Marketing compliance intelligent analysis method based on data mining
By adopting a marketing compliance intelligent analysis method based on data mining in the power grid system, the omissions and violations caused by the experience dependence of inspectors in the existing technology are solved, and more efficient and compliant power abnormality handling is achieved.
Patent Information
- Application Number
- CN202411616133.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-13
- Publication Date
- 2025-03-04
AI Technical Summary
The existing power grid system relies on the auditor's experience and on-site inspections when inspecting abnormalities, resulting in many omissions and violations, making it difficult to effectively detect and deal with power abnormalities.
Using a marketing compliance intelligent analysis method based on data mining, we guide the inspector to perform exception handling by obtaining electrical metering data, inputting an audit recognition model to determine the exception type, generating an exception handling instruction and sending it to the inspector through interactive devices.
It improves the compliance and efficiency of the audit work, reduces violations, and ensures the accuracy and consistency of exception handling, forming a closed loop of work from identifying grid abnormalities to completing audits.
Smart Images
Figure CN119557803A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of power grid systems, and in particular to a marketing compliance intelligent analysis method based on data mining. Background Art
[0002] Nowadays, smart meters have completely replaced traditional meters, and they can regularly send metering data to the power grid system. The power grid system processes the data uploaded by smart meters in a centralized manner in the background, and the power grid system automatically calculates electricity charges and detects anomalies.
[0003] Under the wave of artificial intelligence development, power grid systems are gradually connected to pre-trained neural network models for data analysis and automatic early warning.
[0004] At present, my country's power grid system has gradually completed the digital construction. The digital system background of the distribution network can monitor the operation of the power grid in real time and issue an alarm when an abnormality occurs.
[0005] In the digital system of the distribution network, electric energy meters are installed on one side of the substation and one side of the household line within a substation area (i.e., the power supply range of a transformer), and the metering data of the electric energy meter is sent to the communication terminal in the substation area. The communication terminal uploads the summarized data to the background server.
[0006] In daily power grid inspections, the power grid system background sends alarm information to the inspection team of the corresponding substation after monitoring abnormal power, abnormal load, terminal alarm, main station alarm and abnormal line loss. The inspection team fills out a work order based on the alarm information, sends the work order to the inspector for execution, and then uploads the completed work order back to the power grid system.
[0007] At present, both algorithms based on traditional indicators and intelligent algorithms based on deep learning models can only detect abnormalities in a certain area, and the actual abnormal results depend on on-site inspections by auditors.
[0008] During the audit and inspection work, auditors rely on their own experience and ability to locate abnormal points, and conduct verification, evidence collection, and work order filling. The work quality of auditors varies greatly, and it is inevitable that there will be many omissions and violations in the current audit work.
[0009] Therefore, in order to reduce illegal operations during audit and law enforcement, an embodiment of the present application provides a marketing compliance intelligent analysis method based on data mining. Summary of the invention
[0010] In order to overcome the problems existing in the related art, the present application provides a marketing compliance intelligent analysis method based on data mining, which is characterized by comprising:
[0011] S1. Obtaining electricity metering data of the abnormal area; the electricity metering data includes voltage value, current value, power value and power factor value in a continuous period;
[0012] S2, inputting the electricity metering data into an audit identification model, and determining the power anomaly type of the abnormal area according to the audit identification model;
[0013] S3. Determine an abnormality handling instruction according to the power abnormality type; the abnormality handling instruction is sent to the auditor through the interactive device;
[0014] S4. Obtaining the audit and inspection information fed back by the interactive device;
[0015] S5. Input the audit and inspection information into the marketing compliance system, and generate the next abnormal processing instruction according to the marketing compliance system.
[0016] In one embodiment, before S1, the method further includes:
[0017] S101, obtaining an electricity metering data set;
[0018] S102, dividing the electricity metering data set into a training set and a validation set;
[0019] S103: construct an audit recognition model, and perform model training using the electricity metering data set.
[0020] In one embodiment, before S2, the method further includes:
[0021] S200, judging whether the power fault type is a line loss abnormality fault, if so, determining the line loss abnormality type; if not, executing step S3.
[0022] In one implementation, determining the abnormal line loss type specifically includes:
[0023] S201, obtaining periodic line loss data and periodic light data of abnormal substations;
[0024] S202, determining a line loss timing curve and an illumination timing curve according to the periodic line loss data and the periodic illumination data respectively;
[0025] S203, determining a line loss-illumination correlation according to the line loss timing curve and the illumination timing curve;
[0026] S204, determining whether the line loss illumination correlation is greater than a preset threshold, if not, executing step S3; if yes, terminating the work order generation.
[0027] In one implementation, S203 specifically includes:
[0028] The calculation formula of line loss and illumination correlation is:
[0029]
[0030] Among them, S is the line loss care correlation, x t represents the line loss value at time t, Indicates the average line loss within a period, y t represents the light intensity at time t, Indicates the average light intensity within a period.
[0031] In one embodiment, the exception handling instruction is sent to the auditor via an interactive device.
[0032] The technical solution provided by this application may have the following beneficial effects:
[0033] The marketing compliance system of the present application can extract information from the work order during the on-site audit, and retrieve the exception handling instructions based on the information in the work order, and provide guidance to the auditors based on the exception handling instructions to prevent the occurrence of illegal audit behaviors due to the auditors' insufficient business level. The embodiment of the present application uses the marketing compliance system to identify each step of the auditor's operation when performing the audit task, ensuring that the auditor's behavior is legal and compliant, and forming a closed work loop from identifying power grid anomalies, performing audits to completing audits.
[0034] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] The above and other objects, features and advantages of the present application will become more apparent through a more detailed description of exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.
[0036] Figure 1 This is a flow chart of the marketing compliance intelligent analysis method shown in Example 1;
[0037] Figure 2 This is a schematic diagram of the sub-step flow of the marketing compliance intelligent analysis method shown in Example 2. DETAILED DESCRIPTION
[0038] The preferred embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.
[0039] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.
[0040] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.
[0041] Embodiment 1
[0042] In order to reduce illegal operations during audit and law enforcement, the embodiment of the present application provides a marketing compliance intelligent analysis method based on data mining, which can provide scenario-based guidance for audit work through interactive devices.
[0043] like Figure 1 As shown, the marketing compliance intelligent analysis method shown in the embodiment of the present application includes the following steps:
[0044] S1. Obtaining electricity metering data of abnormal areas;
[0045] Specifically, the electricity metering data includes voltage value, current value, power value and power factor value in a continuous cycle.
[0046] Specifically, after the digital power system identifies an abnormal substation, the marketing compliance intelligent analysis system obtains the electricity metering data of the abnormal substation.
[0047] In an embodiment of the present application, the marketing compliance system is loaded with executable code based on the marketing compliance intelligent analysis method.
[0048] It is understandable that the marketing compliance system described in the embodiment of the present application is connected to the digital power system. The digital power system includes the SG186 system in the State Grid, the electricity information collection system and the automatic metering system.
[0049] S2, inputting the electricity metering data into an audit identification model, and determining the power anomaly type of the abnormal area according to the audit identification model;
[0050] In the embodiment of the present application, the audit recognition model is trained with the electricity metering data of abnormal substations as a data set, and the trained audit recognition model can identify the type of power anomaly based on the electricity metering data of each substation. The power anomaly type includes metering device failure, circuit failure, and line loss abnormality failure.
[0051] The metering device failure refers to the inability of the smart meter to read data such as voltage and current on the line, or a communication failure of the smart meter. The circuit failure refers to open circuit or short circuit, and the line loss abnormality refers to the line loss exceeding the normal threshold.
[0052] S3, determining an abnormality handling instruction according to the power abnormality type;
[0053] Specifically, in the marketing compliance system, the database stores an exception handling strategy corresponding to each power anomaly type, and each exception handling strategy includes an exception handling instruction of multiple steps.
[0054] Specifically, the abnormal handling instruction is sent to the auditor via an interactive device, which may be a mobile communication device or a portable terminal.
[0055] In an embodiment of the present application, when an auditor receives an on-site audit task, he or she needs to conduct the audit according to the exception handling instructions, upload the audit results through an interactive device, and gradually review the auditor's operations through the marketing compliance system.
[0056] S4. Obtaining the audit and inspection information fed back by the interactive device;
[0057] Specifically, the auditor needs to upload the processing results corresponding to each exception processing instruction through the interactive device.
[0058] For example, if the current exception handling instruction is "check the model and number of the new electricity meter", the auditor needs to take photos of the models and numbers of the two electricity meters and upload them.
[0059] S5. Input the audit and inspection information into the marketing compliance system, and generate the next abnormality handling instruction according to the marketing compliance system;
[0060] Exemplarily, if the power anomaly type is a metering device failure, the anomaly handling instruction includes the following steps:
[0061] Check whether the on-site work order information is correct;
[0062] Check whether the work team information is correct based on the work order information;
[0063] Check the current and voltage readings of the old energy meter;
[0064] Check whether the transformer of the old electric energy meter is damaged;
[0065] Check the model and serial number of the new electricity meter;
[0066] Replace the electricity meter on site in accordance with operating regulations.
[0067] Furthermore, at the end of the audit, the auditor needs to perform the following steps through the interactive device:
[0068] Update work orders based on audit and inspection information;
[0069] Print out the completed work sheet and have the householder sign for confirmation.
[0070] Specifically, when checking the model and number of the electricity metering device, OCR is performed in the marketing compliance system to identify the text information of the model and number in the photo uploaded on site, and the text information is checked with the text information registered in the work order. After the verification is correct, the next step of exception handling instructions is pushed.
[0071] In an embodiment of the present application, in order to improve the compliance rate of on-site power audits, the marketing compliance system can generate corresponding exception handling instructions based on the type of power anomalies, and then provide guidance to auditors based on the exception handling instructions to prevent illegal audits caused by insufficient professional skills of auditors.
[0072] The embodiment of the present application uses a marketing compliance system to identify each step of the auditor's operation when performing an audit task, ensuring that the auditor's behavior is legal and compliant, forming a closed work loop from identifying power grid anomalies, performing audits to completing audits.
[0073] Furthermore, before step S1, it is necessary to construct and train an audit recognition model. Specifically, the training of the audit recognition model includes:
[0074] S101, obtaining an electricity metering data set;
[0075] S102, dividing the electricity metering data set into a training set and a validation set;
[0076] S103: construct an audit recognition model, and perform model training using the electricity metering data set.
[0077] Embodiment 2
[0078] In actual audit work, the marketing compliance system usually determines whether the data uploaded by the electricity metering device is within the normal threshold range. If not, an alarm is issued and a work order is automatically generated.
[0079] For example, when the power grid system background detects that the line loss data of a certain substation is greater than 10%, it will send a line inspection work order to the power supply station to which the substation belongs. After receiving the inspection work order, the power supply station will assign offline inspection tasks to the inspector.
[0080] However, in recent years, the number of household photovoltaic power stations connected to low-voltage power grids has increased. After the photovoltaic power station is connected to the grid, the line loss in the power grid will fluctuate suddenly. The power grid inspection system background will identify the line loss fluctuation as abnormal and generate an inspection work order.
[0081] At present, the judgment method based on indicator weighting in the background of the power grid system cannot effectively identify normal line loss fluctuations and line loss fluctuations caused by electricity theft, resulting in a large backlog of abnormal line loss work orders at the power supply station.
[0082] Therefore, in order to reduce the audit pressure on power supply stations, the embodiment of the present application also provides a marketing compliance intelligent analysis method based on data mining, which can identify abnormal line loss work orders and screen out line loss anomalies with electricity theft characteristics.
[0083] The marketing compliance intelligent analysis method shown in the embodiment of the present application includes the following steps:
[0084] S1. Obtaining electricity metering data of abnormal areas;
[0085] S2, inputting the electricity metering data into an audit identification model, and determining the power anomaly type of the abnormal area according to the audit identification model;
[0086] S3. Determine an abnormality handling instruction according to the power abnormality type; the abnormality handling instruction is sent to the auditor through the interactive device;
[0087] S4. Obtaining the audit and inspection information fed back by the interactive device;
[0088] S5. Input the audit and inspection information into the marketing compliance system, and generate the next abnormal processing instruction according to the marketing compliance system.
[0089] When the marketing audit system receives an abnormal line loss fault alarm, it needs to further determine the type of abnormal line loss.
[0090] Further, such as Figure 2 As shown, before step S2, the following steps are also included:
[0091] S200, determining whether the power fault type is a line loss abnormality fault, if so, executing steps S201 to S205, if not, executing step S3.
[0092] S201, obtaining periodic line loss data and periodic light data of abnormal substations;
[0093] Specifically, the periodic line loss data refers to the line loss data of the abnormal substation from the preset deadline to the line loss abnormal day.
[0094] For example, if the preset period is one month, and the abnormal line loss day for the substation determined by the power grid system background is October 4, then the periodic line loss data is the line loss data from September 4 to October 4.
[0095] Specifically, the periodic light data is the sunshine intensity in the area where the abnormal station area is located.
[0096] S202: Determine a line loss timing curve and an illumination timing curve according to the periodic line loss data and the periodic illumination data respectively.
[0097] Specifically, the line loss time series curve represents the change of line loss in the abnormal area over time, and the light intensity time series curve represents the change of light intensity in the abnormal area over time.
[0098] In the embodiment of the present application, the horizontal axis granularity of the line loss timing curve is 1 hour.
[0099] When there is sufficient sunlight, the photovoltaic power generation increases. For users with high power consumption, the load of this phase will become lower, causing imbalance between other phases and increasing line losses. When there is insufficient sunlight, the photovoltaic power generation decreases and the three-phase balance returns to normal.
[0100] S203, determining a line loss-illumination correlation according to the line loss timing curve and the illumination timing curve;
[0101] Specifically, the calculation formula for line loss illumination correlation is:
[0102]
[0103] Where S is the line loss concern correlation, and the value of S is [-1,1]. t represents the line loss value at time t, Indicates the average line loss within a period, y t represents the light intensity at time t, Indicates the average light intensity within a period.
[0104] S204, judging whether the line loss illumination correlation is greater than a preset threshold, if not, executing step S3; if yes, terminating the work order generation.
[0105] In the embodiment of the present application, the line loss abnormality type includes non-photovoltaic line loss abnormality and photovoltaic line loss abnormality. If the line loss illumination correlation is greater than the preset threshold, it means that the current line loss abnormality is caused by photovoltaic power generation in the abnormal area, and there is no need to conduct an inspection of the distribution network. If the line loss illumination correlation is less than or equal to the preset threshold, it means that the current line loss abnormality is other power abnormality types, and the work order is generated normally.
[0106] The scheme of the present application has been described in detail above with reference to the accompanying drawings. In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. Those skilled in the art should also be aware that the actions and modules involved in the description are not necessarily required for the present application.
[0107] In addition, it can be understood that the steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the modules in the device of the embodiment of the present application can be combined, divided and deleted according to actual needs.
[0108] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.
[0109] Alternatively, the present application can also be implemented as a non-temporary machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) on which executable code (or computer program, or computer instruction code) is stored. When the executable code (or computer program, or computer instruction code) is executed by a processor of an electronic device (or electronic device, server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.
[0110] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the application herein may be implemented as electronic hardware, computer software, or combinations of both.
[0111] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system and method according to multiple embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0112] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.
Claims
1. A marketing compliance intelligent analysis method based on data mining, characterized in that: include: S1. Obtaining electricity metering data of abnormal areas; The electrical metering data includes voltage value, current value, power value and power factor value in a continuous period; S2, inputting the electricity metering data into an audit identification model, and determining the power anomaly type of the abnormal area according to the audit identification model; S3, determining an abnormality handling instruction according to the power abnormality type; S4. Obtaining the audit and inspection information fed back by the interactive device; S5. Input the audit and inspection information into the marketing compliance system, and generate the next abnormal processing instruction according to the marketing compliance system.
2. According to claim 1, a marketing compliance intelligent analysis method based on data mining is characterized in that: Before S1, it also included: S101, obtaining an electricity metering data set; S102, dividing the electricity metering data set into a training set and a validation set; S103: construct an audit recognition model, and perform model training using the electricity metering data set.
3. The marketing compliance intelligent analysis method based on data mining according to claim 1 is characterized in that: Prior to S2, it also included: S200, judging whether the power fault type is a line loss abnormality fault, if so, determining the line loss abnormality type; if not, executing step S3.
4. The marketing compliance intelligent analysis method based on data mining according to claim 3 is characterized in that: The determining of the abnormal line loss type specifically includes: S201, obtaining periodic line loss data and periodic light data of abnormal substations; S202, determining a line loss timing curve and an illumination timing curve according to the periodic line loss data and the periodic illumination data respectively; S203, determining a line loss-illumination correlation according to the line loss timing curve and the illumination timing curve; S204, determining whether the line loss illumination correlation is greater than a preset threshold, if not, executing step S3; if yes, terminating the work order generation.
5. The marketing compliance intelligent analysis method based on data mining according to claim 1 is characterized in that: S203 specifically includes: The calculation formula of line loss and illumination correlation is: Among them, S is the line loss care correlation, x t represents the line loss value at time t, Indicates the average line loss within a period, y t represents the light intensity at time t, Indicates the average light intensity within a period.
6. The marketing compliance intelligent analysis method based on data mining according to claim 1 is characterized in that: The exception handling instruction is sent to the auditor via the interactive device.