Marketing and distribution data exception checking method and system based on big data analysis

Abstract

The invention discloses a marketing and distribution data exception checking method and system based on big data analysis. The method comprises the following steps: establishing butt joint with various data sources through a DataWorks platform, executing a power grid graphic data acquisition task according to a predefined time interval, performing format conversion and exception processing on data, and forming a data acquisition log; a multi-level checking rule is defined, abnormal mode recognition is carried out through an abnormal detection algorithm, the checking process of a user on abnormal data is recorded, and optimization suggestions are automatically generated; the state of each key index is displayed and updated in real time, multi-dimensional analysis is carried out on data, and an alarm is given to an abnormal condition according to an alarm rule set by a user; the data is visually displayed based on a geographic information system, the data is further analyzed according to interactive operation of a user, and a report is automatically generated and exported. According to the scheme, the power grid data can be automatically and efficiently processed, the accuracy and attractiveness of the data are improved, and the actual requirement of the power industry for data management is met.

Description

Technical Field

[0001] The present invention belongs to the field of big data analysis and data governance, and particularly relates to a method and system for abnormal verification of operation and distribution data based on big data analysis. Background Art

[0002] In modern power grid management, the quality and accuracy of operation and distribution graphic data are crucial for the stable operation of the power grid, directly affecting the management, operation, and maintenance of the power grid. With the intelligence of the power system and the continuous expansion of the data scale, traditional data processing methods can no longer meet the high requirements of modern power enterprises for data quality. In the prior art, the management of power grid graphic data mainly relies on manual operations and traditional review processes. This method has many drawbacks, seriously affecting the efficiency and effectiveness of power grid operation. Specifically:

[0003] Traditional graphic data review is often time-consuming and inefficient. For example, Patent US20190006838A1 proposes a power system monitoring method that relies on manual experience and judgment. Moreover, in the face of large-scale data, it is often unable to process it in a timely manner. Lack of automated tools makes the data processing speed slow, resulting in operators being unable to quickly respond to potential power grid problems, increasing the risk of system failures. For example, Patent CN106964953A proposes a power grid data processing method. Although a data cleaning process is established, it still requires a considerable amount of manual intervention. Manual processing is not only time-consuming but also prone to omissions and errors, resulting in the inability to guarantee the quality of the cleaned data. This low-efficiency cleaning method is particularly prominent in a large-scale data environment and cannot meet the real-time and accuracy requirements of power enterprises. The power data analysis method based on traditional statistics can only provide descriptive statistics and cannot deeply explore the potential relationships between data. This analysis method may lead to misjudgment of the power grid operation status, affecting the scientificity and effectiveness of decision-making. In addition, the prior art often ignores the integration of multi-source spatial data, and many verification methods only rely on a single data source, which greatly reduces the accuracy of data verification. For example, the monitoring system mentioned in Patent CN107000123A fails to effectively integrate various data from GIS systems, UAV images, and geographical coordinates, resulting in unreliable verification results. In addition, the lack of an effective anomaly detection mechanism makes potential errors in the data not be identified in a timely manner, thus increasing the risk. Most methods still rely on static rules, lacking flexibility and adaptability. The formulation process of traditional rules is cumbersome and difficult to update, resulting in poor performance of machine learning models in practical applications and difficulty in dealing with complex and variable power grid data. Summary of the Invention

[0004] To address the deficiencies in the existing technology, the present invention provides a method and system for abnormal verification of operation and distribution data based on big data analysis, aiming to solve the technical problems such as low data cleaning efficiency, excessive manual intervention, single data analysis method, insufficient integration of spatial data, and lack of intelligent anomaly detection mechanism during the cleaning and verification process of power grid operation and distribution graphic data.

[0005] To solve the above technical problems, the present invention adopts the following technical solutions.

[0006] The present invention first discloses a method for abnormal verification of operation and distribution data based on big data analysis, which includes the following steps:

[0007] Step 1: Establish connections with multiple data sources through the DataWorks platform, execute power grid graphic data collection tasks according to predefined time intervals, perform format conversion and anomaly processing on the collected data, and form a data collection log.

[0008] Step 2: Define multi-level verification rules, identify abnormal patterns in the collected data through anomaly detection algorithms, record the verification process of users for abnormal data, and automatically generate optimization suggestions based on the verification process.

[0009] Step 3: Real-time display and update the status of each key indicator, perform multi-dimensional analysis on the data, and issue alerts for monitored abnormal situations according to personalized alert rules set by users.

[0010] Step 4: Visualize the data based on the geographic information system, further analyze the data according to user interaction operations, and automatically generate and export reports.

[0011] The present invention further includes the following preferred solutions:

[0012] The multiple data sources include sensor data, GPS positioning information, user input, and historical data warehouses.

[0013] The format conversion and anomaly processing of the collected data further include:

[0014] Convert data in JSON, XML, and CSV formats into a unified format, record abnormal information and send notifications for abnormal data found during the collection process.

[0015] The data collection log records the time, data volume, and status of each collection.

[0016] The multi-level verification rules include format verification, business logic verification, and statistical analysis.

[0017] The multi-dimensional analysis includes analysis in dimensions of geographical location, time period, and resource utilization rate.

[0018] The method further includes:

[0019] Establish a data standard document, including data field definitions, data formats, and coding specifications. All data collection and processing follow a unified standard, and the rule base is kept consistent with changes in business processes and the external environment through regular reviews and updates; establish a compliance audit mechanism to regularly check the implementation of data standards and ensure that all data processing operations comply with the predefined standards and rules.

[0020] The present invention also discloses a big data analysis-based power operation and distribution data anomaly verification system using the aforementioned big data analysis-based power operation and distribution data anomaly verification method, including:

[0021] A data collection module for establishing connections with multiple data sources through the DataWorks platform, performing power grid graphic data collection tasks at predefined time intervals, performing format conversion and anomaly processing on the collected data, and forming a data collection log;

[0022] An anomaly detection and optimization module for defining multi-level verification rules, identifying anomaly patterns in the collected data through anomaly detection algorithms, recording the user's verification process for anomaly data, and automatically generating optimization suggestions based on the verification process;

[0023] A real-time monitoring module for displaying and updating the status of key indicators in real time, performing multi-dimensional analysis on the data, and issuing alarms for monitored anomalies according to personalized alarm rules set by the user;

[0024] A visualization display module for visually displaying the data based on a geographic information system, further analyzing the data according to the user's interaction operations, and automatically generating and exporting reports.

[0025] Correspondingly, the present application also discloses a terminal, including a processor and a storage medium;

[0026] The storage medium is used to store instructions;

[0027] The processor is used to operate according to the instructions to execute the steps of the aforementioned big data analysis-based power operation and distribution data anomaly verification method.

[0028] Correspondingly, the present application also discloses a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the steps of the aforementioned big data analysis-based power operation and distribution data anomaly verification method.

[0029] The beneficial effects of the present invention are as follows. Compared with the prior art, the present invention provides a method and system for abnormal verification of operation and distribution data based on big data analysis. By introducing a platform based on DataWorks, efficient and automated cleaning and abnormal verification of power grid operation and distribution graphic data are realized. Through big data analysis technology, redundant, repeated, incorrect, and missing data can be automatically identified and processed, significantly reducing manual participation, remarkably improving the efficiency and accuracy of data processing, and reducing the error risk brought by manual intervention. By adopting a multi-dimensional analysis algorithm, the cleaned data is comprehensively verified. The application of multi-dimensional analysis and multi-source data integration enhances the consistency and reliability of the data, can more comprehensively reflect the actual situation of power grid data, and provides more comprehensive and scientific decision-making support for the power industry. Effectively integrate spatial data from different data sources, including geographical coordinates, UAV images, seven-level addresses, and community electronic fences, etc. The constructed basic verification model improves the verification accuracy of power grid graphic data by comprehensively considering these multi-source data. At the same time, combined with an intelligent anomaly detection mechanism and a flexible rule engine, abnormal data and potential problems can be quickly identified and located, dynamically adapting to changes in power grid data, greatly improving the intelligent level of data governance, and ultimately promoting the efficient operation and management of the power system. In summary, the method for power grid operation and distribution graphic data analysis and abnormal verification based on DataWorks proposed by the present invention improves the cleaning efficiency and verification accuracy of power grid data, and provides strong support for power enterprises to achieve intelligent management. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is the analysis flow chart based on dataworks in the present invention.

[0031] Figure 2 is the python spatial analysis diagram based on big data analysis in the present invention.

[0032] Figure 3 is the distributed data calculation diagram based on spark of dataworks in the present invention.

[0033] Figure 4 is the dataworks scheduling management diagram involved in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0034] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0035] The embodiments described in this application are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the spirit of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0036] In view of the deficiencies of the prior art, the present invention proposes a method and system for abnormal verification of operation and distribution data based on big data analysis. The power grid graphic data from different data sources is integrated through the DataWorks platform and formatted and sorted. An automated tool is used to identify and process redundant, duplicate, incorrect, and missing data to improve data quality. A multi-dimensional analysis algorithm is adopted to deeply analyze the cleaned data to ensure data consistency and accuracy. Multi-source spatial data such as GIS coordinate data, structured addresses, and cell corridor AOIs are integrated to establish a basic verification model. The machine learning algorithm is combined with the rule engine to automatically detect and locate abnormal data. The cleaned and verified data is displayed through the visualization tool of DataWorks to generate a report for decision support.

[0037] The method for abnormal verification of operation and distribution data based on big data analysis disclosed by the present invention includes the following steps:

[0038] Step 1: Establish a connection with multiple data sources through the DataWorks platform, execute the power grid graphic data collection task according to a predefined time interval, perform format conversion and exception handling on the collected data, and form a data collection log.

[0039] Establish a connection with multiple data sources through the DataWorks platform, including but not limited to sensor data, GPS positioning information, user input, historical data warehouses, etc., to ensure the comprehensiveness of the data. Set timed tasks (such as every hour, daily) and real-time trigger mechanisms to ensure the timeliness and accuracy of data collection. During the collection process, convert data in different formats (such as JSON, XML, CSV, etc.) into a unified format for subsequent processing. For abnormal data found during the collection process (such as values outside the reasonable range), record the abnormal information and notify relevant personnel for manual verification. Establish a detailed data collection log to record the time, data volume, and status of each collection for later traceability and auditing.

[0040] Step 2: Define multi-level verification rules, identify abnormal patterns in the collected data through abnormal detection algorithms, record the user's verification process for abnormal data, and automatically generate optimization suggestions based on the verification process.

[0041] Design multi-level verification rules, including basic format verification, business logic verification (such as time and location consistency), and statistical analysis (such as average value, standard deviation, etc.). Use machine learning and data mining technologies to develop abnormal detection algorithms to automatically identify abnormal patterns that do not match historical data.

[0042] Optionally, anomaly detection is performed based on the K-means clustering results. The clustering algorithm divides the dataset into multiple clusters, and the points that are far from the cluster center in the clustering are considered anomaly points.

[0043]

[0044] d(x i , μ k ) = ||x i - μ k ||

[0045] Anomaly point detection: if d(x i , μ k ) > T

[0046] where K is the number of clusters obtained by clustering. Calculate the center point of each cluster, i.e., the centroid. Among them, C k represents the k-th cluster, x i is the data point in the cluster, and μ k is the centroid of the cluster. For each data point x i , calculate its distance from the center of the cluster to which it belongs, where ||·|| represents the Euclidean distance. The data points with a distance greater than a certain threshold T are regarded as anomaly points. Usually, a distance criterion (such as 1.5 times the mean distance) is selected as the anomaly determination criterion.

[0047] During the data collection process, error information is fed back in real time to reduce the complexity and resource waste of later processing. Provide a manual intervention channel for anomaly data that cannot be automatically corrected, allowing users to manually check the errors and record the checking process. Based on the comprehensive checking results, optimization suggestions are automatically generated, including improving the data collection process, adjusting the rule base, etc., to continuously improve the data quality.

[0048] Step 3: Display and update the status of each key indicator in real time, perform multi-dimensional analysis on the data, and alarm the monitored abnormal situations according to the personalized alarm rules set by the user.

[0049] Build a dynamic monitoring dashboard to display the status of each key indicator in real time and automatically update according to data changes. Set up an event trigger mechanism. When abnormal situations (such as transportation delays, equipment failures) are monitored, an event report is automatically generated and pushed to relevant personnel. Compare real-time data with historical data to quickly identify abnormal fluctuations and trends.

[0050] In a further preferred embodiment, the following formula is used for detecting abnormal fluctuations:

[0051]

[0052] Where:

[0053] Yt is the actual observed value. ^Yt is the value predicted using the ARIMA model. τ is the threshold for anomaly detection, usually set according to the standard deviation of the error.

[0054] In a further preferred embodiment, the following formula is used for trend anomaly detection:

[0055] The prediction result of the ARIMA model will include a trend component. If the trend of the predicted value is opposite to the actual trend direction and exceeds the set threshold, it is considered a trend anomaly.

[0056]

[0057] Among them, Slope(Yt) and Slope(^Yt) are the trend change slopes of the actual data and the predicted data. If the trend of the actual data deviates from the direction or amplitude of the predicted trend and exceeds the threshold, it can be considered a trend anomaly.

[0058] The monitoring module supports multi-dimensional data analysis, including geographical location, time period, resource utilization, etc., to ensure a comprehensive understanding of the operation status. It allows users to set personalized alarm rules according to their needs to ensure that key personnel can be informed in a timely manner when an event occurs.

[0059] Step 4: Visualize the data based on the geographical information system, further analyze the data according to the user's interaction operations, and automatically generate and export reports.

[0060] A variety of chart types (such as line charts, bar charts, pie charts, heat maps, etc.) are used to meet different data display needs. Using geographical information system (GIS) technology, the transportation routes, distribution areas, etc. are visualized for spatial analysis. Users can deeply analyze the data through interactive operations (such as filtering, drilling down) to identify potential problems. It supports the backtracking of historical data for trend analysis and decision-making support by users. Users can customize the report template according to business needs, automatically generate and export reports, and support multiple formats (such as PDF, Excel, etc.).

[0061] Furthermore, in the visualization display, the distance formula between two points on the sphere is used to calculate the distance on the earth's surface:

[0062]

[0063] Among them: Δφ = φ2 - φ1 is the latitude difference between two points (unit: radian). Δλ = λ2 - λ1 is the longitude difference between two points (unit: radian). R is the radius of the earth, with the unit of meters (or kilometers).

[0064] The longitude and latitude on the earth's surface are projected onto a plane through the following formula.

[0065] x = R·λ

[0066]

[0067] Wherein: x and y are planar coordinates in the projected coordinate system. λ is the longitude in radians. φ is the latitude in radians. R is the radius of the earth.

[0068] The method further includes:

[0069] Establish clear data standard documents, including data field definitions, data formats, coding specifications, etc., to ensure that all data collection and processing follow a unified standard. Set up a regular review and update mechanism to ensure that the rule base is consistent with changes in business processes and the external environment. When formulating data standards and rules, relevant personnel from different departments and roles participate in the discussion to ensure the comprehensiveness and applicability of the standards. Regularly train relevant personnel on data standards and rules to improve the team's attention to data quality and execution. Establish a compliance audit mechanism to regularly check the implementation of data standards to ensure that all data processing operations comply with the pre-established standards and rules.

[0070] The beneficial effects of the present invention are as follows. Compared with the prior art, the present invention provides a method and system for abnormal verification of operation and distribution data based on big data analysis. By introducing a platform based on DataWorks, it realizes the efficient and automatic cleaning and abnormal verification of power grid operation and distribution graphic data. Through big data analysis technology, it can automatically identify and process redundant, duplicate, incorrect, and missing data, significantly reducing manual participation, remarkably improving the efficiency and accuracy of data processing, and reducing the error risk brought by manual intervention. Adopting a multi-dimensional analysis algorithm to comprehensively verify the cleaned data, the application of multi-dimensional analysis and multi-source data integration enhances the consistency and reliability of the data, can more comprehensively reflect the actual situation of power grid data, and provides more comprehensive and scientific decision-making support for the power industry. Effectively integrate spatial data from different data sources. The constructed basic verification model improves the verification accuracy of power grid graphic data by comprehensively considering these multi-source data. At the same time, combined with an intelligent anomaly detection mechanism and a flexible rule engine, it can quickly identify and locate abnormal data and potential problems, dynamically adapt to changes in power grid data, and greatly improve the intelligent level of data governance, ultimately promoting the efficient operation and management of the power system. In summary, the method for analyzing and abnormally verifying power grid operation and distribution graphic data based on DataWorks proposed by the present invention improves the cleaning efficiency and verification accuracy of power grid data, and provides strong support for power enterprises to achieve intelligent management.

[0071] The present invention can be a system, a method, and / or a computer program product. The present invention also discloses a system for abnormal verification of operation and distribution data based on big data analysis based on the aforementioned method for abnormal verification of operation and distribution data based on big data analysis, including:

[0072] A data acquisition and integration module, which is used to establish connections with multiple data sources through the DataWorks platform, integrate multi-source spatial data such as GIS coordinate data, structured addresses, and community corridor AOIs, establish a basic verification model. At the same time, according to a predefined time interval, it executes the power grid graphic data acquisition task, performs format conversion and exception handling on the acquired data, and forms a data acquisition log;

[0073] An exception detection and optimization module, which is used to define multi-level verification rules, identify abnormal patterns in the acquired data through an exception detection algorithm, record the user's verification process for abnormal data, and automatically generate optimization suggestions based on the verification process;

[0074] A real-time monitoring module, which is used to display and update the status of various key indicators in real time, perform multi-dimensional analysis on the data, and issue alarms for the monitored abnormal situations according to the personalized alarm rules set by the user;

[0075] A visualization display module, which is used to visually display the data based on a geographic information system, further analyze the data according to the user's interaction operations, and automatically generate and export reports.

[0076] Based on the spirit of the present invention, those skilled in the art can easily think that a computer program product can be obtained based on the foregoing method for abnormal verification of operation and distribution data based on big data analysis. The computer program product may include a computer-readable storage medium, on which computer-readable program instructions for causing a processor to implement various aspects of the present disclosure are loaded. That is, the present application also includes a terminal, including a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of the method for abnormal verification of operation and distribution data based on big data analysis as described above.

[0077] A computer-readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. A computer-readable storage medium may be, for example - but not limited to - an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanically encoded device, such as a punched card or raised structures in grooves storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage medium as used herein is not construed as an instantaneous signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through wires.

[0078] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to respective computing / processing devices, or can be downloaded to an external computer or an external storage device through a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include a copper transmission cable, an optical fiber transmission, a wireless transmission, a router, a firewall, a switch, a gateway computer, and / or an edge server. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0079] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine - related instructions, microcode, firmware instructions, state - setting data, or source code or object code written in any combination of one or more programming languages, including object - oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer - readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand - alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, by using the state information of the computer - readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field - programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer - readable program instructions to implement various aspects of the present disclosure.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the protection scope of the claims of the present invention.

Claims

1. A method for checking abnormality of distribution data based on big data analysis, characterized in that: The following steps are involved: Step 1: Use the DataWorks platform to establish connections with multiple data sources, execute power grid graphic data collection tasks at predefined time intervals, convert the format of the collected data and handle exceptions to form data collection logs; Step 2: Define multi-level verification rules, identify abnormal patterns of collected data through anomaly detection algorithms, record the user's verification process of abnormal data, and automatically generate optimization suggestions based on the verification process; Step 3: Display and update the status of each key indicator in real time, analyze the data in multiple dimensions, and issue alerts for abnormal situations detected based on the personalized alert rules set by the user; Step 4: Visualize the data based on the geographic information system, further analyze the data based on user interactions, and automatically generate and export reports.

2. The method for checking anomalies in distribution data based on big data analysis according to claim 1 is characterized in that: The multiple data sources include sensor data, GPS location information, user input, and historical data warehouse.

3. The method for checking anomalies in distribution data based on big data analysis according to claim 2 is characterized in that: The format conversion and exception processing of the collected data further includes: Convert data in JSON, XML, and CSV formats into a unified format. For abnormal data found during the collection process, record the abnormal information and issue a notification.

4. The method for checking anomalies in distribution data based on big data analysis according to claim 3 is characterized in that: The data collection log records the time, data volume and status of each collection.

5. The method for checking anomalies in distribution data based on big data analysis according to claim 4 is characterized in that: The multi-level verification rules include format verification, business logic verification and statistical analysis.

6. The method for checking anomalies in distribution data based on big data analysis according to claim 5 is characterized in that: The multi-dimensional analysis includes analysis of geographical location, time period and resource utilization dimensions.

7. The method for checking anomalies in distribution data based on big data analysis according to claim 6 is characterized in that: The method further comprises: Establish data standard documents, including data field definitions, data formats, and coding specifications. All data collection and processing follow unified standards. Through regular review and updates, the rule base is kept consistent with changes in business processes and the external environment. Establish a compliance audit mechanism to regularly check the implementation of data standards and ensure that all data processing operations comply with pre-established standards and rules.

8. A distribution data anomaly verification system based on big data analysis, characterized in that: include: The data collection and integration module is used to establish connections with various data sources through the DataWorks platform, integrate GIS coordinate data, structured addresses, community corridor AOI and other multi-source spatial data, establish a basic verification model, and execute power grid graphic data collection tasks according to predefined time intervals, perform format conversion and exception processing on the collected data, and form a data collection log; The anomaly detection and optimization module is used to define multi-level verification rules, identify abnormal patterns of collected data through anomaly detection algorithms, record the user's verification process of abnormal data, and automatically generate optimization suggestions based on the verification process; The real-time monitoring module is used to display and update the status of key indicators in real time, conduct multi-dimensional analysis of data, and issue alarms for abnormal situations detected according to the personalized alarm rules set by users; The visualization module is used to visualize data based on the geographic information system, further analyze the data according to user interaction operations, and automatically generate and export reports.

9. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the method for checking anomalies in distribution data based on big data analysis according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method for checking anomalies in distribution data based on big data analysis described in any one of claims 1 to 7 are implemented.

Images