CN113804965B - Abnormal metering point identification method and device based on RPA and AI - Google Patents
Abnormal metering point identification method and device based on RPA and AI Download PDFInfo
- Publication number
- CN113804965B CN113804965B CN202111140457.9A CN202111140457A CN113804965B CN 113804965 B CN113804965 B CN 113804965B CN 202111140457 A CN202111140457 A CN 202111140457A CN 113804965 B CN113804965 B CN 113804965B
- Authority
- CN
- China
- Prior art keywords
- abnormal
- area
- metering
- determining
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 437
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000005259 measurement Methods 0.000 claims description 98
- 238000012545 processing Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000003058 natural language processing Methods 0.000 description 9
- 238000004801 process automation Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000002354 daily effect Effects 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R22/00—Arrangements for measuring time integral of electric power or current, e.g. electricity meters
- G01R22/06—Arrangements for measuring time integral of electric power or current, e.g. electricity meters by electronic methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Power Engineering (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application provides an abnormal metering point identification method and device based on RPA and AI, wherein the method comprises the following steps: controlling a robot flow automatic RPA robot to log in a metering system, and acquiring a plurality of abnormal area lists from the metering system; determining a target abnormal area according to the abnormal area lists; aiming at each target abnormal platform area, acquiring data of each metering point in each target abnormal platform area at a plurality of measuring time points; and determining the abnormal metering point in each target abnormal platform area according to the data of each metering point at a plurality of measuring time points. Therefore, the RPA robot is utilized to acquire a plurality of abnormal area lists from the metering system, the target abnormal areas are determined according to the abnormal area lists, and abnormal metering points in each target abnormal area are identified, so that manpower and material resources are saved, and the identification efficiency and accuracy are improved.
Description
Technical Field
The application relates to the technical field of power grids, in particular to an abnormal metering point identification method and device based on RPA and AI.
Background
The robot process automation (Robotic Process Automation, RPA) is a novel artificial intelligent virtual process automation robot, is used for simulating the operation of a person on a computer, automatically executes process tasks according to rules, and can be widely applied to various fields requiring process automation, such as data aggregation of a big data platform.
Artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is a technical science that studies, develops theories, methods, techniques and application systems for simulating, extending and expanding human intelligence.
In the related art, the transformer substation is provided with more metering points, the daily statistics abnormal data volume is very large, the data is exported through the system and is compared by manpower, the workload is very large, time and labor are wasted, and the manual processing is easy to cause data omission and errors.
Disclosure of Invention
The application provides an abnormal metering point identification method and device based on RPA and AI.
According to an aspect of the present application, there is provided an abnormal metering point identification method based on RPA and AI, including:
Controlling an RPA robot to log in a metering system, and acquiring a plurality of abnormal platform area lists from the metering system;
Determining a target abnormal area according to the abnormal area lists;
Aiming at each target abnormal platform area, acquiring data of each metering point in each target abnormal platform area at a plurality of measuring time points;
and determining the abnormal metering point in each target abnormal platform area according to the data of each metering point at a plurality of measuring time points.
In a possible implementation manner of an embodiment of an aspect of the present application, the determining, according to the multiple abnormal area lists, a target abnormal area includes;
Determining a first degree of matching between the abnormal regions in any two abnormal region lists by using natural language processing (Natural Language Processing, NLP);
according to each first matching degree, determining a candidate abnormal platform area;
determining second matching degrees between each candidate abnormal region and each abnormal region in the rest abnormal region list;
And determining any one of the candidate abnormal areas as a target abnormal area under the condition that the abnormal areas with the second matching degree larger than the first threshold value between any one of the candidate abnormal areas exist in each of the rest abnormal area lists.
In a possible implementation manner of an embodiment of an aspect of the present application, the determining, according to the multiple abnormal area lists, a target abnormal area includes;
Determining a third matching degree between each area and each abnormal area in each abnormal area list according to each area;
and determining the area as a target abnormal area under the condition that the third matching degree between any area and the abnormal areas in each abnormal area list is larger than a second threshold value.
In a possible implementation manner of an embodiment of an aspect of the present application, the determining, according to the data of each metering point at a plurality of measurement time points, an abnormal metering point in each target abnormal platform area includes:
determining, for each metering point, a difference between data of adjacent measurement time points of the plurality of measurement time points;
And determining the metering point as an abnormal metering point when the absolute values of the plurality of continuous differences are all larger than a third threshold value.
In a possible implementation manner of an embodiment of an aspect of the present application, the determining, according to the data of each metering point at a plurality of measurement time points, an abnormal metering point in each target abnormal platform area includes:
when there is a missing data at a plurality of consecutive measurement time points at any one measurement point, it is determined that the any one measurement point is an abnormal measurement point.
In a possible implementation manner of an embodiment of an aspect of the present application, after determining an abnormal metering point in each target abnormal platform area according to the data of each metering point at a plurality of measurement time points, the method further includes:
Generating an abnormal metering point list according to the abnormal metering points corresponding to each target abnormal platform area;
pushing the abnormal metering point list to an associated user of the metering system.
According to another aspect of the present application, there is provided an abnormal metering point identifying apparatus based on RPA and AI, including:
the first acquisition module is used for controlling the robot flow automation RPA robot to log in the metering system and acquiring a plurality of abnormal platform area lists from the metering system;
the first determining module is used for determining a target abnormal area according to the plurality of abnormal area lists;
The second acquisition module is used for acquiring data of each metering point in each target abnormal platform area at a plurality of measuring time points aiming at each target abnormal platform area;
and the second determining module is used for determining the abnormal metering point in each target abnormal platform area according to the data of each metering point at a plurality of measuring time points.
In a possible implementation manner of the embodiment of another aspect of the present application, the first determining module is configured to:
Determining a first matching degree between different abnormal areas in any two abnormal area lists by using NLP;
according to each first matching degree, determining a candidate abnormal platform area;
determining second matching degrees between each candidate abnormal region and each abnormal region in the rest abnormal region list;
And determining any one of the candidate abnormal areas as a target abnormal area under the condition that the abnormal areas with the second matching degree larger than the first threshold value between any one of the candidate abnormal areas exist in each of the rest abnormal area lists.
In a possible implementation manner of the embodiment of another aspect of the present application, the first determining module is configured to:
Determining a third matching degree between each area and each abnormal area in each abnormal area list according to each area;
and determining the area as a target abnormal area under the condition that the third matching degree between any area and the abnormal areas in each abnormal area list is larger than a second threshold value.
In a possible implementation manner of the embodiment of another aspect of the present application, the second determining module is configured to:
determining, for each metering point, a difference between data of adjacent measurement time points of the plurality of measurement time points;
And determining the metering point as an abnormal metering point when the absolute values of the plurality of continuous differences are all larger than a third threshold value.
In a possible implementation manner of the embodiment of another aspect of the present application, the second determining module is configured to:
when there is a missing data at a plurality of consecutive measurement time points at any one measurement point, it is determined that the any one measurement point is an abnormal measurement point.
In a possible implementation manner of the embodiment of another aspect of the present application, the apparatus may further include:
The generation module is used for generating an abnormal metering point list according to the abnormal metering points corresponding to each target abnormal platform area;
and the pushing module is used for pushing the abnormal metering point list to the associated user of the metering system.
According to another aspect of the present application, there is provided a computer apparatus comprising:
A memory storing executable program code;
a processor coupled to the memory;
Wherein the processor invokes executable program code stored in the memory to perform the RPA and AI-based outlier recognition method as described in one aspect above.
According to another aspect of the present application, there is provided a computer-readable storage medium having stored thereon a computer program, characterized in that the program, when executed by a processor, implements the RPA and AI-based outlier recognition method according to the above aspect.
According to the method and the device for identifying the abnormal metering point based on the RPA and the AI, the RPA robot is automatically controlled to log in a metering system by controlling the robot flow, and a plurality of abnormal platform area lists are obtained from the metering system; determining a target abnormal area according to the abnormal area lists; aiming at each target abnormal platform area, acquiring data of each metering point in each target abnormal platform area at a plurality of measuring time points; and determining the abnormal metering point in each target abnormal platform area according to the data of each metering point at a plurality of measuring time points. Therefore, the RPA robot is utilized to acquire a plurality of abnormal area lists from the metering system, the target abnormal areas are determined according to the abnormal area lists, and abnormal metering points in each target abnormal area are identified, so that manpower and material resources are saved, and the identification efficiency and accuracy are improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application and do not constitute a undue limitation on the application.
FIG. 1 is a schematic flow chart of an abnormal metering point identification method based on RPA and AI according to an embodiment of the application;
FIG. 2 is a schematic flow chart of another method for identifying abnormal metering points based on RPA and AI according to an embodiment of the application;
FIG. 3 is a schematic flow chart of another method for identifying abnormal metering points based on RPA and AI according to an embodiment of the application;
Fig. 4 is a schematic structural diagram of an abnormal metering point identifying device based on RPA and AI according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "comprising" and "having" and any variations thereof in the embodiments of the present application and the accompanying drawings are intended to cover non-exclusive inclusions. A process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed but may alternatively include other steps or elements not listed or inherent to such process, method, article, or apparatus.
The following describes an abnormal metering point identification method and device based on RPA and AI according to an embodiment of the present application with reference to the accompanying drawings.
In the description of the present application, the term "plurality" means two or more.
In the description of the present application, the term "metering system" may refer to an electric energy metering system, which mainly realizes metering of electric energy at the network surfing, network surfing and connecting line points of a power plant, and provides basic data for settlement and analysis through time-division storage, collection and processing.
In the description of the present application, the term "bay" refers to the area or region of power supply for one or more transformers, which is a term of power economy operation management.
In the description of the present application, the term "metering point" is a location where a metering device should be installed, and the metering point may be classified into an electric power customer charging point, a gateway metering point, and the like.
In the description of the present application, the term "associated user" may refer to a business person responsible for managing metering points.
Robot process automation (Robotic Process Automation, RPA) is a business process automation technology based on software robots and artificial intelligence (ARTIFICIAL INTELLIGENCE, AI), and by means of specific "robot software", the operation of a human on a computer is simulated, and process tasks are automatically executed according to rules.
Fig. 1 is a schematic flow chart of an abnormal metering point identification method based on RPA and AI according to an embodiment of the present application.
The method for identifying the abnormal metering points based on the RPA and the AI provided by the embodiment of the application can be executed by the device for identifying the abnormal metering points based on the RPA and the AI provided by the embodiment of the application, and the device can be configured in computer equipment so as to identify the abnormal metering points in each area through an RPA robot.
As shown in fig. 1, the method for identifying abnormal metering points based on RPA and AI includes:
and step 101, controlling the RPA robot to log in the metering system, and acquiring a plurality of abnormal area lists from the metering system.
According to the application, the PRA robot can be controlled to open the metering system, and a user name and a password are input for login. After successful login, the PRA robot is controlled to click on the area of the abnormal area in the page of the metering system, and a plurality of abnormal area lists are inquired and obtained in the area. The plurality of abnormal area lists may be a plurality of abnormal area lists generated in a time-continuous manner, and each abnormal area list may include information of an abnormal area determined by the metering system, such as a number, a name, an identification, and the like of the abnormal area.
For example, the RPA robot may be controlled to select the current day time to search for abnormal region data and download the abnormal region data to obtain the current day of the abnormal region list, then switch the time to the previous day, search for abnormal region data and download the abnormal region data to obtain the previous day of the abnormal region list, switch to the previous two days, search for primary region data and download the abnormal region data to obtain the previous day of the abnormal region list, so that the previous day, yesterday and today of the abnormal region list may be obtained.
In order to improve the degree of automation and the real-time performance of the abnormal metering point identification, the RPA robot can be controlled to execute every preset time. For example, the RPA robot may be controlled to automatically log into the metering system at eight am points daily using a timed task and obtain a plurality of abnormal zone lists.
Step 102, determining a target abnormal area according to the plurality of abnormal area lists.
According to the method and the device, the target abnormal area can be determined from the abnormal areas in the abnormal area lists according to the acquired abnormal area lists.
In order to improve accuracy in determining an abnormal region, an abnormal region common in the plurality of abnormal region lists may be used as a target abnormal region. For example, in the abnormal region list of today, yesterday, and previous days, respectively, the abnormal region existing in all of the three abnormal region lists may be acquired as the target abnormal region, that is, the region in which abnormality occurs for three consecutive days may be taken as the target abnormal region. Therefore, the abnormal area caused by other accidental factors can be avoided, and the abnormal area can be used as the metering point.
Step 103, for each target abnormal area, acquiring data of each metering point in each target abnormal area at a plurality of measurement time points.
After the target abnormal areas are determined, the data of each metering point in each target abnormal area at a plurality of measuring time points can be obtained by inquiring the metering system. When the method is realized, the RPA robot can be controlled to switch from a page for inquiring the abnormal platform area to a metering detail data page, information of the target abnormal platform area such as the platform area name is input, the start and stop time of searching is filled in the searching information, the searching data is clicked, and the data of all metering points of the target abnormal platform area in the current time period are read after the page refreshing data are waited.
For example, there is one measurement time point every day, and data of today and the past 6 days can be queried, and then 7 data measured at 7 measurement time points can be acquired. As another example, two measurement time points are set every day, and data of measurement time points in the past 6 days can be acquired.
The measurement time point may be set as needed, which is not limited by the present application.
And 104, determining the abnormal metering point in each target abnormal platform area according to the data of each metering point at a plurality of measuring time points.
In the application, whether each metering point is an abnormal metering point can be determined according to the data of each metering point at a plurality of measuring time points. For example, according to the early-late order of the measurement time points, the data of the measurement points are kept unchanged or gradually increased, the measurement points can be considered to be normal, otherwise, the measurement points can be considered to be abnormal measurement points. Thus, an abnormal metering point among metering points in each target abnormal region can be determined.
According to the method for identifying the abnormal metering point based on the RPA and the AI, the robot flow is controlled to automatically log in a metering system by the RPA robot, and a plurality of abnormal platform area lists are obtained from the metering system; determining a target abnormal area according to the abnormal area lists; aiming at each target abnormal platform area, acquiring data of each metering point in each target abnormal platform area at a plurality of measuring time points; and determining the abnormal metering point in each target abnormal platform area according to the data of each metering point at a plurality of measuring time points. Therefore, the RPA robot is utilized to acquire a plurality of abnormal area lists from the metering system, the target abnormal areas are determined according to the abnormal area lists, and abnormal metering points in each target abnormal area are identified, so that manpower and material resources are saved, and the identification efficiency and accuracy are improved.
Fig. 2 is a flowchart of another method for identifying abnormal metering points based on RPA and AI according to an embodiment of the present application.
As shown in fig. 2, the method for identifying abnormal metering points based on RPA and AI includes:
In step 201, the RPA robot is controlled to log in the metering system, and a plurality of abnormal area lists are acquired from the metering system.
In the present application, step 201 is similar to step 101, and thus will not be described herein.
Step 202, determining a first matching degree between the abnormal areas in any two abnormal area lists by using NLP.
After the multiple abnormal region lists are obtained, the matching degree between the abnormal regions in any two abnormal region lists can be determined by using an NLP technology, so that the first matching degree is conveniently distinguished.
For example, 3 abnormal region lists, A, B and C respectively, are obtained from the metering system, and the matching degree between each abnormal region in a and each abnormal region in B can be calculated.
When calculating the first matching degree between the abnormal areas in the two abnormal area lists, the matching degree between the area information of the abnormal areas, such as the matching degree between the area names or the matching degree between the area identifiers, can be calculated.
And 203, determining candidate abnormal areas according to the first matching degrees.
In the application, when the first matching degree between two abnormal areas is larger than the preset threshold value, the two abnormal areas can be considered to be the same abnormal area. Thus, according to each first matching degree, an abnormal region common to the two abnormal region lists, that is, a region existing in the two abnormal region lists, may be determined, and is referred to as a candidate abnormal region for convenience of distinction.
The magnitude of the preset threshold value may be set as required, which is not limited by the present application.
Step 204, determining each second matching degree between each candidate abnormal region and each abnormal region in the list of each rest abnormal regions.
In the application, the candidate abnormal area is an abnormal area shared by two abnormal area lists, in order to improve the accuracy of the determined abnormal areas, whether each candidate abnormal area exists in the rest abnormal area list can be further determined, and then, for each candidate abnormal area, the second matching degree between each candidate abnormal area and each abnormal area in the rest abnormal area list can be determined.
The method for calculating the second matching degree is similar to the method for calculating the first matching degree, and therefore will not be described herein.
Step 205, determining any one of the candidate abnormal areas as a target abnormal area when the abnormal areas with the second matching degree with any one of the candidate abnormal areas being greater than the first threshold value exist in each of the remaining abnormal area lists.
In the application, if each of the remaining abnormal region lists is an abnormal region having a second matching degree with a certain candidate abnormal region greater than a first threshold value, it is indicated that the candidate abnormal region exists in each of the remaining abnormal region lists, that is, the candidate abnormal region exists in all the abnormal region lists, thereby determining the candidate abnormal region as a target abnormal region. Thus, the target abnormal region can be determined from the candidate abnormal regions.
Step 206, for each target abnormal area, acquiring data of each metering point in each target abnormal area at a plurality of measurement time points.
Step 207, determining an abnormal metering point in each target abnormal platform area according to the data of each metering point at a plurality of measuring time points.
In the present application, steps 206-207 are similar to steps 103-104 described above, and thus are not repeated here.
In the embodiment of the application, when determining the target abnormal region according to the plurality of abnormal region lists, NLP can be utilized to determine the first matching degree between the abnormal regions in any two abnormal region lists; according to each first matching degree, determining a candidate abnormal platform area; determining second matching degrees between each candidate abnormal region and each abnormal region in the rest abnormal region list; and determining any one of the candidate abnormal areas as a target abnormal area under the condition that the abnormal areas with the second matching degree larger than the first threshold value between any one of the candidate abnormal areas exist in each of the rest abnormal area lists. Therefore, the target abnormal area which is the abnormal area shared by the abnormal areas can be determined, so that the abnormal areas needing to be judged are screened from the abnormal areas, and the accuracy is improved.
In one embodiment of the present application, when determining the target abnormal region according to the plurality of abnormal region lists, it may also be determined, for each region under the metering system, whether or not each region exists in each abnormal region list, thereby screening the target abnormal region from the plurality of regions.
When the method is implemented, NLP technology can be utilized to determine the third matching degree between each area and each abnormal area in each abnormal area list. And under the condition that the third matching degree between any one of the areas and the abnormal area in each abnormal area list is larger than the threshold value, indicating that the area appears in all abnormal area lists, and determining the area as the target abnormal area.
For example, the abnormal area lists of today, yesterday and previous days are respectively obtained, if the third matching degree between a certain area and a certain abnormal area in each abnormal area list is greater than the second threshold value, the area appears in the 3 abnormal area lists, that is, the area is an abnormal area for 3 consecutive days, and the area can be determined to be a target abnormal area.
In the embodiment of the application, whether each area is the target abnormal area is determined according to the third matching degree between each area and each abnormal area in each abnormal area list, so that the target abnormal area can be screened out from a plurality of areas, and the accuracy is improved.
Fig. 3 is a flowchart of another method for identifying abnormal metering points based on RPA and AI according to an embodiment of the present application.
As shown in fig. 3, the method for identifying abnormal metering points based on RPA and AI includes:
Step 301, controlling the RPA robot to log in the metering system, and acquiring a plurality of abnormal area lists from the metering system.
Step 302, determining a target abnormal area according to the plurality of abnormal area lists.
Step 303, for each target abnormal area, acquiring data of each metering point in each target abnormal area at a plurality of measurement time points.
In the present application, steps 301 to 303 are similar to steps 101 to 103 described above, and thus are not described herein.
Step 304, for each metering point, determining a difference between data of adjacent measurement time points in the plurality of measurement time points.
In the application, the RPA robot can be controlled to calculate the difference value between the data of each metering point at the adjacent measuring time points in the plurality of measuring time points for each target abnormal area.
For example, data of a certain metering point at 7 continuous measurement time points are acquired, and the data of the metering points are respectively a1, a2, a3, a4, a5, a6 and a7 according to the early-late sequence of the measurement time points, so that the difference between a7 and a6, the difference between a6 and a5, the difference between a5 and a4, the difference between a4 and a3, the difference between a3 and a2 and the difference between a2 and a1 can be calculated.
In step 305, when the absolute values of the plurality of continuous differences are all greater than the threshold value, the measurement point is determined to be an abnormal measurement point.
In the present application, if the absolute difference between the data of two adjacent measurement time points is greater than the threshold, it may be that the difference between the data of the measurement point at the next measurement time point and the data of the measurement point at the previous measurement time point is greater than the threshold, that is, the data of the measurement point at the next measurement time point is far greater than the data of the measurement point at the previous measurement time point, or the difference between the data of the measurement point at the previous measurement time point and the data of the measurement point at the next measurement time point is greater than the threshold, and in normal cases, the data of the measurement point at the next measurement time point should be equal to or greater than the data of the measurement point at the previous measurement time point, which indicates that there is an abnormality in the data of the two measurement time points.
If the plurality of consecutive differences are all greater than the threshold value, the metering point may be regarded as an abnormal metering point. For example, in the above example, the difference between a7 and a6, the difference between a6 and a5, and the difference between a5 and a4 are all greater than the threshold, and the metering point may be considered to be an abnormal metering point.
In the embodiment of the application, when determining the abnormal metering point in each target abnormal platform area according to the data of each metering point at a plurality of measuring time points, the difference value between the data of adjacent measuring time points in the plurality of measuring time points can be determined by aiming at each metering point; and determining the metering point as an abnormal metering point when the absolute values of the plurality of continuous differences are all larger than a third threshold value. Therefore, the RPA robot can be controlled to determine whether the metering point is an abnormal metering point according to the difference value between the data of the adjacent metering time points in the multiple metering time points, and the recognition efficiency and accuracy of the abnormal metering point are improved.
In practical applications, there may be anomalies in metering points that result in failure to successfully upload measured data to the metering system. In view of this, in one embodiment of the present application, when determining an abnormal measurement point in each target abnormal region based on data of each measurement point at a plurality of measurement time points, if there is a missing data of a plurality of consecutive measurement time points of any one measurement point, any one measurement point may be regarded as an abnormal measurement point.
In practical application, the missing of data at a certain measurement time point may be caused by accidental factors, and in order to improve the accuracy of identification, in the present application, if there is missing data at a plurality of continuous measurement time points at a certain measurement point, it may be considered that there is an abnormality at the measurement point, that is, the measurement point is an abnormal measurement point.
For example, data of a certain metering point at 7 continuous measurement time points is acquired, and if there is a missing data of 3 continuous measurement time points, the metering point can be considered as an abnormal metering point.
In the embodiment of the present application, when determining the abnormal measurement point in each target abnormal platform area according to the data of each measurement point at a plurality of measurement time points, any measurement point may be determined to be the abnormal measurement point when there is a loss of the data of a plurality of continuous measurement time points of any measurement point. Thus, it is possible to determine whether or not the metering point is an abnormal metering point based on the data missing condition of the measurement time point.
In an embodiment of the present application, after determining the abnormal metering point in each target abnormal platform area according to the data of each metering point at a plurality of measurement time points, the abnormal metering point list may be generated according to the abnormal metering point corresponding to each target abnormal platform area, that is, the abnormal metering point in each target abnormal platform area, and then the abnormal metering point list is pushed to the associated user of the metering system.
In the application, an abnormal metering point list can be generated according to the abnormal metering points in each target abnormal platform region. That is, all the identified abnormal metering points are included in the abnormal metering point list. The abnormal metering point list may include information of each abnormal metering point, such as identification of the abnormal metering point, a platform area to which the abnormal metering point belongs, and the like.
After the list of outlier metering points is generated, the list of outlier metering points may be sent to associated users of the metering system, such as to associated business personnel. When the abnormal metering point list is sent, the abnormal metering point list can be sent to related business personnel in a mail mode or instant messaging software and the like, so that the related business personnel can check each abnormal metering point in the abnormal metering point list in the field.
In the embodiment of the application, after determining the abnormal metering points in each target abnormal platform area according to the data of each metering point at a plurality of measuring time points, an abnormal metering point list can be generated according to the abnormal metering points corresponding to each target abnormal platform area, and the abnormal metering point list is pushed to the associated user of the metering system. Therefore, the associated user can check the abnormal metering points in time according to the abnormal metering point list, the workload of the associated user is reduced, and the efficiency is improved.
Fig. 4 is a schematic structural diagram of an abnormal metering point identifying device based on RPA and AI according to an embodiment of the present application.
As shown in fig. 4, the RPA and AI-based abnormal metering point identifying apparatus 400 includes:
a first obtaining module 410, configured to control the RPA robot to log into the metering system, and obtain a plurality of abnormal area lists from the metering system;
a first determining module 420, configured to determine a target abnormal region according to the multiple abnormal region lists;
A second obtaining module 430, configured to obtain, for each target abnormal area, data of each metering point in each target abnormal area at a plurality of measurement time points;
the second determining module 440 is configured to determine an abnormal metering point in each target abnormal platform area according to the data of each metering point at a plurality of measurement time points.
In one possible implementation manner of the embodiment of the present application, the first determining module 420 is configured to:
processing NLP by using natural language, and determining a first matching degree between abnormal areas in any two abnormal area lists;
according to each first matching degree, determining a candidate abnormal platform area;
determining second matching degrees between each candidate abnormal region and each abnormal region in the rest abnormal region list;
And determining any one of the candidate abnormal areas as a target abnormal area under the condition that the abnormal areas with the second matching degree larger than the first threshold value between any one of the candidate abnormal areas exist in each of the rest abnormal area lists.
In one possible implementation manner of the embodiment of the present application, the first determining module 420 is configured to:
Determining a third matching degree between each area and each abnormal area in each abnormal area list according to each area;
And determining the area as the target abnormal area under the condition that the third matching degree between any area and the abnormal areas in each abnormal area list is larger than the second threshold value.
In one possible implementation manner of the embodiment of the present application, the second determining module 440 is configured to:
Determining, for each metering point, a difference between data of adjacent ones of the plurality of measurement time points;
And determining the metering point as an abnormal metering point when the absolute values of the plurality of continuous differences are all larger than a third threshold value.
In one possible implementation manner of the embodiment of the present application, the second determining module 440 is configured to:
when there is a missing data at a plurality of consecutive measurement time points at any one measurement point, any one measurement point is determined to be an abnormal measurement point.
In one possible implementation manner of the embodiment of the present application, the apparatus may further include:
The generation module is used for generating an abnormal metering point list according to the abnormal metering points corresponding to each target abnormal platform area;
And the pushing module is used for pushing the abnormal metering point list to the associated user of the metering system.
The device embodiment corresponds to the method embodiment, and has the same technical effects as the method embodiment, and the specific description refers to the method embodiment. The apparatus embodiments are based on the method embodiments, and specific descriptions may be referred to in the method embodiment section, which is not repeated herein.
According to the device for identifying the abnormal metering point based on the RPA and the AI, disclosed by the embodiment of the application, the RPA robot is automatically controlled to log in a metering system by controlling the robot flow, and a plurality of abnormal platform area lists are obtained from the metering system; determining a target abnormal area according to the abnormal area lists; aiming at each target abnormal platform area, acquiring data of each metering point in each target abnormal platform area at a plurality of measuring time points; and determining the abnormal metering point in each target abnormal platform area according to the data of each metering point at a plurality of measuring time points. Therefore, the RPA robot is utilized to acquire a plurality of abnormal area lists from the metering system, the target abnormal areas are determined according to the abnormal area lists, and abnormal metering points in each target abnormal area are identified, so that manpower and material resources are saved, and the identification efficiency and accuracy are improved.
Fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present application. As shown in fig. 5, the computer device may include:
A memory 501 in which executable program codes are stored;
A processor 502 coupled to the memory 501;
the processor 502 invokes executable program codes stored in the memory 501 to execute the method for identifying abnormal metering points based on RPA and AI according to any embodiment of the present application.
The computer device embodiment and the method embodiment are embodiments based on the same inventive concept, and the relevant points can be referred to each other. The computer device embodiment corresponds to the method embodiment, and has the same technical effects as the method embodiment, and the specific description refers to the method embodiment.
The embodiment of the application discloses a computer readable storage medium which stores a computer program, wherein the computer program enables a computer to execute the method for identifying abnormal metering points based on RPA and AI provided by any embodiment of the application.
In various embodiments of the present application, it should be understood that the sequence numbers of the foregoing processes do not imply that the execution sequences of the processes should be determined by the functions and internal logic of the processes, and should not be construed as limiting the implementation of the embodiments of the present application.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units described above, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present application, or a part contributing to the prior art or all or part of the technical solution, may be embodied in the form of a software product stored in a memory, comprising several requests for a computer device (which may be a personal computer, a server or a network device, etc., in particular may be a processor in a computer device) to execute some or all of the steps of the above-mentioned method of the various embodiments of the present application.
The storage medium embodiment and the method embodiment are embodiments based on the same inventive concept, and the relevant points can be referred to each other. The storage medium embodiment corresponds to the method embodiment, and has the same technical effects as the method embodiment, and the specific description refers to the method embodiment.
Those of ordinary skill in the art will appreciate that: the drawing is a schematic diagram of one embodiment and the modules or flows in the drawing are not necessarily required to practice the application.
Those of ordinary skill in the art will appreciate that: the modules in the apparatus of the embodiments may be distributed in the apparatus of the embodiments according to the description of the embodiments, or may be located in one or more apparatuses different from the present embodiments with corresponding changes. The modules of the above embodiments may be combined into one module, or may be further split into a plurality of sub-modules.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (10)
1. An abnormal metering point identification method based on RPA and AI is characterized by comprising the following steps:
Controlling a robot flow automatic RPA robot to log in a metering system, and acquiring a plurality of abnormal area lists from the metering system;
determining a target abnormal platform area according to the abnormal platform area lists, wherein the target abnormal platform area is a common abnormal platform area in the abnormal platform area lists;
Aiming at each target abnormal platform area, acquiring data of each metering point in each target abnormal platform area at a plurality of measuring time points;
Determining an abnormal metering point in each target abnormal platform area according to the data of each metering point at a plurality of measuring time points;
determining a target abnormal area according to the abnormal area lists, wherein the target abnormal area comprises;
processing NLP by using natural language, and determining a first matching degree between abnormal areas in any two abnormal area lists;
according to each first matching degree, determining a candidate abnormal platform area;
determining second matching degrees between each candidate abnormal region and each abnormal region in the rest abnormal region list;
determining any one of the candidate abnormal platform areas as a target abnormal platform area under the condition that the rest abnormal platform areas with the second matching degree larger than the first threshold value between the candidate abnormal platform areas exist in each abnormal platform area list;
Or alternatively, the first and second heat exchangers may be,
Determining a third matching degree between each area and each abnormal area in each abnormal area list according to each area;
and determining the area as a target abnormal area under the condition that the third matching degree between any area and the abnormal areas in each abnormal area list is larger than a second threshold value.
2. The method of claim 1, wherein determining an anomaly metering point in each target anomaly region based on the data for the metering points at a plurality of measurement time points comprises:
determining, for each metering point, a difference between data of adjacent measurement time points of the plurality of measurement time points;
And determining the metering point as an abnormal metering point when the absolute values of the plurality of continuous differences are all larger than a third threshold value.
3. The method of claim 1, wherein determining an anomaly metering point in each target anomaly region based on the data for the metering points at a plurality of measurement time points comprises:
when there is a missing data at a plurality of consecutive measurement time points at any one measurement point, it is determined that the any one measurement point is an abnormal measurement point.
4. A method according to any one of claims 1-3, further comprising, after determining an abnormal metering point in each target abnormal region based on the data of the metering points at a plurality of measurement time points:
Generating an abnormal metering point list according to the abnormal metering points corresponding to each target abnormal platform area;
pushing the abnormal metering point list to an associated user of the metering system.
5. An abnormal metering point identifying device based on RPA and AI, comprising:
the first acquisition module is used for controlling the robot flow automation RPA robot to log in the metering system and acquiring a plurality of abnormal platform area lists from the metering system;
The first determining module is used for determining a target abnormal platform area according to the abnormal platform area lists, wherein the target abnormal platform area is an abnormal platform area common to the abnormal platform area lists;
The second acquisition module is used for acquiring data of each metering point in each target abnormal platform area at a plurality of measuring time points aiming at each target abnormal platform area;
The second determining module is used for determining abnormal metering points in each target abnormal platform area according to the data of each metering point at a plurality of measuring time points;
the first determining module is configured to:
processing NLP by using natural language, and determining a first matching degree between abnormal areas in any two abnormal area lists;
according to each first matching degree, determining a candidate abnormal platform area;
determining second matching degrees between each candidate abnormal region and each abnormal region in the rest abnormal region list;
determining any one of the candidate abnormal platform areas as a target abnormal platform area under the condition that the rest abnormal platform areas with the second matching degree larger than the first threshold value between the candidate abnormal platform areas exist in each abnormal platform area list;
Or alternatively, the first and second heat exchangers may be,
Determining a third matching degree between each area and each abnormal area in each abnormal area list according to each area;
and determining the area as a target abnormal area under the condition that the third matching degree between any area and the abnormal areas in each abnormal area list is larger than a second threshold value.
6. The apparatus of claim 5, wherein the second determination module is to:
determining, for each metering point, a difference between data of adjacent measurement time points of the plurality of measurement time points;
And determining the metering point as an abnormal metering point when the absolute values of the plurality of continuous differences are all larger than a third threshold value.
7. The apparatus of claim 5, wherein the second determination module is to:
when there is a missing data at a plurality of consecutive measurement time points at any one measurement point, it is determined that the any one measurement point is an abnormal measurement point.
8. The apparatus of any one of claims 5-7, further comprising:
The generation module is used for generating an abnormal metering point list according to the abnormal metering points corresponding to each target abnormal platform area;
and the pushing module is used for pushing the abnormal metering point list to the associated user of the metering system.
9. A computer device, the computer device comprising:
A memory storing executable program code;
a processor coupled to the memory;
Wherein the processor invokes executable program code stored in the memory to perform the RPA and AI-based outlier identification method according to any one of claims 1-4.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when executed by a processor, implements the RPA and AI-based outlier recognition method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111140457.9A CN113804965B (en) | 2021-09-28 | 2021-09-28 | Abnormal metering point identification method and device based on RPA and AI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111140457.9A CN113804965B (en) | 2021-09-28 | 2021-09-28 | Abnormal metering point identification method and device based on RPA and AI |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113804965A CN113804965A (en) | 2021-12-17 |
| CN113804965B true CN113804965B (en) | 2024-05-31 |
Family
ID=78896923
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111140457.9A Active CN113804965B (en) | 2021-09-28 | 2021-09-28 | Abnormal metering point identification method and device based on RPA and AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113804965B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110084718A (en) * | 2019-04-25 | 2019-08-02 | 国网湖南省电力有限公司 | A kind of family Tai Qu becomes the accurate method of calibration of relationship and device |
| CN110346661A (en) * | 2019-05-23 | 2019-10-18 | 广西电网有限责任公司 | A kind of method and system of user's electric voltage exception automatic detecting |
| CN111881189A (en) * | 2020-08-04 | 2020-11-03 | 广东电网有限责任公司计量中心 | Method and system for verifying station area user-to-user relationship |
| CN112446601A (en) * | 2020-11-20 | 2021-03-05 | 国网江苏省电力有限公司营销服务中心 | Data diagnosis method and system for non-computable region |
| CN112541011A (en) * | 2020-12-04 | 2021-03-23 | 北京来也网络科技有限公司 | Power grid terminal fault processing method and device based on RPA and AI |
| CN112650785A (en) * | 2020-12-18 | 2021-04-13 | 云南电网有限责任公司 | Metering abnormal data identification method and system |
| CN112699913A (en) * | 2020-11-25 | 2021-04-23 | 国网湖南省电力有限公司 | Transformer area household variable relation abnormity diagnosis method and device |
| WO2021098789A1 (en) * | 2019-11-19 | 2021-05-27 | 深圳市海柔创新科技有限公司 | Goods information checking method and system thereof, robot, and processing terminal |
| CN113159339A (en) * | 2021-04-20 | 2021-07-23 | 国网江西省电力有限公司信息通信分公司 | One-region one-index line loss management method and system based on big data |
| WO2021184727A1 (en) * | 2020-03-19 | 2021-09-23 | 平安科技（深圳）有限公司 | Data abnormality detection method and apparatus, electronic device and storage medium |
-
2021
- 2021-09-28 CN CN202111140457.9A patent/CN113804965B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110084718A (en) * | 2019-04-25 | 2019-08-02 | 国网湖南省电力有限公司 | A kind of family Tai Qu becomes the accurate method of calibration of relationship and device |
| CN110346661A (en) * | 2019-05-23 | 2019-10-18 | 广西电网有限责任公司 | A kind of method and system of user's electric voltage exception automatic detecting |
| WO2021098789A1 (en) * | 2019-11-19 | 2021-05-27 | 深圳市海柔创新科技有限公司 | Goods information checking method and system thereof, robot, and processing terminal |
| WO2021184727A1 (en) * | 2020-03-19 | 2021-09-23 | 平安科技（深圳）有限公司 | Data abnormality detection method and apparatus, electronic device and storage medium |
| CN111881189A (en) * | 2020-08-04 | 2020-11-03 | 广东电网有限责任公司计量中心 | Method and system for verifying station area user-to-user relationship |
| CN112446601A (en) * | 2020-11-20 | 2021-03-05 | 国网江苏省电力有限公司营销服务中心 | Data diagnosis method and system for non-computable region |
| CN112699913A (en) * | 2020-11-25 | 2021-04-23 | 国网湖南省电力有限公司 | Transformer area household variable relation abnormity diagnosis method and device |
| CN112541011A (en) * | 2020-12-04 | 2021-03-23 | 北京来也网络科技有限公司 | Power grid terminal fault processing method and device based on RPA and AI |
| CN112650785A (en) * | 2020-12-18 | 2021-04-13 | 云南电网有限责任公司 | Metering abnormal data identification method and system |
| CN113159339A (en) * | 2021-04-20 | 2021-07-23 | 国网江西省电力有限公司信息通信分公司 | One-region one-index line loss management method and system based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113804965A (en) | 2021-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110493025B (en) | Fault root cause diagnosis method and device based on multilayer digraphs | |
| US20210118067A1 (en) | Configuration and parameterization of energy control system | |
| CN1026832C (en) | Apparatus for controlling sensor processing algorithms response to expert sensor diagnoses | |
| CN111835582B (en) | Configuration method and device of Internet of things inspection equipment and computer equipment | |
| CN111835585B (en) | Inspection method and device for Internet of things equipment, computer equipment and storage medium | |
| EP3671374A1 (en) | Method and system for determining system settings for an industrial system | |
| CN111860667A (en) | Method and device for determining equipment fault, storage medium and electronic device | |
| CN110377703A (en) | Error information processing method, device and equipment | |
| CN115441456A (en) | Fault diagnosis method and device for power grid dispatching support system | |
| Huang et al. | Efficient identification of approximate best configuration of training in large datasets | |
| CN111813655A (en) | Embedded point testing method and device, embedded point management system and storage medium | |
| CN113804965B (en) | Abnormal metering point identification method and device based on RPA and AI | |
| CN105653430A (en) | Method, device and system for processing server management information | |
| CN112541011A (en) | Power grid terminal fault processing method and device based on RPA and AI | |
| CN106844420B (en) | User grouping method and device based on social network and big data analysis | |
| CN115001948B (en) | Equipment health state detection method based on data analysis and related device | |
| Mokashi et al. | Performance comparison of MSER-5 and N-Skart on the simulation start-up problem | |
| CN116450451A (en) | Server hardware management method, system, equipment and storage medium | |
| CN114019946B (en) | Method and device for processing monitoring data of industrial control terminal | |
| CN112541841B (en) | Method, device and terminal equipment for simulating past future data | |
| CN106330556B (en) | A kind of method and apparatus calling related information for generating service module | |
| CN114416489A (en) | System running state monitoring method and device, computer equipment and storage medium | |
| CN114862098A (en) | Resource allocation method and device | |
| CN112560938A (en) | Model training method and device and computer equipment | |
| CN113781237B (en) | Product purchase order consumption method based on distributed artificial intelligence system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |