An electricity meter electricity stealing detection method and device, electronic equipment and storage medium

Abstract

The application relates to an electricity meter electricity stealing detection method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring the daily electricity usage of a user in a preset time period, classifying the dates in the preset time period based on the electricity usage, obtaining at least two date categories, determining the date category corresponding to the current date, acquiring the daily electricity usage of the user, determining whether the daily electricity usage is abnormal based on the daily electricity usage and the electricity usage in the date category, if the daily electricity usage is abnormal, acquiring the monitoring video at the electricity meter of the user, and determining whether electricity stealing behavior occurs based on the monitoring video. The application has the effect of discovering electricity stealing behavior in a timely manner.

Description

Technical Field

[0001] This application relates to the field of electricity meter equipment, and in particular to a method, device, electronic equipment, and storage medium for detecting electricity theft from electricity meters. Background Technology

[0002] With the development of power technology, electricity meters, as devices for measuring users' electricity consumption, are becoming increasingly intelligent, and smart meters with functions such as wireless networking, wireless communication, and automatic meter reading are gradually being developed.

[0003] Electricity theft is rampant. When stealing electricity, perpetrators often disconnect the power line from their own meter and connect it to another user's meter. This increases the electricity consumption of the victim, who may not be able to detect the theft in time, thus causing property damage. Summary of the Invention

[0004] In order to detect electricity theft in a timely manner, this application provides a method, device, electronic device and storage medium for detecting electricity theft from electricity meters.

[0005] Firstly, this application provides a method for detecting electricity theft from electricity meters, employing the following technical solution:

[0006] A method for detecting electricity theft from electricity meters, comprising:

[0007] Get the user's daily battery usage within a preset time period;

[0008] Based on the electricity usage, dates within a preset time period are classified to obtain at least two date categories;

[0009] Determine the date category corresponding to the current date;

[0010] Get the user's daily battery usage;

[0011] Determine whether the daily electricity usage is abnormal based on the electricity usage data for that day and the electricity usage data within the same date category;

[0012] If an anomaly is detected, the monitoring video at the user's electricity meter will be retrieved.

[0013] The surveillance video is used to determine whether electricity theft has occurred.

[0014] By employing the above technical solution, the daily electricity usage of users within a preset time period is obtained. This electricity usage data characterizes users' electricity consumption habits. Dates within the preset time period are categorized based on daily electricity usage, grouping dates with similar usage data together to facilitate determining the date category for each day. After determining the date category and obtaining the day's electricity usage data, anomalies are assessed based on the day's usage and the usage data within the same date category. Once the date category is determined, the difference between the day's usage and the usage data within the same date category confirms any anomalies. Upon detecting anomalies, surveillance video from the user's electricity meter is retrieved. This video footage records events at the meter, allowing for the identification of electricity theft. Therefore, electricity theft can be detected on the day it occurs, achieving timely detection.

[0015] In another possible implementation, the electricity usage includes total daily electricity consumption and / or changes in electricity usage, and the determination of whether the electricity usage is abnormal on a given day based on the electricity usage on that day and the electricity usage within the same date category includes at least one of the following:

[0016] Determine the average daily electricity consumption within the date category, and determine the difference between the total electricity consumption on the current day and the average daily electricity consumption. If the difference is greater than a preset difference, then the electricity consumption on that day is determined to be abnormal.

[0017] The nearest date to the current day is determined from the date categories. A first line graph and a second line graph are then determined. The first line graph shows the change in battery power over time within the nearest date, and the second line graph shows the change in battery power on the current day. The similarity between the first line graph and the second line graph is calculated. It is then determined whether the similarity is less than a first preset similarity threshold. If it is less than the threshold, the battery power on that day is determined to be abnormal.

[0018] By adopting the above technical solution, the average daily electricity consumption within the same date category represents the baseline daily electricity consumption within that date category. After determining the difference between the daily electricity consumption and the average daily electricity consumption, the magnitude of this difference compared to a preset threshold can be used to determine whether there is an abnormality in electricity consumption. Under normal circumstances, the electricity consumption variation between adjacent days within the same date category is relatively small. Therefore, a second line graph showing the daily electricity consumption variation and a first line graph showing the electricity consumption variation of the most recent day within the same date category can be determined. The similarity between the first and second line graphs is calculated, and the magnitude of this similarity compared to a first preset similarity threshold can be used to determine whether there is an abnormality in the daily electricity consumption.

[0019] In another possible implementation, acquiring the surveillance video at the user's electricity meter includes:

[0020] The first line chart and the second line chart are segmented to obtain a pair of sub-segments corresponding to the first line chart and multiple sub-segments corresponding to the second line chart.

[0021] Calculate the similarity of each sub-segment of the first and second line graphs respectively;

[0022] Identify suspicious segments in the second line graph whose similarity is less than a second preset similarity threshold;

[0023] Determine the time interval corresponding to the suspicious sub-segment;

[0024] Based on the time interval corresponding to the suspicious sub-segment, obtain the monitoring video at the user's electricity meter.

[0025] By employing the above technical solution, the similarity of each segment in the first and second line graphs is calculated. Segments in the second line graph with a similarity less than a second preset similarity threshold are considered suspicious segments. Electricity theft may occur within the time frame corresponding to a suspicious segment. Therefore, after identifying a suspicious segment, the surveillance video within the corresponding time interval is obtained, facilitating subsequent targeted analysis and processing. This method saves computational resources compared to analyzing the surveillance video for the entire day.

[0026] In another possible implementation, determining whether electricity theft has occurred based on the surveillance video includes:

[0027] Feature recognition is performed on the surveillance video to determine whether there are people in the surveillance video;

[0028] If a person is identified, determine the duration of their presence in the surveillance video.

[0029] Individuals whose presence lasts longer than a preset time will be identified as suspicious individuals.

[0030] The suspicious individuals are subjected to motion feature recognition to determine whether they are engaging in electricity theft.

[0031] By employing the above technical solution, after identifying individuals, those whose presence time is no longer than a preset time are filtered out, while those whose presence time is longer than the preset time are identified as suspicious individuals. This means that individuals whose presence time is longer than the preset time may be engaged in electricity theft in the meter area, while those whose presence time is shorter than the preset time may simply be passing through the meter area or briefly checking the meters. After identifying suspicious individuals, their behavioral characteristics are analyzed to more accurately determine whether they are actually stealing electricity.

[0032] In another possible implementation, the process of identifying the suspicious person's behavioral characteristics then includes:

[0033] If electricity theft is confirmed, then determine the start time corresponding to the occurrence of the electricity theft.

[0034] Acquire the change in electricity consumption of the meter within a preset range from the start time;

[0035] The user corresponding to the electricity theft is determined based on the changes in electricity consumption.

[0036] By adopting the above technical solution, after determining that electricity theft has occurred, the start time of the electricity theft is determined, and the changes in electricity consumption of other users' meters within a preset range are obtained from the start time. Since electricity theft has been committed, the electricity consumption of both the user's meter and the meter of the user who committed the electricity theft has changed, thereby enabling the user who committed the electricity theft to be identified based on the changes in electricity consumption of other users' meters within the preset range.

[0037] In another possible implementation, the process of identifying the suspicious person as having engaged in electricity theft then includes:

[0038] Extract the video clips corresponding to the suspicious persons from the surveillance video;

[0039] Output the video clip.

[0040] By adopting the above technical solution, the electronic device can capture and output video clips corresponding to suspicious persons, thereby enabling more timely knowledge of the process by which suspicious persons commit electricity theft.

[0041] In another possible implementation, the method further includes:

[0042] If electricity theft is confirmed, the electricity meter corresponding to the theft will be marked.

[0043] By adopting the above technical solution, after it is determined that electricity theft has occurred, the electricity meter of the user who committed the theft is marked, which facilitates subsequent key management and monitoring of the electricity meter of the user who committed the theft.

[0044] Secondly, this application provides an electricity meter theft detection device, which adopts the following technical solution:

[0045] An electricity meter theft detection device, comprising:

[0046] The first acquisition module is used to acquire the user's daily battery usage within a preset time period;

[0047] The classification module is used to classify dates within a preset time period based on the electricity usage, resulting in at least two date categories;

[0048] The first determination module is used to determine the date category corresponding to the current date.

[0049] The second acquisition module is used to acquire the user's daily battery usage.

[0050] The second determining module is used to determine whether the daily electricity usage is abnormal based on the daily electricity usage and the electricity usage within the date category.

[0051] The third acquisition module is used to acquire the monitoring video at the user's electricity meter when an anomaly occurs;

[0052] The third determining module is used to determine whether electricity theft has occurred based on the surveillance video.

[0053] By adopting the above technical solution, the first acquisition module acquires the user's daily electricity usage within a preset time period, which reflects the user's electricity consumption habits. The classification module categorizes the dates within the preset time period based on the daily electricity usage, grouping dates with similar usage into one category, thus facilitating the determination of the date category for a given day. The first determination module determines the date category for the current day, and after the second acquisition module acquires the daily electricity usage, it determines whether the daily electricity usage is abnormal based on the daily usage and the electricity usage within the same date category. After determining the corresponding date category, the difference between the daily electricity usage and the electricity usage within the same date category confirms whether the daily electricity usage is abnormal. Upon detecting an anomaly, the third acquisition module acquires the surveillance video at the user's electricity meter. The surveillance video records the events at the meter, allowing the third determination module to determine whether electricity theft has occurred. Therefore, electricity theft can be detected on the same day it occurs, achieving the effect of timely detection.

[0054] In another possible implementation, the electricity usage includes total daily electricity consumption and / or changes in electricity usage. When the second determining module determines whether the electricity usage is abnormal on a given day based on the electricity usage for that day and the electricity usage within the same date category, it is specifically used for at least one of the following:

[0055] Determine the average daily electricity consumption within the date category, and determine the difference between the total electricity consumption on the current day and the average daily electricity consumption. If the difference is greater than a preset difference, then the electricity consumption on that day is determined to be abnormal.

[0056] The nearest date to the current day is determined from the date categories. A first line graph and a second line graph are then determined. The first line graph shows the change in battery power over time within the nearest date, and the second line graph shows the change in battery power on the current day. The similarity between the first line graph and the second line graph is calculated. It is then determined whether the similarity is less than a first preset similarity threshold. If it is less than the threshold, the battery power on that day is determined to be abnormal.

[0057] In another possible implementation, the third acquisition module, when acquiring the monitoring video at the user's electricity meter, is specifically used for:

[0058] The first line chart and the second line chart are segmented according to a preset time interval to obtain multiple sub-segments corresponding to the first line chart and multiple sub-segments corresponding to the second line chart.

[0059] Calculate the similarity of each sub-segment of the first and second line graphs respectively;

[0060] Identify suspicious segments in the second line graph whose similarity is less than a second preset similarity threshold;

[0061] Based on the time interval corresponding to the suspicious sub-segment, obtain the monitoring video at the user's electricity meter.

[0062] In another possible implementation, when the third determining module determines whether electricity theft has occurred based on the surveillance video, it is specifically used for:

[0063] Feature recognition is performed on the surveillance video to determine whether there are people in the surveillance video;

[0064] If a person is identified, determine the duration of their presence in the surveillance video.

[0065] Individuals whose presence lasts longer than a preset time will be identified as suspicious individuals.

[0066] The suspicious individuals are subjected to motion feature recognition to determine whether they are engaging in electricity theft.

[0067] In another possible implementation, the device further includes:

[0068] The fourth determination module is used to determine the start time corresponding to the occurrence of electricity theft when it is determined that electricity theft has occurred.

[0069] The fourth acquisition module is used to acquire the change in electricity consumption of the meter within a preset range from the start time.

[0070] The fifth determining module is used to determine the user corresponding to the electricity theft behavior based on the changes in electricity consumption.

[0071] In another possible implementation, the device further includes:

[0072] The interception module is used to extract video segments corresponding to the suspicious persons from the surveillance video.

[0073] The output module is used to output the video clip.

[0074] In another possible implementation, the device further includes:

[0075] The marking module is used to mark the electricity meter corresponding to the electricity theft when it is determined that an electricity theft has occurred.

[0076] Thirdly, this application provides an electronic device that adopts the following technical solution:

[0077] An electronic device comprising:

[0078] One or more processors;

[0079] Memory;

[0080] One or more applications, wherein the applications are stored in memory and configured to be executed by one or more processors, the applications being configured to: execute a method for detecting electricity theft from a meter according to any possible implementation of the first aspect.

[0081] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution:

[0082] A computer-readable storage medium, when the computer program is executed in a computer, causes the computer to perform a method for detecting electricity theft from an electricity meter as described in any of the first aspects.

[0083] In summary, this application includes at least one of the following beneficial technical effects:

[0084] 1. Obtain daily electricity usage data for users within a preset time period. This data reflects users' electricity consumption habits. Dates within the preset time period are categorized based on daily usage data, grouping dates with similar usage data together to facilitate determining the date category for each day. After determining the date category and obtaining the day's electricity usage data, anomalies are identified by comparing the day's usage with that of other dates within the same category. If an anomaly is detected, access the surveillance video at the user's electricity meter. This video footage records events at the meter, allowing for the identification of electricity theft. Therefore, electricity theft can be detected on the day it occurs, enabling timely detection.

[0085] 2. After identifying individuals, those whose presence time is less than a preset time are filtered out. Individuals whose presence time is longer than the preset time are identified as suspicious, meaning they may be stealing electricity in the meter area, while those whose presence time is less than the preset time may simply be passing through the meter area or briefly checking the meters. After identifying suspicious individuals, their behavioral characteristics are analyzed to more accurately determine whether they are actually stealing electricity. Attached Figure Description

[0086] Figure 1 This is a flowchart illustrating a method for detecting electricity theft using an electricity meter, according to an embodiment of this application.

[0087] Figure 2 This is a schematic diagram of the structure of an electricity meter theft detection device according to an embodiment of this application.

[0088] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0089] The present application will be further described in detail below with reference to the accompanying drawings.

[0090] After reading this specification, those skilled in the art may make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.

[0091] 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, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0092] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0093] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0094] This application provides a method for detecting electricity theft from electricity meters, executed by an electronic device. This electronic device can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these. The terminal device and the server can be directly or indirectly connected via wired or wireless communication. This application does not impose any limitations on this. Figure 1 As shown, the method includes steps S101, S102, S103, S104, S105, S106, and S107, wherein,

[0095] S101, obtain the user's daily battery usage within a preset time period.

[0096] In this embodiment of the application, the electronic device obtains the daily electricity usage at the end of the day. This electricity usage can be obtained by the electricity meter collecting data in real time and sending it to the electronic device. Alternatively, the electricity meter can collect data in real time, store it in its internal storage medium, and send it to the electronic device at the end of the day. The electricity usage within a preset time period is the electricity usage at the time of the theft; that is, the electricity usage within the preset time period can serve as a benchmark reference. Assuming the preset time period is 30 days, the electronic device obtains the user's daily electricity usage within 30 days, thereby facilitating the understanding of the user's electricity consumption habits.

[0097] S102, classify the dates within a preset time period based on power usage to obtain at least two date categories.

[0098] In this embodiment of the application, users have different electricity consumption habits on different days. For example, users consume less electricity from Monday to Friday and more electricity on Saturday and Sunday. Taking step S101 as an example, once the electronic device obtains the electricity usage data for 30 days, it can classify the data according to the daily electricity usage data over the 30 days. For example, it can classify the data based on the daily electricity usage, dividing Monday to Friday into one date category and Saturday and Sunday into another date category.

[0099] S103, determine the date category corresponding to the current date.

[0100] In the embodiments of this application, the electronic device can obtain the date of the day via the Internet or a server, and then obtain the corresponding day of the week. Alternatively, it can determine the corresponding day of the week through a clock chip and date calculation program set locally within the electronic device. After determining the corresponding day of the week, the corresponding date category can be determined. For example, if the current day is Wednesday, then the date category for that day can be determined as Monday to Friday.

[0101] S104 retrieves the user's daily battery usage.

[0102] For the embodiments of this application, the method of obtaining the daily electricity consumption can be the same as the method of obtaining the daily electricity consumption in step S101, or other methods can be used to obtain the user's daily electricity consumption.

[0103] S105, determine whether the daily electricity usage is abnormal based on the daily electricity usage and the electricity usage within the date category.

[0104] In the embodiments of this application, after determining the date category of the day, since the day is consistent with the corresponding date category, it can be considered that the electricity consumption of the day is similar to the daily electricity consumption and electricity consumption habits within the date category. Therefore, by determining the electricity consumption of the day and the corresponding date category, it is possible to determine whether the electricity consumption of the day is abnormal based on the electricity consumption within the date category.

[0105] S106, if an anomaly is detected, obtain the monitoring video at the user's electricity meter.

[0106] In this embodiment of the application, after the electronic device determines that the daily electricity consumption is abnormal, it acquires the monitoring video at the electricity meter. The monitoring video at the meter indicates whether the meter has been affected by external factors, such as collisions with foreign objects or human intervention. The acquired monitoring video at the meter can be captured by a camera device placed near the meter capable of collecting monitoring video at the meter, and then sent to the electronic device. Alternatively, a camera device can be installed on the meter to capture monitoring video directly in front of the meter, and then sent to the electronic device.

[0107] S107, determine whether electricity theft has occurred based on surveillance video.

[0108] In this embodiment, after acquiring the surveillance video, the electronic device can determine whether electricity theft has occurred because the video records what happens at the electricity meter. Since the electronic device can determine the theft on the same day it occurs, it is more timely than manual inspection, thus reducing losses.

[0109] One possible implementation of this application embodiment is that the electricity usage includes the total daily electricity consumption and / or changes in electricity usage. In step S105, it is determined whether the electricity usage is abnormal on that day based on the electricity usage for that day and the electricity usage within the date category. Specifically, this includes at least one of steps S1051 (not shown in the figure) and S1052 (not shown in the figure):

[0110] S1051, determine the average daily electricity consumption within the date category, determine the difference between the total electricity consumption on the current day and the average daily electricity consumption, and if the difference is greater than a preset difference, determine that the electricity consumption on that day is abnormal.

[0111] In this embodiment, since the total daily electricity consumption within the same date category is relatively small, after determining the date category, the electronic device calculates the average daily electricity consumption over a preset time period. This average daily electricity consumption represents the baseline electricity consumption for dates within the same date category. The difference between the daily electricity consumption and the average daily electricity consumption within the date category is calculated. This difference represents the degree of deviation between the daily electricity consumption and the average daily electricity consumption. If the difference is greater than a preset difference, it indicates a significant discrepancy between the daily electricity consumption and the average daily electricity consumption, suggesting abnormal electricity consumption. For example, if the average daily electricity consumption is 4 kWh, the preset difference is 3 kWh, and the obtained daily electricity consumption is 4.5 kWh, the difference between 4.5 kWh and the average daily electricity consumption is 1.5 kWh, which is less than the preset difference of 3 kWh. Therefore, the electronic device determines that the daily electricity consumption is within the normal range.

[0112] S1052, determine the date closest to the current day from the date category, determine the first line graph and the second line graph. The first line graph is a line graph showing the change of power consumption over time within the closest date, and the second line graph is a line graph showing the change of power consumption on the current day. Calculate the similarity between the first line graph and the second line graph, and determine whether the similarity is less than the first preset similarity threshold. If it is less than the threshold, determine that the power consumption on the current day is abnormal.

[0113] In this embodiment of the application, the electronic device determines the nearest date, for example, "May 1, 2022, Friday". Taking the date category in step S102 as an example, the electronic device determines that the date category corresponding to the current day belongs to the Monday to Friday date category. The electronic device determines that the nearest date to May 1, 2022 is April 30, 2022. Because April 30 and May 1 belong to the same date category and are adjacent, under normal circumstances, the possibility of a significant change in the user's total electricity consumption and electricity usage is small. That is, under normal circumstances, the total electricity consumption and electricity usage habits on April 30 and May 1 are similar. The electronic device obtains the changes in electricity consumption at various times of the day on April 30 and May 1, for example, it calculates the electricity usage within half an hour every half hour and generates a first line graph and a second line graph. The horizontal axis of the first line graph and the second line graph represent time, and the vertical axis represents electricity consumption. If no electricity theft occurred, the first and second line graphs are quite similar in shape. Therefore, the similarity between the first and second line graphs is calculated to determine whether an abnormal electricity consumption occurred. The similarity can be obtained by calculating the Euclidean distance between the first and second line graphs, or by calculating the cosine similarity (the cosine of the angle between vectors in the first and second line graphs). Alternatively, the first and second line graphs can be input into a trained neural network for similarity calculation. The trained neural network outputs the similarity score. Other methods can also be used to calculate the similarity of the two contour information, which are not limited here. Assuming the first preset similarity threshold is 90%, and the determined similarity is 95%, the determined similarity is greater than the first preset similarity threshold, indicating that the first and second line graphs have a high similarity, meaning that no abnormal electricity consumption occurred on May 1st.

[0114] In this embodiment of the application, it is also possible to determine whether an abnormal power consumption situation has occurred based on both the power difference and the similarity. That is, when the power difference is greater than a preset difference and the similarity is less than a first preset similarity threshold, the electronic device is determined to have an abnormal power consumption situation.

[0115] One possible implementation of this application embodiment is that step S106, which involves acquiring the monitoring video at the user's electricity meter, specifically includes steps S1061 (not shown in the figure), S1062 (not shown in the figure), S1063 (not shown in the figure), and S1064 (not shown in the figure), wherein...

[0116] S1061, the first line graph and the second line graph are segmented according to a preset time interval to obtain multiple sub-segments corresponding to the first line graph and multiple sub-segments corresponding to the second line graph.

[0117] In this embodiment of the application, for example, the first line graph and the second line graph can be segmented according to the same preset time interval, which can be half an hour, one hour, etc. After the electronic device segments the first line graph and the second line graph, it obtains multiple sub-segments, which represent the changes in power consumption within the preset time interval.

[0118] S1062, calculate the similarity of each sub-segment of the first line graph and the second line graph respectively.

[0119] In this embodiment of the application, the electronic device calculates the similarity of each segment of the first and second line graphs within the same time interval. Taking half an hour as an example, the electronic device calculates the similarity of the segment between 9:00 and 9:30 in both the first and second line graphs; it calculates the similarity of the segment between 9:30 and 10:00; and so on. The method for calculating the segment similarity can be the same as or different from the method used in step S1061.

[0120] S1063, identify suspicious segments in the second line graph whose similarity is less than the second preset similarity threshold.

[0121] In this embodiment of the application, the second preset similarity threshold and the first preset similarity threshold can be the same or different. Assuming the second preset similarity threshold is 95%, the electronic device will identify segments with a similarity less than 95% as suspicious segments, meaning segments with a significantly different similarity to the corresponding segments in the first line graph. The electronic device identifies all suspicious segments in the second line graph, thus making subsequent detection of electricity theft more comprehensive and less prone to omissions.

[0122] S1064, Obtain the monitoring video at the user's electricity meter based on the time interval corresponding to the suspicious sub-segment.

[0123] In the embodiments of this application, after the electronic device identifies a suspicious segment, it can determine the time interval corresponding to the suspicious segment according to a preset time interval. For example, if the suspicious segment is a segment from 9:00 to 9:30, the time interval corresponding to the suspicious segment is from 9:00 to 9:30.

[0124] The time interval corresponding to the suspicious segment is the time interval when the user's battery level is abnormal. Therefore, electronic devices acquire surveillance video within the time interval corresponding to the suspicious segment for easier analysis. Compared to acquiring surveillance video for the entire day, analyzing the entire day's surveillance video is more computationally efficient. Acquiring surveillance video within the time interval corresponding to the suspicious segment is more targeted.

[0125] One possible implementation of this application embodiment is that step S107 determines whether electricity theft has occurred based on surveillance video, including steps S1071 (not shown in the figure), S1072 (not shown in the figure), S1073 (not shown in the figure), and S1074 (not shown in the figure), wherein...

[0126] S1071, Perform feature recognition on surveillance video to determine whether there are people in the surveillance video.

[0127] In this embodiment of the application, feature recognition of surveillance video can be performed by inputting the surveillance video corresponding to all suspicious segments into a trained neural network model capable of personnel recognition for feature recognition, thereby determining whether there are personnel in the surveillance video corresponding to the suspicious segments. In this embodiment of the application, the surveillance video of the entire day can also be input into a trained neural network model capable of personnel recognition for feature recognition.

[0128] S1072, If a person is identified, determine the duration of their presence in the surveillance video.

[0129] In this embodiment of the application, after the electronic device identifies a person, if the person's presence in the monitoring video is brief, it indicates that the person only passed through the area where the electricity meter is located. When the electronic device identifies a person, it determines the start time of the person's presence in the area where the electricity meter is located and starts timing. The timing stops when the person leaves the area where the electricity meter is located, thereby obtaining the duration of the person's presence in the area where the electricity meter is located.

[0130] S1073, identify individuals whose presence time exceeds a preset time as suspicious individuals.

[0131] In this embodiment of the application, assuming a preset time of 10 seconds, individuals present for less than 10 seconds are considered normal personnel, who may simply be passing by the area where the electricity meter is located or briefly checking the meter. Electronic devices identify individuals present for more than 10 seconds as suspicious personnel, meaning that suspicious personnel have been in the electricity meter area for an excessively long time and may be engaging in electricity theft.

[0132] S1074, perform motion feature recognition on suspicious persons to identify whether they are stealing electricity.

[0133] In this embodiment of the application, the surveillance video corresponding to a suspicious person can be input into a trained neural network model capable of recognizing features of electricity theft actions for action recognition, thereby determining whether the suspicious person has engaged in electricity theft. In this embodiment of the application, surveillance video from the entire day can also be input into the neural network model capable of recognizing features of electricity theft actions for action recognition.

[0134] Since electricity theft requires personnel to manually connect the power line to the meter, in this embodiment of the application, the arm features of the suspicious person can also be identified to determine whether the action made by the arm features is the action corresponding to electricity theft, thereby determining whether electricity theft has occurred.

[0135] One possible implementation of this application embodiment includes steps S108 (not shown in the figure), S109 (not shown in the figure), and S110 (not shown in the figure) after step S074, wherein...

[0136] S108, determine the start time corresponding to the occurrence of electricity theft.

[0137] In this embodiment of the application, when the electronic device detects a suspicious person committing electricity theft, it records the start time of the electricity theft. For example, it is assumed that the electricity theft was detected at 15:33 on May 1, 2022.

[0138] S109, Obtain the change in electricity consumption of the meter within the preset range from the start time.

[0139] In this embodiment of the application, the suspected perpetrator of electricity theft is typically another user near the user's electricity meter, and the meters within a preset range are the meters of other users near the user's electricity meter. Based on the determined start time of the electricity theft, the user's electricity meter reading changes due to the theft, and simultaneously, the readings of another user within the preset range also change. By acquiring the electricity reading changes of other users' meters from the start time, the user committing the electricity theft can be located.

[0140] S110 determines the user corresponding to the electricity theft behavior based on changes in electricity consumption.

[0141] In this embodiment of the application, if the electricity usage collected by a user's electricity meter suddenly drops, it is determined that the user corresponding to that meter has committed electricity theft. In this embodiment, the electronic device can also determine the user's electricity meter whose electricity usage started decreasing from a start time. The electronic device determines the increase in electricity usage of the user's electricity meter from the start time to a specified time, and also determines the decrease in electricity usage of the user's electricity meter whose usage was decreasing from the start time to the specified time. The user's electricity meter whose decrease in electricity usage matches the increase in electricity usage is identified as the meter corresponding to the person committing electricity theft, thus identifying the user who committed the theft.

[0142] One possible implementation of this application embodiment includes steps S111 (not shown in the figure) and S112 (not shown in the figure) after step S1074, wherein...

[0143] S111: Extract video clips corresponding to suspicious persons from surveillance videos.

[0144] In this embodiment of the application, the electronic device determines the start time of the suspicious person's electricity theft, and identifies the suspicious person leaving the electricity meter area after completing the electricity theft. The time of leaving the electricity meter area is determined as the end time of the suspicious person's electricity theft. After determining the start time and end time, the electronic device extracts the video segment corresponding to the suspicious person based on the start time and end time.

[0145] S112, output video clip.

[0146] In this embodiment of the application, after the electronic device extracts a video clip, it can send the video clip to the user's corresponding terminal device so that the user can be promptly notified of suspicious individuals committing electricity theft. The video clip can also be sent to the electricity meter management center so that management personnel can be promptly notified of the electricity theft. In this embodiment of the application, the video information can also be stored on the electronic device's local storage medium or stored on a cloud server.

[0147] One possible implementation of this application embodiment includes step S113 (not shown in the figure) after step S110, wherein...

[0148] S113 If it is determined that electricity theft has occurred, the electricity meter corresponding to the electricity theft shall be marked.

[0149] In this embodiment of the application, after the electronic device identifies a user who has committed electricity theft, it marks the electricity meter corresponding to that user, thereby facilitating subsequent focused monitoring of the meter by management personnel. The electronic device can add an identification field or identifier to the address or serial number of the meter to distinguish it from other normal meters. The electronic device can also mark the data transmitted from the meter to the electronic device, which is not limited here.

[0150] The above embodiments describe a method for detecting electricity theft from a process flow perspective. The following embodiments describe an electricity theft detection device from the perspective of a virtual module or virtual unit. For details, please refer to the following embodiments.

[0151] This application provides an electricity meter theft detection device 20, such as... Figure 2 As shown, the electricity theft detection device 20 may specifically include:

[0152] The first acquisition module 201 is used to acquire the user's daily electricity usage within a preset time period;

[0153] The classification module 202 is used to classify dates within a preset time period based on electricity usage to obtain at least two date categories;

[0154] The first determining module 203 is used to determine the date category corresponding to the current date.

[0155] The second acquisition module 204 is used to acquire the user's daily battery usage.

[0156] The second determining module 205 is used to determine whether the daily electricity usage is abnormal based on the daily electricity usage and the electricity usage within the date category.

[0157] The third acquisition module 206 is used to acquire the monitoring video at the user's electricity meter when an anomaly occurs;

[0158] The third determination module 207 is used to determine whether electricity theft has occurred based on the surveillance video.

[0159] In this embodiment, the first acquisition module 201 acquires the user's daily electricity usage within a preset time period, which reflects the user's electricity consumption habits. The classification module 202 classifies the dates within the preset time period based on the daily electricity usage, grouping dates with similar electricity usage into one category to facilitate determining the date category for that day. The first determination module 203 determines the date category for that day, and after the second acquisition module 204 acquires the day's electricity usage, the second determination module 205 determines whether the day's electricity usage is abnormal based on the day's usage and the electricity usage within the same date category. After determining the date category, the difference between the day's electricity usage and the electricity usage within the same date category determines whether the day's electricity usage is abnormal. If an abnormality is detected, the third acquisition module 206 acquires the monitoring video at the user's electricity meter. The monitoring video records what happens at the meter, so the third determination module 207 can determine whether electricity theft has occurred based on the monitoring video. Therefore, electricity theft can be detected on the same day it occurs, achieving the effect of timely detection of electricity theft.

[0160] In one possible implementation of this application embodiment, the electricity usage includes the total daily electricity consumption and / or changes in electricity usage. When the second determining module 205 determines whether the electricity usage is abnormal on a given day based on the electricity usage on that day and the electricity usage within the date category, it is specifically used for at least one of the following:

[0161] Determine the average daily electricity consumption within the given date category, and determine the difference between the daily electricity consumption and the average daily electricity consumption. If the difference is greater than a preset value, then the electricity consumption for that day is considered abnormal.

[0162] The nearest date to the current day is determined from the date categories. A first line graph and a second line graph are then determined. The first line graph shows the change in battery power over time within the nearest date, and the second line graph shows the change in battery power on the current day. The similarity between the first line graph and the second line graph is calculated, and it is determined whether the similarity is less than a first preset similarity threshold. If it is less than the threshold, the battery power on that day is determined to be abnormal.

[0163] In one possible implementation of this application embodiment, when the third acquisition module 206 acquires the monitoring video at the user's electricity meter, it is specifically used for:

[0164] The first and second line charts are segmented according to a preset time interval to obtain multiple sub-segments corresponding to the first line chart and multiple sub-segments corresponding to the second line chart.

[0165] Calculate the similarity of each sub-segment in the first and second line graphs respectively;

[0166] Identify suspicious segments in the second line graph whose similarity is less than a second preset similarity threshold;

[0167] The surveillance video at the user's electricity meter is obtained based on the time interval corresponding to the suspicious segment.

[0168] In one possible implementation of this application embodiment, when the third determining module 207 determines whether electricity theft has occurred based on surveillance video, it is specifically used for:

[0169] Feature recognition is performed on surveillance videos to determine whether people are present in the videos.

[0170] If a person is identified, determine the duration of their presence in the surveillance video.

[0171] Individuals whose presence lasts longer than a preset time will be identified as suspicious individuals.

[0172] Behavioral signatures of suspicious individuals to identify whether they are stealing electricity.

[0173] In one possible implementation of this application embodiment, the apparatus 20 further includes:

[0174] The fourth determination module is used to determine the start time corresponding to the occurrence of electricity theft when it is determined that electricity theft has occurred.

[0175] The fourth acquisition module is used to acquire the change in electricity consumption of the meter within a preset range from the start time.

[0176] The fifth determination module is used to determine the user corresponding to the electricity theft behavior based on the changes in electricity consumption.

[0177] In one possible implementation of this application embodiment, the apparatus 20 further includes:

[0178] The extraction module is used to extract video clips corresponding to suspicious persons from surveillance videos.

[0179] The output module is used to output video clips.

[0180] In one possible implementation of this application embodiment, the apparatus 20 further includes:

[0181] The marking module is used to mark the electricity meter corresponding to the electricity theft when it is determined that an electricity theft has occurred.

[0182] In the embodiments of this application, the first acquisition module 201, the second acquisition module 204, the third acquisition module 206, and the fourth acquisition module may be the same acquisition module, different acquisition modules, or partially the same acquisition module. The first determination module 203, the second determination module 205, the third determination module 207, the fourth determination module, and the fifth determination module may be the same determination module, different determination modules, or partially the same determination module.

[0183] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electricity meter theft detection device 20 described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0184] This application provides an electronic device, such as... Figure 3 As shown, Figure 3 The illustrated electronic device 30 includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 30 does not constitute a limitation on the embodiments of this application.

[0185] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0186] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0187] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0188] The memory 303 is used to store application code that executes the solution of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0189] Electronic devices include, but are not limited to: mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Servers can also be included. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0190] This application provides a computer-readable storage medium storing a computer program. When the program is run on a computer, it enables the computer to execute the corresponding content in the aforementioned method embodiments. Compared with related technologies, this application obtains a user's daily electricity usage within a preset time period. The electricity usage within this preset time period characterizes the user's electricity consumption habits. Dates within the preset time period are categorized based on daily electricity usage, grouping dates with similar usage into one category to facilitate determining the date category. After determining the date category and obtaining the electricity usage for that day, it is determined whether the electricity usage is abnormal based on the day's usage and the usage within the date category. Once the date category is determined, the difference between the day's electricity usage and the usage within the same date category confirms whether the day's electricity usage is abnormal. Upon detecting an anomaly, monitoring video from the user's electricity meter is obtained. The monitoring video records the events at the meter, thus determining whether electricity theft has occurred. Therefore, electricity theft can be detected on the day it occurs, achieving timely detection of electricity theft.

[0191] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0192] The above description is only a partial embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for detecting electricity theft by an electricity meter, characterized by, The method comprises: obtaining the power consumption of the user every day within a preset time period; classifying the dates within the preset time period based on the power consumption, to obtain at least two date categories; determining the date category corresponding to the current date; obtaining the power consumption of the user on the current day; determining whether the power consumption on the current day is abnormal based on the power consumption on the current day and the power consumption within the date category; if it is abnormal, obtaining the monitoring video at the user's power meter; determining whether electricity stealing behavior occurs based on the monitoring video; The power consumption includes daily total power consumption and / or power consumption change, and determining whether the power consumption on the current day is abnormal based on the power consumption on the current day and the power consumption within the date category comprises at least one of the following: determining the average daily total power consumption within the date category, determining the power difference between the total power consumption on the current day and the average daily total power consumption, and if the power difference is greater than a preset difference, determining that the power consumption on the current day is abnormal; determining the date closest to the current day from the date category, determining a first line chart and a second line chart, the first line chart being a line chart of the power consumption change over time within the date closest to the current day, and the second line chart being a line chart of the power consumption change on the current day, calculating the similarity of the first line chart and the second line chart, and determining whether the similarity is less than a first preset similarity threshold, and if it is less than, determining that the power consumption on the current day is abnormal; The method comprises: segmenting the first line chart and the second line chart according to a preset time interval to obtain a plurality of sub-segments corresponding to the first line chart and a plurality of sub-segments corresponding to the second line chart; calculating the similarity of each sub-segment corresponding to the first line chart and the second line chart respectively; determining a suspicious sub-segment in the second line chart whose similarity is less than a second preset similarity threshold; obtaining the monitoring video at the user's power meter based on the time interval corresponding to the suspicious sub-segment.

2. The method of claim 1, wherein, The method comprises: performing feature recognition on the monitoring video to determine whether there is a person in the monitoring video; if a person is identified, determining the presence time of the person in the monitoring video; determining a suspicious person if the presence time is greater than a preset time; performing action feature recognition on the suspicious person to determine whether the suspicious person has electricity stealing behavior.

3. The method of claim 2, wherein, The method further comprises: if it is determined that electricity stealing behavior occurs, determining the start time corresponding to the electricity stealing behavior; obtaining the power consumption change of the power meter within a preset range from the start time; determining the user corresponding to the electricity stealing behavior based on the power consumption change.

4. The method of claim 2, wherein, The method further comprises: if it is determined that electricity stealing behavior occurs, marking the power meter corresponding to the electricity stealing behavior. The method comprises:

5. The method of claim 1, wherein, a first obtaining module for obtaining the power consumption of the user every day within a preset time period; ​ 6. An electricity meter electricity theft detection apparatus characterized by, ​ ​ The classification module is configured to classify dates in a preset time period based on the power usage to obtain at least two date categories. The first determination module is configured to determine a date category corresponding to a current date. The second acquisition module is configured to acquire a power usage of the current date of the user. The second determination module is configured to determine whether the power usage of the current date is abnormal based on the power usage of the current date and the power usage in the date category. The third acquisition module is configured to acquire monitoring video at a power meter of the user when the power usage is abnormal. The third determination module is configured to determine whether electricity stealing occurs based on the monitoring video. The second determination module is specifically configured to determine an average daily total power consumption in the date category, determine a power difference between the total power consumption of the current date and the average daily total power consumption, and determine that the power usage of the current date is abnormal if the power difference is greater than a preset difference. In addition, the second determination module is configured to determine a date closest to the current date from the date category, determine a first line chart and a second line chart, determine a first line chart of the power usage in the date closest to the current date changing with time, determine a second line chart of the power usage of the current date changing with time, calculate a similarity between the first line chart and the second line chart, and determine that the power usage of the current date is abnormal if the similarity is less than a first preset similarity threshold. The third acquisition module is specifically configured to segment the first line chart and the second line chart according to a preset time interval to obtain a plurality of subsegments corresponding to the first line chart and a plurality of subsegments corresponding to the second line chart, calculate a similarity corresponding to each subsegment of the first line chart and the second line chart, determine a suspicious subsegment of the second line chart with a similarity less than a second preset similarity threshold, and acquire the monitoring video at the power meter of the user based on a time interval corresponding to the suspicious subsegment.

7. An electronic device, comprising: It includes: One or more processors; Memory; One or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more application programs are configured to execute the power meter electricity stealing detection method according to any one of claims 1-5.

8. A computer readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed in the computer, the computer is caused to execute the power meter electricity stealing detection method according to any one of claims 1-5.

Images