Power grid service interaction data early warning method and system based on big data and medium
Through big data analysis, identify abnormalities in power grid service interaction data, calculate the abnormality index and early warning level, solve the problem of difficult to detect abnormal network service interaction data in smart grid, and realize real-time, accurate and safe abnormal warning of power grid service interaction data. .
Patent Information
- Application Number
- CN202411064904.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-29
AI Technical Summary
It is difficult to detect abnormal network service interaction data in smart power grids in real time, accurately and safely, making it difficult to identify potential risks in a timely manner.
Using the power grid business interaction data early warning method based on big data, by obtaining power grid business data and financial data, conducting coordinated processing and logging, identifying abnormal information, extracting attribute information and feature data, calculating the abnormality index and early warning level, and realizing Anomaly warning of power grid business interaction data.
It improves the real-time and accuracy of power grid business interaction data, can timely identify potential risks, and meets the security requirements of power grid business interaction data.
Smart Images

Figure CN119047622A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of power grid business interaction, and in particular to a power grid business interaction data early warning method, system and medium based on big data. Background Art
[0002] Smart grids are in a stage of rapid development, and the operating environment is becoming increasingly complex. The amount of interactive data in power grid services is growing exponentially. Currently, interactive data anomalies are mainly discovered manually by operation and maintenance personnel, which makes it difficult to meet the requirements of real-time, accuracy and security, and it is difficult to detect potential interactive data risks in a timely manner.
[0003] In view of the above problems, effective technical solutions are urgently needed. Summary of the invention
[0004] The purpose of this application is to provide a big data-based power grid business interaction data early warning method, system and medium, which can obtain interaction data anomalies by weighting the obtained power grid business interaction log information, thereby realizing the technology of early warning of power grid business interaction data anomalies.
[0005] The present application also provides a big data-based power grid business interaction data early warning method, comprising the following steps:
[0006] Obtain the grid business data and grid financial data of the grid within a preset time period, and perform business-finance interaction processing and log recording and information recording through a preset business-finance collaboration system, and extract the business interaction log information of the recorded log;
[0007] Identify abnormal information of the business interaction log information through a preset business interaction state identification model, and obtain abnormal log information of power grid business interaction within the preset time period;
[0008] Extracting attribute information according to the abnormal log information of the power grid business interaction to obtain attribute information of each log item and corresponding weight value of each item;
[0009] Perform feature category identification on the power grid business interaction abnormality log information, obtain interaction abnormality category feature data corresponding to each log sub-item information, and perform a comparison query through a preset category feature weight mapping relationship table to obtain the corresponding sub-item feature weight coefficient;
[0010] Extracting power grid business interaction abnormality data according to the power grid business interaction abnormality log information;
[0011] The grid business interaction abnormality data is processed in combination with the corresponding sub-item weight values and sub-item feature weight coefficients to obtain the grid business interaction abnormality index and warning level of the grid within the preset time period.
[0012] Optionally, in the big data-based power grid business interaction data early warning method described in the present application, the obtaining of power grid business data and power grid financial data within a preset time period, and performing business-finance interaction processing and log recording and information recording through a preset business-finance collaboration system, and extracting business interaction log information of the recorded log include:
[0013] Obtaining grid business data and grid financial data within a preset time period;
[0014] Inputting the power grid business data and power grid financial data into a preset business-finance collaboration system for business-finance interaction processing and log recording, and recording information;
[0015] Extract the business interaction log information recorded in the log, including permission interaction information, document integration interaction information, business attribution interaction information, account mapping interaction information and data link interaction information.
[0016] Optionally, in the big data-based power grid business interaction data early warning method described in the present application, the abnormal information identification of the business interaction log information by using a preset business interaction state identification model, and obtaining the abnormal log information of the power grid business interaction within the preset time period, includes:
[0017] Inputting the business interaction log information into a preset business interaction state recognition model to identify abnormal information;
[0018] The abnormal log information of power grid business interaction within the preset time period is obtained, including asymmetric information of authority interaction, interruption information of document integration interaction, conflict information of business attribution interaction, error information of account mapping interaction and disconnection information of data link interaction.
[0019] Optionally, in the big data-based power grid business interaction data early warning method described in the present application, the extracting of attribute information according to the power grid business interaction abnormality log information to obtain each log item attribute information and corresponding item weight value includes:
[0020] Extracting attribute information of each item from the asymmetric information of authority interaction, the interruption information of document integration interaction, the conflict information of business attribution interaction, the error information of account mapping interaction, and the disconnection information of data link interaction, and obtaining the log item attribute information corresponding to each log item information in the business interaction log information;
[0021] The log item attribute information includes keywords, user name, error code, operator, organization and timestamp;
[0022] Each of the log item attribute information is queried through a preset attribute weight mapping relationship table to obtain the item weight value corresponding to each of the log item attribute information.
[0023] Optionally, in the big data-based power grid business interaction data early warning method described in the present application, the feature category identification of the power grid business interaction abnormality log information is performed to obtain the interaction abnormality category feature data corresponding to each log sub-item information, and a comparison query is performed through a preset category feature weight mapping relationship table to obtain the corresponding sub-item feature weight coefficient, including:
[0024] Inputting the power grid business interaction abnormality log information into a preset interaction abnormality category recognition model for feature category recognition, and obtaining interaction abnormality category feature data corresponding to each log item information, including error code feature data and stack feature data;
[0025] According to the error code feature data and the stack feature data, a comparison query is performed through a preset category feature weight mapping relationship table to obtain the sub-item feature weight coefficients corresponding to each log sub-item information.
[0026] Optionally, in the big data-based power grid business interaction data early warning method described in the present application, the extracting power grid business interaction abnormality data according to the power grid business interaction abnormality log information includes:
[0027] According to the power grid business interaction abnormality log information, power grid business interaction abnormality data is extracted, including authority interaction failure rate data, document integration interaction interruption rate data, business attribution interaction mismatch data, account mapping interaction error rate data and data link interaction missing rate data.
[0028] Optionally, in the big data-based power grid business interaction data early warning method described in the present application, the power grid business interaction abnormality data is processed in combination with the corresponding sub-item weight value and the sub-item feature weight coefficient to obtain the power grid business interaction abnormality index and early warning level of the power grid within the preset time period, including:
[0029] The power grid business interaction abnormality data is combined with the corresponding sub-item weight value and the sub-item feature weight coefficient and input into a preset business interaction abnormality detection model for processing to obtain a power grid business interaction abnormality index of the power grid within the preset time period;
[0030] The warning level is determined according to the threshold range to which the power grid service interaction abnormality index belongs, including a first-level warning, a second-level warning or a third-level warning.
[0031] Optionally, in the big data-based power grid business interaction data early warning method described in the present application, it also includes:
[0032] Compare the multiple log item attribute information corresponding to each log item information in the business interaction log information with the item attribute comparison information in the preset log item attribute information library, and mark one or more log item attribute information that does not match the log item attribute information in the log item attribute information library as marked log item attribute information;
[0033] Comparing the marked log item attribute information with the corresponding item attribute comparison information by using a preset similarity comparison method to obtain a corresponding similarity;
[0034] Performing a threshold comparison based on the similarity and a preset similarity threshold, and determining whether the attributes are associated based on the threshold comparison result;
[0035] If the threshold comparison result meets the requirements, the attributes are associated;
[0036] If the threshold comparison result does not meet the requirements, it is not attribute association, and the corresponding sub-item weight value of the corresponding log sub-item attribute information is corrected.
[0037] In a second aspect, the present application provides a power grid business interaction data early warning system based on big data, the system comprising: a memory and a processor, the memory comprising a program of a power grid business interaction data early warning method based on big data, and the program of the power grid business interaction data early warning method based on big data is executed by the processor to implement the following steps:
[0038] Obtain the grid business data and grid financial data of the grid within a preset time period, and perform business-finance interaction processing and log recording and information recording through a preset business-finance collaboration system, and extract the business interaction log information of the recorded log;
[0039] Identify abnormal information of the business interaction log information through a preset business interaction state identification model, and obtain abnormal log information of power grid business interaction within the preset time period;
[0040] Extracting attribute information according to the abnormal log information of the power grid business interaction to obtain attribute information of each log item and corresponding weight value of each item;
[0041] Perform feature category identification on the power grid business interaction abnormality log information, obtain interaction abnormality category feature data corresponding to each log item information, and perform a comparison query through a preset category feature weight mapping relationship table to obtain the corresponding item feature weight coefficient;
[0042] Extracting power grid business interaction abnormality data according to the power grid business interaction abnormality log information;
[0043] The grid business interaction abnormality data is processed in combination with the corresponding sub-item weight values and sub-item feature weight coefficients to obtain the grid business interaction abnormality index and warning level of the grid within the preset time period.
[0044] In the third aspect, the present application also provides a computer-readable storage medium, which stores a big data-based power grid business interaction data early warning method program. When the big data-based power grid business interaction data early warning method program is executed by a processor, the steps of the big data-based power grid business interaction data early warning method as described in any one of the above items are implemented.
[0045] As can be seen from the above, the big data-based power grid business interaction data early warning method, system and medium provided in the present application input the preset business-finance collaboration system into the preset business-finance interaction processing according to the power grid business data and financial data within the preset time period, extract the business interaction log information, and identify the interaction abnormality log information, extract the sub-item attribute information of each log and the corresponding sub-item weight value, and perform feature category identification to obtain the interaction abnormality category feature data and the corresponding sub-item feature weight coefficient, and then extract the interaction abnormality log information to obtain the interaction abnormality data, and process the power grid business interaction abnormality data in combination with the corresponding sub-item weight value and the sub-item feature weight coefficient to obtain the power grid business interaction abnormality index and early warning level; thereby, the interaction data abnormality is obtained by performing weight calculation on the obtained power grid business interaction log information, and the technology of abnormal early warning of power grid business interaction data is realized.
[0046] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0048] Figure 1 A flowchart of a big data-based power grid business interaction data early warning method provided in an embodiment of the present application;
[0049] Figure 2 A flowchart of obtaining business interaction log information of a power grid business interaction data early warning method based on big data provided in an embodiment of the present application;
[0050] Figure 3 A flowchart of obtaining abnormal log information of power grid business interaction in a power grid business interaction data early warning method based on big data provided in an embodiment of the present application;
[0051] Figure 4 A flowchart of obtaining a power grid business interaction anomaly index and a warning level for a power grid business interaction data warning method based on big data provided in an embodiment of the present application. DETAILED DESCRIPTION
[0052] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.
[0053] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0054] Please refer to Figure 1 , Figure 1 The flowchart of the power grid business interaction data early warning method based on big data in some embodiments of the present application. The power grid business interaction data early warning method based on big data is used in terminal devices, such as computers, mobile phone terminals, etc. The power grid business interaction data early warning method based on big data includes the following steps:
[0055] S11, obtaining the grid business data and grid financial data of the grid within a preset time period, and performing business-finance interaction processing and log recording and information recording through a preset business-finance collaboration system, and extracting the business interaction log information of the recorded log;
[0056] S12, identifying abnormal information of the business interaction log information through a preset business interaction state identification model, and obtaining abnormal log information of power grid business interaction within the preset time period;
[0057] S13, extracting attribute information according to the abnormal log information of the power grid business interaction, and obtaining attribute information of each log item and corresponding weight value of each item;
[0058] S14, identifying the feature category of the abnormal interaction log information of the power grid business, obtaining the abnormal interaction category feature data corresponding to each log item information, and performing a comparison query through a preset category feature weight mapping relationship table to obtain the corresponding item feature weight coefficient;
[0059] S15, extracting power grid business interaction abnormality data according to the power grid business interaction abnormality log information;
[0060] S16. Process the power grid service interaction abnormality data in combination with the corresponding sub-item weight values and sub-item feature weight coefficients to obtain a power grid service interaction abnormality index and a warning level within the preset time period.
[0061] It should be noted that during the preset time period, the power grid business data and financial data are interactively processed in the preset business-finance collaboration system, which will generate a large amount of data. Data collection is carried out through real-time online monitoring technology, and the data is pre-processed. The interaction abnormality log information is obtained through the preset business interaction status recognition model, and then the sub-item attribute information of the abnormal log information is extracted, and the corresponding sub-item weight value is queried. At the same time, the category feature data of the abnormal log information is identified, and the corresponding weight coefficient is queried. Finally, the interaction abnormality index is calculated by combining the obtained interaction abnormality data with the weight value and weight coefficient, and then the warning level is determined according to the range level of the interaction abnormality index, and it is sent to the corresponding person in charge for processing.
[0062] Please refer to Figure 2 , Figure 2 The present invention is a flowchart of obtaining business interaction log information of a method for early warning of power grid business interaction data based on big data in some embodiments of the present application. According to an embodiment of the present invention, the acquisition of power grid business data and power grid financial data within a preset time period, and the business and financial interaction processing and log recording and information recording through a preset business and financial collaboration system, and the extraction of business interaction log information of the recorded log include:
[0063] S21, obtaining power grid business data and power grid financial data within a preset time period;
[0064] S22, inputting the power grid business data and power grid financial data into a preset business-finance collaboration system for business-finance interaction processing and log recording, and recording information;
[0065] S23. Extract the business interaction log information recorded in the log, including authority interaction information, document integration interaction information, business attribution interaction information, account mapping interaction information and data link interaction information.
[0066] It should be noted that the power grid business data and financial data over a period of time are input into the preset business-finance collaboration system for interactive processing, and information about the processing process is recorded, such as the interaction process, interaction status and interaction data, and business interaction log information is extracted based on the recorded interaction information.
[0067] Please refer to Figure 3 , Figure 3 The present invention is a flowchart of obtaining abnormal log information of power grid business interaction in a method for early warning of power grid business interaction data based on big data in some embodiments of the present application. According to an embodiment of the present invention, the abnormal information of the business interaction log information is identified by a preset business interaction state identification model, and the abnormal log information of the power grid business interaction within the preset time period is obtained, including:
[0068] S31, inputting the business interaction log information into a preset business interaction state recognition model to identify abnormal information;
[0069] S32. Obtain abnormal log information of power grid business interactions within the preset time period, including information on asymmetric authority interactions, information on interruption of document integration interactions, information on conflict of business attribution interactions, information on account mapping interaction errors, and information on disconnection of data links interactions.
[0070] It should be noted that the interaction exception log information is extracted from the interaction log information, among which the asymmetric interaction information of authority means that the person in charge does not have the business document authority, the document integration interaction interruption information means that the document integration process cannot be found, the business attribution interaction conflict information means that the unit to which the business master data belongs is inconsistent with the unit where the business occurs, the account mapping interaction error information means that the mapping between the user account and the employee is incorrect, and the data chain interaction broken chain information means that the master data mapping is missing.
[0071] According to an embodiment of the present invention, the extracting of attribute information according to the abnormal log information of the power grid business interaction to obtain attribute information of each log item and a corresponding weight value of each item includes:
[0072] Extracting attribute information of each item from the asymmetric information of authority interaction, the interruption information of document integration interaction, the conflict information of business attribution interaction, the error information of account mapping interaction, and the disconnection information of data link interaction, and obtaining the log item attribute information corresponding to each log item information in the business interaction log information;
[0073] The log item attribute information includes keywords, user name, error code, operator, organization and timestamp;
[0074] Each of the log item attribute information is queried through a preset attribute weight mapping relationship table to obtain the item weight value corresponding to each of the log item attribute information.
[0075] It should be noted that the corresponding attribute information of each sub-item log information in the obtained interaction abnormality log information is extracted respectively, and the sub-item weight value corresponding to the log sub-item attribute information of each sub-project log information is queried according to the preset relationship table, that is, the weight values corresponding to the sub-item log information of the authority interaction asymmetric information, document integration interaction interruption information, business attribution interaction conflict information, account mapping interaction error information and data link interaction disconnection information in the power grid business interaction abnormality log information.
[0076] According to an embodiment of the present invention, the feature category identification of the power grid business interaction abnormality log information is performed to obtain the interaction abnormality category feature data corresponding to the sub-item log information, and the corresponding sub-item feature weight coefficient is obtained by performing a comparison query through a preset category feature weight mapping relationship table, including:
[0077] Inputting the power grid service interaction abnormality log information into a preset interaction abnormality category recognition model for feature category recognition, and obtaining interaction abnormality category feature data corresponding to the sub-item log information, including error code feature data and stack feature data;
[0078] According to the error code feature data and the stack feature data, a comparison query is performed through a preset category feature weight mapping relationship table to obtain the sub-item feature weight coefficients corresponding to each log sub-item information.
[0079] It should be noted that the preset interaction exception category recognition model is used to identify each sub-item log information in the obtained interaction exception log information, and the corresponding interaction exception category feature data is obtained. The corresponding weight coefficient of the interaction exception category feature data corresponding to each sub-item log information is queried through the mapping relationship table, that is, the corresponding weight coefficient is queried through the feature data of the error code and the stack.
[0080] According to an embodiment of the present invention, extracting power grid service interaction abnormality data according to the power grid service interaction abnormality log information includes:
[0081] According to the power grid business interaction abnormality log information, power grid business interaction abnormality data is extracted, including authority interaction failure rate data, document integration interaction interruption rate data, business attribution interaction mismatch data, account mapping interaction error rate data and data link interaction missing rate data.
[0082] It should be noted that the power grid business interaction abnormality data in the interaction abnormality log information is extracted to provide data support for the subsequent judgment of the interaction status.
[0083] Please refer to Figure 4 , Figure 4The present invention is a flowchart of obtaining a power grid business interaction abnormality index and a warning level of a power grid business interaction data warning method based on big data in some embodiments of the present application. According to an embodiment of the present invention, the power grid business interaction abnormality data is processed in combination with the corresponding sub-item weight value and the sub-item feature weight coefficient to obtain the power grid business interaction abnormality index and the warning level of the power grid within the preset time period, including:
[0084] S41, combining the power grid service interaction abnormality data with the corresponding sub-item weight value and the sub-item feature weight coefficient and inputting them into a preset service interaction abnormality detection model for processing, to obtain a power grid service interaction abnormality index within the preset time period;
[0085] S42. Determine a warning level according to the threshold range to which the power grid service interaction abnormality index belongs, including a first-level warning, a second-level warning, or a third-level warning.
[0086] It should be noted that, by obtaining the abnormal data of power grid business interaction corresponding to each sub-item log information, combining the sub-item weight value and the sub-item feature weight coefficient corresponding to each sub-item log information, and using the calculation formula of the preset business interaction abnormality detection model, the power grid business interaction abnormality index within the preset time period is obtained;
[0087] The business interaction abnormality detection calculation formula is:
[0088]
[0089] Among them, δ gP is the power grid business interaction abnormality index, F d is the permission interaction failure rate data, I r Integrate the interaction interruption rate data for the document, M s is the business attribution interaction mismatch data, E h is the account mapping interaction error rate data, P g is the data link interaction missing degree data, s a1 、s a2 、s a3 、s a4 、s a5 The weight values of the sub-items corresponding to the permission interaction failure rate data, document integration interaction interruption rate data, business attribution interaction mismatch data, account mapping interaction error rate data, and data link interaction missing degree data are θ. z1 ,θ z2 ,θ z3 ,θ z4 ,θ z5They are the sub-item weight coefficients corresponding to the permission interaction failure rate data, document integration interaction interruption rate data, business attribution interaction mismatch data, account mapping interaction error rate data, and data link interaction missing rate data. The preset characteristic coefficient is obtained by querying the preset power grid industry-finance collaborative interaction database;
[0090] In this embodiment, the threshold setting range of the power grid business interaction abnormality index is [0, 0.3), [0.3, 0.7], (0.7, 1], corresponding to the third-level warning, the second-level warning and the first-level warning respectively, among which the first-level warning is the highest level warning. For example, if the power grid business interaction abnormality index within the preset time period is 0.4, the second-level warning is activated.
[0091] According to an embodiment of the present invention, it also includes:
[0092] Compare the multiple log item attribute information corresponding to each log item information in the business interaction log information with the item attribute comparison information in the preset log item attribute information library, and mark one or more log item attribute information that does not match the log item attribute information in the log item attribute information library as marked log item attribute information;
[0093] Comparing the marked log item attribute information with the corresponding item attribute comparison information by using a preset similarity comparison method to obtain a corresponding similarity;
[0094] Performing a threshold comparison based on the similarity and a preset similarity threshold, and determining whether the attributes are associated based on the threshold comparison result;
[0095] If the threshold comparison result meets the requirements, the attributes are associated;
[0096] If the threshold comparison result does not meet the requirements, it is not attribute association, and the corresponding sub-item weight value of the corresponding log sub-item attribute information is corrected.
[0097] It should be noted that if the preset log sub-item attribute information does not contain the log sub-item attribute information, it will be used as a marked log sub-item attribute information, and the correlation degree will be calculated to determine whether there is a correlation with the log sub-item attribute information in the preset log sub-item attribute information library. If there is a correlation, the correlation score will be calculated to correct the power grid business interaction abnormality index within the preset time period. If there is no correlation, it means that new sub-item attribute information appears in the abnormal interaction log information, and the preset log sub-item attribute information library will be corrected.
[0098] It is worth mentioning that, according to the example of the present invention, the step of matching the marked log item attribute information with the log item attribute information in the preset log item attribute information library one by one to obtain the corresponding correlation degree includes:
[0099] Obtaining stack feature data corresponding to the marked log item attribute information;
[0100] Obtain the total number of occurrences of the marked log item attribute information and the log item attribute information in the power grid business interaction abnormality log information;
[0101] Obtain the number of times the marked log item attribute information and the log item attribute information appear simultaneously in the same stack;
[0102] Compare the number of times with the total number of times to obtain a correlation coefficient;
[0103] The correlation coefficient is compared with a preset correlation threshold, and the corresponding correlation is determined according to the comparison result, including whether there is a correlation or not.
[0104] It should be noted that the more abnormal log information of the power grid business interaction, the more accurate the correlation judgment. In this embodiment, the preset correlation thresholds are (0, 0.6), [0.6, 1], which correspond to the existence or non-existence of correlation, respectively. First, the stack feature data corresponding to the marked log sub-item attribute information is queried. For example, if it is in the first stack, the total number of times the marked log sub-item attribute information and the log sub-item attribute information appear in the first stack is 20, and the number of times the marked log sub-item attribute information and the log sub-item attribute information appear together is 15, then the correlation coefficient is 0.75, and the marked log sub-item attribute information and the log sub-item attribute information are correlated.
[0105] It is worth mentioning that the examples of the present invention also include:
[0106] Comparing and analyzing the interaction anomaly category feature data with a preset interaction anomaly category feature data set to obtain first coincidence degree data;
[0107] Compare the similarity between the keyword and a preset keyword library to obtain second coincidence data;
[0108] Performing weighted processing on the first coincidence data and the second coincidence data in combination with a first preset correction coefficient and a second preset correction coefficient to obtain third coincidence data;
[0109] The third coincidence data is compared with a preset coincidence threshold value, and if the third coincidence data is greater than the preset coincidence threshold value, a first-level warning response is activated.
[0110] It should be noted that by comparing the interaction abnormality category feature data and keywords, when the overlap reaches the threshold, it means that the interaction is seriously abnormal, and the first-level warning should be activated to immediately notify the relevant responsible person to handle it. In this embodiment, the preset overlap threshold is 0.5. For example, if the third overlap data is 0.6, the first-level warning response is activated;
[0111] The third coincidence data calculation formula is:
[0112]
[0113] Among them, C d3 is the third coincidence data, C d1 , C d2 are the first coincidence data and the second coincidence data respectively, μ1 and μ2 are the first preset correction coefficient and the second preset correction coefficient respectively, τ1 and τ2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset power grid industry-finance collaborative interaction database).
[0114] The present invention also discloses a power grid business interaction data early warning system based on big data, comprising a memory and a processor, wherein the memory comprises a power grid business interaction data early warning method program based on big data, and when the power grid business interaction data early warning method program based on big data is executed by the processor, the following steps are implemented:
[0115] Obtain the grid business data and grid financial data of the grid within a preset time period, and perform business-finance interaction processing and log recording and information recording through a preset business-finance collaboration system, and extract the business interaction log information of the recorded log;
[0116] Identify abnormal information of the business interaction log information through a preset business interaction state identification model, and obtain abnormal log information of power grid business interaction within the preset time period;
[0117] Extracting attribute information according to the abnormal log information of the power grid business interaction to obtain attribute information of each log item and corresponding weight value of each item;
[0118] Perform feature category identification on the power grid business interaction abnormality log information, obtain interaction abnormality category feature data corresponding to each log item information, and perform a comparison query through a preset category feature weight mapping relationship table to obtain the corresponding item feature weight coefficient;
[0119] Extracting power grid business interaction abnormality data according to the power grid business interaction abnormality log information;
[0120] The grid business interaction abnormality data is processed in combination with the corresponding sub-item weight values and sub-item feature weight coefficients to obtain the grid business interaction abnormality index and warning level of the grid within the preset time period.
[0121] It should be noted that during the preset time period, the power grid business data and financial data are interactively processed in the preset business-finance collaboration system, which will generate a large amount of data. Data collection is carried out through real-time online monitoring technology, and the data is pre-processed. The interaction abnormality log information is obtained through the preset business interaction status recognition model, and then the sub-item attribute information of the abnormal log information is extracted, and the corresponding sub-item weight value is queried. At the same time, the category feature data of the abnormal log information is identified, and the corresponding weight coefficient is queried. Finally, the interaction abnormality index is calculated by combining the obtained interaction abnormality data with the weight value and weight coefficient, and then the warning level is determined according to the range level of the interaction abnormality index, and it is sent to the corresponding person in charge for processing.
[0122] According to an embodiment of the present invention, the obtaining of power grid business data and power grid financial data within a preset time period, performing business-finance interaction processing and log recording and information recording through a preset business-finance collaboration system, and extracting business interaction log information of the recorded logs include:
[0123] Obtaining grid business data and grid financial data within a preset time period;
[0124] Inputting the power grid business data and power grid financial data into a preset business-finance collaboration system for business-finance interaction processing and log recording, and recording information;
[0125] Extract the business interaction log information recorded in the log, including permission interaction information, document integration interaction information, business attribution interaction information, account mapping interaction information and data link interaction information.
[0126] It should be noted that the power grid business data and financial data over a period of time are input into the preset business-finance collaboration system for interactive processing, and information about the processing process is recorded, such as the interaction process, interaction status and interaction data, and business interaction log information is extracted based on the recorded interaction information.
[0127] According to an embodiment of the present invention, the process of identifying abnormal information of the business interaction log information by using a preset business interaction state identification model and obtaining abnormal log information of power grid business interaction within the preset time period includes:
[0128] Inputting the business interaction log information into a preset business interaction state recognition model to identify abnormal information;
[0129] The abnormal log information of power grid business interaction within the preset time period is obtained, including asymmetric information of authority interaction, interruption information of document integration interaction, conflict information of business attribution interaction, error information of account mapping interaction and disconnection information of data link interaction.
[0130] It should be noted that the interaction exception log information is extracted from the interaction log information, among which the asymmetric interaction information of authority means that the person in charge does not have the business document authority, the document integration interaction interruption information means that the document integration process cannot be found, the business attribution interaction conflict information means that the unit to which the business master data belongs is inconsistent with the unit where the business occurs, the account mapping interaction error information means that the mapping between the user account and the employee is incorrect, and the data chain interaction broken chain information means that the master data mapping is missing.
[0131] According to an embodiment of the present invention, the extracting of attribute information according to the abnormal log information of the power grid business interaction to obtain attribute information of each log item and a corresponding weight value of each item includes:
[0132] Extracting attribute information of each item from the asymmetric information of authority interaction, the interruption information of document integration interaction, the conflict information of business attribution interaction, the error information of account mapping interaction, and the disconnection information of data link interaction, and obtaining the log item attribute information corresponding to each log item information in the business interaction log information;
[0133] The log item attribute information includes keywords, user name, error code, operator, organization and timestamp;
[0134] Each of the log item attribute information is queried through a preset attribute weight mapping relationship table to obtain the item weight value corresponding to each of the log item attribute information.
[0135] It should be noted that the corresponding attribute information of each sub-item log information in the obtained interaction abnormality log information is extracted respectively, and the sub-item weight value corresponding to the log sub-item attribute information of each sub-project log information is queried according to the preset relationship table, that is, the weight values corresponding to the sub-item log information of the authority interaction asymmetric information, document integration interaction interruption information, business attribution interaction conflict information, account mapping interaction error information and data link interaction disconnection information in the power grid business interaction abnormality log information.
[0136] According to an embodiment of the present invention, the feature category identification of the power grid business interaction abnormality log information is performed to obtain the interaction abnormality category feature data corresponding to the sub-item log information, and the corresponding sub-item feature weight coefficient is obtained by performing a comparison query through a preset category feature weight mapping relationship table, including:
[0137] Inputting the power grid service interaction abnormality log information into a preset interaction abnormality category recognition model for feature category recognition, and obtaining interaction abnormality category feature data corresponding to the sub-item log information, including error code feature data and stack feature data;
[0138] According to the error code feature data and the stack feature data, a comparison query is performed through a preset category feature weight mapping relationship table to obtain the sub-item feature weight coefficients corresponding to each log sub-item information.
[0139] It should be noted that the preset interaction exception category recognition model is used to identify each sub-item log information in the obtained interaction exception log information, and the corresponding interaction exception category feature data is obtained. The corresponding weight coefficient of the interaction exception category feature data corresponding to each sub-item log information is queried through the mapping relationship table, that is, the corresponding weight coefficient is queried through the feature data of the error code and the stack.
[0140] According to an embodiment of the present invention, extracting power grid service interaction abnormality data according to the power grid service interaction abnormality log information includes:
[0141] According to the power grid business interaction abnormality log information, power grid business interaction abnormality data is extracted, including authority interaction failure rate data, document integration interaction interruption rate data, business attribution interaction mismatch data, account mapping interaction error rate data and data link interaction missing rate data.
[0142] It should be noted that the power grid business interaction abnormality data in the interaction abnormality log information is extracted to provide data support for the subsequent judgment of the interaction status.
[0143] According to an embodiment of the present invention, the abnormal data of power grid business interaction is processed in combination with the corresponding sub-item weight value and the sub-item feature weight coefficient to obtain the power grid business interaction abnormality index and warning level of the power grid within the preset time period, including:
[0144] The power grid business interaction abnormality data is combined with the corresponding sub-item weight value and the sub-item feature weight coefficient and input into a preset business interaction abnormality detection model for processing to obtain a power grid business interaction abnormality index of the power grid within the preset time period;
[0145] The warning level is determined according to the threshold range to which the power grid service interaction abnormality index belongs, including a first-level warning, a second-level warning or a third-level warning.
[0146] It should be noted that, by obtaining the abnormal data of power grid business interaction corresponding to each sub-item log information, combining the sub-item weight value and the sub-item feature weight coefficient corresponding to each sub-item log information, and using the calculation formula of the preset business interaction abnormality detection model, the power grid business interaction abnormality index within the preset time period is obtained;
[0147] The business interaction abnormality detection calculation formula is:
[0148]
[0149] Among them, δ gP is the power grid business interaction abnormality index, F d is the permission interaction failure rate data, I r Integrate the interaction interruption rate data for the document, M s is the business attribution interaction mismatch data, E h is the account mapping interaction error rate data, P g is the data link interaction missing degree data, s a1 、s a2 、s a3 、s a4 、s a5 The weight values of the sub-items corresponding to the permission interaction failure rate data, document integration interaction interruption rate data, business attribution interaction mismatch data, account mapping interaction error rate data, and data link interaction missing degree data are θ. z1 ,θ z2 ,θ z3 ,θ z4 ,θ z5 They are the sub-item weight coefficients corresponding to the permission interaction failure rate data, document integration interaction interruption rate data, business attribution interaction mismatch data, account mapping interaction error rate data, and data link interaction missing rate data. The preset characteristic coefficient is obtained by querying the preset power grid industry-finance collaborative interaction database;
[0150] In this embodiment, the threshold setting range of the power grid business interaction abnormality index is [0, 0.3), [0.3, 0.7], (0.7, 1], corresponding to the third-level warning, the second-level warning and the first-level warning respectively, among which the first-level warning is the highest level warning. For example, if the power grid business interaction abnormality index within the preset time period is 0.4, the second-level warning is activated.
[0151] According to an embodiment of the present invention, it also includes:
[0152] Compare the multiple log item attribute information corresponding to each log item information in the business interaction log information with the item attribute comparison information in the preset log item attribute information library, and mark one or more log item attribute information that does not match the log item attribute information in the log item attribute information library as marked log item attribute information;
[0153] Comparing the marked log item attribute information with the corresponding item attribute comparison information by using a preset similarity comparison method to obtain a corresponding similarity;
[0154] Performing a threshold comparison based on the similarity and a preset similarity threshold, and determining whether the attributes are associated based on the threshold comparison result;
[0155] If the threshold comparison result meets the requirements, the attributes are associated;
[0156] If the threshold comparison result does not meet the requirements, it is not attribute association, and the corresponding sub-item weight value of the corresponding log sub-item attribute information is corrected.
[0157] It should be noted that if the preset log sub-item attribute information does not contain the log sub-item attribute information, it will be used as a marked log sub-item attribute information, and the correlation degree will be calculated to determine whether there is a correlation with the log sub-item attribute information in the preset log sub-item attribute information library. If there is a correlation, the correlation score will be calculated to correct the power grid business interaction abnormality index within the preset time period. If there is no correlation, it means that new sub-item attribute information appears in the abnormal interaction log information, and the preset log sub-item attribute information library will be corrected.
[0158] It is worth mentioning that, according to the example of the present invention, the step of matching the marked log item attribute information with the log item attribute information in the preset log item attribute information library one by one to obtain the corresponding correlation degree includes:
[0159] Obtaining stack feature data corresponding to the marked log item attribute information;
[0160] Obtain the total number of occurrences of the marked log item attribute information and the log item attribute information in the power grid business interaction abnormality log information;
[0161] Obtain the number of times the marked log item attribute information and the log item attribute information appear simultaneously in the same stack;
[0162] Compare the number of times with the total number of times to obtain a correlation coefficient;
[0163] The correlation coefficient is compared with a preset correlation threshold, and the corresponding correlation is determined according to the comparison result, including whether there is a correlation or not.
[0164] It should be noted that the more abnormal log information of the power grid business interaction, the more accurate the correlation judgment. In this embodiment, the preset correlation thresholds are (0, 0.6), [0.6, 1], which correspond to the existence or non-existence of correlation, respectively. First, the stack feature data corresponding to the marked log sub-item attribute information is queried. For example, if it is in the first stack, the total number of times the marked log sub-item attribute information and the log sub-item attribute information appear in the first stack is 20, and the number of times the marked log sub-item attribute information and the log sub-item attribute information appear together is 15, then the correlation coefficient is 0.75, and the marked log sub-item attribute information and the log sub-item attribute information are correlated.
[0165] It is worth mentioning that the examples of the present invention also include:
[0166] Comparing and analyzing the interaction anomaly category feature data with a preset interaction anomaly category feature data set to obtain first coincidence degree data;
[0167] Compare the similarity between the keyword and a preset keyword library to obtain second coincidence data;
[0168] Performing weighted processing on the first coincidence data and the second coincidence data in combination with a first preset correction coefficient and a second preset correction coefficient to obtain third coincidence data;
[0169] The third coincidence data is compared with a preset coincidence threshold value, and if the third coincidence data is greater than the preset coincidence threshold value, a first-level warning response is activated.
[0170] It should be noted that by comparing the interaction abnormality category feature data and keywords, when the overlap reaches the threshold, it means that the interaction is seriously abnormal, and the first-level warning should be activated to immediately notify the relevant responsible person to handle it. In this embodiment, the preset overlap threshold is 0.5. For example, if the third overlap data is 0.6, the first-level warning response is activated;
[0171] The third coincidence data calculation formula is:
[0172]
[0173] Among them, C d3 is the third coincidence data, C d1 , C d2 are the first coincidence data and the second coincidence data respectively, μ1 and μ2 are the first preset correction coefficient and the second preset correction coefficient respectively, τ1 and τ2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset power grid industry-finance collaborative interaction database).
[0174] The third aspect of the present invention provides a readable storage medium, which stores a program for a power grid business interaction data early warning method based on big data. When the program for a power grid business interaction data early warning method based on big data is executed by a processor, the steps of the power grid business interaction data early warning method based on big data as described in any one of the above items are implemented.
[0175] The present invention discloses a big data-based power grid business interaction data early warning method, system and medium. The power grid business data and financial data within a preset time period are input into a preset business-finance collaboration system for business-finance interaction processing, business interaction log information is extracted, and interaction abnormality log information is identified and obtained. The sub-item attribute information of each log and the corresponding sub-item weight value are extracted, and feature category identification is performed to obtain interaction abnormality category feature data and the corresponding sub-item feature weight coefficient. The interaction abnormality log information is then extracted to obtain interaction abnormality data. The power grid business interaction abnormality data is processed in combination with the corresponding sub-item weight value and the sub-item feature weight coefficient to obtain a power grid business interaction abnormality index and an early warning level. Thus, the interaction data abnormality is obtained by weighting the obtained power grid business interaction log information, thereby realizing a technology for early warning of power grid business interaction data abnormality.
[0176] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.
[0177] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0178] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0179] Those skilled in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.
[0180] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.
Claims
1. A power grid business interaction data early warning method based on big data, characterized in that: The following steps are involved: Obtain the grid business data and grid financial data of the grid within a preset time period, and perform business-finance interaction processing and log recording and information recording through a preset business-finance collaboration system, and extract the business interaction log information of the recorded log; Identify abnormal information of the business interaction log information through a preset business interaction state identification model, and obtain abnormal log information of power grid business interaction within the preset time period; Extracting attribute information according to the abnormal log information of the power grid business interaction to obtain attribute information of each log item and corresponding weight value of each item; Perform feature category identification on the power grid business interaction abnormality log information, obtain interaction abnormality category feature data corresponding to each log sub-item information, and perform a comparison query through a preset category feature weight mapping relationship table to obtain the corresponding sub-item feature weight coefficient; Extracting power grid business interaction abnormality data according to the power grid business interaction abnormality log information; The grid business interaction abnormality data is processed in combination with the corresponding sub-item weight values and sub-item feature weight coefficients to obtain the grid business interaction abnormality index and warning level of the grid within the preset time period.
2. The big data-based power grid business interaction data early warning method according to claim 1 is characterized in that: The obtaining of the grid business data and grid financial data of the grid within a preset time period, and performing business-finance interaction processing and log recording and information recording through a preset business-finance collaboration system, and extracting the business interaction log information of the recorded logs, includes: Obtaining grid business data and grid financial data within a preset time period; Inputting the power grid business data and power grid financial data into a preset business-finance collaboration system for business-finance interaction processing and log recording, and recording information; Extract the business interaction log information recorded in the log, including permission interaction information, document integration interaction information, business attribution interaction information, account mapping interaction information and data link interaction information.
3. The big data-based power grid business interaction data early warning method according to claim 2 is characterized in that: The identifying abnormal information of the business interaction log information by using a preset business interaction state identification model, and obtaining abnormal log information of power grid business interaction within the preset time period, includes: Inputting the business interaction log information into a preset business interaction state recognition model to identify abnormal information; The abnormal log information of power grid business interaction within the preset time period is obtained, including asymmetric information of authority interaction, interruption information of document integration interaction, conflict information of business attribution interaction, error information of account mapping interaction and disconnection information of data link interaction.
4. The method for early warning of power grid business interaction data based on big data according to claim 3 is characterized in that: The extracting of attribute information according to the abnormal log information of the power grid business interaction to obtain attribute information of each log item and corresponding weight value of each item includes: Extracting attribute information of each item from the asymmetric information of authority interaction, the interruption information of document integration interaction, the conflict information of business attribution interaction, the error information of account mapping interaction, and the disconnection information of data link interaction, and obtaining the log item attribute information corresponding to each log item information in the business interaction log information; The log item attribute information includes keywords, user name, error code, operator, organization and timestamp; Each of the log item attribute information is queried through a preset attribute weight mapping relationship table to obtain the item weight value corresponding to each of the log item attribute information.
5. The big data-based power grid business interaction data early warning method according to claim 4 is characterized in that: The feature category identification is performed on the abnormal interaction log information of the power grid business to obtain the abnormal interaction category feature data corresponding to each log item information, and a comparison query is performed through a preset category feature weight mapping relationship table to obtain the corresponding item feature weight coefficient, including: Inputting the power grid business interaction abnormality log information into a preset interaction abnormality category recognition model for feature category recognition, and obtaining interaction abnormality category feature data corresponding to each log item information, including error code feature data and stack feature data; According to the error code feature data and the stack feature data, a comparison query is performed through a preset category feature weight mapping relationship table to obtain the sub-item feature weight coefficients corresponding to each log sub-item information.
6. The big data-based power grid business interaction data early warning method according to claim 5 is characterized in that: The extracting the power grid business interaction abnormality data according to the power grid business interaction abnormality log information includes: According to the power grid business interaction abnormality log information, power grid business interaction abnormality data is extracted, including authority interaction failure rate data, document integration interaction interruption rate data, business attribution interaction mismatch data, account mapping interaction error rate data and data link interaction missing rate data.
7. The big data-based power grid business interaction data early warning method according to claim 6 is characterized in that: The processing according to the abnormal data of the power grid business interaction in combination with the corresponding sub-item weight value and the sub-item feature weight coefficient to obtain the power grid business interaction abnormality index and warning level of the power grid within the preset time period includes: The power grid business interaction abnormality data is combined with the corresponding sub-item weight value and the sub-item feature weight coefficient and input into a preset business interaction abnormality detection model for processing to obtain a power grid business interaction abnormality index of the power grid within the preset time period; The warning level is determined according to the threshold range to which the power grid service interaction abnormality index belongs, including a first-level warning, a second-level warning or a third-level warning.
8. The big data-based power grid business interaction data early warning method according to claim 7 is characterized in that: Also includes: Compare the multiple log item attribute information corresponding to each log item information in the business interaction log information with the item attribute comparison information in the preset log item attribute information library, and mark one or more log item attribute information that does not match the log item attribute information in the log item attribute information library as marked log item attribute information; Comparing the marked log item attribute information with the corresponding item attribute comparison information by using a preset similarity comparison method to obtain a corresponding similarity; Performing a threshold comparison based on the similarity and a preset similarity threshold, and determining whether the attributes are associated based on the threshold comparison result; If the threshold comparison result meets the requirements, the attributes are associated; If the threshold comparison result does not meet the requirements, it is not attribute association, and the corresponding sub-item weight value of the corresponding log sub-item attribute information is corrected.
9. The power grid industry-finance collaborative data early warning system based on big data is characterized by: The invention comprises a memory and a processor, wherein the memory comprises a program of a method for early warning of power grid business interaction data based on big data, and the program of the method for early warning of power grid business interaction data based on big data is executed by the processor to implement the following steps: Obtain the grid business data and grid financial data of the grid within a preset time period, and perform business-finance interaction processing and log recording and information recording through a preset business-finance collaboration system, and extract the business interaction log information of the recorded log; Identify abnormal information of the business interaction log information through a preset business interaction state identification model, and obtain abnormal log information of power grid business interaction within the preset time period; Extracting attribute information according to the abnormal log information of the power grid business interaction to obtain attribute information of each log item and corresponding weight value of each item; Perform feature category identification on the power grid business interaction abnormality log information, obtain interaction abnormality category feature data corresponding to each log sub-item information, and perform a comparison query through a preset category feature weight mapping relationship table to obtain the corresponding sub-item feature weight coefficient; Extracting power grid business interaction abnormality data according to the power grid business interaction abnormality log information; The grid business interaction abnormality data is processed in combination with the corresponding sub-item weight values and sub-item feature weight coefficients to obtain the grid business interaction abnormality index and warning level of the grid within the preset time period.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program for the power grid business interaction data early warning method based on big data. When the program for the power grid business interaction data early warning method based on big data is executed by the processor, the steps of the power grid business interaction data early warning method based on big data as described in any one of claims 1 to 8 are implemented.
