CN113887830A - Method, device, equipment and medium for determining power failure sensitivity - Google Patents
Method, device, equipment and medium for determining power failure sensitivity Download PDFInfo
- Publication number
- CN113887830A CN113887830A CN202111249730.1A CN202111249730A CN113887830A CN 113887830 A CN113887830 A CN 113887830A CN 202111249730 A CN202111249730 A CN 202111249730A CN 113887830 A CN113887830 A CN 113887830A
- Authority
- CN
- China
- Prior art keywords
- sensitivity
- power failure
- power outage
- power
- client
- 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.)
- Pending
Links
- 230000035945 sensitivity Effects 0.000 title claims abstract description 334
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 38
- 238000002372 labelling Methods 0.000 claims abstract description 33
- 230000005611 electricity Effects 0.000 claims abstract description 29
- 238000003860 storage Methods 0.000 claims description 19
- 238000009826 distribution Methods 0.000 claims description 17
- 238000012795 verification Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000002996 emotional effect Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The embodiment of the invention discloses a method, a device, equipment and a medium for determining power failure sensitivity. The method comprises the following steps: according to the plurality of items of electricity utilization description data, power failure sensitivity description information corresponding to each customer is formed; dividing the clients into first type clients and second type clients, and acquiring the marking result of the power failure sensitivity corresponding to each first type client; training and verifying the XGboost model according to the power outage sensitivity description information of each first class of client and the power outage sensitivity labeling result to obtain a power outage sensitivity prediction model; and inputting the power outage sensitivity description information of each second type of client into the power outage sensitivity prediction model, and acquiring the power outage sensitivity corresponding to each second type of client. The technical scheme of the embodiment of the invention realizes that the data type useful for judging the power failure sensitivity is excavated from the massive data, thereby achieving the effect of carrying out quantifiable effective prediction on the power failure sensitivity of the client.
Description
Technical Field
The embodiment of the invention relates to an artificial intelligence technology, in particular to a method, a device, equipment and a medium for determining power failure sensitivity.
Background
The power failure in the power production process is unavoidable, including peak avoidance and power limitation, prearranged power failure and fault power failure and the like, the power failure or less power failure is the strongest requirement of vast power consumers on power supply enterprises, the power failure feeling and influence of different customers are different, and the different feeling and influence of the customers are defined as sensitivity.
At present, the discrimination standards of the power failure sensitivity are different, and the discrimination standards of the power failure sensitivity are different among different departments of a power grid company. For example, 95598 customer service staff think that a client who repeatedly dials a 95598 hot line in the case of a power failure accident belongs to a power failure sensitive group, or a client who dials a telephone attitude excitement belongs to a power failure sensitive client; the large customer manager considers that the customers who cause economic loss to the business income of enterprises and power grid companies due to industrial and enterprise power failure belong to power failure sensitive customers; the power utilization client data of the government departments, the public institutions and the hospitals which are considered as important by the power grid company are power failure sensitive clients; ordinary residential customers think that the power failure in the case of summer and winter or for the normal life that influences of power failure at night is sensitive to power failure for the customers.
In the process of implementing the invention, the inventor finds that the prior art mainly has the following defects: the power failure sensitivity clients spread throughout various industries and various client types, so that the power failure sensitivity judgment standards are different, and the power failure sensitivity of the clients cannot be effectively judged.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a medium for determining power failure sensitivity, so as to dig out a data type useful for power failure sensitivity judgment in massive data, thereby achieving the effect of quantifiable effective prediction of the power failure sensitivity of a client.
In a first aspect, an embodiment of the present invention provides a method for determining a power outage sensitivity, where the method includes:
according to the plurality of items of electricity utilization description data, power outage sensitivity description information corresponding to each client is formed, and the power outage sensitivity description information comprises: customer attribute information, historical power failure complaint information and historical power failure information;
dividing the clients into first type clients and second type clients, and acquiring the marking result of the power failure sensitivity corresponding to each first type client;
training and verifying the XGboost model according to the power outage sensitivity description information of each first class of client and the power outage sensitivity labeling result to obtain a power outage sensitivity prediction model;
and inputting the power outage sensitivity description information of each second type of client into the power outage sensitivity prediction model, and acquiring the power outage sensitivity corresponding to each second type of client.
In a second aspect, an embodiment of the present invention further provides an apparatus for determining a power outage sensitivity, where the apparatus includes:
the description information forming module is used for forming power outage sensitivity description information corresponding to each customer according to the plurality of items of electricity utilization description data, and the power outage sensitivity description information comprises: customer attribute information, historical power failure complaint information and historical power failure information;
the marking result acquisition module is used for dividing the clients into first type clients and second type clients and acquiring the marking result of the power failure sensitivity corresponding to each first type client;
the prediction model acquisition module is used for training and verifying the XGboost model according to the power outage sensitivity description information of each first class of client and the power outage sensitivity marking result to obtain a power outage sensitivity prediction model;
and the power outage sensitivity acquisition module is used for inputting the power outage sensitivity description information of each second type of client into the power outage sensitivity prediction model and acquiring the power outage sensitivity corresponding to each second type of client.
In a third aspect, an embodiment of the present invention further provides a computer device, where the computer device includes:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method for determining outage susceptibility according to any embodiment of the invention.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the program, when executed by a processor, implements the method for determining the power outage sensitivity according to any embodiment of the present invention.
According to the power consumption description data, power failure sensitivity description information corresponding to each customer is formed; dividing the clients into first type clients and second type clients, and acquiring the marking result of the power failure sensitivity corresponding to each first type client; training and verifying the XGboost model according to the power outage sensitivity description information of each first class of client and the power outage sensitivity labeling result to obtain a power outage sensitivity prediction model; and inputting the power outage sensitivity description information of each second type of client into the power outage sensitivity prediction model, and acquiring the power outage sensitivity corresponding to each second type of client. The technical scheme of the embodiment of the invention solves the problem of inconsistent power failure sensitivity judgment standards caused by the fact that power failure sensitivity clients are distributed in various industries and various client types, and realizes the purpose of excavating data types useful for power failure sensitivity judgment in massive data, thereby achieving the effect of carrying out quantifiable effective prediction on the power failure sensitivity of the clients.
Drawings
Fig. 1 is a flowchart illustrating a method for determining power outage susceptibility according to an embodiment of the present invention;
fig. 2 is a flowchart of another method for determining power outage susceptibility according to the second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a power outage sensitivity determination apparatus according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an apparatus according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a method for determining blackout sensitivity according to an embodiment of the present invention, where the method is applicable to a case of quantitatively evaluating blackout sensitivity of a client, and the method may be executed by a blackout sensitivity determination device, where the device may be implemented in a software and/or hardware manner, and may be generally configured in a terminal device or a server, and specifically includes the following steps:
and S110, forming power failure sensitivity description information corresponding to each client according to the plurality of items of electricity utilization description data.
Wherein, the electricity usage description data can be data describing customer electricity usage activity. The electricity usage description data may include: customer service work order data, customer archive data, line transformer data and power failure description data.
Specifically, the customer service work order data may be recorded data of a customer service work document, such as service types of complaints, reports, opinions, consultation queries, electricity services, fault reports and the like, and data of incoming call numbers, appealing persons, service subclasses, service channels, emergency degrees, incoming call contents, user addresses, user names, power supply units, service labels, whether to directly handle or not, and the like. The customer profile data may refer to various forms of customer profile data directly formed by customers in various electricity utilization activities, and may include attribute characteristics of electricity utilization customers, such as a user number, a user name, a user status (e.g., running, selling, or suspending, etc.), an electricity utilization category (e.g., major industry, general industry, non-industry, business, agricultural production, or residential life, etc.), a user category (e.g., public line private customer, private line private customer, or public transformer customer, etc.), a contract capacity, a running capacity, a standing time, an industry classification (e.g., individual, enterprise, or major industrial enterprise, etc.). The line transformer data may be attribute data of the line and the line subordinate transformers. For example: the transformer substation comprises a transformer substation name, a line segment name, a line number, a station area name, a station area number, a transformer name, an installation address and a transformer capacity. The power failure description data can be the customer description data of the power failure condition and the corresponding power failure and power restoration information. For example: the power outage list number, the user name, the power utilization address, the type of power outage (e.g., planned power outage, fault power outage, or other power outage), the cause of the power outage, the planned power outage time, the planned restoration time, the actual power outage time, and the actual restoration time.
The power outage sensitivity may be a psychological state of the electricity consumer, such as the degree of the consumer's reaction to the power outage. The outage sensitivity may be graded, for example, into a low sensitivity, a medium sensitivity, and a high sensitivity.
The blackout sensitivity description information may be information capable of describing blackout sensitivity of the customer. The higher the power failure sensitivity of the customer is, the lower the tolerance of the customer to the power failure phenomenon is, the greater the influence of the power failure phenomenon on the customer is, and the more likely the customer complains about the power failure phenomenon.
Optionally, the power outage sensitivity description information may include: customer attribute information, historical power outage complaint information and historical power outage information. The client attribute information may be attribute information of the electricity consumer, and the client attribute information may include: user category, electricity usage category, industry category, and customer behavior information. The historical outage complaint information may include: the type of complaint, the complaint time, the complaint frequency and the complaint content emotional intensity in the set historical time interval. The power outage description information may include: the power failure times and the power failure types of the line in the set historical time interval, and the power failure times and the power failure types of the station area in the set historical time interval.
Specifically, according to a plurality of items of electricity utilization description data of customers, the power outage sensitivity description information with the customers as dimensionalities can be sorted and screened out. Further, after obtaining the plurality of items of electricity usage description data of the customer, the plurality of items of electricity usage description data of the customer may be preprocessed, and the specific preprocessing method may include: missing value processing, data stability inspection and processing, time series data conversion supervision learning, data normalization and the like, so that power outage sensitivity description information with customers as dimensions can be formed.
And S120, dividing the clients into first type clients and second type clients, and acquiring the marking result of the power failure sensitivity corresponding to each first type client.
In this embodiment, a first number of customers may be obtained as the first type of customers among all the customers, and a remaining number of customers among all the customers may be obtained as the second type of customers. Wherein the first number is typically much smaller than the second number.
The first type of clients are used as the marking samples for training to obtain the power outage sensitivity prediction model, and after the power outage sensitivity prediction model is obtained through training, the power outage sensitivity prediction model can be used for predicting the power outage sensitivity of the second type of clients.
It can be understood that, since the first category customers are used as training samples, the labeling result of the power outage sensitivity corresponding to each first category customer needs to be labeled. In order to conveniently label the power failure sensitivity, correspondingly, the first type of customers can be obtained by screening all customers through analyzing some abnormal information values included in the power failure sensitivity description information of each customer, for example, an abnormal complaint customer whose complaint frequency in a set historical time interval is much higher than that of other customers is taken as the first type of customer, or an abnormal power failure customer whose power failure frequency in a set historical time interval is much higher than that of other customers is taken as the first type of customer, and the like.
Of course, it can be understood by those skilled in the art that other manners may be adopted to filter out the first type of clients from all the clients, for example, a manner of random selection, which is not limited in this embodiment.
In an optional embodiment of the present invention, obtaining the labeling result of the blackout sensitivity corresponding to each first type customer may include: and sending the power failure sensitivity description information of each first type of client to a manual marking platform, and acquiring the marking result of the power failure sensitivity corresponding to each first type of client by the manual marking platform.
Specifically, the manual labeling platform may first send the power outage sensitivity description information of each first class of client to the power outage sensitivity labeling model, obtain an initialized power outage sensitivity labeling result corresponding to each first class of client, and then manually perform review and quality inspection on the initialized labeling result to form a final power outage sensitivity labeling result corresponding to each first class of client.
Optionally, the labeling result of the power outage sensitivity may include: a blackout sensitivity score value (typically, a percentage), and at least one blackout sensitivity period. Wherein the blackout sensitivity time period is marked when the blackout sensitivity score is greater than or equal to a preset threshold (e.g., 80 points, 90 points, etc.).
In a specific example, the value of the power failure sensitivity score obtained by marking the first type customer A is 95 points, and the power failure sensitivity time periods corresponding to the first type customer A are marked as (9:00-11:00) and (13:00-17: 00); the power failure sensitivity score value obtained by marking the first type of client B is 20 points, and the power failure sensitivity score value is lower, so that a power failure sensitivity time period is not marked for the first type of client B.
In an optional implementation manner of this embodiment, the outage sensitivity annotation model may be an annotation model containing annotation rules. The marking rule can judge the power outage sensitivity score value of the customer according to the power outage sensitivity description information.
For example, the power outage sensitivity labeling model may obtain an initialized power outage sensitivity score according to the historical power outage complaint times of the customer, and if the historical power outage complaint times of the customer exceeds 5 times within 1 year, the initialized power outage sensitivity of the customer is labeled to be a higher power outage sensitivity score.
The power failure sensitivity score value can be a judgment standard for the power failure sensitivity of the client, and can be calculated according to the power failure sensitivity description information. For example, if the emotional intensity of the complaint content of a certain client is expressed as strong within 5 times of 1 year, the power failure sensitivity of the client can be initialized and marked to be 80 points by the power failure sensitivity marking model.
The power failure sensitive time period can be a time range in which a customer has the strongest response to the power failure, and can be determined according to the complaint time of the customer or the power failure time of a line or a station area to which the customer belongs. For example, a customer complains about power outage 5 times in 1 year, wherein 3 complains occur between 19 hours and 21 hours, and the time period from 19 hours to 21 hours can be initialized and marked as the power outage sensitivity time period of the customer through the power outage sensitivity marking model. It should be noted that, when a certain client is subjected to power outage sensitivity marking, if the power outage sensitivity score value of the client is greater than or equal to the preset threshold, the power outage sensitivity time period of the client may be marked at the same time.
Optionally, according to the formed power outage sensitivity description information with the customer as the dimension, the power outage sensitivity description information with the customer as the dimension can be sent to a power outage sensitivity labeling model containing a labeling rule, after the power outage sensitivity description information with the customer as the dimension is initialized and labeled according to the labeling rule, manual intervention and rechecking are performed, and therefore a final power outage sensitivity labeling result corresponding to the first class of customers is obtained.
S130, according to the power outage sensitivity description information of each first class of client and the power outage sensitivity labeling result, training and verifying the XGboost model to obtain a power outage sensitivity prediction model.
The power failure sensitivity prediction model can be a prediction model obtained by training a first class of clients as a labeling sample.
Specifically, the power outage sensitivity description information of the first class of clients and the matched power outage sensitivity marking result can be sent to the XGboost model for at least one round of training verification, so that the XGboost model learns the internal relationship between the power outage sensitivity description information and the power outage sensitivity marking result, the internal relationship is embodied through model parameters, and the XGboost model after the model parameters are adjusted serves as a power outage sensitivity prediction model. The XGboost model is one of gradient lifting tree models, and is also a series generation model, the sum of all models is taken as output for supervising learning problems, and training data with multiple functions can be used for predicting target variables.
In an optional embodiment of the present invention, the training and verification of the XGBoost model according to the blackout sensitivity description information of each first class of client and the blackout sensitivity labeling result to obtain the blackout sensitivity prediction model may include:
and dividing each first class of client into a training sample and a verification sample, and performing at least one round of training verification on the XGboost model by using the training sample and the verification sample to obtain the power outage sensitivity prediction model.
The training samples can be sample type first type clients used for training the XGboost model in the first type clients, and the verification samples can be verification type first type clients used for verifying training results of the training samples in the first type clients. The training samples and the verification samples can be alternately changed, and the setting has the advantage that the accuracy of the prediction result of the power failure sensitivity prediction model can be improved.
In this embodiment, the first class of clients may be divided into one or more groups of training samples and verification samples, the blackout sensitivity description information of the training samples and the verification samples, and the blackout sensitivity labeling result are input to the XGBoost model to perform at least one round of training verification, and finally, the blackout sensitivity prediction model may be obtained.
And S140, inputting the power outage sensitivity description information of each second type of client into the power outage sensitivity prediction model, and acquiring the power outage sensitivity corresponding to each second type of client.
Alternatively, the blackout sensitivity description information of each second-class client may be input to a blackout sensitivity prediction model trained and verified in advance, so that the output result of the blackout sensitivity prediction model may be determined as blackout sensitivities corresponding to the second-class clients, respectively.
The power failure sensitivity forecasting model simultaneously comprises a power failure sensitivity score and at least one power failure sensitivity time period aiming at the power failure sensitivity output by each second type customer; alternatively, only the blackout sensitivity score value is included in the blackout sensitivity.
Specifically, if the output blackout sensitivity score is greater than or equal to a preset threshold, at least one blackout sensitivity time period is output at the same time, and if the output blackout sensitivity score is less than the preset threshold, the blackout sensitivity score is only output. According to the technical scheme of the embodiment, power failure sensitivity description information corresponding to each client is formed according to a plurality of items of electricity utilization description data; dividing the clients into first type clients and second type clients, and acquiring the marking result of the power failure sensitivity corresponding to each first type client; training and verifying the XGboost model according to the power outage sensitivity description information of each first class of client and the power outage sensitivity labeling result to obtain a power outage sensitivity prediction model; and inputting the power outage sensitivity description information of each second type of client into the power outage sensitivity prediction model, and acquiring the power outage sensitivity corresponding to each second type of client. The technical scheme of the embodiment of the invention solves the problem of inconsistent power failure sensitivity judgment standards caused by the fact that power failure sensitivity clients are distributed in various industries and various client types, and realizes the purpose of excavating the data types useful for power failure sensitivity judgment in massive data, thereby achieving the effect of carrying out quantifiable effective prediction on the power failure sensitivity of the clients.
Example two
Fig. 2 is a flowchart of another method for determining blackout sensitivity according to a second embodiment of the present invention, in this embodiment, based on the foregoing embodiments, it is preferable to further increase operations after acquiring blackout sensitivities respectively corresponding to the second type customers, and the technical solution in this embodiment may be combined with various alternatives in one or more of the foregoing embodiments. As shown in fig. 2, the method for determining the power outage sensitivity may include the following steps:
and S210, forming power failure sensitivity description information corresponding to each client according to the plurality of items of power utilization description data.
And S220, dividing the clients into first type clients and second type clients, and acquiring the marking result of the power failure sensitivity corresponding to each first type client.
And S230, training and verifying the XGboost model according to the power outage sensitivity description information of each first class of client and the power outage sensitivity labeling result to obtain a power outage sensitivity prediction model.
And S240, inputting the power outage sensitivity description information of each second type of client into the power outage sensitivity prediction model, and acquiring the power outage sensitivity corresponding to each second type of client.
And S250, calculating power outage sensitivities respectively corresponding to the areas and the lines according to the areas and the lines to which the clients belong and by using the power outage sensitivities of the clients.
The blackout sensitivity of each district and each line can include a blackout sensitivity score value and at least one blackout sensitivity time period.
Optionally, according to the obtained power outage sensitivities of the clients, the power outage sensitivities of the distribution area and the line to which the clients belong can be calculated and obtained respectively.
For example, the average of the blackout sensitivity score values of all subordinate customers in a certain area is used as the blackout sensitivity score value corresponding to the certain area. If the power failure sensitivity score value corresponding to the distribution area is greater than or equal to the preset threshold, the power failure sensitive time periods of all subordinate customers or the power failure sensitive time periods with higher occurrence frequency in all subordinate customers can be used as the power failure sensitive time periods corresponding to the distribution area.
Specifically, the blackout sensitive time periods of the station areas and the lines to which the customers belong can be respectively determined according to the blackout sensitive time periods of the customers. For example, if 80% of all subordinate customers corresponding to a line have a blackout sensitivity time period of (19:00-20:00), then (19:00-20:00) may be determined as a blackout sensitivity time period of the line.
According to the technical scheme of the embodiment, power failure sensitivity description information corresponding to each client is formed according to a plurality of items of electricity utilization description data; dividing the clients into first type clients and second type clients, and acquiring the marking result of the power failure sensitivity corresponding to each first type client; training and verifying the XGboost model according to the power outage sensitivity description information of each first class of client and the power outage sensitivity labeling result to obtain a power outage sensitivity prediction model; inputting the power outage sensitivity description information of each second type of client into the power outage sensitivity prediction model, and acquiring power outage sensitivities corresponding to the second type of clients respectively; and calculating the power failure sensitivity corresponding to each station area and the power failure sensitivity corresponding to each line respectively according to the station area and the line to which each client belongs and by using the power failure sensitivity of each client. The technical scheme of the embodiment of the invention solves the problem of inconsistent power failure sensitivity judgment standards caused by the fact that power failure sensitivity clients are distributed in various industries and various client types, and realizes the purpose of excavating the data types useful for power failure sensitivity judgment in massive data, thereby achieving the effect of carrying out quantifiable effective prediction on the power failure sensitivity of the clients.
In an optional embodiment of the present invention, after calculating the outage sensitivities respectively corresponding to the distribution areas and the lines, the method may further include: acquiring a target station area and a target line of which the power failure sensitivity score value in the power failure sensitivity is greater than or equal to a preset early warning threshold; and sending matched early warning information to the target transformer area and a power supply station where the target line is located so as to carry out power failure sensitivity early warning.
The early warning threshold may be an upper limit value of the power failure sensitivity score of each station area and each line. The target station zone may be a station zone on which an early warning operation is to be performed. The target line may be a line on which an early warning operation is to be performed. The early warning information may be information for warning in advance, for example, "XX power supply bureau, XX station area belongs to high power outage susceptibility station area, please arrange power outage plan reasonably. ".
Specifically, the power distribution area and the line with the power outage susceptibility score value larger than or equal to the preset early warning threshold in the power outage susceptibility can be screened out to serve as the target power distribution area and the target line, and for the power supply bureau where the target power distribution area and the target line are located, matched early warning information is sent according to the power outage susceptibility corresponding to the target power distribution area and the target line to perform power outage susceptibility early warning, so that the power outage plan is reasonably arranged in the current power supply bureau.
The method has the advantages that the power supply station area and the power supply line with high power failure sensitivity can be screened out, early warning information is issued in advance, and the power supply station where the target power supply station area and the target power supply line are located is reminded of making power failure plan arrangement, so that the customer satisfaction degree is improved.
In an optional embodiment of the present invention, after calculating the outage sensitivities respectively corresponding to the distribution areas and the lines, the method may further include: acquiring power failure sensitivity of each line and each distribution area in a target area according to power failure demand information matched with the target area; and executing a power outage optimization processing strategy matched with the power outage sensitivities of each line and each station area included in the target area.
The target area may be an area to be determined as a subordinate area and line outage sensitivity. The power outage demand information may be information that a power outage plan must be executed, and may include planned, temporary, orderly power utilization and outage, fault and outage information, and the like. The blackout optimization processing strategy can be an improvement method for blackout planning according to blackout sensitivity. For example, for a station area and a line with high power failure sensitivity, when the power supply bureau aims at scheduled, temporary and orderly power utilization and power failure, the power supply bureau can optimally arrange the power failure or reasonably avoid the power failure sensitivity time period. When power failure occurs, transformation maintenance and customer communication pacifying can be carried out by issuing each district and county bureau, and customer satisfaction is improved.
In this embodiment, the blackout sensitivities of each area and each line included in the target area may be obtained according to the blackout demand information of a certain area, so as to match a scientific blackout optimization processing strategy with the blackout sensitivities of each line and each area included in the target area.
The method has the advantages that the power failure sensitivity of the power consumption client is judged in advance, so that the coping strategy can be made in advance, the scientificity of the strategy is improved, the client satisfaction is improved, and the reliability and public praise of the power supply company are improved.
EXAMPLE III
Fig. 3 is a schematic structural diagram of an apparatus for determining blackout sensitivity according to a third embodiment of the present invention, which is capable of executing a method for determining blackout sensitivity according to any embodiment of the present invention, and referring to fig. 3, the apparatus includes: a description information forming module 310, a labeling result obtaining module 320, a prediction model obtaining module 330 and a power outage sensitivity obtaining module 340.
A description information forming module 310, configured to form, according to the multiple items of electricity usage description data, blackout sensitivity description information corresponding to each customer, where the blackout sensitivity description information includes: customer attribute information, historical power failure complaint information and historical power failure information;
a labeling result obtaining module 320, configured to divide the clients into first type clients and second type clients, and obtain a labeling result of the power outage sensitivity corresponding to each first type client;
the prediction model acquisition module 330 is configured to train and verify the XGBoost model according to the power outage sensitivity description information of each first class of client and the power outage sensitivity labeling result to obtain a power outage sensitivity prediction model;
the blackout sensitivity obtaining module 340 is configured to input blackout sensitivity description information of each second type customer into the blackout sensitivity prediction model, and obtain blackout sensitivities corresponding to the second type customers respectively.
According to the technical scheme of the embodiment, power failure sensitivity description information corresponding to each client is formed according to a plurality of items of electricity utilization description data; dividing the clients into first type clients and second type clients, and acquiring the marking result of the power failure sensitivity corresponding to each first type client; training and verifying the XGboost model according to the power outage sensitivity description information of each first class of client and the power outage sensitivity labeling result to obtain a power outage sensitivity prediction model; and inputting the power outage sensitivity description information of each second type of client into the power outage sensitivity prediction model, and acquiring the power outage sensitivity corresponding to each second type of client. The technical scheme of the embodiment of the invention solves the problem of inconsistent power failure sensitivity judgment standards caused by the fact that power failure sensitivity clients are distributed in various industries and various client types, and realizes the purpose of excavating the data types useful for power failure sensitivity judgment in massive data, thereby achieving the effect of carrying out quantifiable effective prediction on the power failure sensitivity of the clients.
In the above apparatus, optionally, the electricity usage description data includes: customer service work order data, customer archive data, line transformer data and power failure description data; the client attribute information includes: user category, electricity usage category, industry category, and customer behavior information; the historical power failure complaint information comprises: the type, time, frequency and content of complaints of the complaint are determined in a set historical time interval; the power failure description information includes: the power failure times and the power failure types of the line in the set historical time interval, and the power failure times and the power failure types of the station area in the set historical time interval.
In the above apparatus, optionally, the labeling result obtaining module 320 may be specifically configured to: sending the power failure sensitivity description information of each first type of client to a manual marking platform, and acquiring the marking result of the power failure sensitivity corresponding to each first type of client by the manual marking platform; wherein, the marking result of the power failure sensitivity comprises: the system comprises a power outage sensitivity score value and at least one power outage sensitivity time period, wherein the power outage sensitivity time period is marked when the power outage sensitivity score value is larger than or equal to a preset threshold value.
In the above apparatus, optionally, the prediction model obtaining module 330 may be specifically configured to: and dividing each first class of client into a training sample and a verification sample, and performing at least one round of training verification on the XGboost model by using the training sample and the verification sample to obtain the power outage sensitivity prediction model.
Optionally, in the above apparatus, the apparatus further includes a power outage sensitivity calculation module, which is specifically configured to, after acquiring the power outage sensitivities respectively corresponding to the second type customers, calculate, according to the station area to which each customer belongs and the line to which each customer belongs, the power outage sensitivities of each customer, using the power outage sensitivities of each customer, to obtain the power outage sensitivities respectively corresponding to each station area and each line.
In the above apparatus, optionally, further comprising a power outage sensitivity early warning module, which may be specifically configured to: after calculating power failure sensitivity corresponding to each distribution area and power failure sensitivity corresponding to each line, acquiring a target distribution area and a target line, of which the power failure sensitivity score value is greater than or equal to a preset early warning threshold, in the power failure sensitivity; and sending matched early warning information to the target transformer area and a power supply station where the target line is located so as to carry out power failure sensitivity early warning.
Optionally, the apparatus further includes a power outage optimization processing policy execution module, which is specifically configured to, after calculating power outage sensitivities respectively corresponding to the distribution areas and power outage sensitivities respectively corresponding to the lines, obtain power outage sensitivities of the lines and the distribution areas included in the target area according to power outage requirement information matched with the target area; and executing a power outage optimization processing strategy matched with the power outage sensitivities of each line and each station area included in the target area.
The power failure sensitivity determining device provided by the embodiment of the invention can execute the power failure sensitivity determining method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.
Example four
Fig. 4 is a schematic structural diagram of an apparatus according to a fourth embodiment of the present invention, as shown in fig. 4, the apparatus includes a processor 410, a storage device 420, an input device 430, and an output device 440; the number of the processors 410 in the device may be one or more, and one processor 410 is taken as an example in fig. 4; the processor 410, the storage 420, the input 430 and the output 440 of the apparatus may be connected by a bus or other means, as exemplified by the bus connection in fig. 4.
The storage device 420 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the method for determining the blackout sensitivity in the embodiment of the present invention (for example, the description information forming module 310, the annotation result obtaining module 320, the prediction model obtaining module 330, and the blackout sensitivity obtaining module 340 in the device for determining the blackout sensitivity). The processor 410 executes software programs, instructions and modules stored in the storage device 420 to execute various functional applications and data processing of the equipment, namely, to implement the above power outage susceptibility determination method, which includes:
according to the plurality of items of electricity utilization description data, power outage sensitivity description information corresponding to each client is formed, and the power outage sensitivity description information comprises: customer attribute information, historical power failure complaint information and historical power failure information;
dividing the clients into first type clients and second type clients, and acquiring the marking result of the power failure sensitivity corresponding to each first type client;
training and verifying the XGboost model according to the power outage sensitivity description information of each first class of client and the power outage sensitivity labeling result to obtain a power outage sensitivity prediction model;
and inputting the power outage sensitivity description information of each second type of client into the power outage sensitivity prediction model, and acquiring the power outage sensitivity corresponding to each second type of client.
The storage device 420 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the storage 420 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the storage 420 may further include memory located remotely from the processor 410, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 430 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the apparatus. The output device 440 may include a display device such as a display screen.
EXAMPLE five
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a method for determining a power outage susceptibility, the method including:
according to the plurality of items of electricity utilization description data, power outage sensitivity description information corresponding to each client is formed, and the power outage sensitivity description information comprises: customer attribute information, historical power failure complaint information and historical power failure information;
dividing the clients into first type clients and second type clients, and acquiring the marking result of the power failure sensitivity corresponding to each first type client;
training and verifying the XGboost model according to the power outage sensitivity description information of each first class of client and the power outage sensitivity labeling result to obtain a power outage sensitivity prediction model;
and inputting the power outage sensitivity description information of each second type of client into the power outage sensitivity prediction model, and acquiring the power outage sensitivity corresponding to each second type of client.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the method operations described above, and may also perform related operations in the method for determining the power outage sensitivity provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the above search apparatus, each included unit and module are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method for determining outage susceptibility, comprising:
according to the plurality of items of electricity utilization description data, power outage sensitivity description information corresponding to each client is formed, and the power outage sensitivity description information comprises: customer attribute information, historical power failure complaint information and historical power failure information;
dividing the clients into first type clients and second type clients, and acquiring the marking result of the power failure sensitivity corresponding to each first type client;
training and verifying the XGboost model according to the power outage sensitivity description information of each first class of client and the power outage sensitivity labeling result to obtain a power outage sensitivity prediction model;
and inputting the power outage sensitivity description information of each second type of client into the power outage sensitivity prediction model, and acquiring the power outage sensitivity corresponding to each second type of client.
2. The method of claim 1, wherein the electricity usage description data comprises: customer service work order data, customer archive data, line transformer data and power failure description data;
the client attribute information includes: user category, electricity usage category, industry category, and customer behavior information;
the historical power failure complaint information comprises: the type, time, frequency and content of complaints of the complaint are determined in a set historical time interval;
the power failure description information includes: the power failure times and the power failure types of the line in the set historical time interval, and the power failure times and the power failure types of the station area in the set historical time interval.
3. The method of claim 1 or 2, wherein obtaining the annotated result of outage susceptibility corresponding to each first type of customer comprises:
sending the power failure sensitivity description information of each first type of client to a manual marking platform, and acquiring the marking result of the power failure sensitivity corresponding to each first type of client by the manual marking platform;
wherein, the marking result of the power failure sensitivity comprises: the system comprises a power outage sensitivity score value and at least one power outage sensitivity time period, wherein the power outage sensitivity time period is marked when the power outage sensitivity score value is larger than or equal to a preset threshold value.
4. The method as claimed in claim 1, wherein training and verifying the XGBoost model according to the blackout sensitivity description information of each first class customer and the blackout sensitivity labeling result to obtain a blackout sensitivity prediction model comprises:
and dividing each first class of client into a training sample and a verification sample, and performing at least one round of training verification on the XGboost model by using the training sample and the verification sample to obtain the power outage sensitivity prediction model.
5. The method of claim 1, after obtaining blackout sensitivities corresponding to the second type customers, further comprising:
and calculating the power failure sensitivity corresponding to each station area and the power failure sensitivity corresponding to each line respectively according to the station area and the line to which each client belongs and by using the power failure sensitivity of each client.
6. The method of claim 5, wherein after calculating the outage sensitivities corresponding to the respective distribution areas and the respective lines, further comprising:
acquiring a target station area and a target line of which the power failure sensitivity score value in the power failure sensitivity is greater than or equal to a preset early warning threshold;
and sending matched early warning information to the target transformer area and a power supply station where the target line is located so as to carry out power failure sensitivity early warning.
7. The method of claim 5, wherein after calculating the outage sensitivities corresponding to the respective distribution areas and the respective lines, further comprising:
acquiring power failure sensitivity of each line and each distribution area in a target area according to power failure demand information matched with the target area;
and executing a power outage optimization processing strategy matched with the power outage sensitivities of each line and each station area included in the target area.
8. An apparatus for determining susceptibility to blackouts, comprising:
the description information forming module is used for forming power outage sensitivity description information corresponding to each customer according to the plurality of items of electricity utilization description data, and the power outage sensitivity description information comprises: customer attribute information, historical power failure complaint information and historical power failure information;
the marking result acquisition module is used for dividing the clients into first type clients and second type clients and acquiring the marking result of the power failure sensitivity corresponding to each first type client;
the prediction model acquisition module is used for training and verifying the XGboost model according to the power outage sensitivity description information of each first class of client and the power outage sensitivity marking result to obtain a power outage sensitivity prediction model;
and the power outage sensitivity acquisition module is used for inputting the power outage sensitivity description information of each second type of client into the power outage sensitivity prediction model and acquiring the power outage sensitivity corresponding to each second type of client.
9. A computer device, characterized in that the computer device comprises:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method for determining outage susceptibility according to any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method for determining blackout sensitivity according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111249730.1A CN113887830A (en) | 2021-10-26 | 2021-10-26 | Method, device, equipment and medium for determining power failure sensitivity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111249730.1A CN113887830A (en) | 2021-10-26 | 2021-10-26 | Method, device, equipment and medium for determining power failure sensitivity |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113887830A true CN113887830A (en) | 2022-01-04 |
Family
ID=79014519
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111249730.1A Pending CN113887830A (en) | 2021-10-26 | 2021-10-26 | Method, device, equipment and medium for determining power failure sensitivity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113887830A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220732A (en) * | 2017-05-31 | 2017-09-29 | 福州大学 | A kind of power failure complaint risk Forecasting Methodology based on gradient boosted tree |
| CN108537682A (en) * | 2018-03-26 | 2018-09-14 | 国家电网公司客户服务中心 | Scheduled outage sensitive client recognition methods based on improved entropy method |
| CN109063943A (en) * | 2018-06-01 | 2018-12-21 | 广东电网有限责任公司 | A kind of method of plan for adjustment power off time window |
| CN109948913A (en) * | 2019-03-01 | 2019-06-28 | 长沙理工大学 | A kind of multi-source feature power consumer composite portrait system based on double-deck xgboost algorithm |
| CN111415049A (en) * | 2020-04-27 | 2020-07-14 | 国网河北能源技术服务有限公司 | Power failure sensitivity analysis method based on neural network and clustering |
| CN112418541A (en) * | 2020-12-02 | 2021-02-26 | 国网浙江省电力有限公司营销服务中心 | Method for predicting and evaluating customer power failure sensitivity |
| CN112766550A (en) * | 2021-01-08 | 2021-05-07 | 佰聆数据股份有限公司 | Power failure sensitive user prediction method and system based on random forest, storage medium and computer equipment |
-
2021
- 2021-10-26 CN CN202111249730.1A patent/CN113887830A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220732A (en) * | 2017-05-31 | 2017-09-29 | 福州大学 | A kind of power failure complaint risk Forecasting Methodology based on gradient boosted tree |
| CN108537682A (en) * | 2018-03-26 | 2018-09-14 | 国家电网公司客户服务中心 | Scheduled outage sensitive client recognition methods based on improved entropy method |
| CN109063943A (en) * | 2018-06-01 | 2018-12-21 | 广东电网有限责任公司 | A kind of method of plan for adjustment power off time window |
| CN109948913A (en) * | 2019-03-01 | 2019-06-28 | 长沙理工大学 | A kind of multi-source feature power consumer composite portrait system based on double-deck xgboost algorithm |
| CN111415049A (en) * | 2020-04-27 | 2020-07-14 | 国网河北能源技术服务有限公司 | Power failure sensitivity analysis method based on neural network and clustering |
| CN112418541A (en) * | 2020-12-02 | 2021-02-26 | 国网浙江省电力有限公司营销服务中心 | Method for predicting and evaluating customer power failure sensitivity |
| CN112766550A (en) * | 2021-01-08 | 2021-05-07 | 佰聆数据股份有限公司 | Power failure sensitive user prediction method and system based on random forest, storage medium and computer equipment |
Non-Patent Citations (1)
| Title |
|---|
| 刘平: "基于快速恢复供电的应急抢修研究", 《电力安全技术》, vol. 16, no. 4, 10 April 2014 (2014-04-10), pages 1 - 4 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106815709B (en) | Service quick response center support system and method | |
| CN111815132B (en) | Network security management information publishing method and system for power monitoring system | |
| CN111291076B (en) | Abnormal water use monitoring alarm system based on big data and construction method thereof | |
| CN110097297A (en) | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium | |
| CN113159339A (en) | One-region one-index line loss management method and system based on big data | |
| CN112307003B (en) | Power grid data multidimensional auxiliary analysis method, system, terminal and readable storage medium | |
| CN110807550A (en) | Distribution transformer overload identification early warning method based on neural network and terminal equipment | |
| CN206312210U (en) | State evaluation system of power distribution network equipment | |
| CN111310803B (en) | Environment data processing method and device | |
| CN111552686B (en) | Power data quality assessment method and device | |
| CN111507013A (en) | Line loss fault positioning implementation method for power system | |
| CN105488118A (en) | Electrical equipment fault information display method and device | |
| CN116596512B (en) | Electric power operation and maintenance safety strengthening method and system based on information system | |
| CN114596693A (en) | Method, system, medium, and program product for energy monitoring and management | |
| CN108304990B (en) | Power failure sensitivity pre-judging method and system | |
| CN113610253A (en) | Operation and maintenance management type photovoltaic station control system based on CS version | |
| CN112862172A (en) | State network 95598 power failure complaint prediction method and device, computer equipment and storage medium | |
| CN116522746A (en) | Power distribution hosting method for high-energy-consumption enterprises | |
| CN115965266A (en) | Intelligent analysis system based on big data | |
| CN114548800A (en) | Future-state power grid maintenance risk identification method and device based on power grid knowledge graph | |
| CN115409264A (en) | Power distribution network emergency repair stagnation point position optimization method based on feeder line fault prediction | |
| CN114254806A (en) | Power distribution network heavy overload early warning method and device, computer equipment and storage medium | |
| CN117614137A (en) | Power distribution network optimization system based on multi-source data fusion | |
| CN112598257A (en) | Power failure analysis method and system based on big data feature mining | |
| CN104484765A (en) | Method for evaluating whether urban power supply network reaches world first-class level or not |
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 |