Power consumption anomaly detection method, device and electronic equipment

Abstract

The application discloses an abnormal electricity use detection method and device and electronic equipment. The method comprises the following steps: obtaining target attribute data, daily electricity consumption data and hourly electricity consumption data of a target enterprise, wherein the target attribute data comprises a target enterprise scale, a target industry type and a target business time type of the target enterprise; determining a first abnormal result of the target enterprise in the target industry type and a second abnormal result of the target enterprise in the target business time type according to the target attribute data, the daily electricity consumption data and the hourly electricity consumption data of the target enterprise; and determining a target abnormal result of whether the target enterprise is an abnormal electricity use enterprise according to the first abnormal result and the second abnormal result. The application solves the technical problem that it is difficult to accurately determine an abnormal electricity use enterprise in the related art.

Description

Technical Field

[0001] This invention relates to the field of computers, and more specifically, to a method, apparatus, and electronic device for detecting abnormal power consumption. Background Technology

[0002] Work safety is a major issue concerning the safety of people's lives and property, and a sign of coordinated and healthy economic and social development. To implement the work safety supervision system and prevent and mitigate major safety risks, it is necessary to accurately identify enterprises with abnormal electricity usage. However, current technologies struggle to accurately identify such abnormalities.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a method, apparatus, and electronic device for detecting abnormal electricity consumption, thereby at least solving the technical problem in the related art of accurately identifying enterprises with abnormal electricity consumption.

[0005] According to one aspect of the present invention, a method for detecting abnormal electricity consumption is provided, comprising: acquiring target attribute data, daily electricity consumption data, and hourly electricity consumption data of a target enterprise, wherein the target attribute data includes the target enterprise size, target industry type, and target business hour type of the target enterprise; determining a first abnormal result of the target enterprise under the target industry type and a second abnormal result of the target enterprise under the target business hour type based on the target attribute data, daily electricity consumption data, and hourly electricity consumption data of the target enterprise; and determining whether the target enterprise is a target abnormal result of an abnormal electricity consumption enterprise based on the first abnormal result and the second abnormal result.

[0006] Optionally, after determining whether the target enterprise is an abnormal electricity user based on the first abnormal result and the second abnormal result, the method further includes: when the target abnormal result indicates that the target enterprise is an abnormal electricity user, determining the abnormal electricity consumption type of the target enterprise based on the target attribute data, daily electricity consumption data and hourly electricity consumption data of the target enterprise.

[0007] Optionally, the step of determining whether the target enterprise is an abnormal electricity user based on the first abnormal result and the second abnormal result includes: inputting the target attribute data, daily electricity consumption data and hourly electricity consumption data of the target enterprise into the electricity consumption anomaly identification model to obtain a third abnormal result; and determining whether the target enterprise is an abnormal electricity user based on the first abnormal result, the second abnormal result and the third abnormal result.

[0008] Optionally, the step of determining whether the target enterprise is an abnormal electricity user based on the first abnormal result and the second abnormal result includes: obtaining the target enterprise's historical daily electricity consumption data and historical hourly electricity consumption data; determining the year-on-year and month-on-month comparisons between the target enterprise's daily electricity consumption data and the historical daily electricity consumption data, and the year-on-year and month-on-month comparisons between the target enterprise's hourly electricity consumption data and the historical hourly electricity consumption data, to obtain a fourth abnormal result; and determining whether the target enterprise is an abnormal electricity user based on the first abnormal result, the second abnormal result, and the fourth abnormal result.

[0009] Optionally, determining the first abnormal result of the target enterprise under the target industry type based on the target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data includes: determining the first upper limit and the first lower limit of electricity consumption for the target enterprise's size within a predetermined time period under the target industry type; determining the first target electricity consumption for the target enterprise within the predetermined time period based on the target enterprise's daily electricity consumption data and hourly electricity consumption data; and comparing the first target electricity consumption with the first upper limit and the first lower limit of electricity consumption to determine the first abnormal result of the target enterprise under the target industry type.

[0010] Optionally, determining the second abnormal result of the target enterprise under the target business time type based on the target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data includes: determining the second upper limit and the second lower limit of electricity consumption for the target enterprise's size within a predetermined time period under the target business time type; determining the second target electricity consumption for the target enterprise within the predetermined time period based on the target enterprise's daily electricity consumption data and hourly electricity consumption data; and comparing the second target electricity consumption with the second upper limit and the second lower limit of electricity consumption to determine the second abnormal result of the target enterprise under the target business time type.

[0011] Optionally, obtaining the target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data includes: obtaining the target enterprise's initial attribute data, initial daily electricity consumption data, and initial hourly electricity consumption data; and standardizing the initial attribute data, initial daily electricity consumption data, and initial hourly electricity consumption data to obtain the target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data.

[0012] According to one aspect of the present invention, an electricity consumption anomaly detection device is provided, comprising: an acquisition module, configured to acquire target attribute data, daily electricity consumption data, and hourly electricity consumption data of a target enterprise, wherein the target attribute data includes the target enterprise size, target industry type, and target business hour type of the target enterprise; a first determination module, configured to determine, based on the target attribute data, daily electricity consumption data, and hourly electricity consumption data of the target enterprise, a first anomaly result of the target enterprise under the target industry type, and a second anomaly result of the target enterprise under the target business hour type; and a second determination module, configured to determine, based on the first anomaly result and the second anomaly result, whether the target enterprise is a target anomaly result of an abnormal electricity consumption enterprise.

[0013] According to one aspect of the present invention, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the power consumption anomaly detection method described in any of the preceding embodiments.

[0014] According to one aspect of the present invention, a computer-readable storage medium is provided, wherein when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the power consumption anomaly detection method described above.

[0015] In this embodiment of the invention, target attribute data, including target enterprise size, target industry type, and target business hour type, as well as daily and hourly electricity consumption data, are obtained for the target enterprise. Based on these data, a first abnormal result for the target enterprise under the target industry type and a second abnormal result for the target enterprise under the target business hour type are determined. The first and second abnormal results are then used to jointly determine whether the target enterprise is an enterprise with abnormal electricity consumption. Since the first abnormal result is an abnormal result among enterprises of the same industry type obtained from daily and hourly electricity consumption data, and the second abnormal result is an abnormal result among enterprises of the same business hour type obtained from daily and hourly electricity consumption data, the comprehensive determination of whether the target enterprise is an enterprise with abnormal electricity consumption through these two abnormal results allows for a more accurate identification of enterprises with abnormal electricity consumption, thus solving the technical problem in related technologies where it is difficult to accurately identify enterprises with abnormal electricity consumption. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 This is a flowchart of an electricity anomaly detection method according to an embodiment of the present invention;

[0018] Figure 2 This is a flowchart illustrating the method provided by an optional embodiment of the present invention;

[0019] Figure 3 This is a structural block diagram of an electrical anomaly detection device according to an embodiment of the present invention. Detailed Implementation

[0020] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0021] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0022] Example 1

[0023] According to an embodiment of the present invention, an embodiment of a method for detecting abnormal electricity consumption is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0024] Figure 1 This is a flowchart of an electricity anomaly detection method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0025] Step S102: Obtain the target attribute data, daily electricity consumption data and hourly electricity consumption data of the target enterprise. The target attribute data includes the target enterprise size, target industry type and target business time type of the target enterprise.

[0026] Step S104: Based on the target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data, determine the first abnormal result of the target enterprise under the target industry type, and the second abnormal result of the target enterprise under the target business time type.

[0027] Step S106: Based on the first abnormal result and the second abnormal result, determine whether the target enterprise is a target abnormal result of an abnormal electricity consumption enterprise.

[0028] Through the above steps, target attribute data, including target company size, target industry type, and target business hours type, as well as daily and hourly electricity consumption data, are obtained for the target company. Based on this data, the first anomaly result for the target company within the target industry type and the second anomaly result for the target company within the target business hours type are determined. These two anomaly results are then used to jointly determine whether the target company is an enterprise with abnormal electricity consumption. Since the first anomaly result is an anomaly result within the same industry type obtained from daily and hourly electricity consumption data, and the second anomaly result is an anomaly result within the same business hours type obtained from daily and hourly electricity consumption data, using both anomaly results to comprehensively determine whether the target company is an enterprise with abnormal electricity consumption allows for a more accurate identification of enterprises with abnormal electricity consumption, thus solving the technical problem of accurately identifying enterprises with abnormal electricity consumption in related technologies.

[0029] It should be noted that the above daily and hourly electricity consumption data do not simply refer to electricity consumption data for a single day or hour. These data can be customized according to the actual application and scenario, such as daily electricity consumption data for a continuous week or hourly electricity consumption data for a continuous 24-hour period.

[0030] As an optional implementation, when acquiring the target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data, the initial attribute data, initial daily electricity consumption data, and initial hourly electricity consumption data of the target enterprise can be obtained first. This initial attribute data, initial daily electricity consumption data, and initial hourly electricity consumption data can be standardized to obtain the target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data. Through data standardization, the target attribute data, daily electricity consumption data, and hourly electricity consumption data can be made as standardized as possible, making them easier to use, reducing the computational load during the detection process, and accelerating the detection process.

[0031] As an optional implementation, when determining whether a target enterprise is an abnormal electricity user based on the first and second abnormal results, an electricity consumption anomaly identification model can be added for auxiliary judgment. This involves inputting the target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data into the electricity consumption anomaly identification model to obtain a third abnormal result. Based on the first, second, and third abnormal results, the determination of whether the target enterprise is an abnormal electricity user is then made. The electricity consumption anomaly identification model can be a combination of multiple algorithms, such as a model combining the Mann-Kendall mutation point algorithm, the Pettitt algorithm, the Buishand U test algorithm, and the Standard Normal Homogeneity Test (SNHT). Using the electricity consumption anomaly identification model can make the obtained target abnormal results more accurate.

[0032] As an optional embodiment, when determining whether a target enterprise is an abnormal electricity user based on the first and second abnormal results, further judgment can be made by comparing it with the enterprise's own historical data: obtaining the target enterprise's historical daily and hourly electricity consumption data, determining the year-on-year and month-on-month comparisons between the target enterprise's daily electricity consumption data and historical daily electricity consumption data, and the year-on-year and month-on-month comparisons between the target enterprise's hourly electricity consumption data and historical hourly electricity consumption data, to obtain a fourth abnormal result. Based on the first, second, and fourth abnormal results, the target enterprise is determined to be an abnormal electricity user. The fourth abnormal result allows for comparison to see if the target enterprise has exhibited behavior significantly different from its historical activities, and further data analysis can be conducted to determine if the target enterprise has engaged in abnormal activities. This optional embodiment can promptly detect sudden behavioral anomalies in target enterprises.

[0033] As an optional implementation, when determining the first abnormal result of a target enterprise under a target industry type based on the target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data, the following method can be adopted: Determine the first upper limit and the first lower limit of electricity consumption for the target enterprise within a predetermined time period under the target industry type; determine the first target electricity consumption for the target enterprise within the predetermined time period based on the target enterprise's daily and hourly electricity consumption data; compare the first target electricity consumption with the first upper limit and the first lower limit of electricity consumption to determine the first abnormal result of the target enterprise under the target industry type. Because multiple enterprises within the same industry type may have different sizes, their electricity consumption should also be different. Therefore, it is necessary to obtain the electricity consumption of enterprises with the same size as the target enterprise to analyze the upper and lower limits of electricity consumption. Enterprises with the same size as the target enterprise can be those whose size is inherently the same as the target enterprise, or they can be inferred proportionally. By comparing the first target electricity consumption with the first upper limit and the first lower limit of electricity consumption, the first abnormal result of the target enterprise under the target industry type is determined. If the first target electricity consumption exceeds the first electricity consumption upper limit or is lower than the first electricity consumption lower limit, it can be seen that the first target electricity consumption is different from the electricity consumption of the target industry type in which the target enterprise is located. Therefore, the first abnormal result can be preliminarily judged as abnormal, so further analysis can be carried out, and the abnormality is considered from the perspective of industry-specific electricity consumption.

[0034] As an optional implementation, when determining the second abnormal result of a target enterprise under a target business time type based on the target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data, the following method can be adopted: determine the second upper limit and second lower limit of electricity consumption for the target enterprise's size within a predetermined time period under the target business time type; determine the second target electricity consumption for the target enterprise within the predetermined time period based on the target enterprise's daily and hourly electricity consumption data; compare the second target electricity consumption with the second upper limit and second lower limit of electricity consumption to determine the second abnormal result of the target enterprise under the target business time type. Because multiple enterprises under the same business time type may have different sizes, their electricity consumption should also be different. Therefore, it is necessary to obtain the electricity consumption of enterprises with the same size as the target enterprise to analyze the upper and lower limits of electricity consumption. Enterprises with the same size as the target enterprise can be those whose size is inherently the same as the target enterprise, or they can be inferred proportionally. By comparing the second target electricity consumption with the second upper limit and second lower limit of electricity consumption, the second abnormal result of the target enterprise under the target business time type is determined. If the second target electricity consumption exceeds the upper limit or falls below the lower limit, it indicates a discrepancy between the second target electricity consumption and the electricity consumption during the target business hours of the target enterprise. Therefore, the second abnormal result can be preliminarily identified as abnormal, paving the way for further analysis. The abnormality was considered in terms of electricity consumption during business hours.

[0035] As an optional embodiment, after determining whether the target enterprise is an abnormal electricity user based on the first abnormal result and the second abnormal result, the following operation can also be performed: when the target abnormal result indicates that the target enterprise is an abnormal electricity user, the abnormal electricity consumption type of the target enterprise can be determined based on the target attribute data, daily electricity consumption data and hourly electricity consumption data of the target enterprise. Common types of abnormal electricity consumption by enterprises include: **Ostensible shutdown, covert operation:** Enterprises ordered to cease production within a specified period experience a significant increase in daily electricity consumption compared to their usual non-production usage. **Emergency production shutdown:** Enterprises operating normally experience a decrease in daily electricity consumption exceeding 70% of the previous day's consumption. **Overload production:** Enterprises operating normally experience a significant increase in daily electricity consumption compared to their usual production usage. **Automatic shutdown:** Enterprises operating normally experience daily electricity consumption consistently lower than their usual non-production usage for several consecutive days. **Long-term shutdown:** Enterprises that automatically shut down experience daily electricity consumption consistently lower than their usual production usage. **Resumption of production after shutdown:** Enterprises that have experienced long-term shutdowns or automatic shutdowns experience daily electricity consumption consistently higher than their production and non-production usage for several consecutive days. **Daytime shutdown, nighttime operation:** Enterprises ordered to cease production within a specified period experience a significant increase in nighttime electricity consumption compared to daytime consumption. Identifying specific types of abnormal electricity consumption allows for better monitoring and verification of target enterprises.

[0036] It should be noted that the above-mentioned determination of whether a target enterprise is an abnormal electricity user is based on the first and second abnormal results. The determination of whether a target enterprise is an abnormal electricity user is based on the first, second, and third abnormal results. The determination of whether a target enterprise is an abnormal electricity user is based on the first, second, and fourth abnormal results. The rules for determining the target abnormal results can be customized according to the actual application and scenario. For example, different weight values ​​can be assigned to different abnormal results based on business hours and industry type. When the combined abnormal results exceed a predetermined threshold, the target enterprise is determined to be an abnormal electricity user. The rules for determining the target abnormal results are not limited here. This makes this optional embodiment more flexible and applicable.

[0037] Based on the above embodiments and optional embodiments, an optional implementation method is provided, which is described in detail below.

[0038] An optional embodiment of this invention provides a method for monitoring enterprise safety production status based on electricity consumption data. This method fully leverages the advantages of power data resources, data sharing, and innovative applications. Focusing on areas such as smart supervision and big data-enabled safety supervision, it actively promotes the innovative application of power data in the field of safety production supervision. Combined with the State Grid's unified enterprise safety production electricity consumption monitoring and analysis system, it constructs an enterprise safety status monitoring and analysis model to identify enterprises with abnormal electricity consumption. By analyzing changes in electricity consumption, it identifies enterprises with abnormal safety production and explores a new smart supervision model of "safety supervision + power big data". Figure 2 This is a flowchart illustrating the method provided by an optional embodiment of the present invention, such as... Figure 2 As shown below, the method provided by the optional embodiments of the present invention will be described in detail:

[0039] S1, Obtain the initial attribute data, initial daily electricity consumption data and initial hourly electricity consumption data of the target enterprise;

[0040] The data sources are electricity consumption behavior information from the electricity consumption data collection system and data from the marketing business application system, such as enterprise information, enterprise file data, enterprise daily electricity consumption data, enterprise hourly electricity load data, and enterprise early warning result data.

[0041] S2, standardize the initial attribute data, initial daily electricity consumption data and initial hourly electricity consumption data to obtain the target attribute data, daily electricity consumption data and hourly electricity consumption data of the target enterprise;

[0042] Data standardization can be used for data cleaning. To improve the accuracy of indicators, the initial data needs to be cleaned. The data cleaning rules are as follows:

[0043] (1) Any missing data in any field is defined as missing data, such as empty area name, area number, power outage time, company name, company number, etc.

[0044] (2) Duplicate entries in the details are defined as data redundancy, such as duplicate or conflicting data such as area name, area number, and power outage time.

[0045] (3) There are obvious common sense errors in the business data, which is defined as inaccurate data, such as the power supply unit, the number of the public distribution transformer, the start time of the power outage, etc., which are inconsistent with common sense.

[0046] Common handling methods include: filling missing values ​​with a uniform default value or filling them with a specific value (such as the mean, minimum, median, etc.); deleting records containing outliers.

[0047] S3. Based on the target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data, determine the first abnormal result of the target enterprise under the target industry type;

[0048] This involves exploring commonalities among companies in the same industry. Based on the target company's daily and hourly electricity consumption data, the month-on-month and year-on-year electricity consumption of each company in the same industry are calculated. Correlation analysis is performed on the month-on-month and year-on-year changes in electricity consumption of companies according to industry classification. Box plots are drawn for the month-on-month and year-on-year electricity consumption data of companies in the industry, and the upper and lower edges are calculated. The average value of the upper edge and the average value of the lower edge (same as the first upper limit and the first lower limit of electricity consumption mentioned above) are taken as the threshold for identifying abnormal companies in the industry. The threshold is compared with the average value of the upper edge and the average value of the lower edge to determine the first abnormal result of the target company in the target industry type.

[0049] S4, based on the target enterprise's target attribute data, daily electricity consumption data and hourly electricity consumption data, the second abnormal result of the target enterprise under the target business time type;

[0050] This involves exploring commonalities among enterprises during the same period. Based on the daily and hourly electricity consumption data of the target enterprise, the month-on-month and year-on-year electricity consumption of each enterprise during the same business hours are calculated. Correlation analysis is performed on the month-on-month and year-on-year changes in electricity consumption of enterprises over time. Box plots are drawn on the month-on-month and year-on-year electricity consumption data of enterprises, and the upper and lower edges are calculated. The average values ​​of the upper and lower edges (similar to the second upper and lower limits of electricity consumption mentioned above) are taken as the threshold for identifying enterprises with abnormal electricity consumption during this period. The threshold is compared with the average values ​​of the upper and lower edges to determine the second abnormal result of the target enterprise under the target business time type.

[0051] S5, input the target enterprise's target attribute data, daily electricity consumption data and hourly electricity consumption data into the electricity consumption anomaly identification model to obtain the third anomaly result;

[0052] The electricity consumption anomaly identification model incorporates multiple algorithms. Since a single method for detecting time-series mutation points may contain errors, a combination of algorithms is used, with the final result obtained by combining the results. The target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data are processed using four algorithms: Mann-Kendall mutation point, Petitt's algorithm, BuishandU test algorithm, and Standard Normal Homogeneity Test (SNHT). Then, the anomaly identification results from these four algorithms are combined, the intersection of the results is taken, and the upward and downward trend results are extracted to output the third anomaly result.

[0053] S6. Based on the first abnormal result, the second abnormal result and the third abnormal result, determine whether the target enterprise is a target abnormal result of an abnormal electricity consumption enterprise.

[0054] It should be noted that when the third abnormal result output by the electricity anomaly identification model is a non-abnormal electricity user enterprise, but it is actually an abnormal electricity user enterprise, the reasons for the error in the model result can be analyzed, and special conditions can be formulated to optimize the model based on the actual data.

[0055] S7. When the target abnormal result is that the target enterprise is an abnormal electricity user, the abnormal electricity consumption type of the target enterprise is determined based on the target enterprise's target attribute data, daily electricity consumption data and hourly electricity consumption data.

[0056] Based on the analysis results, the common types of abnormal electricity consumption in enterprises are as follows:

[0057] ① Overt shutdown but covert operation: The electricity consumption characteristics of enterprises that are ordered to suspend production within a specified period are significantly higher than their daily non-production electricity consumption.

[0058] ② Emergency production shutdown: Its electricity consumption characteristics are that the daily electricity consumption of enterprises that are operating normally decreases by more than 70% compared with the previous day.

[0059] ③ Overloaded production: Its electricity consumption characteristics are that the daily electricity consumption of enterprises that are operating normally is significantly higher than the daily production electricity consumption of enterprises.

[0060] ④ Automatic shutdown: Its electricity consumption characteristics are that the daily electricity consumption of enterprises that are operating normally is lower than the daily non-production electricity consumption of enterprises for several consecutive days.

[0061] ⑤ Long-term shutdown: The electricity consumption characteristics of enterprises that automatically shut down are that their daily electricity consumption is lower than their daily production electricity consumption for a long period of time.

[0062] ⑥ Resumption of production after shutdown: The electricity consumption characteristics of enterprises that have been shut down for a long time or have automatically stopped production are higher than the daily electricity consumption for production and non-production purposes for many consecutive days.

[0063] ⑦ Daytime shutdown and nighttime operation: The electricity consumption characteristics of enterprises that are ordered to suspend production within a specified period are significantly higher at night than during the day.

[0064] The above optional implementation methods can achieve at least the following beneficial effects:

[0065] (1) Conduct correlation analysis on enterprise electricity consumption from multiple dimensions such as industry and time to accurately describe the characteristics of enterprise electricity consumption and judge whether the enterprise has abnormal electricity consumption behavior from multiple aspects.

[0066] (2) By using multiple algorithms to identify anomalies, the problem of possible errors in the result of a single method for detecting time series mutation points is avoided. By combining multiple algorithms to finally obtain the intersection result and extract the rising and falling trend results, enterprises with abnormal electricity consumption can be identified more accurately and efficiently.

[0067] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0068] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0069] Example 2

[0070] According to embodiments of the present invention, an apparatus for implementing the above-described method for detecting abnormal electricity consumption is also provided. Figure 3 This is a structural block diagram of an electrical anomaly detection device according to an embodiment of the present invention, such as... Figure 3 As shown, the device includes: an acquisition module 302, a first determination module 304, and a second determination module 306. The device will be described in detail below.

[0071] The acquisition module 302 is used to acquire target attribute data, daily electricity consumption data, and hourly electricity consumption data of the target enterprise. The target attribute data includes the target enterprise size, target industry type, and target business time type of the target enterprise. The first determination module 304 is connected to the acquisition module 302 and is used to determine the first abnormal result of the target enterprise under the target industry type and the second abnormal result of the target enterprise under the target business time type based on the target attribute data, daily electricity consumption data, and hourly electricity consumption data of the target enterprise. The second determination module 306 is connected to the first determination module 304 and is used to determine whether the target enterprise is a target abnormal result of an abnormal electricity consumption enterprise based on the first abnormal result and the second abnormal result.

[0072] It should be noted that the above-mentioned acquisition module 302, the first determination module 304 and the second determination module 306 correspond to steps S102 to S106 in the implementation of the power consumption anomaly detection method. The multiple modules and the corresponding steps are the same in terms of implementation instances and application scenarios, but are not limited to the content disclosed in the above embodiment 1.

[0073] Example 3

[0074] According to another aspect of the present invention, an electronic device is also provided, comprising: a processor; and a memory for storing processor-executable instructions, wherein the processor is configured to execute instructions to implement the power consumption anomaly detection method of any of the above embodiments.

[0075] Example 4

[0076] According to another aspect of the present invention, a computer-readable storage medium is also provided, which, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform any of the above-described power consumption anomaly detection methods.

[0077] Example 5

[0078] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the power consumption anomaly detection method described in any of the preceding embodiments.

[0079] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0080] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0081] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0082] 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 units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0083] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0084] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a 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 the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0085] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for detecting abnormal electricity usage, characterized in that, include: Obtain target attribute data, daily electricity consumption data and hourly electricity consumption data of the target enterprise, wherein the target attribute data includes the target enterprise size, target industry type and target business time type of the target enterprise; Based on the target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data, determine the first abnormal result of the target enterprise under the target industry type, and the second abnormal result of the target enterprise under the target business time type; Based on the first abnormal result and the second abnormal result, determine whether the target enterprise is a target abnormal result of an abnormal electricity consumption enterprise; The step of determining whether the target enterprise is an abnormal electricity user based on the first abnormal result and the second abnormal result includes: inputting the target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data into the electricity consumption anomaly identification model to obtain a third abnormal result; determining whether the target enterprise is an abnormal electricity user based on the first abnormal result, the second abnormal result, and the third abnormal result, wherein the electricity consumption anomaly identification model is obtained by combining the Mann-Kendall mutation point algorithm, the Pettitt algorithm, the BuishandUtest algorithm, and the Standard Normal Homogeneity Test algorithm; The step of determining whether the target enterprise is an abnormal electricity user based on the first abnormal result and the second abnormal result includes: obtaining the target enterprise's historical daily electricity consumption data and historical hourly electricity consumption data; determining the year-on-year and month-on-month comparisons between the target enterprise's daily electricity consumption data and the historical daily electricity consumption data, and the year-on-year and month-on-month comparisons between the target enterprise's hourly electricity consumption data and the historical hourly electricity consumption data, to obtain a fourth abnormal result; and determining whether the target enterprise is an abnormal electricity user based on the first abnormal result, the second abnormal result, and the fourth abnormal result.

2. The method according to claim 1, characterized in that, After determining whether the target enterprise is an abnormal electricity user based on the first abnormal result and the second abnormal result, the method further includes: When the target abnormality result indicates that the target enterprise is an abnormal electricity user, the abnormal electricity consumption type of the target enterprise is determined based on the target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data.

3. The method according to claim 1, characterized in that, The step of determining the first abnormal result of the target enterprise under the target industry type based on the target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data includes: Determine the first upper limit and the first lower limit of electricity consumption for the target enterprise size within a predetermined time period under the target industry type; Based on the daily and hourly electricity consumption data of the target enterprise, the first target electricity consumption of the target enterprise within the predetermined time period is determined; By comparing the first target electricity consumption with the first electricity consumption upper limit and the first electricity consumption lower limit, the first abnormal result of the target enterprise under the target industry type is determined.

4. The method according to claim 1, characterized in that, The step of determining the second abnormal result of the target enterprise under the target business time type based on the target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data includes: Determine the second upper limit and the second lower limit of electricity consumption for the target enterprise size within a predetermined time period under the target business time type; Based on the daily and hourly electricity consumption data of the target enterprise, a second target electricity consumption of the target enterprise within the predetermined time period is determined; By comparing the second target electricity consumption with the second upper limit of electricity consumption and the second lower limit of electricity consumption, a second abnormal result of the target enterprise under the target business time type is determined.

5. The method according to any one of claims 1 to 4, characterized in that, The acquisition of target enterprise's target attribute data, daily electricity consumption data, and hourly electricity consumption data includes: Obtain the initial attribute data, initial daily electricity consumption data, and initial hourly electricity consumption data of the target enterprise; The initial attribute data, initial daily electricity consumption data, and initial hourly electricity consumption data are standardized to obtain the target attribute data, daily electricity consumption data, and hourly electricity consumption data of the target enterprise.

6. A device for detecting abnormal electricity usage, characterized in that, include: The acquisition module is used to acquire target attribute data, daily electricity consumption data and hourly electricity consumption data of the target enterprise, wherein the target attribute data includes the target enterprise size, target industry type and target business time type of the target enterprise; The first determining module is used to determine, based on the target enterprise's target attribute data, daily electricity consumption data and hourly electricity consumption data, the first abnormal result of the target enterprise under the target industry type and the second abnormal result of the target enterprise under the target business time type. The second determining module is used to determine whether the target enterprise is a target abnormal result of an abnormal electricity consumption enterprise based on the first abnormal result and the second abnormal result; The second determining module is used to input the target attribute data, daily electricity consumption data and hourly electricity consumption data of the target enterprise into the electricity consumption anomaly identification model to obtain a third anomaly result; based on the first anomaly result, the second anomaly result and the third anomaly result, to determine whether the target enterprise is a target anomaly result of an abnormal electricity consumption enterprise, wherein the electricity consumption anomaly identification model is obtained by combining the Mann-Kendall mutation point algorithm, the Pettitt algorithm, the BuishandUtest algorithm and the Standard Normal Homogeneity Test algorithm; The second determining module is used to acquire the historical daily electricity consumption data and historical hourly electricity consumption data of the target enterprise; determine the year-on-year and month-on-month comparisons between the daily electricity consumption data of the target enterprise and the historical daily electricity consumption data, and the year-on-year and month-on-month comparisons between the hourly electricity consumption data of the target enterprise and the historical hourly electricity consumption data, to obtain a fourth abnormal result; and determine whether the target enterprise is a target abnormal result of an abnormal electricity consumption enterprise based on the first abnormal result, the second abnormal result, and the fourth abnormal result.

7. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the power consumption anomaly detection method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the power consumption anomaly detection method as described in any one of claims 1 to 5.

Images