, during the day when brightness is high and infrared values ​​are constant (no one is home), electricity consumption should be lower than in summer when brightness is high but infrared values ​​are not constant (someone is home), because air conditioning is needed. In any weather condition, electricity consumption when someone is home will not be higher than when no one is home, and electricity consumption when someone is home usually will not remain zero.

[0079] For long-term conditions, such as the residents' daily routine being normal over a certain period of time, normal within a day could mean: someone is detected by the infrared sensor at night, no one is detected by the infrared sensor during the day, and the brightness value at night is the brightness of the lighting fixtures. Of course, different "normal" standards can also be set according to the residents' living information.

[0080] For example, a normal week can mean that a certain number of days in a week meet the standards mentioned in the previous paragraph.

[0081] In addition to the aforementioned method of using absolute values ​​of brightness and infrared values ​​for verification, a relative value method can also be used. Specifically, for each initially abnormal household, the degree of overlap between the individual and group electricity meter data is determined based on the group electricity meter data of the household type to which the initially abnormal household belongs and the individual electricity meter data of the initially abnormal household. Based on the degree of overlap, it is determined whether the initially abnormal household is ultimately an abnormal household.

[0082] In other words, the electricity meter readings of households of the same type should be the same or similar, so the degree of similarity can be used to verify whether a household is abnormal.

[0083] Besides verifying whether a resident is ultimately an abnormal household, electricity meter testing data can also help determine the resident type. That is, in step S103, electricity meter testing data from a period after a resident moves in can be used to help determine the resident type. Alternatively, after step S103, the electricity meter testing data for each type of resident can be clustered. Then, based on the clustering results, outliers can be removed (residents who do not fit the category are removed from that category). In practice, it is preferable to verify the electricity meter testing data after step S103. This is mainly because the acquisition of residential data is uncertain, but electricity meter testing data is always available. Therefore, if electricity meter testing data is included during clustering, the clustering results will be too heavily influenced by the electricity meter testing data, potentially distorting the final classification results.

[0084] As explained above, steps S104 and S106 respectively determine the preliminary and final identification of households with abnormal electricity usage. In step S104, different rules can be set to determine which abnormal state a household is more likely to be in (physical malfunction of the electricity meter, or abnormality caused by user electricity theft). Therefore, after step S106 is executed, the following additional steps can be performed:

[0085] If the household with the initial abnormal electricity consumption is determined to be physically abnormal in step S104, and the household is determined to be the final abnormal household in step S106, the voltage value, current value, temperature value and image of the electricity meter of the final abnormal household (i.e., the household with the final abnormal electricity consumption) can be obtained by the voltage detector, current detector, temperature sensor and image sensor installed in the electricity meter.

[0086] like Figure 2 As shown, the electricity meter of the finally abnormal household sends the electricity meter voltage value, electricity meter current value, electricity meter temperature value and electricity meter display area image to the backend server through the corresponding concentrator. The backend server then generates a correlation curve analysis graph based on the electricity meter voltage value, electricity meter current value and electricity meter temperature value, and determines whether the electricity meter is in a state of physical damage based on the correlation curve analysis graph and the electricity meter display area image.

[0087] Specifically, the voltage, current, and temperature values ​​of an electricity meter all have corresponding reasonable ranges. Under normal operating conditions, these three values ​​should fluctuate within these ranges. Any abnormal fluctuations in these values ​​indicate a problem with the meter's physical structure. The image displayed on the meter is used to verify whether the meter's display is malfunctioning.

[0088] Furthermore, as the working state of an electricity meter changes (workload increases), the voltage, current, and temperature will all show regular changes. To address this, we can pre-collect data on the working load of a normal electricity meter and the changes in voltage, current, and temperature (numerical correlation) to train a large model. Then, after obtaining these three data points from the backend server, the data can be input into the large model for verification.

[0089] Based on the same technical concept, embodiments of this application also provide a power consumption anomaly analysis device, such as... Figure 3 As shown, the device includes:

[0090] The first acquisition module 301 is used to acquire residential electricity data of different households in multiple residential communities in real time.

[0091] The segmentation module 302 is used to segment residential communities within the target area into different types of residential communities based on the attribute information of the residential communities and the road connectivity between different residential communities.

[0092] The classification module 303 is used to classify different residents in each type of residential community based on the residents' living information.

[0093] Analysis module 304 is used to perform preliminary analysis of abnormal electricity consumption for each type of household in each type of residential community, based on the household electricity consumption data of that type of household.

[0094] The retrieval module 305 is used to retrieve the electricity meter detection data of the households with preliminary abnormal electricity consumption in the preliminary electricity consumption anomaly analysis results; the electricity meter detection data includes the brightness value detected by the photosensitive sensor installed on the electricity meter and the infrared value detected by the infrared sensor installed on the electricity meter.

[0095] The determination module 306 is used to determine whether the preliminary abnormal households in the preliminary electricity consumption anomaly analysis results are final abnormal households based on the electricity meter detection data.

[0096] Optionally, the attribute information of the residential community is determined based on the following information: the density of bus stops within a preset range of the residential community, the density and prices of restaurants within a preset range of the residential community, and the density and prices of infant and toddler service units.

[0097] Optionally, the road connectivity is determined based on the following information: the correlation between two residential communities is measured by the length of the road connecting them, the consistency of road specifications, and the number of short-distance routes that can connect the two residential communities.

[0098] Optionally, when the analysis module 304 performs preliminary electricity consumption anomaly analysis for each type of household in each type of residential community based on the household electricity consumption data of that type of household, it is specifically used for:

[0099] Households are clustered based on time period-based electricity consumption data, and preliminary analysis of electricity consumption anomalies is conducted based on the clustering results.

[0100] or,

[0101] For each household, a preliminary analysis of abnormal electricity usage is conducted based on the similarity between the household's first historical electricity usage habits and its electricity usage habits during a specified time period.

[0102] or,

[0103] The system determines residents' second historical electricity consumption habits in each time period in real time and performs preliminary electricity consumption anomaly analysis based on the similarity between multiple second historical electricity consumption habits.

[0104] Optionally, when the analysis module 304 is used to determine the second historical electricity consumption habits of residents in each time period in real time, and to perform preliminary electricity consumption anomaly analysis based on the similarity between multiple second historical electricity consumption habits, it is specifically used for:

[0105] For each household, the household's historical electricity consumption data is segmented according to a reference time unit to obtain historical electricity consumption data for multiple different target time periods;

[0106] For each household, the household's historical living information is segmented according to a reference time unit to obtain historical living information for multiple different time periods;

[0107] For each household and each time period, determine the electricity usage habits for that time period based on historical electricity consumption data and historical living information.

[0108] For each household, based on the relative values ​​between electricity usage habits at different time periods, abnormal electricity usage habits that conform to the preset jump pattern are identified from multiple electricity usage habits, and the household is identified as a household with preliminary abnormal electricity usage.

[0109] For each household, the initial abnormal electricity usage period is determined based on the target time period corresponding to the household's abnormal electricity usage habits.

[0110] Optionally, when the determining module 306 is used to determine whether the initially abnormal households in the preliminary electricity consumption anomaly analysis results are ultimately abnormal households based on the electricity meter detection data, it is specifically used for:

[0111] For each household with preliminary abnormalities, the degree of correlation between the individual electricity meter data and the group electricity meter data is determined based on the group electricity meter data of the household type to which the household with preliminary abnormalities belongs and the individual electricity meter data of the household with preliminary abnormalities.

[0112] Based on the degree of abnormality, determine whether the initially abnormal household is the final abnormal household.

[0113] Optionally, the device further includes:

[0114] The second acquisition module is used to acquire the electricity meter voltage value, electricity meter current value, electricity meter temperature value and electricity meter display area image of the final abnormal household by means of voltage detector, current detector, temperature sensor and image sensor set in the electricity meter if it is determined that the household with the initial abnormal electricity consumption is a physical abnormality and is determined to be the final abnormal household.

[0115] The sending module is used to send the voltage, current, temperature, and display area image of the electricity meter of the finally abnormal household to the back-end server through the corresponding concentrator. This allows the back-end server to generate a correlation curve analysis graph based on the voltage, current, and temperature values, and determine whether the electricity meter is physically damaged based on the correlation curve analysis graph and the display area image.

[0116] Figure 4 A schematic diagram of an electronic device provided in this application embodiment includes: a processor 401, a memory 402, and a bus 403. The memory 402 stores machine-readable instructions executable by the processor 401. When the electronic device runs the above-described information processing method, the processor 401 and the memory 402 communicate through the bus 403. The processor 401 executes the machine-readable instructions to perform the steps of the method described in Embodiment 1.

[0117] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps described in Embodiment 1.

[0118] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, electronic devices, and computer-readable storage media described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0119] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0120] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0121] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0122] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0123] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The scope of protection of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of protection of the claims.

Claims

1. A method for analyzing abnormal electricity consumption, characterized in that, include: Real-time acquisition of residential electricity consumption data from different households in multiple residential communities; Based on the attribute information of residential communities and the road connectivity between different residential communities, the residential communities within the target area are divided into different types of residential communities; For each type of residential community, the different households in that type of community are classified according to their living information; For each type of household in each type of residential community, a preliminary analysis of abnormal electricity consumption is conducted based on the household electricity consumption data of that type of household. Retrieve the electricity meter detection data of the households with preliminary abnormal electricity consumption from the preliminary electricity consumption anomaly analysis results; the electricity meter detection data includes the brightness value detected by the photosensitive sensor installed on the electricity meter and the infrared value detected by the infrared sensor installed on the electricity meter. Based on the electricity meter detection data, determine whether the preliminary abnormal households in the preliminary electricity consumption anomaly analysis results are the final abnormal households; For each type of household in each type of residential community, a preliminary analysis of abnormal electricity usage is conducted based on the household electricity consumption data of that type of household, including: For each household, the household's historical electricity consumption data is segmented according to a reference time unit to obtain historical electricity consumption data for multiple different target time periods; For each household, the household's historical living information is segmented according to a reference time unit to obtain historical living information for multiple different time periods; For each household and each time period, determine the electricity usage habits for that time period based on historical electricity consumption data and historical living information. For each household, based on the relative values ​​between electricity usage habits at different time periods, abnormal electricity usage habits that conform to the preset jump pattern are identified from multiple electricity usage habits, and the household is identified as a household with preliminary abnormal electricity usage. For each household, the initial abnormal electricity usage time period is determined based on the target time period corresponding to the household's abnormal electricity usage habits. The step of determining whether the initially abnormal households in the preliminary electricity consumption anomaly analysis results are ultimately abnormal households based on the electricity meter detection data includes: For each household with preliminary abnormalities, the degree of correlation between the individual electricity meter data and the group electricity meter data is determined based on the group electricity meter data of the household type to which the household with preliminary abnormalities belongs and the individual electricity meter data of the household with preliminary abnormalities. Based on the degree of abnormality, determine whether the initially abnormal household is the final abnormal household.

2. The method according to claim 1, characterized in that, The attribute information of the residential community is determined based on the following information: the density of bus stops within the preset range of the residential community, the density and prices of restaurants within the preset range of the residential community, and the density and prices of infant and toddler service units.

3. The method according to claim 1, characterized in that, The road connectivity is determined based on the following information: the length of the road connecting the two residential communities to measure the relevance of the two communities, the consistency of the road specifications, and the number of short-distance routes that can connect the two residential communities.

4. The method according to claim 1, characterized in that, The method further includes: If the household with the initial abnormal electricity consumption is determined to have a physical abnormality, and is determined to be the final abnormal household, then the voltage value, current value, temperature value and image of the electricity meter of the final abnormal household are obtained by the voltage detector, current detector, temperature sensor and image sensor installed in the electricity meter, respectively. The electricity meter of the resident with the final abnormality sends the meter's voltage, current, and temperature values, along with an image of the meter's display area, to the backend server via the corresponding concentrator. The backend server then generates a correlation curve analysis graph based on the meter's voltage, current, and temperature values, and determines whether the meter is physically damaged based on the correlation curve analysis graph and the meter's display area image.

5. A power consumption anomaly analysis device, characterized in that, include: The first acquisition module is used to acquire residential electricity data of different households in multiple residential communities in real time. The segmentation module is used to divide residential communities within a target area into different types of residential communities based on the attribute information of the residential communities and the road connectivity between different residential communities. The classification module is used to categorize different households in each type of residential community based on their living information. The analysis module is used to perform preliminary analysis of abnormal electricity consumption for each type of household in each type of residential community, based on the household electricity consumption data of that type of household. The retrieval module is used to retrieve the electricity meter detection data of the households with preliminary abnormal electricity consumption analysis results; the electricity meter detection data includes the brightness value detected by the photosensitive sensor installed on the electricity meter and the infrared value detected by the infrared sensor installed on the electricity meter. The determination module is used to determine whether the preliminary abnormal households in the preliminary electricity consumption anomaly analysis results are final abnormal households based on the electricity meter detection data; The analysis module, when used to conduct preliminary electricity consumption anomaly analysis for each type of household in each type of residential community based on the household's electricity usage data, is specifically used for: For each household, the household's historical electricity consumption data is segmented according to a reference time unit to obtain historical electricity consumption data for multiple different target time periods; For each household, the household's historical living information is segmented according to a reference time unit to obtain historical living information for multiple different time periods; For each household and each time period, determine the electricity usage habits for that time period based on historical electricity consumption data and historical living information. For each household, based on the relative values ​​between electricity usage habits at different time periods, abnormal electricity usage habits that conform to the preset jump pattern are identified from multiple electricity usage habits, and the household is identified as a household with preliminary abnormal electricity usage. For each household, the initial abnormal electricity usage time period is determined based on the target time period corresponding to the household's abnormal electricity usage habits. When the determining module is used to determine whether a preliminarily abnormal household in the preliminary electricity consumption anomaly analysis results is a final abnormal household based on the electricity meter detection data, it is specifically used for: For each household with preliminary abnormalities, the degree of correlation between the individual electricity meter data and the group electricity meter data is determined based on the group electricity meter data of the household type to which the household with preliminary abnormalities belongs and the individual electricity meter data of the household with preliminary abnormalities. Based on the degree of abnormality, determine whether the initially abnormal household is the final abnormal household.

6. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is in operation, the processor communicates with the memory via the bus, and the machine-readable instructions, when executed by the processor, perform the steps of the method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the method as described in any one of claims 1 to 4.

Images