Data processing method, electronic device, and storage medium

Abstract

The application discloses a data processing method, an electronic device and a storage medium. The method comprises the following steps: obtaining device profile data, wherein the device profile data comprises device archive data and device operation data; preprocessing the device archive data and the device operation data respectively to obtain first analysis data and second analysis data; performing data anomaly analysis based on the first analysis data and the second analysis data to obtain an abnormal device list; determining an abnormal processing strategy corresponding to each abnormal device in the abnormal device list; and forming a data management work order corresponding to each abnormal device according to the abnormal processing strategy corresponding to each abnormal device. Through the scheme provided in the application, the device profile data can be subjected to abnormal analysis to form an abnormal device list and an abnormal processing strategy, so that the on-site staff can be guided to perform data management work, and the accuracy of on-site operation business analysis can be ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to a data processing method, an electronic device and a storage medium. BACKGROUND

[0002] Due to the reasons such as non-uniform data management standards of various production systems of power grid enterprises, and large differences in data synchronization interfaces, there are still a large number of inconsistent phenomena between device archives and actual situations in the field in various production systems. At present, the data anomaly analysis of the device archives mainly depends on manual checking and business rule discrimination, and there are great deficiencies in real-time, accuracy and practicability of the anomaly processing, the manual cost is high, and the development effectiveness of the device archive analysis and field checking work is seriously affected, and the accuracy of other work such as line loss management is affected.

[0003] Therefore, it is urgent to propose a data processing method capable of performing anomaly analysis on device profile data, so as to form an abnormal device list and an abnormal processing strategy to guide field staff to perform data management work, and ensure the accuracy of field operation business analysis. SUMMARY

[0004] In order to overcome the problems in the related art, the present application provides a data processing method, an electronic device and a storage medium. The data processing method can perform anomaly analysis on device profile data, form an abnormal device list and an abnormal processing strategy to guide field staff to perform data management work, and ensure the accuracy of field operation business analysis.

[0005] The first aspect of the present application provides a data processing method, comprising:

[0006] Obtaining device profile data, the device profile data comprising device archive data and device running data; respectively pre-processing the device archive data and the device running data to obtain first to-be-analyzed data and second to-be-analyzed data; performing data anomaly analysis based on the first to-be-analyzed data and the second to-be-analyzed data to obtain an abnormal device list; determining an abnormal processing strategy corresponding to each abnormal device in the abnormal device list; and forming a data management work order corresponding to each abnormal device according to the abnormal processing strategy corresponding to each abnormal device.

[0007] In an implementation, the device archive data includes transformer archive data, user device data, access point archive, meter box archive data, user archive data, and archive relationship data; the device archive data and the device operation data are preprocessed respectively, wherein the preprocessing of the device archive data includes: determining vacant transformer archive, newly-added transformer archive, stopped transformer archive, and normally-operating transformer archive based on the transformer archive data; determining abnormal user device archive and normal user device archive in the normally-operating transformer archive based on the user device data; checking the archive relationship data based on the normally-operating transformer archive, the normal user device archive, the access point archive, the meter box archive data, and the user archive data to obtain target archive relationship chain; and determining first to-be-analyzed data based on the target archive relationship chain.

[0008] In an implementation, the device operation data includes operation power data, collected power data, transformer line loss data, and device disassembly data; the collected power data includes public transformer power data and low-voltage power data; the device archive data and the device operation data are preprocessed respectively, wherein the preprocessing of the device operation data includes: determining power-missing transformer, power-abnormal transformer, and power-normal transformer based on the operation power data; determining abnormal power data and normal power data in the power-normal transformer based on the public transformer power data and operation power threshold; the operation power threshold is the maximum power value of daily full-load operation; determining abnormal power user device and normal power user device in the power-normal transformer based on the low-voltage power data, wherein the low-voltage power data includes user power data, photovoltaic user online power, and photovoltaic user generated power; determining power-abnormal transformer and power-normal transformer in the power-normal transformer based on the transformer line loss data; determining abnormal user device and normal user device in the normal power user device based on the device disassembly data; and determining second to-be-analyzed data based on the power-normal transformer, the normal power data, and the normal user device.

[0009] In an implementation, the data anomaly analysis based on the first to-be-analyzed data and the second to-be-analyzed data includes: determining archive abnormal device based on the first to-be-analyzed data; determining operation abnormal device based on the second to-be-analyzed data; and determining abnormal device list based on the archive abnormal device and the operation abnormal device.

[0010] In an embodiment, determining the abnormal equipment based on the first data to be analyzed comprises: determining a connection abnormal equipment profile, a meter abnormal equipment profile, a transformer abnormal equipment profile, a coverage abnormal equipment profile, and a household abnormal equipment profile based on the first data to be analyzed; the connection abnormal equipment profile is an equipment profile with abnormal connection relationship between the access point profile and the meter profile data; the meter abnormal equipment profile is an equipment profile with abnormal belonging relationship between the meter profile data and the normal user equipment profile; the transformer abnormal equipment profile is an equipment profile with abnormal belonging relationship between the normal operation transformer profile and the meter profile data; the coverage abnormal equipment profile is a user equipment profile with device coordinates outside the coordinate coverage range recorded in the user equipment data, and a user profile with user address outside the meter installation address coverage range recorded in the meter profile data; the household abnormal equipment profile is an equipment profile with abnormal corresponding relationship between the normal user equipment profile and the normal operation transformer profile; and determining the abnormal equipment based on the connection abnormal equipment profile, the meter abnormal equipment profile, the transformer abnormal equipment profile, the coverage abnormal equipment profile, and the household abnormal equipment profile.

[0011] In an embodiment, determining the abnormal equipment based on the second data to be analyzed comprises: determining whether a first operation relationship exists error based on the second data to be analyzed; the first operation relationship is a connection relationship between the transformer total meter and the transformer; if the first operation relationship exists error, determining the transformer total meter as the abnormal equipment; determining whether a second operation relationship exists error based on the second data to be analyzed; the second operation relationship is a belonging relationship between the user equipment and the transformer; if the second operation relationship exists error, determining the current user equipment as the abnormal equipment.

[0012] In an embodiment, determining whether the first operation relationship exists error based on the second data to be analyzed comprises: determining the normal operation transformer and the preliminary abnormal transformer based on the second data to be analyzed; determining the target abnormal transformer according to the preliminary abnormal transformer, the minimum value of the supply and sale power coefficient, and the transformer supply and sale power coefficient; if the transformer supply and sale power coefficient of the target abnormal transformer is greater than the minimum value of the supply and sale power coefficient, and the transformer line loss rate of the target abnormal transformer is within the preset line loss rate range, determining that the transformer total meter of the current target abnormal transformer is connected incorrectly.

[0013] In an implementation, determining whether the second operation relationship has an error based on the second data to be analyzed includes: if the power supply and sale coefficient of the target abnormal transformer area is greater than the power supply and sale coefficient minimum value, and the transformer line loss rate of the target abnormal transformer area is less than the line loss rate interval minimum value of the preset line loss rate interval, determining that the current target abnormal transformer area has a candidate user equipment with abnormal ownership relationship; determining a target abnormal user equipment in the candidate user equipment based on the candidate user equipment, a user power line loss relationship, a line loss rate adjustment value, and a user power failure event time; the user power line loss relationship is a relationship between user power and transformer line loss rate, and the line loss rate adjustment value is a line loss rate calculated after excluding each user power corresponding to the minimum line loss rate of the target abnormal transformer area.

[0014] In an implementation, after determining that the current user equipment is an abnormal operation equipment, the data processing method further includes: if the power supply and sale coefficient of the target abnormal transformer area is greater than the power supply and sale coefficient minimum value, and the transformer line loss rate of the target abnormal transformer area is greater than the line loss rate interval maximum value of the preset line loss rate interval, determining that the current target abnormal transformer area is a high-loss transformer area; determining a high-loss transformer line loss rate of the high-loss transformer area based on the power value of the target abnormal user equipment; if the high-loss transformer line loss rate is within the preset line loss rate interval, and the power failure time of the target abnormal user equipment is consistent with that of the high-loss transformer area, determining that the target abnormal user equipment belongs to the high-loss transformer area.

[0015] The second aspect of the present application provides an electronic device, comprising: a processor and a memory, the memory storing executable code, when the executable code is executed by the processor, the processor executes the method as described above.

[0016] The third aspect of the present application provides a non-transitory machine readable storage medium, which stores executable code, when the executable code is executed by the processor of the electronic device, the processor executes the method as described above.

[0017] The technical solution provided by the present application can include the following beneficial effects:

[0018] The data processing method, the electronic device and the storage medium provided in the application obtain device profile data such as device archive data and device running data, preprocess the device archive data and the device running data respectively to obtain first to-be-analyzed data and second to-be-analyzed data. Then, data anomaly analysis is performed based on the first to-be-analyzed data and the second to-be-analyzed data to obtain an abnormal device list. Then, an abnormal processing strategy corresponding to each abnormal device in the abnormal device list is determined, and a data management work order corresponding to each abnormal device is formed according to the abnormal processing strategy corresponding to each abnormal device. Thus, the device profile data can be subjected to abnormal analysis to form an abnormal device list and an abnormal processing strategy to guide on-site staff to perform data management work on abnormal devices, thereby ensuring the accuracy of on-site operation business analysis.

[0019] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory and are not restrictive of the application. BRIEF DESCRIPTION OF DRAWINGS

[0020] The above and other objects, features and advantages of the present application will become readily apparent from the detailed description that follows, read in conjunction with the accompanying drawings. In the drawings, several embodiments of the application are shown by way of example, and like or corresponding elements are indicated by like or corresponding reference numbers.

[0021] Figure 1 is one of the flowcharts of the data processing method according to an embodiment of the application;

[0022] Figure 2 is a flowchart of preprocessing of device archive data in the data processing method according to an embodiment of the application;

[0023] Figure 3 is a flowchart of preprocessing of device running data in the data processing method according to an embodiment of the application;

[0024] Figure 4 is another flowchart of the data processing method according to an embodiment of the application;

[0025] Figure 5 is a structural diagram of the electronic device according to an embodiment of the application. DETAILED DESCRIPTION

[0026] Embodiments will now be described with reference to the drawings. It should be understood that, for the sake of brevity, the figures can not be drawn to scale, and that certain features of the figures can be shown exaggerated in scale or in somewhat schematic form and that the identification of certain acts or events in certain figures may not imply that they are advantageous, preferred, essential, or useful in all embodiments. In addition, a manner in which the application is set forth in the application is not intended to limit the scope of the application, but rather a scope of the application is defined by the appended claims.

[0027] At present, data anomaly analysis of equipment archives mainly relies on manual checking and business rule discrimination, and there are great deficiencies in real-time performance, accuracy and practicability of anomaly processing, and the cost of manual work is high, which seriously affects the development effectiveness of equipment archive analysis and on-site checking work, and affects the accuracy of line loss management and other work. Therefore, it is urgent to propose a data processing method capable of performing anomaly analysis on equipment profile data to form an abnormal equipment list and an abnormal processing strategy to guide on-site workers to perform data management work and ensure the accuracy of on-site operation business analysis.

[0028] In view of the above problems, the embodiment of the present application provides a data processing method which can perform anomaly analysis on equipment profile data to form an abnormal equipment list and an abnormal processing strategy to guide on-site workers to perform data management work and ensure the accuracy of on-site operation business analysis.

[0029] The technical solutions of the embodiments of the present application will be described in detail below with reference to the drawings.

[0030] Figure 1 is one of the flowcharts of the data processing method shown in the embodiments of the present application. Please refer to Figure 1 The data processing method shown in the embodiments of the present application can include:

[0031] In step 101, equipment profile data is obtained. The equipment profile data can include but is not limited to equipment archive data and equipment operation data. The equipment archive data refers to the archive data associated with each device in each production system and recorded in the system memory. It can be understood that the equipment archive data can be recorded in the system memory when each device is put into operation, and can be used to describe the basic state information and associated action information of the device, so that the information of the device registered in the system can be understood by reading the equipment archive data. In addition, the equipment operation data refers to the data collected during the operation of each device capable of operating in the production system. It can be understood that the equipment operation data can be used to determine whether each device is located in a suitable position and is in a normal operating state.

[0032] It can be understood that the acquisition manner of the equipment profile data is various, for example, data is directly acquired from each production system through an interface. In actual application, a suitable acquisition manner is selected according to actual application conditions, and the application does not make any limitation in this aspect.

[0033] In step 102, the equipment profile data and the equipment operation data are respectively preprocessed to obtain first analysis data and second analysis data. In the embodiment of the application, the process of pre-processing the equipment profile data and the equipment operation data can be regarded as the process of data cleaning of the equipment profile data and the equipment operation data respectively, so that the first analysis data is obtained after the equipment profile data is pre-processed, and the second analysis data is obtained after the equipment operation data is pre-processed. The purpose of pre-processing is to eliminate data that does not meet the data analysis quality requirements, so as to ensure the analysis accuracy and analysis processing efficiency of subsequent data anomaly analysis.

[0034] In step 103, data anomaly analysis is performed based on the first analysis data and the second analysis data to obtain an abnormal equipment list. In the embodiment of the application, the data anomaly analysis of the first analysis data and the data anomaly analysis of the second analysis data can be performed separately, simultaneously or sequentially, and the application does not make any limitation in this aspect. The data anomaly analysis of the first analysis data can analyze the equipment with abnormal profile data, and the data anomaly analysis of the second analysis data can analyze the equipment with abnormal operation process, so that the final abnormal equipment list is formed based on the above two analysis results.

[0035] In step 104, an abnormal processing strategy corresponding to each abnormal equipment in the abnormal equipment list is determined. The abnormal processing strategy is a strategy for guiding the on-site operator to manage the abnormal equipment to eliminate the abnormal situation. For example, if the current electric energy meter is determined not to belong to the current area through analysis, the on-site operator needs to be guided to manage and adjust the profile of the electric energy meter, so that the current electric energy meter belongs to the correct area. It can be understood that the abnormal processing strategy can vary with different abnormal equipment, and in actual application, the corresponding abnormal processing strategy is determined according to the abnormal equipment in the actual application. The above example is only illustrative, and the application does not make any limitation in this aspect.

[0036] In step 105, a data management work order corresponding to each abnormal device is formed according to the abnormal processing strategy corresponding to each abnormal device. It can be understood that the field staff can receive the work order through the mobile device and perform the work according to the received work order. Therefore, in the embodiment of the present application, the current abnormal device and the abnormal processing strategy corresponding to the current abnormal device can be summarized to form the data management work order corresponding to the current abnormal device, and then the data management work order is sent to the mobile device of the field staff to guide the field staff to perform management adjustment.

[0037] Further, in the embodiment of the present application, the data management work order can include a check work order and a management work order. The check work order is used to check the abnormal device on site to determine whether the abnormal device actually occurs abnormal situation. If it is found that the abnormal device actually occurs abnormal situation after checking, the management work order is executed to guide the field staff to perform management adjustment. Then the field staff feeds back the managed archive data to the system, and the system further verifies the feedback archive data for data specification, and after successful verification, the managed archive data replaces the original archive data to complete the update of the data archive. At the same time, the abnormal processing strategy used in the data management work order is optimized according to the processing situation of the data management work order, so as to provide more accurate and comprehensive management suggestions when the abnormal processing strategy is proposed next time.

[0038] By obtaining the device profile data such as device archive data and device running data, the device archive data and the device running data are preprocessed to obtain first analysis data and second analysis data. Then, data anomaly analysis is performed based on the first analysis data and the second analysis data to obtain an abnormal device list. Then, the abnormal processing strategy corresponding to each abnormal device is determined according to each abnormal device in the abnormal device list, and the data management work order corresponding to each abnormal device is formed according to the abnormal processing strategy corresponding to each abnormal device. Thus, the device profile data can be analyzed for abnormality to form an abnormal device list and an abnormal processing strategy to guide the field staff to perform data management work on the abnormal device, and ensure the accuracy of the field operation business analysis.

[0039] In some embodiments, when the device archive data and the device running data are preprocessed, the first analysis data is obtained after the preprocessing of the device archive data, and the second analysis data is obtained after the preprocessing of the device running data. Figure 2 is a flowchart of preprocessing the device archive data in the data processing method according to the embodiment of the present application, Figure 3 is a flowchart of preprocessing the device running data in the data processing method according to the embodiment of the present application. Please refer to Figure 2In the data processing method shown in the embodiments of the present application, the device archive data can include, but is not limited to, transformer area archive data, user device data, access point archive, meter box archive data, user archive data, and archive relationship data. The preprocessing of the device archive data can include:

[0040] In step 201, based on the transformer area archive data, determine the vacant transformer area archive, the newly-added transformer area archive, the out-of-service transformer area archive, and the normally-operating transformer area archive. In the embodiments of the present application, the transformer area archive data can include, but is not limited to, transformer area identifier, transformer area operating state, transformer area capacity, and the like. In actual application, the transformer area archive data can be acquired daily, and then the daily acquired transformer area archive data is processed for checking, and according to the checking result, the transformer area archive is divided into the vacant transformer area archive, the newly-added transformer area archive, the out-of-service transformer area archive, and the normally-operating transformer area archive.

[0041] Specifically, if the current transformer area marker exists the transformer area archive, but there is no user under the current transformer area, or there is a user but all the users have no long-term power consumption data, the current transformer area archive is determined as the vacant transformer area archive. In addition, according to the transformer area operation time, 31 days before the current transformer area is put into operation, combined with the daily line loss data and the monthly line loss data to judge the operation state, if the current transformer area has not been put into operation for 31 days, the current transformer area archive is determined as the newly-added transformer area archive. Furthermore, if the operating state of the current transformer area is out of service or removed, but the user device, such as the electric energy meter, of the current transformer area can still collect the load data, the current transformer area archive is determined as the out-of-service transformer area archive. Then, if the archive data of the current transformer area after the checking is correct, the current transformer area archive is determined as the normally-operating transformer area archive. It can be understood that in actual application, the determination methods of the vacant transformer area archive, the newly-added transformer area archive, the out-of-service transformer area archive, and the normally-operating transformer area archive are various, and the appropriate determination method needs to be determined according to the actual application, and the present application does not make any limitation in this aspect.

[0042] Further, in the embodiments of the present application, the above-mentioned vacant transformer area archive, newly-added transformer area archive, and out-of-service transformer area archive do not participate in the subsequent data anomaly analysis, and the above-mentioned vacant transformer area archive, newly-added transformer area archive, and out-of-service transformer area archive need to be eliminated to ensure the analysis accuracy and analysis processing efficiency of the data anomaly analysis.

[0043] In step 202, the abnormal user equipment archives and normal user equipment archives in the normal operation transformer station archives are determined based on user equipment data. In the embodiment of the present application, the user equipment data can include but is not limited to user type (photovoltaic user, ordinary user), user comprehensive ratio, user equipment state, user equipment identification, user equipment capacity and the like, wherein the user equipment can be an electric energy metering device such as an electric energy meter, and the user comprehensive ratio is the ratio of voltage and current conversion of the user equipment. In actual application, the user equipment data can be acquired daily, and then the user equipment data acquired daily is checked, and the user equipment archives are divided into abnormal user equipment archives and normal user equipment archives according to the checking result. The abnormal user equipment archives do not participate in subsequent data anomaly analysis, and the above-mentioned abnormal user equipment archives need to be removed from all archives under the normal operation transformer station, so as to ensure the analysis accuracy and analysis processing efficiency of data anomaly analysis.

[0044] In step 203, the archive relationship data is checked based on the normal operation transformer station archives, the normal user equipment archives, the access point archives, the meter box archives data and the user archives data, and the target archive relationship chain is obtained. In the embodiment of the present application, the archive relationship data can include first archive relationship, second archive relationship and third archive relationship. The first archive relationship is the archive relationship among transformer station, access point and meter box; the second archive relationship is the archive relationship between meter box and electric energy meter; and the third archive relationship is the archive relationship between electric energy meter and user. The first archive relationship, the second archive relationship and the third archive relationship are checked based on the normal operation transformer station archives, the normal user equipment archives, the access point archives, the meter box archives data and the user archives data, and the transformer station, the access point, the meter box, the electric energy meter or the user without corresponding relationship in the first archive relationship, the second archive relationship and the third archive relationship are removed. After the removal, the target archive relationship chain among the transformer station, the access point, the meter box, the electric energy meter and the user is formed, and the archive data of the transformer station, the access point, the meter box, the electric energy meter and the user is recorded on the target archive relationship chain.

[0045] In step 204, the first to-be-analyzed data is determined based on the target archive relationship chain. The first to-be-analyzed data is constituted by the archive data recorded in the target archive relationship chain.

[0046] Please refer to Figure 3 In the data processing method shown in the embodiment of the present application, the equipment operation data can include but is not limited to operation power data, collected power data, transformer station line loss data and equipment disassembly data; the collected power data includes public variable power data and low-voltage power data. The pre-processing of the equipment operation data can include:

[0047] In step 301, the power missing area, the power abnormal area and the power normal area are determined based on the running power data. In the embodiment of the present application, the running power data can be daily acquired 96 / 24 point A / B / C phase voltage / current data. After eliminating the voltage / current values exceeding the normal value range, specifically, if the 96 / 24 point voltage / current data of all users belonging to the area are all missing, it is determined that the area is a power missing area. In addition, if the missing data amount of the 96 / 24 point voltage / current data of all users belonging to the area exceeds the preset threshold, it is determined that the area is a power abnormal area. Furthermore, if the 96 / 24 point voltage / current data of all users belonging to the area are all normal, it is determined that the area is a power normal area.

[0048] Further, in the embodiment of the present application, the power missing area and the power abnormal area do not participate in subsequent data anomaly analysis, and the power missing area and the power abnormal area need to be eliminated to ensure the analysis accuracy and analysis processing efficiency of the data anomaly analysis.

[0049] In step 302, the abnormal power data and the normal power data in the power normal area are determined based on the public variable power data and the running power threshold. The running power threshold is the maximum power value of the public variable daily full load operation, and the public variable is a public transformer. Each power supply data in the public variable power data is compared with the running power threshold, the power supply data exceeding the running power threshold is determined as the abnormal power data, and the normal power data is obtained after eliminating the abnormal power data.

[0050] In step 303, the abnormal power user equipment and the normal power user equipment in the power normal area are determined based on the low-voltage power data. The low-voltage power data includes user power data, photovoltaic user on-grid power and photovoltaic user power generation power. The user equipment flying away, walking backward and power missing are marked as abnormal power user equipment, and the normal power user equipment is obtained after eliminating the abnormal power user equipment in all user equipment in the power normal area.

[0051] In step 304, the power abnormal area and the power normal area in the power normal area are determined based on the area line loss data. In the embodiment of the present application, the acquired area power supply, area power supply, area line loss rate, area loss power and other data can be checked daily, the area with abnormal or missing power data is marked as the power abnormal area, and the power normal area is obtained after eliminating the power abnormal area in the power normal area.

[0052] In step 305, the abnormal user equipment and the normal user equipment are determined in the normal power consumption user equipment based on the equipment disassembly data. In the embodiment of the present application, the user equipment with disassembly record, for example, the electric energy meter equipment, is checked daily according to the equipment replacement record, the equipment power consumption data, the equipment metering anomaly and other data according to the business rules. The user equipment not meeting the business rules is marked as the abnormal user equipment. After the abnormal user equipment is excluded from the normal power consumption user equipment, the normal user equipment is obtained.

[0053] In step 306, the second to-be-analyzed data is determined based on the normal power consumption area, the normal power consumption data and the normal user equipment. Specifically, the second to-be-analyzed data can be constituted based on the area profile data of the normal power consumption area, the normal power consumption data and the equipment profile data of the normal user equipment.

[0054] In some embodiments, when the data anomaly analysis is performed based on the first to-be-analyzed data and the second to-be-analyzed data, the data anomaly analysis on the first to-be-analyzed data can analyze the equipment with abnormal profile data, and the data anomaly analysis on the second to-be-analyzed data can analyze the equipment with abnormal running process. Figure 4 is a flowchart of the data processing method according to the embodiment of the present application. Please refer to Figure 4 The data processing method according to the embodiment of the present application can include:

[0055] In step 401, the profile abnormal equipment is determined based on the first to-be-analyzed data.

[0056] In the embodiment of the present application, the first to-be-analyzed data can be used to determine the abnormal equipment profile of the connection, the abnormal equipment profile of the meter box, the abnormal equipment profile of the transformer box, the abnormal equipment profile of the coverage and the abnormal equipment profile of the user and transformer. The abnormal equipment profile of the connection is the abnormal equipment profile of the connection between the access point profile and the meter box profile data. The abnormal equipment profile of the meter box is the abnormal equipment profile of the attribution relationship between the meter box profile data and the normal user equipment profile. The abnormal equipment profile of the transformer box is the abnormal equipment profile of the attribution relationship between the normal running area profile and the meter box profile data. The abnormal equipment profile of the coverage is the user equipment profile in which the equipment coordinates are outside the coordinate coverage range recorded in the user equipment data, and the user profile data in which the user address is outside the meter box installation address coverage range recorded in the meter box profile data. The abnormal equipment profile of the user and transformer is the abnormal equipment profile of the corresponding relationship between the normal user equipment profile and the normal running area profile.

[0057] Specifically, according to the power distribution cabinet space and the meter installation requirements, if the number of meter boxes hung under the same access point is greater than 15, it is judged that the hanging relationship between the access point profile and the meter box profile data is abnormal. If the number of user equipment in the same meter box, for example, the number of electric energy meters is greater than 48, it is judged that the ownership relationship between the meter box profile data and the normal user equipment profile is abnormal. If the meter box has no ownership electric energy meter, or if the electric energy meter has no ownership meter box, it is also judged that the ownership relationship between the meter box profile data and the normal user equipment profile is abnormal. If all the user equipment belonging to the substation have no ownership meter box, or if the meter box has no ownership substation, it is judged that the ownership relationship between the normal running substation profile and the meter box profile data is abnormal. If the same normal user equipment corresponds to multiple normal running substations in different production systems, for example, marketing system and data acquisition system, instead of being unique, it is judged that the corresponding relationship between the normal user equipment profile and the normal running substation profile is abnormal.

[0058] In the embodiments of the present application, when judging whether the device coordinates in the normal user equipment profile are outside the coordinate coverage range recorded in the user equipment data, the latitude and longitude coordinate data of the meter box and the user equipment (for example, the electric energy meter) can be obtained in the meter box profile data and the normal user equipment profile, and then a clustering algorithm is used to analyze whether all the user equipment coordinates under the substation are within the coverage range of the coordinates of the belonging meter box, to identify the user equipment profile that is not within the coverage range. When judging whether the user address in the user profile data is outside the meter box installation address coverage range recorded in the meter box profile data, the meter box installation address and the text address or address code data of the user can be obtained in the meter box profile data and the normal user equipment profile.

[0059] If the text address of the user is obtained, the text address is first structured, which can be processed by text segmentation and using Word2Vec, and then according to the structured address data of all the users belonging to each substation, a clustering algorithm is used to analyze whether all the user addresses under the substation are within the coverage range of the belonging meter box installation address, to identify the user profile that is not within the coverage range. Since the user and the user equipment are bound, identifying the user profile that is not within the coverage range can be regarded as identifying the user equipment profile that is not within the coverage range. Through the above-mentioned manner, the coverage abnormal equipment profile can be analyzed and screened in the normal user equipment profile. It can be understood that in actual application, the manner of identifying the coverage abnormal equipment profile is various, and a suitable manner needs to be selected according to the actual application situation, and the present application does not make any limitation in this aspect.

[0060] Further, each abnormal profile corresponding to the abnormal equipment profile can be determined based on the above-mentioned hanging abnormal equipment profile, box-table abnormal equipment profile, transformer-box abnormal equipment profile, coverage abnormal equipment profile and household-transformer abnormal equipment profile.

[0061] In step 402, the running abnormal equipment is determined based on the second to-be-analyzed data.

[0062] In the embodiment of the present application, whether the first running relationship exists error can be determined based on the second to-be-analyzed data, and the first running relationship is the connection relationship between the transformer area total table and the transformer area. If the first running relationship exists error, the transformer area total table is determined as the running abnormal equipment. Whether the first running relationship exists error can be analyzed by using the feature that the transformer area power selling amount and the transformer area power supply amount are positively correlated. Specifically, first, the normal running transformer area and the preliminary abnormal transformer area can be determined based on the second to-be-analyzed data, wherein the transformer areas in the second to-be-analyzed data can be clustered based on the line loss rate, because theoretically the line loss rates of the same type of transformer areas are less different; then the abnormal detection is performed on each type of transformer area based on the daily line loss rate.

[0063] If the daily line loss rate is within the preset line loss rate interval, the transformer area is determined as the normal running transformer area, otherwise the transformer area is the preliminary abnormal transformer area. Then the target abnormal transformer area is determined according to the preliminary abnormal transformer area, the power supply and power selling amount coefficient minimum value, and the transformer area power supply and power selling amount coefficient. The power supply and power selling amount coefficient minimum value is the minimum value of the transformer area corresponding power supply and power selling amount correlation coefficient, wherein if the transformer area power supply and power selling amount coefficient of the current preliminary abnormal transformer area is greater than or equal to the transformer area power supply and power selling amount coefficient, the current preliminary abnormal transformer area is determined as the normal running transformer area, then after the normal running transformer area is further screened out from the preliminary abnormal transformer area, the target abnormal transformer area can be determined. Then the correlation analysis is performed on the power supply and power selling amount of the target abnormal transformer area, if strong correlation is presented, that is, the transformer area power supply and power selling amount coefficient of the target abnormal transformer area is greater than the transformer area power supply and power selling amount coefficient, and the transformer area line loss rate of the target abnormal transformer area is within the preset line loss rate interval, it is determined that the transformer area total table connection error of the current target abnormal transformer area exists, that is, the first running relationship exists error.

[0064] In addition, whether the second running relationship exists error can be determined based on the second to-be-analyzed data, and the second running relationship is the ownership relationship between the user equipment and the transformer area. If the second running relationship exists error, the current user equipment is determined as the running abnormal equipment. Whether the second running relationship exists error can be analyzed by using the feature that the user power amount and the transformer area line loss rate are negatively correlated. Specifically, first, if the transformer area power supply and power selling amount coefficient of the target abnormal transformer area is greater than the power supply and power selling amount coefficient minimum value, and the transformer area line loss rate of the target abnormal transformer area is less than the line loss rate interval minimum value of the preset line loss rate interval, it is determined that the current target abnormal transformer area exists the candidate user equipment with ownership relationship abnormality.

[0065] Afterwards, a target abnormal user equipment in the candidate user equipments can be determined based on the candidate user equipment, the user electricity quantity-line loss relationship, the line loss rate adjustment value and the user power failure event time. The user electricity quantity-line loss relationship is the relationship between the user electricity quantity and the line loss rate of the transformer area, and the line loss rate adjustment value is the line loss rate calculated after excluding the user electricity quantity corresponding to the minimum line loss rate in the target abnormal transformer area. If the user electricity quantity-line loss relationship is a strong negative relationship, the line loss rate adjustment value changes greatly relative to the original line loss rate of the target abnormal transformer area, and the user power failure event time of the current user equipment is inconsistent with the power failure time of other user equipments, the current user equipment is determined as the target abnormal user equipment, and the ownership relationship between the current user equipment and the transformer area is abnormal. The target abnormal user equipment is determined as the running abnormal equipment.

[0066] Further, after determining that the current user equipment is the running abnormal equipment, it is judged whether the transformer area electricity supply and sale quantity coefficient of the target abnormal transformer area is greater than the electricity supply and sale quantity coefficient minimum value, and the line loss rate of the target abnormal transformer area is greater than the line loss rate interval maximum value of the preset line loss rate interval. If yes, the current target abnormal transformer area is determined as a high-loss transformer area. Then, the high-loss transformer area line loss rate of the high-loss transformer area is determined based on the electricity quantity value of the target abnormal user equipment, that is, the electricity quantity value of the running abnormal equipment is calculated into the high-loss transformer area, and the high-loss transformer area line loss rate of the high-loss transformer area is recalculated. Then, if the high-loss transformer area line loss rate is within the preset line loss rate interval, and the power failure time of the target abnormal user equipment is consistent with that of the high-loss transformer area, it is determined that the target abnormal user equipment belongs to the high-loss transformer area.

[0067] It can be understood that in actual application, the way of judging whether the second running relationship is wrong based on the second to-be-analyzed data is various, for example, based on an electricity balance model, for example, through line loss correlation analysis, for example, based on a power-on and power-off analysis model, for example, based on a multi-element data fusion analysis model, for example, based on a voltage correlation model, and the like. The appropriate analysis method needs to be determined according to the actual application, which can be multiple analysis methods at the same time, or one of the analysis methods can be selected for judgment. The present application does not make any limitation in this aspect.

[0068] The power balance model can exemplarily adopt a multiple linear regression algorithm. The power of all user devices (e.g., power meters) in the two transformer areas are taken as independent variables of the regression equation, and the power of the two transformer area total meters are taken as dependent variables to make linear regression respectively. If the power of a user device belongs to a transformer area total meter, the regression coefficient of the user device will be close to 1, and the t-statistic of the user device will be relatively large. If the power of a user device does not belong to a transformer area total meter, the regression coefficient of the user device will be close to 0, and the t-statistic of the user device will be relatively small. By comparing the results of the two regression calculations, the membership of each user device can be determined, so as to determine whether the ownership relationship between the user device and the transformer area is abnormal. The t-statistic is a confidence interval of a certain confidence level of the mean value under the condition that the population variance is unknown.

[0069] In the above analysis process through line loss correlation, exemplarily, when the user device does not belong to the current transformer area, how much the user device measures the power consumption increases kW·h, and how much the transformer line loss decreases kW·h at the same time, showing a high negative correlation characteristic. In actual application, branch user devices can be introduced, and the power of the branch user devices is merged for correlation analysis. Since the power value increases after merging, the disadvantage of small power consumption of a single user being difficult to identify is overcome, and the analysis calculation efficiency and effect are improved.

[0070] The above power-on / off analysis model can exemplarily determine whether the second operation relationship is incorrect according to the corresponding relationship between different production systems, such as the marketing system and the data acquisition system. Specifically, in the case of transformer area power-off, the user device, i.e., the power meter, can be used to determine whether the second operation relationship is abnormal by transparent copying (copying the power value, clock, etc.). Because if the transformer area is powered off, the power meter will not have a reading, and if there is a reading, it can be determined that the second operation relationship is abnormal. In the case of transformer area power-on, the power-off duration of the transformer area total meter and the power meter under the transformer area, and the deviation time of the power-off / on event can be calculated and compared. If the power-off duration deviation is greater than 5 minutes, and the power-off time and power-on time deviation of the total meter and the power meter are both greater than 5 minutes, it is determined that the second operation relationship is abnormal.

[0071] On the contrary, if the power-off duration deviation is less than 5 minutes, and the power-off / on deviation time is also less than 5 minutes, it can be determined that the second operation relationship is normal. In addition, the transformer area association check can be performed based on the power meter with suspected abnormal second operation relationship, the historical power-off / on events of the acquisition terminal of the adjacent transformer area are queried for association check comparison. If the power-off / on event of the suspected abnormal power meter deviates within 5 minutes from the historical power-off / on event of a certain adjacent transformer area, and the associated transformer area is unique, it is determined that the suspected abnormal power meter belongs to the adjacent transformer area.

[0072] The multi-element data fusion analysis model can be used to analyze the archive data, the collected power data, the HPLC data, etc. to determine the accuracy of the relationship between the transformer area, the metering box and the user equipment. Specifically, by analyzing the collected data of the transformer area with the second normal operation relationship, the abnormal conditions such as voltage surge and temporary drop are excluded. The difference between the maximum voltage and the minimum voltage of the user equipment in the similar metering box or the same metering box at the same time should be less than 1.5V. If the difference is greater than 1.5V for 10 consecutive days, it can be determined that the relationship between the metering box and the user equipment is suspected to be abnormal. Further, if the distance between the electric energy meter or the metering box and the distribution transformer in the transformer area is greater than the first specified distance (500m in the city and 1km in the countryside), and the distance between the electric energy meter or the metering box and the distribution transformer in the adjacent transformer area is less than the second specified distance (300m in the city and 800m in the countryside), it is determined that the relationship between the transformer area, the metering box and the user equipment is suspected to be abnormal, and it is further determined that the second operation relationship is suspected to be abnormal. Further, according to the list of the second operation relationship suspected to be abnormal, the negative loss transformer area (the transformer area with a daily loss of less than or equal to -3kW·h for more than 3 days) determined by the data collection system is obtained, and the associated transformer area of the negative loss transformer area in the marketing system is obtained. If the total meter of the negative loss transformer area does not have voltage drop (the voltage is lower than the rated voltage*85%), and the power of the user equipment with the second operation relationship suspected to be abnormal is less than the absolute value of the loss of the associated transformer area, it is determined that the user equipment with the second operation relationship suspected to be abnormal belongs to the associated transformer area.

[0073] The voltage correlation model can be used to determine whether the electric energy meters of the same phase belong to the same metering box by comparing the correlation of the voltage curves of the same phase. Because the voltage curves of the electric energy meters of the same phase in the same metering box are very close and basically coincide, the difference between the voltage curves of the electric energy meters not in the same metering box is more obvious. Specifically, the Pearson correlation analysis technology can be used to calculate the correlation coefficient of the voltage curves of all the electric energy meters of the same phase in the transformer area. The higher the correlation coefficient is, the higher the correlation is. If the correlation coefficient of the electric energy meter in other metering boxes is higher than that in the current metering box, it is considered that the electric energy meter may have abnormal metering box relationship. The same principle can also be used for the second operation relationship analysis. In practical application, branch user equipment can be introduced to reduce the data frequency requirement of the voltage correlation analysis to a very low level, greatly reduce the analysis range of the voltage correlation analysis, and significantly improve the effectiveness of the analysis result, which is more conducive to finding abnormal user equipment.

[0074] In step 403, the abnormal device list is determined based on the archive abnormal device and the running abnormal device. The archive abnormal device and the running abnormal device are combined and summarized to form the abnormal device list.

[0075] Corresponding to the foregoing application function implementation method embodiments, the present application also provides an electronic device for executing a data processing method and corresponding embodiments.

[0076] Figure 5 A block diagram showing a hardware configuration of an electronic device 500 that can implement the data processing method of the embodiments of the present application is shown. As shown in the figure, Figure 5 The electronic device 500 can include a processor 510 and a memory 520. In the electronic device 500, Figure 5 In the electronic device 500, only the constituent elements related to the present embodiments are shown. Therefore, it is obvious to those skilled in the art that the electronic device 500 can also include common constituent elements different from those shown in the figure. For example, a fixed-point operator. Figure 5

[0077] The electronic device 500 can correspond to a computing device having various processing functions, for example, functions for generating a neural network, training or learning a neural network, quantizing a floating-point neural network into a fixed-point neural network, or retraining a neural network. For example, the electronic device 500 can be implemented as various types of devices, such as a personal computer (PC), a server device, a mobile device, etc.

[0078] The processor 510 controls all functions of the electronic device 500. For example, the processor 510 controls all functions of the electronic device 500 by executing a program stored in the memory 520 on the electronic device 500. The processor 510 can be implemented by a central processing unit (CPU), a graphics processing unit (GPU), an application processor (AP), an artificial intelligence processor chip (IPU), etc. provided in the electronic device 500. However, the present application is not limited thereto.

[0079] ​In some embodiments, the processor 510 can include an input / output (I / O) unit 511 and a computing unit 512. The I / O unit 511 can be configured to receive various data, such as device profile data. Illustratively, the computing unit 512 can be configured to preprocess device profile data and device operation data in the device profile data and the device operation data received via the I / O unit 511, respectively, perform data anomaly analysis based on the obtained first data to be analyzed and second data to be analyzed, respectively, determine an abnormal device in an abnormal device list obtained from the analysis for each abnormal device, respectively, determine an abnormal processing strategy corresponding to each abnormal device, respectively, and form a data governance work order corresponding to each abnormal device, respectively, according to the abnormal processing strategy corresponding to each abnormal device, respectively. The data governance work order can be output by the I / O unit 511, for example. The output data can be provided to the memory 520 for reading and use by other devices (not shown) or directly provided to other devices for use.

[0080] The memory 520 is hardware for storing various data processed in the electronic device 500. For example, the memory 520 can store processed data and data to be processed in the electronic device 500. The memory 520 can store data related to a data processing method processed or to be processed by the processor 510, such as device profile data, etc. In addition, the memory 520 can store applications, drivers, etc. to be driven by the electronic device 500. For example, the memory 520 can store various programs related to a data processing method to be executed by the processor 510. The memory 520 can be a DRAM, but the present application is not limited thereto. The memory 520 can include at least one of a volatile memory or a non-volatile memory. The non-volatile memory can include a read only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, a phase change RAM (PRAM), a magnetic RAM (MRAM), a resistive RAM (RRAM), a ferroelectric RAM (FRAM), etc. The volatile memory can include a dynamic RAM (DRAM), a static RAM (SRAM), a synchronous DRAM (SDRAM), a PRAM, an MRAM, an RRAM, a ferroelectric RAM (FeRAM), etc. In an embodiment, the memory 520 can include at least one of a hard disk drive (HDD), a solid state drive (SSD), a compact flash (CF), a secure digital (SD) card, a micro secure digital (Micro-SD) card, a mini secure digital (Mini-SD) card, an extreme digital (xD) card, a cache, or a memory stick.

[0081] In summary, the specific functions of the memory 520 and the processor 510 of the electronic device 500 provided by the embodiments of the present disclosure can be explained in contrast to the foregoing embodiments of the present disclosure and can achieve the technical effects of the foregoing embodiments of the present disclosure, and thus repeated descriptions thereof will be omitted herein.

[0082] In the present embodiment, the processor 510 can be implemented in any appropriate manner. For example, the processor 510 can take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, etc.

[0083] It should be understood that the possible terms "first" or "second" or the like in the claims, the specification, and the drawings of the present disclosure are used to distinguish different objects, rather than to describe a particular order. The terms "include" and "comprise" used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or sets thereof.

[0084] It should also be understood that the terms used in the present disclosure specification herein are only for the purpose of describing specific embodiments, and are not intended to limit the present disclosure. As used in the present disclosure specification and claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms. It should be further understood that the term "and / or" used in the present disclosure specification and claims means any combination of one or more of the associated listed terms and all possible combinations thereof, and includes these combinations.

[0085] It should also be understood that any module, unit, component, server, computer, terminal or device exemplifying an execution instruction herein can include or otherwise access a computer readable medium, such as a storage medium, a computer storage medium or a data storage device (removable and / or non-removable), for example, a magnetic disk, an optical disk or a magnetic tape. The computer storage medium can include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer readable instructions, data structures, program modules or other data.

[0086] Although the embodiments of the present application are as above, the content is only for the convenience of understanding the application and is not used to limit the scope and application scenarios of the application. Any person skilled in the art described in the application can make any modification and change in the form and details without departing from the spirit and scope of the application disclosed by the application, but the patent protection scope of the application shall be subject to the scope defined by the appended claims.

Claims

1. A data processing method, characterized in that, include: Obtain equipment overview data, which includes equipment file data and equipment operation data; the equipment file data includes transformer area file data, user equipment data, access point file data, meter box file data, user file data, and file relationship data; The equipment operation data includes operating power data, collected power data, transformer area line loss data, and equipment disassembly and assembly data. The collected power data includes power data from public transformers and power data from low-voltage systems. The equipment file data and the equipment operation data are preprocessed respectively to obtain the first data to be analyzed and the second data to be analyzed. The preprocessing of the equipment file data includes: determining vacant transformer area files, newly added transformer area files, out-of-service transformer area files, and normally operating transformer area files based on the transformer area file data; and determining abnormal user equipment files and normal user equipment files among the normally operating transformer area files based on the user equipment data. The preprocessing of the equipment operation data includes: determining power outage areas, power abnormality areas, and power normal areas based on the operation power data; Based on the first data to be analyzed and the second data to be analyzed, a data anomaly analysis is performed to obtain a list of abnormal devices; The data anomaly analysis based on the first data to be analyzed and the second data to be analyzed includes: Based on the first data to be analyzed, identify the abnormal equipment in the archive; Based on the second set of data to be analyzed, identify the malfunctioning devices; The list of abnormal devices is determined based on the abnormal files and the abnormal operating devices. The step of determining the malfunctioning equipment based on the second data to be analyzed includes: Based on the second data to be analyzed, determine whether there is an error in the first operational relationship; the first operational relationship is the connection between the transformer area master table and the transformer area; If there is an error in the first operation relationship, then the transformer area master table is determined to be an abnormal operating device; Based on the second data to be analyzed, determine whether there is an error in the second operational relationship; the second operational relationship is the attribution relationship between user equipment and distribution area. If there is an error in the second running relationship, the current user equipment is determined to be a device with abnormal operation; The step of determining whether there is an error in the first operational relationship based on the second data to be analyzed includes: Based on the second set of data to be analyzed, determine the normally operating transformer areas and the preliminary abnormal transformer areas; The target abnormal distribution area is determined based on the preliminary abnormal distribution area, the minimum value of the power supply and sales coefficient, and the power supply and sales coefficient of the distribution area; the minimum value of the power supply and sales coefficient is the minimum value of the power supply and sales coefficient corresponding to the distribution area. If the power supply coefficient of the target abnormal transformer area is greater than the minimum value of the power supply coefficient, and the line loss rate of the target abnormal transformer area is within the preset line loss rate range, then it is determined that the transformer master meter of the current target abnormal transformer area is incorrectly connected. The step of determining whether there is an error in the second operational relationship based on the second data to be analyzed includes: If the power supply coefficient of the target abnormal transformer area is greater than the minimum value of the power supply coefficient, and the line loss rate of the target abnormal transformer area is less than the minimum value of the line loss rate range of the preset line loss rate range, then it is determined that there are candidate user equipment with abnormal affiliation in the current target abnormal transformer area. The target abnormal user equipment is determined based on the candidate user equipment, the user power consumption line loss relationship, the line loss rate adjustment value, and the user power outage event time; wherein, the user power consumption line loss relationship is the relationship between the user power consumption and the line loss rate of the transformer area, and the line loss rate adjustment value is the line loss rate calculated after removing the power consumption of each user on the date corresponding to the minimum line loss rate in the target abnormal transformer area; Determine the corresponding exception handling strategy for each exception device based on each exception device in the exception device list. Based on the specific exception handling strategy for each malfunctioning device, a data governance work order is generated for each malfunctioning device.

2. The data processing method according to claim 1, characterized in that, The preprocessing of the equipment file data and the equipment operation data, respectively, further includes: Based on the normal operating area files, normal user equipment files, access point files, meter box files, and user file data, the file relationship data is verified to obtain the target file relationship chain; The first data to be analyzed is determined based on the target file relationship chain.

3. The data processing method according to claim 2, characterized in that, The preprocessing of the equipment file data and the equipment operation data, respectively, further includes the following: Based on the power consumption data of the public transformer and the operating power consumption threshold, abnormal power consumption data and normal power consumption data in the normal power distribution area are determined; the operating power consumption threshold is the maximum power consumption value for full-load operation each day. Based on the low-voltage power data, abnormal power user equipment and normal power user equipment in the normal power distribution area are determined. The low-voltage power data includes user power data, photovoltaic user grid-connected power, and photovoltaic user power generation. Based on the line loss data of the distribution area, the distribution areas with abnormal power consumption and the distribution areas with normal power consumption are identified in the distribution areas with normal power consumption. Based on the device disassembly and assembly data, abnormal user equipment and normal user equipment are identified among the normal power user equipment. The second data to be analyzed is determined based on the normal power supply area, the normal power supply data, and the normal user equipment.

4. The data processing method according to claim 1, characterized in that, The device for identifying abnormal files based on the first data to be analyzed includes: Based on the first data to be analyzed, determine the files of abnormal connected equipment, abnormal meter equipment, abnormal transformer equipment, abnormal coverage equipment, and abnormal household transformer equipment. The abnormal device files are defined as follows: The abnormal device files are those where the connection between the access point file and the meter box file data is abnormal; the abnormal meter box file is those where the attribution relationship between the meter box file data and the normal user equipment file is abnormal; the abnormal transformer box file is those where the attribution relationship between the normally operating transformer area file and the meter box file data is abnormal; the abnormal coverage device files are those where the device coordinates in the normal user equipment file are outside the coverage area of ​​the coordinates recorded in the user equipment data, and those where the user address in the user file data is outside the coverage area of ​​the meter box installation address recorded in the meter box file data; the abnormal transformer household file is those where the correspondence between the normal user equipment file and the normally operating transformer area file is abnormal. The abnormal device in the file is determined based on the abnormal device file for the connection, the abnormal device file for the meter box, the abnormal device file for the transformer box, the abnormal device file for the coverage, and the abnormal device file for the household transformer.

5. The data processing method according to claim 1, characterized in that, After determining that the current user equipment is a malfunctioning device, the data processing method further includes: If the power supply coefficient of the target abnormal transformer area is greater than the minimum value of the power supply coefficient, and the line loss rate of the target abnormal transformer area is greater than the maximum value of the line loss rate range of the preset line loss rate range, then the current target abnormal transformer area is determined to be a high-loss transformer area. The line loss rate of the high-loss distribution area is determined based on the power value of the target abnormal user equipment. If the line loss rate of the high-loss distribution area is within the preset line loss rate range, and the power outage time of the target abnormal user equipment is the same as that of the high-loss distribution area, then the target abnormal user equipment is determined to belong to the high-loss distribution area.

6. An electronic device, characterized in that, include: processor; as well as A memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method as described in any one of claims 1-5.

7. A non-transitory machine-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method as described in any one of claims 1-5.

Images