Measurement anomaly analysis method and apparatus, storage medium and computer device

Abstract

A measurement anomaly analysis method and apparatus, a storage medium, and a computer device. The measurement anomaly analysis method comprises: acquiring first-order analysis data analyzed by a source-end system and, on the basis of the first-order analysis data, determining at least one data filtering rule (101); on the basis of the data filtering rule, performing a filtering operation on monitoring data of the source-end system to obtain target measurement anomaly data (102); performing contrastive analysis on the target measurement anomaly data and pre-configured anomaly case data to determine at least one piece of target case data from among the anomaly case data (103); and performing multi-dimensional clustering analysis on the target measurement anomaly data so as to obtain the degrees of aggregation of the target measurement anomaly data in a plurality of data dimensions and, on the basis of the target case data and the degrees of aggregation, analyzing a measurement anomaly cause (104).

Description

Method and device for analyzing measurement anomalies, storage medium, and computer equipment

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on June 16, 2023, with application number 202310720828.3, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the technical field of data processing and analysis, for example, to an analysis method and device for measurement anomalies, a storage medium, and a computer device. Background Art

[0003] Metering anomalies are crucial to the fairness and justice of the electricity market and customer service perception. Ensuring the proper functioning of power metering equipment is a crucial component of the overall power marketing environment. The causes of metering anomalies are complex and can include business issues, equipment problems, unique operating conditions, and environmental issues. Failure to address metering anomalies clearly and promptly can lead to serious accidents.

[0004] The method for analyzing metering anomalies involves selecting certain data items from a large amount of metering equipment operating information based on their level of concern and importance, as key performance data. This data is then used to calculate indicators, thereby determining the overall quality of the metering equipment and metering services based on the indicator values. However, this analysis method has a narrow analysis dimension and simple verification logic, resulting in low accuracy in assessing the combined effects of multiple factors. This can lead to the recurrence, spread, and migration of metering anomalies, and fails to effectively reduce power operation and maintenance costs.

[0005] Summary of the Invention

[0006] The present application provides a method and device for analyzing metering anomalies, a storage medium, and a computer device, which solves the problem of low accuracy in abnormal problem analysis due to the small analysis dimension and simple verification logic of the power metering anomaly analysis method.

[0007] In one aspect, the present application provides a method for analyzing measurement anomalies, comprising:

[0008] Obtaining primary analysis data obtained through analysis by a source end system, and determining at least one data filtering rule based on the primary analysis data;

[0009] Filtering the monitoring data of the source system based on the data filtering rules to obtain target measurement abnormality data;

[0010] Comparing and analyzing the target measurement abnormality data with pre-configured abnormal case data, and determining at least one target case data from the abnormal case data;

[0011] Perform multidimensional cluster analysis on the target measurement anomaly data to obtain the aggregation degree of the target measurement anomaly data in multiple data dimensions; and analyze the cause of the measurement anomaly based on the target case data and the aggregation degree.

[0012] In another aspect of the present application, a device for analyzing measurement anomalies is provided, comprising:

[0013] a filtering rule determination module configured to obtain primary analysis data obtained by analysis by a source end system and determine at least one data filtering rule based on the primary analysis data;

[0014] A data acquisition module is configured to filter the monitoring data of the source system based on the data filtering rules to obtain target measurement abnormality data;

[0015] a case determination module configured to compare and analyze the target measurement abnormality data with pre-configured abnormal case data, and determine at least one target case data from the abnormal case data;

[0016] The cause analysis module is configured to perform multidimensional cluster analysis on the target measurement anomaly data to obtain the aggregation degree of the target measurement anomaly data in multiple data dimensions; and analyze the cause of the measurement anomaly based on the target case data and the aggregation degree.

[0017] In another aspect of the present application, a storage medium is provided, wherein the storage medium stores at least one executable instruction, and the executable instruction enables a processor to execute the above-mentioned measurement anomaly analysis method.

[0018] In another aspect of the present application, a computer device is provided, comprising a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0019] The memory is configured to store at least one executable instruction, and the executable instruction enables the processor to execute the above-mentioned measurement anomaly analysis method. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] FIG1 is a flow chart of a method for analyzing measurement anomalies provided in an embodiment of the present application;

[0021] FIG2 is a flow chart of another method for analyzing measurement anomalies provided in an embodiment of the present application;

[0022] FIG3 is a flow chart of another method for analyzing measurement anomalies provided in an embodiment of the present application;

[0023] FIG4 is a schematic structural diagram of a measurement anomaly analysis device provided in an embodiment of the present application;

[0024] FIG5 is a schematic structural diagram of another device for analyzing measurement anomalies provided in an embodiment of the present application;

[0025] FIG6 is a schematic structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The following will describe exemplary embodiments of the present application with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the accompanying drawings, the present application can be implemented in various forms. These embodiments are provided for understanding the present application.

[0027] The present application provides an analysis method for a measuring device, as shown in FIG1 , comprising:

[0028] 101. Obtain primary analysis data obtained through analysis by a source system, and determine at least one data filtering rule based on the primary analysis data.

[0029] In an embodiment of the present application, the current execution end obtains the primary analysis data obtained through the source end system analysis, wherein the source end system is used to characterize a system with functions such as online data monitoring of electric power metering equipment, inaccuracy monitoring of electric power metering equipment, and receiving customer complaints. It can collect the operating status data of all metering equipment in the system in real time, and can also dispatch work orders based on discrete functions, and find problems such as a high incidence of abnormalities in metering equipment and a decline in customer service satisfaction in the monthly indicator measurement. Among them, the primary analysis data is used to characterize the analysis data obtained by the system analysis function of the source end system, including nearly 100 key indicators such as acquisition success rate, electric energy meter inaccuracy, electric energy meter flow reversal, voltage phase failure, customer complaints, line loss exceeding the limit, load overcapacity, and sudden change in electricity. The embodiment of the present application does not limit the type of primary analysis data. After the current execution end obtains the primary analysis data, it determines at least one data filtering rule based on the primary analysis data.

[0030] Since the preliminary analysis data can reflect the abnormal problems of some metering equipment, that is, at least one key indicator has an indicator deviation problem, the key indicator with the indicator deviation problem is called a key indicator deviation item. When determining the data filtering rules, it is necessary to filter the data based on the key indicator deviation item. For example, if there is a deviation in the success rate of the electric energy meter acquisition, then based on the normal acquisition success, the time period in which the success rate of the electric energy meter acquisition has deviated, the metering equipment corresponding to the acquisition failure, and the detailed information related to the acquisition are first determined. The detailed information includes the acquisition equipment file information (manufacturer, batch, model, protocol and other static information), business information (operating time, acquisition and maintenance, on-site re-recording, on-site inspection, on-site inspection, assembly and disassembly, etc.), operation information that may affect the acquisition quality (voltage curve, current curve, terminal address, clock, battery undervoltage event, power-on event, cover opening record, clock error and other dynamic information), etc. The embodiment of the present application does not limit the type of detailed information. The current execution end filters the collection-related detailed information involved in the above-mentioned key indicator deviation item of the electricity meter collection success rate according to the time period when the deviation occurred and the metering equipment corresponding to the collection failure to determine the data filtering rules corresponding to the key indicator deviation item of the electricity meter collection success rate, etc. The embodiment of this application does not limit the determination method.

[0031] 102. Filter the monitoring data of the source system based on the data filtering rule to obtain target measurement abnormality data.

[0032] In the embodiment of the present application, the current execution end performs a filtering operation on the monitoring data of the source end system based on the data filtering rules to obtain the target metering abnormality data. For example, if the data filtering rule corresponding to the key indicator deviation item of the electric energy meter acquisition success rate in step 101 is used, when performing the filtering operation, the detailed information related to the acquisition corresponding to the acquisition failure time period A of the electric energy meter 001 in the source end system, the detailed information related to the acquisition corresponding to the acquisition failure time period B of the electric energy meter 003 in the acquisition failure time period C of the electric energy meter 014 in the acquisition failure time period C of the electric energy meter 036 in the acquisition failure time period D of the electric energy meter 036 in the acquisition failure time period D of the electric energy meter 102 in the acquisition failure time period E of the electric energy meter 102 in the acquisition failure time period E of the electric energy meter 001 in the source end system should be obtained. Among them, the detailed information related to the acquisition is shown in step 101.

[0033] 103. Compare and analyze the target measurement abnormality data with pre-configured abnormal case data, and determine at least one target case data from the abnormal case data.

[0034] In an embodiment of the present application, the current execution end compares and analyzes target metering anomaly data with pre-configured anomaly case data, and determines at least one target case data from the anomaly case data. The anomaly case data includes anomaly data in multiple dimensions, and the current execution end compares the anomaly data in multiple dimensions based on similarity when performing the comparative analysis, thereby determining the at least one target case data.

[0035] 104. Perform multidimensional cluster analysis on the target measurement anomaly data to obtain the aggregation degree of the target measurement anomaly data in multiple data dimensions; and analyze the cause of the measurement anomaly based on the target case data and the aggregation degree.

[0036] In an embodiment of the present application, the current execution end performs a multi-dimensional cluster analysis on the target measurement anomaly data to obtain the aggregation degree of the target measurement anomaly data in multiple data dimensions. Among them, the multi-dimensional cluster analysis can use statistical principles to perform quantitative statistics, and can also use machine learning models for cluster analysis, such as fuzzy clustering, multivariate regression, decision trees, support vector machines, etc. The embodiment of the present application does not limit the corresponding method of multi-dimensional cluster analysis. The current execution end also analyzes the causes of measurement anomalies based on the target case data and the aggregation degree, such as analyzing the correlation between the causes of anomalies in the target case data and the attribute values ​​on the data dimensions with high aggregation degrees, etc. The embodiment of the present application does not limit this.

[0037] In one embodiment, in order to obtain data related to metering anomalies and filter out data unrelated to metering anomalies, at least one data filtering rule is determined based on the primary analysis data, including:

[0038] Obtain a mapping relationship between key indicators and indicator association information, and determine the target indicator association information corresponding to the key indicator deviation item based on the mapping relationship; obtain the time period in which the key indicator deviation item is generated, and determine the data filtering rule based on the time period and the target indicator association information.

[0039] In an embodiment of the present application, the current execution end obtains a mapping relationship between the key indicator and the indicator association information, and determines the target indicator association information corresponding to the key indicator deviation item based on the mapping relationship. Wherein, the mapping relationship is pre-configured based on experience. For example, the target indicator association information having a mapping relationship with the key indicator deviation item, the electric energy meter acquisition success rate deviation, can be electric energy meter file information (manufacturer, batch, model, specification and other static information), business information (operating time, acquisition and maintenance, on-site re-recording, on-site inspection, on-site inspection, installation and disassembly, etc.), operation information that may affect the quality of electric energy meter acquisition (voltage curve, current curve, terminal address, clock, battery undervoltage event, power-on event, cover opening record, clock error and other dynamic information), etc. For another example, the target indicator-related information that has a mapping relationship with the key indicator deviation item, the inaccuracy deviation of the electricity meter, can be the electricity meter file information (static information such as manufacturer, batch, model, specification, accuracy level, calibration error, etc.), business information (previous on-site inspection errors, installation time, installation location, operating environment, recent on-site business content and personnel, recent status evaluation conclusions, etc.), operating information that may affect the operating error (voltage, current, overload, phase loss, load imbalance, special power factor, cover opening record, etc.), etc. The embodiment of the present application does not limit the type of target indicator-related information.

[0040] In an embodiment of the present application, the current execution end obtains the time period in which the key indicator deviation item is generated, and determines the data filtering rule based on the time period in which the key indicator deviation item is generated and the target indicator association information. For example, when the key indicator deviation item is the deviation of the success rate of electric energy meter acquisition, the target indicator association information of the corresponding electric energy meter in the time period in which the above deviation is generated is determined as the data filtering rule; when the key indicator deviation item is the inaccuracy deviation of the electric energy meter, the target indicator association information of the corresponding electric energy meter in the time period in which the above deviation is generated is determined as the data filtering rule, etc. The embodiment of the present application does not limit the method of determining the data filtering rule based on the time period and the target indicator association information.

[0041] In one embodiment, in order to make the acquired source system monitoring data more accurate in terms of logic and data consistency and facilitate subsequent data analysis, after filtering the source system monitoring data based on the data filtering rules to obtain target measurement abnormality data, the method further includes:

[0042] performing data logic verification on the target metering abnormal data, and deleting the target metering abnormal data that does not conform to data logic; and / or performing data consistency verification on the target metering abnormal data, and deleting the target metering abnormal data that does not conform to data consistency.

[0043] In the embodiment of the present application, the current execution end performs data logic verification on the target metering anomaly data and deletes any target metering anomaly data that does not conform to the data logic, thereby achieving data cleansing based on the data logic. In addition, the current execution end can also perform data consistency verification on the target metering anomaly data and delete any target metering anomaly data that does not conform to the data consistency, thereby achieving data cleansing based on the data consistency.

[0044] In one embodiment, in order to support similar case retrieval and improve the referenceability of similar case retrieval, target measurement anomaly data is compared and analyzed with pre-configured abnormal case data, and at least one target case data is determined from the abnormal case data, including:

[0045] Acquire case attribute information of the abnormal case data, match the case attribute information with the to-be-matched attribute information of the target measurement abnormal data, and determine the target attribute information from the to-be-matched attribute information; perform similarity calculation based on the attribute value corresponding to the target attribute information and the attribute value corresponding to the case attribute information, and determine the abnormal case data corresponding to the case attribute information with a similarity higher than a threshold as the target case data.

[0046] In the embodiment of the present application, the current execution end obtains case attribute information of the abnormal case data, including the name of the abnormal metering device, abnormality indicator, abnormality duration, and abnormal impact range. The embodiment of the present application does not limit the type of case attribute information. The current execution end uses multiple attribute information of the target metering abnormal data as the attribute information to be matched, matches the case attribute information with the attribute information to be matched, and determines the target attribute information from the attribute information to be matched. For example, from the numerous attribute information of the target metering abnormal data, the name of the abnormal metering device, abnormality indicator, abnormality duration, and abnormal impact range that successfully matches are determined as the target attribute information.

[0047] In the embodiment of the present application, the current execution end performs a degree of calculation based on the attribute value corresponding to the target attribute information and the attribute value corresponding to the case attribute information. For example, the attribute value corresponding to the name of the abnormal metering device is the electric energy meter, the attribute value corresponding to the abnormal indicator is the acquisition success rate value, the attribute value corresponding to the abnormal duration is the duration (such as 5 minutes, 1 hour, 30 minutes, etc.), and the attribute value corresponding to the abnormal impact range is the size of the affected area (such as the number of abnormal electric energy meters, the number of areas with abnormal electric energy meters, etc.). The embodiment of the present application does not limit the measurement method of the attribute value. The current execution end determines the abnormal case data corresponding to the case attribute information with a similarity higher than the similarity threshold as the target case data. Among them, the threshold is a numerical value pre-set according to needs.

[0048] In one embodiment, in order to conduct an in-depth analysis of target measurement anomaly data from multiple dimensions, as shown in FIG2 , a multidimensional cluster analysis is performed on the target measurement anomaly data to obtain the aggregation degree of the target measurement anomaly data in multiple data dimensions, including:

[0049] 201. Obtain an attribute value corresponding to a single attribute information in the target measurement abnormality data.

[0050] 202. Perform cluster analysis on the attribute values ​​using a cluster analysis model to obtain a degree of aggregation on a single data dimension.

[0051] 203. Merge the aggregation degrees on the single data dimensions to obtain aggregation degrees on multiple data dimensions.

[0052] In an embodiment of the present application, the current execution end obtains attribute values ​​corresponding to individual attribute information in the target metering anomaly data, performs cluster analysis on the attribute values ​​using a cluster analysis model, and obtains the degree of aggregation for a single data dimension. For example, the attribute values ​​corresponding to the manufacturer attribute information {Manufacturer A, Manufacturer B, Manufacturer A, Manufacturer C, Manufacturer B, ...} are obtained and clustered to obtain the degree of aggregation for Manufacturer A, Manufacturer B, and Manufacturer C, etc.; another example, the attribute values ​​corresponding to the installation location attribute information {Location 1, Location 3, Location 1, Location 1, Location 2, Location 3, Location 3, ...} are obtained and clustered to obtain the degree of aggregation for Location 1, Location 2, Location 3, etc.

[0053] The current execution end combines the aggregation degrees obtained for individual data dimensions to obtain aggregation degrees for multiple data dimensions. This aggregation degree can be used to analyze batch anomalies of metering equipment. For example, the deviation in the inaccuracy rate of electric energy meters is mainly due to products from manufacturer A; the deviation in the success rate of electric energy meter data collection mainly occurs at installation location 3.

[0054] In one embodiment, in order to avoid survivor error, that is, to avoid the analyzed abnormality cause from not matching the actual abnormal situation, and to improve the accuracy of measurement abnormality analysis, as shown in FIG3 , after performing multidimensional cluster analysis on the target measurement abnormality data to obtain the aggregation degree of the target measurement abnormality data in multiple data dimensions, the method further includes:

[0055] 301. Sort the aggregation degrees on at least one data dimension in descending order, and obtain the attribute value to be analyzed with the highest aggregation degree on each data dimension.

[0056] In an embodiment of the present application, the current execution end sorts the aggregation degrees in descending order, and obtains the attribute value with the highest aggregation degree in at least one data dimension as the attribute value to be analyzed. For example, when the aggregation degrees of the electric energy meter manufacturer A, the aggregation degrees of the manufacturer B, and the aggregation degrees of the manufacturer C in the above embodiment are 74, 8, and 11 respectively, the manufacturer A can be determined as the attribute value to be analyzed; when the aggregation degrees of the electric energy meter installation position 1, the aggregation degrees of the installation position 2, and the aggregation degrees of the installation position 3 in the above embodiment are 9, 7, and 77 respectively, the installation position 3 can be determined as the attribute value to be analyzed, etc.

[0057] In this embodiment, there is no limit on the number of data dimensions that can be sorted. If the degree of aggregation on only one data dimension exhibits the degree of aggregation characteristic, then only the degree of aggregation on that data dimension can be sorted. If the degree of aggregation on multiple data dimensions exhibits the degree of aggregation characteristic, then multiple conditional constraints, weighted statistics, or conditional analysis can be used to sort the degrees of aggregation on multiple data dimensions to form a combination scheme of attribute values ​​to be analyzed.

[0058] 302. Obtain a source system backtracking rule associated with the attribute value to be analyzed.

[0059] In an embodiment of the present application, the current execution end obtains a source-end system backtracking rule associated with the attribute value to be analyzed, wherein the source-end system backtracking rule is used to represent a method of backtracking the source-end system anomaly of the attribute value to be analyzed using the control variable method. For example, the actual cause of the metering anomaly is a process problem of the installer, but due to the objective laws of procurement and supply, a batch of electric energy meters are generated by the same manufacturer, with the same specifications, the same production batch, and even the geographical locations of the installations are relatively close. In this case, the determined attribute values ​​to be analyzed include attribute values ​​of the same manufacturer, the same specifications, the same batch, and the same installation location. Then, the associated source-end system backtracking rule can be to obtain monitoring data of electric energy meters with the same manufacturer, the same production batch, and the same specifications, but installed in different power units, and determine whether there are any anomalies or an increase in the anomaly rate; or to obtain monitoring data of electric energy meters with the same installation location, the same manufacturer, and the same specifications, but with different installation times, and determine whether there are any anomalies or an increase in the anomaly rate, etc. The embodiment of the present application does not limit the content of the source-end system backtracking rule.

[0060] 303. Determine whether the attribute value to be analyzed is an abnormal cause based on the source system backtracking rule, and delete the attribute value to be analyzed that does not correspond to an abnormal cause.

[0061] In an embodiment of the present application, the current execution end judges whether the attribute value to be analyzed is the cause of an abnormality based on the source end system backtracking rule, and deletes the attribute value to be analyzed corresponding to the abnormality cause. For example, if the source end system backtracking rule is used in step 302 to obtain monitoring data of electric energy meters with the same manufacturer, the same production batch, and the same specifications, but installed in different power units, and it is determined that the electric energy meters installed in different power units have no abnormalities, the attribute value corresponding to the installation location is deleted, and the cause of the abnormality of the electric energy meter caused by the installation location is excluded, that is, the attribute value corresponding to the installation location is not an abnormal cause; if the source end system backtracking rule is used in step 302 to obtain monitoring data of electric energy meters with the same installation location, the same manufacturer, and the same specifications, but different installation times, and it is determined that the monitoring data of electric energy meters with different installation times have no abnormalities, the attribute value corresponding to the installation time is deleted, and the cause of the abnormality of the electric energy meter caused by the installation time is excluded, that is, the attribute value corresponding to the installation time is not an abnormal cause, etc.

[0062] In one embodiment, in order to quickly and accurately send warning information to relevant operation and maintenance parties, after analyzing the cause of the measurement anomaly based on the target case data and the aggregation degree, the method further includes:

[0063] Based on the cause of the measurement anomaly, the measurement anomaly is risk graded according to a preset classification and grading strategy to obtain a measurement anomaly risk level; when the measurement anomaly risk level exceeds the risk level threshold, a language model is used to generate risk warning information; and the risk warning information is sent to the relevant operation and maintenance party through a preset risk warning interface.

[0064] In an embodiment of the present application, the current execution end classifies the risk of the metering anomaly based on the cause of the metering anomaly and in accordance with a preset classification and grading strategy to obtain the metering anomaly risk level. For example, the metering anomaly risk is divided into level one, level two, level three, etc. according to factors such as the potential risk range, the degree of harmfulness, and the size of the impact range. The embodiment of the present application does not limit the method of dividing the metering anomaly risk level. The current execution end compares the metering anomaly risk level with the set risk level threshold. When the metering anomaly risk level exceeds the risk level threshold, a language model is used to generate risk warning information. For example, when the metering anomaly risk level is level three and exceeds the risk level threshold, a risk warning information is generated. The embodiment of the present application does not limit the set risk level threshold. The current execution end obtains a pre-configured risk warning interface and sends the risk warning information to the relevant operation and maintenance party through the risk warning interface. Among them, the risk warning interface is used to characterize the network interface of the peripheral communication unit that completes data communication in a wired or wireless manner. The peripheral communication unit is responsible for performing the necessary transcoding of warning information and control commands, and for transmitting them to external devices such as system servers, monitoring screens, data collection terminals, energy meters, operation terminals, handheld devices, and staff mobile phones through appropriate communication methods, while ensuring data transmission quality. When the transmission channel involves public networks or external network devices, data desensitization or encryption should be performed as required.

[0065] In addition to the risk warning methods described in the above embodiments, other methods for risk warnings include system prompts, screen pop-ups, emails, and phone calls. In addition to sending warnings, the current execution end can also access and temporarily store risk information in the system, and then include it in the abnormal case database after the cause of the problem is verified.

[0066] The embodiment of the present application provides a method for analyzing metering anomalies. Compared with the related art, the present application obtains primary analysis data obtained through source system analysis, and determines at least one data filtering rule based on the primary analysis data; filters the monitoring data of the source system based on the data filtering rule to obtain target metering anomaly data; compares and analyzes the target metering anomaly data with pre-configured abnormal case data, and determines at least one target case data from the abnormal case data; performs multi-dimensional clustering analysis on the target metering anomaly data to obtain the aggregation degree of the target metering anomaly data in multiple data dimensions; and analyzes the cause of metering anomalies based on the target case data and the aggregation degree, thereby realizing the analysis of the cause of power metering anomalies. The present application utilizes the primary analysis data obtained by the indicator calculation in the related art to obtain source data of more dimensions, which not only expands the analysis dimension but also reduces the amount of data obtained from the source system. The present application adopts a method that combines case matching and cluster analysis on the source system data to improve the accuracy of the analysis and judgment of metering anomaly problems under the joint action of multiple factors.

[0067] As an implementation of the method shown in FIG1 , an embodiment of the present application provides a device for analyzing measurement anomalies, as shown in FIG4 , which includes:

[0068] The filtering rule determination module 41 is configured to obtain primary analysis data obtained through analysis by the source system and determine at least one data filtering rule based on the primary analysis data; the data acquisition module 42 is configured to filter the monitoring data of the source system based on the data filtering rule to obtain target measurement abnormality data; the case determination module 43 is configured to compare and analyze the target measurement abnormality data with pre-configured abnormal case data and determine at least one target case data from the abnormal case data; the cause analysis module 44 is configured to perform multidimensional clustering analysis on the target measurement abnormality data to obtain the aggregation degree of the target measurement abnormality data in multiple data dimensions; and analyze the cause of the measurement abnormality based on the target case data and the aggregation degree.

[0069] The primary analysis data includes at least one key indicator deviation item; the filtering rule determination module 41 is further configured to:

[0070] Obtain a mapping relationship between key indicators and indicator association information, and determine the target indicator association information corresponding to the key indicator deviation item based on the mapping relationship; obtain the time period in which the key indicator deviation item is generated, and determine the data filtering rule based on the time period and the target indicator association information.

[0071] As shown in FIG5 , the device further includes a data cleaning module 45 configured to:

[0072] performing data logic verification on the target metering abnormal data, and deleting the target metering abnormal data that does not conform to data logic; and / or performing data consistency verification on the target metering abnormal data, and deleting the target metering abnormal data that does not conform to data consistency.

[0073] The case determination module 43 is further configured to:

[0074] Acquire case attribute information of the abnormal case data, match the case attribute information with the to-be-matched attribute information of the target measurement abnormal data, and determine the target attribute information from the to-be-matched attribute information; perform similarity calculation based on the attribute value corresponding to the target attribute information and the attribute value corresponding to the case attribute information, and determine the abnormal case data corresponding to the case attribute information with a similarity higher than a threshold as the target case data.

[0075] The cause analysis module 44 is further configured to:

[0076] Acquire an attribute value corresponding to a single attribute information in the target measurement abnormal data; perform cluster analysis on the attribute value using a cluster analysis model to obtain a degree of aggregation on a single data dimension; and merge the degrees of aggregation on the single data dimension to obtain degrees of aggregation on multiple data dimensions.

[0077] As shown in FIG5 , the apparatus further includes an exception backtracking module 46 configured to:

[0078] The aggregation degrees on at least one data dimension are sorted in descending order, and the attribute value to be analyzed with the highest aggregation degree on each data dimension is obtained; a source-end system backtracking rule associated with the attribute value to be analyzed is obtained, wherein the source-end system backtracking rule is used to characterize a method of performing source-end system anomaly backtracking on the attribute value to be analyzed using a control variable method; based on the source-end system backtracking rule, whether the attribute value to be analyzed is an abnormal cause is judged, and the attribute value to be analyzed corresponding to a non-abnormal cause is deleted.

[0079] As shown in FIG5 , the device further includes an abnormality warning module 47 configured to:

[0080] Based on the cause of the measurement anomaly, the measurement anomaly is risk graded according to a preset classification and grading strategy to obtain a measurement anomaly risk level; when the measurement anomaly risk level exceeds the risk level threshold, a language model is used to generate risk warning information; and the risk warning information is sent to the relevant operation and maintenance party through a preset risk warning interface.

[0081] The embodiment of the present application provides an analysis device for metering anomalies. Compared with the related art, the present application obtains primary analysis data obtained through source system analysis, and determines at least one data filtering rule based on the primary analysis data; filters the monitoring data of the source system based on the data filtering rule to obtain target metering anomaly data; compares and analyzes the target metering anomaly data with pre-configured abnormal case data, and determines at least one target case data from the abnormal case data; performs multi-dimensional clustering analysis on the target metering anomaly data to obtain the aggregation degree of the target metering anomaly data in multiple data dimensions; and analyzes the cause of metering anomalies based on the target case data and the aggregation degree, thereby realizing the analysis of the cause of power metering anomalies. The present application utilizes the primary analysis data obtained by the indicator calculation in the related art to obtain source data of more dimensions, which not only expands the analysis dimension but also reduces the amount of data obtained from the source system. The present application adopts a method that combines case matching and cluster analysis on the source system data to improve the accuracy of the analysis and judgment of metering anomalies under the joint action of multiple factors.

[0082] According to one embodiment of the present application, a storage medium is provided, wherein the storage medium stores at least one executable instruction. The computer-executable instruction can execute the measurement anomaly analysis method in any of the above method embodiments.

[0083] FIG6 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. The embodiment of the present application does not limit the implementation of the computer device.

[0084] As shown in FIG. 6 , the computer device may include a processor 602 , a communications interface 604 , a memory 606 , and a communication bus 608 .

[0085] The processor 602 , the communication interface 604 , and the memory 606 communicate with each other via a communication bus 608 .

[0086] The communication interface 604 is configured to communicate with other devices such as clients or other servers.

[0087] The processor 602 is configured to execute the program 610 and can perform the relevant steps of the above-mentioned measurement anomaly analysis method.

[0088] The program 610 may include program codes including computer operating instructions.

[0089] Processor 602 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. The one or more processors included in a computer device may be processors of the same type, such as one or more CPUs, or may be processors of different types, such as one or more CPUs and one or more ASICs.

[0090] The memory 606 is configured to store the program 610. The memory 606 may include a high-speed random access memory (RAM) memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0091] The program 610 may be configured to cause the processor 602 to perform the following operations:

[0092] Acquire primary analysis data obtained through source-end system analysis, and determine at least one data filtering rule based on the primary analysis data; perform filtering operations on the monitoring data of the source-end system based on the data filtering rules to obtain target measurement anomaly data; compare and analyze the target measurement anomaly data with pre-configured abnormal case data, and determine at least one target case data from the abnormal case data; perform multidimensional clustering analysis on the target measurement anomaly data to obtain aggregation degrees of the target measurement anomaly data in multiple data dimensions; and analyze the cause of the measurement anomaly based on the target case data and the aggregation degrees.

[0093] Those skilled in the art will appreciate that the aforementioned multiple modules or multiple steps of the present application can be implemented using a general-purpose computing device, can be centralized on a single computing device, or can be distributed across a network of multiple computing devices, can be implemented using program code executable by the computing device, and thus can be stored in a storage device and executed by the computing device, and in some cases, can be performed in a different order than that shown or described herein, or can be fabricated into multiple integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module for implementation. Thus, the present application is not limited to any particular combination of hardware and software.

Claims

1. A method for analyzing measurement anomalies, comprising: Acquire primary analysis data obtained through analysis by the source end system, and determine at least one data filtering rule based on the primary analysis data; Performing a filtering operation on the monitoring data of the source end system based on the data filtering rule to obtain target measurement abnormal data; Comparing and analyzing the target measurement abnormal data with pre-configured abnormal case data, and determining at least one target case data from the abnormal case data; Perform multidimensional cluster analysis on the target measurement anomaly data to obtain the aggregation degree of the target measurement anomaly data in multiple data dimensions; and analyze the cause of measurement anomaly based on the target case data and the aggregation degree.

2. The method according to claim 1, wherein: The primary analysis data includes at least one key indicator deviation item; The determining at least one data filtering rule based on the preliminary analysis data comprises: Acquire a mapping relationship between key indicators and indicator association information, and determine target indicator association information corresponding to the key indicator deviation item based on the mapping relationship; The time period in which the key indicator deviation item is generated is obtained, and the data filtering rule is determined based on the time period and the target indicator association information.

3. The method according to claim 1, after filtering the monitoring data of the source system based on the data filtering rule to obtain target measurement abnormal data, further comprises at least one of the following: Performing data logic verification on the target measurement abnormal data, and deleting the target measurement abnormal data that does not conform to the data logic; The target measurement abnormal data is subjected to data consistency verification processing, and the target measurement abnormal data that does not meet the data consistency is deleted.

4. The method according to claim 1, wherein: The comparing and analyzing the target measurement abnormal data with the pre-configured abnormal case data and determining at least one target case data from the abnormal case data includes: Acquire case attribute information of the abnormal case data, and match the case attribute information with the to-be-matched attribute information of the target measurement abnormal data, and determine the target attribute information from the to-be-matched attribute information; Based on the attribute value corresponding to the target attribute information and the attribute value corresponding to the case attribute information A similarity calculation is performed, and the abnormal case data corresponding to the case attribute information with a similarity higher than a threshold is determined as the target case data.

5. The method according to claim 1, wherein: The performing multidimensional cluster analysis on the target measurement abnormal data to obtain the aggregation degree of the target measurement abnormal data in multiple data dimensions includes: Obtaining an attribute value corresponding to a single attribute information in the target measurement abnormal data; Performing cluster analysis on the attribute values ​​using a cluster analysis model to obtain a degree of aggregation on the single data dimension; The aggregation degrees on a single data dimension are combined to obtain the aggregation degrees on multiple data dimensions.

6. The method according to claim 1, after performing multidimensional cluster analysis on the target measurement abnormal data to obtain the aggregation degree of the target measurement abnormal data in multiple data dimensions, further comprises: The aggregation degrees on at least one data dimension are sorted in descending order, and the attribute value to be analyzed with the highest aggregation degree on each data dimension is obtained; Acquire a source end system backtracking rule associated with the attribute value to be analyzed, wherein the source end system backtracking rule is used to characterize a method of performing source end system abnormality backtracking on the attribute value to be analyzed by using a control variable method; Based on the source system backtracking rule, it is judged whether the attribute value to be analyzed is an abnormal cause, and the attribute value to be analyzed corresponding to the non-abnormal cause is deleted.

7. The method according to any one of claims 1 to 6, further comprising: after analyzing the cause of measurement anomaly based on the target case data and the aggregation degree: Based on the causes of the measurement anomaly, the measurement anomaly is risk graded according to a preset classification and grading strategy to obtain a measurement anomaly risk level; When the measurement abnormality risk level exceeds the risk level threshold, a language model is used to generate risk warning information; The risk warning information is sent to the operation and maintenance party through a preset risk warning interface.

8. A device for analyzing measurement anomalies, comprising: A filtering rule determination module, configured to obtain primary analysis data obtained through analysis by a source end system, and determine at least one data filtering rule based on the primary analysis data; A data acquisition module, configured to filter the monitoring data of the source system based on the data filtering rule to obtain target measurement abnormal data; a case determination module, configured to compare and analyze the target measurement abnormal data with pre-configured abnormal case data, and determine at least one target case data from the abnormal case data; The cause analysis module is configured to perform multidimensional cluster analysis on the target measurement abnormality data to obtain the aggregation degree of the target measurement abnormality data in multiple data dimensions; and analyze the cause of the measurement abnormality based on the target case data and the aggregation degree.

9. A storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction executes the measurement abnormality analysis method according to any one of claims 1 to 7.

10. A computer device, comprising a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is configured to store at least one executable instruction, and the executable instruction enables the processor to execute the measurement anomaly analysis method according to any one of claims 1-7.

Images