CN108009224A - The sorting technique and device of power customer - Google Patents
The sorting technique and device of power customer Download PDFInfo
- Publication number
- CN108009224A CN108009224A CN201711193121.2A CN201711193121A CN108009224A CN 108009224 A CN108009224 A CN 108009224A CN 201711193121 A CN201711193121 A CN 201711193121A CN 108009224 A CN108009224 A CN 108009224A
- Authority
- CN
- China
- Prior art keywords
- data
- power customer
- multiple power
- reconstructed
- customer
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses the sorting technique and device of a kind of power customer.Wherein, this method includes：Obtain the data of multiple power customers；Data reconstruction processing is carried out to the data of multiple power customers, obtains reconstruct data；Based on reconstruct data structure disaggregated model；Classified according to disaggregated model to multiple power customers, obtain classification results.The present invention solves the technical problem that can not fast and accurately classify in the prior art to power customer.
Description
Technical field
The present invention relates to electric power network field, in particular to the sorting technique and device of a kind of power customer.
Background technology
State Council started new round power system reform in 2015, encouraged societal forces to participate in electrical power services industry,
Form electrical power services marketization general layout.Electrical power services market-oriented reform proposes conventional electric power company new requirement, tradition electricity
Power company must be from traditional passive customer service model to the active client service transformation of the marketization.Change one of basis
It is as customer-centric to provide a variety of services such as power supply, maintenance, sale of electricity, energy saving.
Traditional client segmentation usually classifies client according to industry, electricity consumption type, power consumption size, however, mesh
Preceding Electric Power Marketing System and power information acquisition system are supported to carry out meterage, point belonging to user by the cycle to Electricity customers
Class from carry out per year before examination change at present monthly, ten days, week, or even classifying, updating is daily carried out to key client, from now on
With the maturation in the markets such as Demand Side Response, electric power stock, futures, hour, 15 are up to the requirement of customer type renewal frequency
The rank of minute once.Since customer action is a dynamic process, the obtained client of existing sorting technique point is used
The subdivision degree of class result, classification results update cycle are longer, it is impossible to accurately reflect the type belonging to client.
For above-mentioned the problem of can not fast and accurately classifying in the prior art to power customer, not yet propose at present
Effective solution.
The content of the invention
An embodiment of the present invention provides the sorting technique and device of a kind of power customer, with least solve in the prior art without
The technical problem that method fast and accurately classifies power customer.
One side according to embodiments of the present invention, there is provided a kind of sorting technique of power customer, including：Obtain multiple
The data of power customer；Data reconstruction processing is carried out to the data of multiple power customers, obtains reconstruct data；Based on reconstruct data
Build disaggregated model；Classified according to disaggregated model to multiple power customers, obtain classification results.
Another aspect according to embodiments of the present invention, additionally provides a kind of sorter of power customer, including：Obtain mould
Block, for obtaining the data of multiple power customers；Reconstructed module, for being carried out to the data of multiple power customers at data reconstruction
Reason, obtains reconstruct data；Module is built, for based on reconstruct data structure disaggregated model；Sort module, for according to classification mould
Type classifies multiple power customers, obtains classification results.
Another aspect according to embodiments of the present invention, additionally provides a kind of storage medium, which includes storage
Program, wherein, program performs the sorting technique of power customer.
Another aspect according to embodiments of the present invention, additionally provides a kind of processor, which is used for operation program, its
In, the sorting technique of execution power customer when program is run.
In embodiments of the present invention, by the way of big data reconstruct, by obtaining the data of multiple power customers, to more
The data of a power customer carry out data reconstruction processing, obtain reconstruct data, are then based on reconstruct data structure disaggregated model, most
Classified afterwards according to disaggregated model to multiple power customers, obtain classification results, reached and power customer has been carried out accurately, soon
The purpose of speed classification, and then solve the technical problem that can not fast and accurately classify in the prior art to power customer.
Brief description of the drawings
Attached drawing described herein is used for providing a further understanding of the present invention, forms the part of the application, this hair
Bright schematic description and description is used to explain the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 is a kind of sorting technique flow chart of power customer according to embodiments of the present invention；
Fig. 2 is a kind of schematic diagram of disaggregated model optionally based on three dimensions according to embodiments of the present invention；
Fig. 3 is a kind of block schematic illustration of the sorting technique of preferable power customer according to embodiments of the present invention；And
Fig. 4 is a kind of block schematic illustration of the sorting technique of preferable power customer according to embodiments of the present invention.
Embodiment
In order to make those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Attached drawing, is clearly and completely described the technical solution in the embodiment of the present invention, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
Member's all other embodiments obtained without making creative work, should all belong to the model that the present invention protects
Enclose.
It should be noted that term " first " in description and claims of this specification and above-mentioned attached drawing, "
Two " etc. be for distinguishing similar object, without for describing specific order or precedence.It should be appreciated that so use
Data can exchange in the appropriate case, so as to the embodiment of the present invention described herein can with except illustrating herein or
Order beyond those of description is implemented.In addition, term " comprising " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, be not necessarily limited to for example, containing the process of series of steps or unit, method, system, product or equipment
Those steps or unit clearly listed, but may include not list clearly or for these processes, method, product
Or the intrinsic other steps of equipment or unit.
Embodiment 1
According to embodiments of the present invention, there is provided a kind of sorting technique embodiment of power customer is, it is necessary to illustrate, attached
The step of flow of figure illustrates can perform in the computer system of such as a group of computer-executable instructions, though also,
So logical order is shown in flow charts, but in some cases, can be with different from shown by order execution herein
Or the step of description.
Fig. 1 is the sorting technique flow chart of power customer according to embodiments of the present invention, as shown in Figure 1, this method includes
Following steps：
Step S102, obtains the data of multiple power customers.
It should be noted that the sorter of power customer can perform the classification side of power customer provided herein
Method.Wherein, taken out according to the demand of subdivision business, the sorter of power customer from the relevant database of power business system
Take the data of power customer, and the data to being drawn into carry out the analysis of the quality of data, data conversion, cleaning etc. and operate, and then
Generate the data of qualified power customer.
In addition it is also necessary to explanation, the sorter of power customer can pass through ETL (Extract-Transform-
Load, data warehouse technology) extract, database replicates and the technology such as Web Service interfaces extracts data.Wherein, close
It is that data pick-up between type database can use Kettle instruments to realize, on the sorter of power customer
Data pick-up Sqoop instruments between Hadoop system and relevant database realize that substantial amounts of daily record data uses Flume systems
System is extracted.In addition, the sorter of power customer can extract number by Web Service interfaces from power business system
According to.
The data of multiple power customers are carried out data reconstruction processing, obtain reconstruct data by step S104.
It should be noted that the data of multiple power customers to being drawn into are reconstructed, it can effectively remove electric power visitor
Redundant data in the data at family, so as to form the data of effective power customer, that is, obtains reconstruct data.It is easily noted that
It is during the data of power customer are reconstructed, to eliminate redundant data, effectively reduces and power customer is carried out
The burden of classification, and then improve the processing speed classified to power customer.
Step S106, based on reconstruct data structure disaggregated model.
It should be noted that after reconstruct data are obtained, disaggregated model is established according to reconstruct data, wherein, this point
Class model can be built into the disaggregated model with three dimensions as shown in Figure 2.
Step S108, classifies multiple power customers according to disaggregated model, obtains classification results.
It should be noted that after reconstruct data are obtained, according to disaggregated model combination Hadoop technologies and Spark skills
Art, classifies reconstruct data.Wherein, clustering algorithm can be used to classify reconstruct data, above-mentioned clustering algorithm can be with
For but be not limited to k-means clustering algorithms.
The scheme limited based on above-mentioned steps S102 to step S108, can know, by obtaining multiple power customers
Data, data reconstruction processing is carried out to the data of multiple power customers, obtains reconstruct data, is then based on reconstruct data structure
Disaggregated model, finally classifies multiple power customers according to disaggregated model, obtains classification results.
It is easily noted that, since the data of multiple power customers to getting have carried out data reconstruction processing, because
This, can effectively filter out the redundant data in the data of multiple power customers, power customer is divided so as to reduce
The burden of class processing, and then the accuracy and real-time calculated the data of power customer is improved, realize to electric power
The technique effect that customer segmentation is quick and precisely classified.
As shown in the above, embodiment provided herein, which can reach, carries out power customer accurate, quick point
The purpose of class, and then solve the technical problem that can not fast and accurately classify in the prior art to power customer.
In addition it is also necessary to explanation, due to the data in original data source, that is, the number of the multiple power customers got
According to, from multiple systems or file, the quality of data there are it is inconsistent the problem of, therefore, obtaining multiple power customers
After data, it is also necessary to carry out filtration treatment to the data of multiple power customers, specific method includes the following steps：
Step S102a, obtains preset condition and preset algorithm in preset algorithm storehouse；
Step S102b, determines to be unsatisfactory for the first data of preset condition in the data of multiple power customers；
Step S102c, handles the first data based on preset algorithm, obtains the second data；
Step S102d, the first data in the data of the multiple power customers of the second data update, after being updated
The data of multiple power customers.
It should be noted that above-mentioned preset algorithm storehouse includes preset condition and preset algorithm, wherein, above-mentioned preset condition is
The verification rule that the data of multiple power customers are filtered, above-mentioned preset algorithm be to be unsatisfactory for the data of preset condition into
Row processing, makes it meet the algorithm of preset condition.In addition, above-mentioned first data are the number for the power customer for being unsatisfactory for preset condition
According to the second data are the obtained power customer for meeting preset condition after being handled using preset algorithm the first data
Data.
In a kind of optional embodiment, after the data of multiple power customers are obtained, to the number of multiple power customers
According to the filtering for rule of testing, and obtain being unsatisfactory for verifying regular data from handling result.Then preset algorithm is used
The data for being unsatisfactory for verification rule are handled, and the data after processing are continued with the filtering of verification rule, until institute
Untill the data of some power customers are satisfied by preset condition.In addition, complete the verification to the data of multiple power customers
After process, can by used in checking procedure to preset algorithm and preset condition store or be updated to preset algorithm storehouse
In, so as to which when verifying next time, preset condition and/or preset algorithm can be directly invoked.
It should be noted that after being verified to the data of multiple power customers, the sorter of power customer after
The continuous data to multiple power customers carry out data reconstruction, i.e. data reconstruction is the data in the multiple power customers got
On the basis of, reorganized according to multiple dimensions of power customer demand, so as to obtain reconstruct data.Wherein, to multiple electricity
The data of power client carry out data reconstruction processing, and the method for obtaining reconstruct data includes the following steps：
The data of multiple power customers are reconstructed processing based on the first parameter, obtain the first reconstruct number by step S104a
According to, wherein, the first parameter includes at least one of following：Annual electricity, cycle electricity and the cycle electricity ring ratio of power customer
Change rate；
The data of multiple power customers are reconstructed processing based on the second parameter, obtain the second reconstruct number by step S104b
According to, wherein, the second parameter includes at least one of following：Annual troublshooting number, the cycle fault of power customer report number for repairment
And the cycle reports ring for repairment and compares change rate；
The data of multiple power customers are reconstructed processing based on the 3rd parameter, obtain third reconstructed number by step S104c
According to, wherein, the 3rd parameter includes at least one of following：Power customer uses number, the cycle access system number of mobile terminal
And the number of electricity is bought by mobile terminal.
It should be noted that reconstruct data include the first reconstruct data, the second reconstruct data and third reconstructed data.Its
In, first reconstruct data be power customer value data, second reconstruct data be power customer electricity consumption level data, the 3rd
It is that the data of mobile terminal are used based on power consumer to reconstruct data.
Specifically, the data of multiple power customers are reconstructed by the following method, the first reconstruct data are obtained：
The first power customer that annual electricity is more than annual power threshold X1 is filtered out from multiple power customers；Then,
The second power customer that cycle electricity is more than cycle power threshold Y1 is filtered out from the first power customer；Finally, from the second electricity
The 3rd power customer that cycle electricity ring is more than change rate threshold value W1 than change rate is filtered out in power client.Wherein.3rd electric power
The data of client are the first reconstruct data.After the first reconstruct data are obtained, the first reconstruct data are stored to relationship type
In database.
It should be noted that the data of multiple power customers are reconstructed, the process for obtaining the second reconstruct data is main
It is the number of reporting for repairment based on power consumer and the aspect of nature of trouble two to carry out data reconstruction.Specifically, power customer
The data that sorter determines to meet the power customer of following three condition at the same time from the data of multiple power customers are used as the
Two reconstruct data：
Condition one：The annual troublshooting number of power customer is more than reporting threshold X 2 year for repairment；
Condition two：The cycle fault of power customer reports number for repairment and reports threshold value Y2 for repairment more than the cycle；
Condition three：The cycle of power customer reports ring for repairment and is more than ring than change rate threshold value W2 than change rate.
Wherein, while meet that the data of the power customer of above three condition are the second reconstruct data, and by the second weight
Structure data are stored into relevant database.
In addition, the data of multiple power customers are reconstructed, the process of third reconstructed data is obtained mainly to electric power
Client uses the number of mobile terminal, three sides of number at this time and by mobile terminal purchase electricity of cycle access system
Face carries out data reconstruction.Wherein, if the data of multiple power customers meet following three condition at the same time, it is determined that meet with
The data of the power customer of lower three conditions are third reconstructed data：
Condition one：Power customer is more than preset times threshold X 3 using the number of mobile terminal；
Condition two：The cycle access system number of power customer is more than default access times W3；
Condition three：The number that power customer buys electricity by mobile terminal is more than default power purchase number Y3.
Wherein, after third reconstructed data are obtained, third reconstructed data are stored into relevant database.
It should be noted that after reconstruct data are obtained, the sorter of power customer is according to the first reconstruct data, the
Two reconstruct data and third reconstructed data structure disaggregated model, and classified according to disaggregated model to multiple power customers,
Classification results are obtained, are comprised the following steps that：
The data of multiple power customers are carried out clustering processing according to disaggregated model, obtain cluster result by step S108a；
Step S108b, classifies multiple power customers according to cluster result, obtains classification results.
In a kind of optional embodiment, the sorter of power customer can build the disaggregated model of single dimension, also may be used
The disaggregated model of various dimensions is built, wherein, Fig. 2 shows a kind of disaggregated model optionally based on three dimensions, in the classification
In model, the first reconstruct data, the second reconstruct data and third reconstructed data are respectively three dimensions of disaggregated model, each
Diverse location in dimension represents different parameters, wherein, the parameter in the dimension where the first reconstruct data is electric power visitor
Annual electricity, cycle electricity and the cycle electricity ring at family are than change rate, the parameter in the dimension where the second reconstruct data
Annual troublshooting number, cycle fault for power customer report number for repairment and the cycle reports ring for repairment than change rate, triple
The parameter in dimension where structure data for the access times of power customer mobile terminal, cycle access system number and passes through
Mobile terminal buys the number of electricity.
In an alternative embodiment, after disaggregated model is built, using clustering algorithm to power customer
Data carry out clustering processing, wherein, clustering algorithm can be but be not limited to k-means clustering algorithms.To the data of power consumer
The process for carrying out k-means clustering algorithms is as follows：
(1) n data are arbitrarily selected from m data as initial cluster center, wherein, m >=n；
(2) (m-n) a data and the distance of initial cluster center；
(3) cluster of each data in (m-n) a data, the cluster (4) after being updated are determined according to above-mentioned distance
Determine the cluster centre of the cluster after renewal, and all data in the cluster are determined according to the cluster centre of the cluster after renewal
Canonical measure function；
(5) in the case of above-mentioned standard measure function is convergent, cluster result is obtained.
It should be noted that the canonical measure function of data can be determined using the mean square deviation function of data.
In addition it is also necessary to explanation, according to the difference of power customer demand, can use different indexs, dimension with
And set different threshold values to classify power customer, and sorted structure is saved in the classification of power business system
In result set.Power business system can dynamic collection, analysis external system use sorted power customer data, dynamically
Application effect is analyzed and machine learning, the classification results of good application effect are stored to knowledge base, and to application effect
Poor classification results are excavated, analyzed, compared, and are found differences a little, and classification results are adjusted into Mobile state, after adjustment
Topology update to classification results concentrate.Comprise the following steps that：
Step S110, judges whether classification results meet class condition；
Step S112, in the case where classification results are unsatisfactory for class condition, adjust classification results, is adjusted knot
Fruit；
Step S114, is updated classification results processing based on adjustment result, obtains renewal result.
In a kind of optional embodiment, monthly electricity is respectively 1000 and 900 two power customers A and B, and electric power is objective
Monthly SOC values are steady by family A, and the fluctuation of power customer B electricity consumptions value is larger.When being classified according to the fluctuation of charge value, electricity
Power client A is divided into electricity consumption specification user, and power customer B is divided into electricity consumption user lack of standardization.But in marketing system, 95598
After a period of time is run in system, it is found that the trouble shooting number of power customer A is more, and power customer B trouble shootings
Number is less, and marketing system business personnel has objection classification results.Meanwhile the sorter of power customer passes through to power customer
Data and classification results constantly learnt, determine that the fluctuation of user's charge value of power customer A and B has differences, but electricity
The failure rate result of power client A and B are opposite.Thus, the sorter of power customer determines power customer A and B by analysis
Existing failure rate is also influenced by other factors, and therefore, it is that electricity consumption lack of standardization is used that classification results are adjusted to power customer A
Family, and power customer B is specification Electricity customers.
It should be noted that classification results may be updated in power business system, classification results in the updated marketing system,
After being applied in customer service system etc., determine whether classification results are correct by work about electric power personnel, and in the incorrect feelings of classification results
Under condition, dynamic adjusts classification results, and classification results are stored to classification results and are concentrated, and recorded knowledge base, to be used as machine
Learn learning data to use.
In a kind of preferred embodiment, Fig. 3 shows a kind of frame signal of the sorting technique of preferable power customer
Figure.From the figure 3, it may be seen that the sorter of power customer can be by ETL technologies respectively from marketing system database, customer service system data
Extracted respectively in storehouse, acquisition system database and other systems database marketing data, customer service data, gathered data and
Other data, and the data to being drawn into carry out data reconstruction, obtain the reconstruct data of multiple dimensions, for example, grouped data with
And customer data, wherein, customer data can be but be not limited to the data of power customer value, the use data of electric power customer with
And the internet data of power customer.Then, classify to obtained reconstruct data, i.e., power customer is divided into value
Client, demand response client and credit client.The unreasonable feelings of the classification results of power customer are determined in work about electric power personnel
Under condition, but the sorter of power customer its be adjusted, and the result after adjustment is stored in the classification of power business system
In result set, for example, the classification results after adjustment are deposited in the way of common customer, key customer and stock client
Storage.
Embodiment 2
According to embodiments of the present invention, a kind of sorter embodiment of power customer is additionally provided, wherein, Fig. 4 is basis
The sorter structure diagram of the power customer of the embodiment of the present invention, as shown in figure 4, the device includes：Acquisition module 401,
Reconstructed module 403, structure module 405 and sort module 407.
Wherein, acquisition module 401, for obtaining the data of multiple power customers；Reconstructed module 403, for multiple electricity
The data of power client carry out data reconstruction processing, obtain reconstruct data；Module 405 is built, for based on reconstruct data structure point
Class model；Sort module 407, for classifying according to disaggregated model to multiple power customers, obtains classification results.
It should be noted that above-mentioned acquisition module 401, reconstructed module 403, structure module 405 and sort module 407 are right
Should be in the step S102 in embodiment 1 to step S108, four modules example realized with corresponding step and application scenarios
It is identical, but it is not limited to 1 disclosure of that of above-described embodiment.
In a kind of optional embodiment, the sorter of power customer further includes：First acquisition module, first determine mould
Block, processing module and the second determining module.Wherein, the first acquisition module, for obtaining the preset condition in preset algorithm storehouse
And preset algorithm；First determining module, the first data of preset condition are unsatisfactory in the data for determining multiple power customers；
Processing module, for being handled based on preset algorithm the first data, obtains the second data；Second determining module, for root
According to the first data in the data of the multiple power customers of the second data update, the data of multiple power customers after being updated.
It should be noted that above-mentioned first acquisition module, the first determining module, processing module and the second determining module pair
The example and applied field that should be realized in the step S102a in embodiment 1 to step S102d, four modules with corresponding step
Scape is identical, but is not limited to 1 disclosure of that of above-described embodiment.
In a kind of optional embodiment, it is triple that reconstruct data include the first reconstruct data, the second reconstruct data and the
Structure data, wherein, reconstructed module includes：First reconstructed module, the second reconstructed module and third reconstruction module.Wherein, first
Reconstructed module, for processing to be reconstructed to the data of multiple power customers based on the first parameter, obtains the first reconstruct data, its
In, the first parameter includes at least one of following：Annual electricity, cycle electricity and the cycle electricity ring of power customer are than change
Rate；Second reconstructed module, for processing to be reconstructed to the data of multiple power customers based on the second parameter, obtains the second reconstruct
Data, wherein, the second parameter includes at least one of following：Annual troublshooting number, the cycle fault of power customer report for repairment secondary
Number and cycle report ring for repairment and compare change rate；Third reconstruction module, for based on the 3rd parameter to the data of multiple power customers into
Row reconstruction processing, obtains third reconstructed data, wherein, the 3rd parameter includes at least one of following：Power customer uses mobile whole
Number, cycle access system number and the number that electricity is bought by mobile terminal at end.
Implement it should be noted that above-mentioned first reconstructed module, the second reconstructed module and third reconstruction module correspond to
Step S104a to step S104c in example 1, three modules are identical with example and application scenarios that corresponding step is realized, but
It is not limited to 1 disclosure of that of above-described embodiment.
In a kind of optional embodiment, sort module includes：Cluster module and the first sort module.Wherein, cluster
Module, for carrying out clustering processing to the data of multiple power customers according to disaggregated model, obtains cluster result；First classification mould
Block, for classifying according to cluster result to multiple power customers, obtains classification results.
It should be noted that above-mentioned cluster module and the first sort module correspond to step S108a in embodiment 1 extremely
Step S108b, two modules are identical with example and application scenarios that corresponding step is realized, but are not limited to above-described embodiment 1
Disclosure of that.
In a kind of optional embodiment, the sorter of power customer further includes：Judgment module, adjustment module and more
New module.Wherein, judgment module, for judging whether classification results meet class condition；Module is adjusted, in classification results
In the case of being unsatisfactory for class condition, classification results are adjusted, are adjusted result；Update module, for based on adjustment result
Classification results are updated with processing, obtains renewal result.
It should be noted that above-mentioned judgment module, adjustment module and update module correspond to the step in embodiment 1
S110 to step S114, three modules are identical with example and application scenarios that corresponding step is realized, but are not limited to above-mentioned reality
Apply 1 disclosure of that of example.
Embodiment 3
Another aspect according to embodiments of the present invention, additionally provides a kind of storage medium, which includes storage
Program, wherein, program performs the sorting technique of the power customer in embodiment 1.
Embodiment 4
Another aspect according to embodiments of the present invention, additionally provides a kind of processor, which is used for operation program, its
In, program run when perform embodiment 1 in power customer sorting technique.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
In the above embodiment of the present invention, the description to each embodiment all emphasizes particularly on different fields, and does not have in some embodiment
The part of detailed description, may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed technology contents, can pass through others
Mode is realized.Wherein, device embodiment described above is only schematical, such as the division of the unit, Ke Yiwei
A kind of division of logic function, can there is an other dividing mode when actually realizing, for example, multiple units or component can combine or
Person is desirably integrated into another system, or some features can be ignored, or does not perform.Another, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some interfaces, unit or module
Connect, can be electrical or other forms.
The unit illustrated as separating component may or may not be physically separate, be shown as unit
The component shown may or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On unit.Some or all of unit therein can be selected to realize the purpose of this embodiment scheme according to the actual needs.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units integrate in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and is used as independent production marketing or use
When, it can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part to contribute in other words to the prior art or all or part of the technical solution can be in the form of software products
Embody, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or network equipment etc.) perform each embodiment the method for the present invention whole or
Part steps.And foregoing storage medium includes：USB flash disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various can be with store program codes
Medium.
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (10)
- A kind of 1. sorting technique of power customer, it is characterised in that including：Obtain the data of multiple power customers；Data reconstruction processing is carried out to the data of the multiple power customer, obtains reconstruct data；Based on the reconstruct data structure disaggregated model；Classified according to the disaggregated model to the multiple power customer, obtain classification results.
- 2. according to the method described in claim 1, it is characterized in that, after the data of multiple power customers are obtained, the side Method further includes：Obtain the preset condition and preset algorithm in preset algorithm storehouse；Determine to be unsatisfactory for the first data of preset condition in the data of the multiple power customer；First data are handled based on the preset algorithm, obtain the second data；According to the first data in the data of the multiple power customer of the second data update, multiple electricity after being updated The data of power client.
- 3. according to the method described in claim 1, it is characterized in that, the reconstruct data include the first reconstruct data, the second weight Structure data and third reconstructed data, wherein, data reconstruction processing is carried out to the data of the multiple power customer, is obtained described Reconstruct data include：Processing is reconstructed to the data of the multiple power customer based on the first parameter, obtains the first reconstruct data, its In, first parameter includes at least one of following：Annual electricity, cycle electricity and the cycle electricity ring of power customer are than becoming Rate；Processing is reconstructed to the data of the multiple power customer based on the second parameter, obtains the second reconstruct data, its In, second parameter includes at least one of following：Annual troublshooting number, the cycle fault of power customer report for repairment number with And the cycle reports ring for repairment and compares change rate；Processing is reconstructed to the data of the multiple power customer based on the 3rd parameter, obtains the third reconstructed data, its In, the 3rd parameter includes at least one of following：Power customer using the number of mobile terminal, cycle access system number with And the number of electricity is bought by mobile terminal.
- 4. according to the method described in claim 1, it is characterized in that, according to the disaggregated model to the multiple power customer into Row classification, obtaining classification results includes：Clustering processing is carried out to the data of the multiple power customer according to the disaggregated model, obtains cluster result；Classified according to the cluster result to the multiple power customer, obtain the classification results.
- 5. according to the method described in claim 4, it is characterized in that, according to the disaggregated model to the multiple power customer Classify, after obtaining classification results, the method further includes：Judge whether the classification results meet class condition；In the case where the classification results are unsatisfactory for the class condition, the classification results are adjusted, are adjusted result；Processing is updated to the classification results based on the adjustment result, obtains renewal result.
- A kind of 6. sorter of power customer, it is characterised in that including：Acquisition module, for obtaining the data of multiple power customers；Reconstructed module, for carrying out data reconstruction processing to the data of the multiple power customer, obtains reconstruct data；Module is built, for based on the reconstruct data structure disaggregated model；Sort module, for classifying according to the disaggregated model to the multiple power customer, obtains classification results.
- 7. device according to claim 6, it is characterised in that described device further includes：First acquisition module, for obtaining preset condition and preset algorithm in preset algorithm storehouse；First determining module, the first data of preset condition are unsatisfactory in the data for determining the multiple power customer；Processing module, for being handled based on the preset algorithm first data, obtains the second data；Second determining module, for the first data in the data according to the multiple power customer of the second data update, The data of multiple power customers after being updated.
- 8. device according to claim 6, it is characterised in that the reconstruct data include the first reconstruct data, the second weight Structure data and third reconstructed data, wherein, reconstructed module includes：First reconstructed module, for processing to be reconstructed to the data of the multiple power customer based on the first parameter, obtains institute The first reconstruct data are stated, wherein, first parameter includes at least one of following：Annual electricity, the cycle electricity of power customer And cycle electricity ring compares change rate；Second reconstructed module, for processing to be reconstructed to the data of the multiple power customer based on the second parameter, obtains institute The second reconstruct data are stated, wherein, second parameter includes at least one of following：The annual troublshooting number of power customer, Cycle fault reports number for repairment and the cycle reports ring for repairment and compares change rate；Third reconstruction module, for processing to be reconstructed to the data of the multiple power customer based on the 3rd parameter, obtains institute Third reconstructed data are stated, wherein, the 3rd parameter includes at least one of following：Power customer using mobile terminal number, Cycle access system number and the number that electricity is bought by mobile terminal.
- A kind of 9. storage medium, it is characterised in that the storage medium includes the program of storage, wherein, described program right of execution Profit requires the sorting technique of the power customer described in any one in 1 to 5.
- A kind of 10. processor, it is characterised in that the processor is used for operation program, wherein, right of execution when described program is run Profit requires the sorting technique of the power customer described in any one in 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711193121.2A CN108009224A (en) | 2017-11-24 | 2017-11-24 | The sorting technique and device of power customer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711193121.2A CN108009224A (en) | 2017-11-24 | 2017-11-24 | The sorting technique and device of power customer |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108009224A true CN108009224A (en) | 2018-05-08 |
Family
ID=62053606
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711193121.2A Pending CN108009224A (en) | 2017-11-24 | 2017-11-24 | The sorting technique and device of power customer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108009224A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921323A (en) * | 2018-06-04 | 2018-11-30 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN110135795A (en) * | 2019-04-10 | 2019-08-16 | 杭州博世数据网络有限公司 | A kind of Database Systems based on cloud teaching platform |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006081256A (en) * | 2004-09-08 | 2006-03-23 | Hitachi Ltd | Electrical energy sorting system and method |
| CN102982489A (en) * | 2012-11-23 | 2013-03-20 | 广东电网公司电力科学研究院 | Power customer online grouping method based on mass measurement data |
| CN107133652A (en) * | 2017-05-17 | 2017-09-05 | 国网山东省电力公司烟台供电公司 | Electricity customers Valuation Method and system based on K means clustering algorithms |
| CN107247737A (en) * | 2017-05-10 | 2017-10-13 | 国家电网公司 | Platform area promise breaking electrical energy consumption analysis and method for digging based on power consumption |
| CN107368918A (en) * | 2017-06-27 | 2017-11-21 | 国网北京市电力公司 | Data processing method and device |
-
2017
- 2017-11-24 CN CN201711193121.2A patent/CN108009224A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006081256A (en) * | 2004-09-08 | 2006-03-23 | Hitachi Ltd | Electrical energy sorting system and method |
| CN102982489A (en) * | 2012-11-23 | 2013-03-20 | 广东电网公司电力科学研究院 | Power customer online grouping method based on mass measurement data |
| CN107247737A (en) * | 2017-05-10 | 2017-10-13 | 国家电网公司 | Platform area promise breaking electrical energy consumption analysis and method for digging based on power consumption |
| CN107133652A (en) * | 2017-05-17 | 2017-09-05 | 国网山东省电力公司烟台供电公司 | Electricity customers Valuation Method and system based on K means clustering algorithms |
| CN107368918A (en) * | 2017-06-27 | 2017-11-21 | 国网北京市电力公司 | Data processing method and device |
Non-Patent Citations (1)
| Title |
|---|
| 熊赟等: "《大数据挖掘》", 30 April 2016, 上海科学技术出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921323A (en) * | 2018-06-04 | 2018-11-30 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN110135795A (en) * | 2019-04-10 | 2019-08-16 | 杭州博世数据网络有限公司 | A kind of Database Systems based on cloud teaching platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021073462A1 (en) | 10 kv static load model parameter identification method based on similar daily load curves | |
| CN105335400B (en) | Enquirement for user is intended to obtain the method and device of answer information | |
| CN107220732A (en) | A kind of power failure complaint risk Forecasting Methodology based on gradient boosted tree | |
| CN109583651A (en) | A kind of method and apparatus for insuring electric business platform user attrition prediction | |
| CN111738462B (en) | Fault first-aid repair active service early warning method for electric power metering device | |
| CN104346698B (en) | Based on the analysis of the food and drink member big data of cloud computing and data mining and checking system | |
| CN108470022A (en) | A kind of intelligent work order quality detecting method based on operation management | |
| CN110147389A (en) | Account number treating method and apparatus, storage medium and electronic device | |
| CN110458376A (en) | A kind of suspicious risk trade screening method and corresponding system | |
| CN107784518A (en) | A kind of power customer divided method based on multidimensional index | |
| CN107358456A (en) | Data show method and apparatus | |
| CN111986027A (en) | Abnormal transaction processing method and device based on artificial intelligence | |
| CN106846082A (en) | Tourism cold start-up consumer products commending system and method based on hardware information | |
| CN109165337A (en) | A kind of method and system of knowledge based map construction bidding field association analysis | |
| CN113379530A (en) | User risk determination method and device and server | |
| CN108009224A (en) | The sorting technique and device of power customer | |
| CN114140248A (en) | AI artificial intelligence technology-based abnormal transaction identification method | |
| CN107274025A (en) | A kind of system and method realized with power mode Intelligent Recognition and management | |
| CN113535667A (en) | Method, device and system for automatically analyzing system logs | |
| CN108182453B (en) | User power failure sensitivity classification method | |
| Li et al. | A study on customer churn of commercial banks based on learning from label proportions | |
| CN115049107A (en) | Electric quantity prediction system based on thing allies oneself with collection edge calculation | |
| CN113327033A (en) | Power distribution network fault diagnosis method and system | |
| CN108629475A (en) | A kind of exchange method of the operation information analysis system based on macroeconomic data | |
| CN106779800A (en) | Tobacco marketing 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180508 |