CN110427418A - A kind of customer analysis grouping method based on client's energy value index system - Google Patents
A kind of customer analysis grouping method based on client's energy value index system Download PDFInfo
- Publication number
- CN110427418A CN110427418A CN201910598659.4A CN201910598659A CN110427418A CN 110427418 A CN110427418 A CN 110427418A CN 201910598659 A CN201910598659 A CN 201910598659A CN 110427418 A CN110427418 A CN 110427418A
- Authority
- CN
- China
- Prior art keywords
- client
- data
- electricity consumption
- customer
- electricity
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000004519 manufacturing process Methods 0.000 claims abstract description 4
- 230000005611 electricity Effects 0.000 claims description 80
- 230000003993 interaction Effects 0.000 claims description 20
- 238000009826 distribution Methods 0.000 claims description 13
- 230000003542 behavioural effect Effects 0.000 claims description 12
- 238000012512 characterization method Methods 0.000 claims description 12
- 238000007418 data mining Methods 0.000 claims description 10
- 238000007619 statistical method Methods 0.000 claims description 8
- 238000012550 audit Methods 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 7
- 230000002045 lasting effect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 239000004744 fabric Substances 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 239000013642 negative control Substances 0.000 claims description 3
- 238000011160 research Methods 0.000 claims description 3
- 238000010206 sensitivity analysis Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000017105 transposition Effects 0.000 description 1
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
- G06F16/26—Visual data mining; Browsing structured data
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
- Y04S50/16—Energy services, e.g. dispersed generation or demand or load or energy savings aggregation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of customer analysis grouping method based on client's energy value index system.It (such as markets, measure, production data) based on existing internal data, in conjunction with power market transaction rule, industry background, GDP growth trend and related crawler data (such as business information of enterprise, bidding information, Financial Statement of Listed Corporations, industrial trend report), comprehensive analysis is carried out to power consumer, design relevant algorithm model, it realizes the classification to existing customer, divide group and customer portrait, it realizes the precise positioning of high value customer, provides support with precision marketing for client's positioning of comprehensive energy service enterprise.
Description
Technical field
The present invention relates to comprehensive energy service technology fields more particularly to a kind of based on client's energy value index system
Customer analysis grouping method.
Background technique
With the quickening of Internet information technique, the high speed development of renewable energy technologies and electric Power Reform process, I
The service of state's comprehensive energy has entered high-speed development period, and new comprehensive energy service ecology is accelerating to be formed, and carries out comprehensive energy
Service have become promoted energy efficiency, reduce with can cost important development direction, also become the new Strategic Competition of each enterprise and
Cooperate focus, a large amount of enterprises carry out Overall Transformation to comprehensive energy service enterprise one after another.Hundreds of millions grades of comprehensive energy service markets
At the rudiment initial stage that cruelty generates, accurately client's positioning and marketing, are the key that can market quickly open, lack currently on the market
Weary efficient client's positioning means, generally use phone, mail is marketed extensively, and at high cost, low efficiency, degree of belief is low, also
It easily causes client's dislike and causes to contradict.
Summary of the invention
Technical problem to be solved by the present invention lies in provide a kind of client based on client's energy value index system point
Grouping method is analysed, provides support with precision marketing for client's positioning of comprehensive energy service enterprise.
In order to solve the above technical problem, the present invention provides a kind of customer analyses based on client's energy value index system
Grouping method, comprising:
The full dimension archives of client are established in step S1, analysis, construct efficiency customer grouping label, building energy value index system and
It constructs energy demand and excavates Indentification model；
Step S2 is carried out in conjunction with each system that the step S1 is constructed from each system of comprehensive energy service by ETL tool
The extraction of data, cleaning and processing；
Step S3 audits each field using Data Mining Tools, and Check sees the distribution and quality of its data；According to business demand, really
Determine the critical field of separate service view, and for statistical analysis in the dimension of critical field, determines point of critical field data
Cloth situation；
Step S4, sampling belong to the primary sources of specific a certain business and do not meet the primary sources decimation rule
Secondary sources；
Step S5 carries out data prediction to data source and establishes each separate service view according to demand；
Step S6 audits each field information in each separate service view using Data Mining Tools, check its data distribution and
Quality；
Step S7 determines the critical field in each separate service view, determined and closed based on statistical analysis to critical field
The distribution situation of data in key field；
Step S8 is divided in critical field according to the statistical result of the step S7, thus in critical field dimension
Each separate service view is subjected to a point group；
Step S9 determines the field information of unified view of customers, establishes unified view of customers；
Step S10 unifies the third class data that sampling in Client view belongs to a group of specific a certain business from client, and
The 4th class data of the third class data pick-up rule are not met；
Step S11 models the step S10 data sampled using sorting algorithm, and generation belongs to some client
The characterization rules collection of group；
Step S12 is assessed using test data set come the model established to the step S11, the accuracy of comparison model,
Choose optimal model and publication；
The step S11 characterization rules collection generated is converted to the characteristic information of customers, and is added to client by step S13
The group character description section of group.
Wherein, in the step S1, the full dimension archives of client specifically include geographical location, building type and price, unit/
Industry attribute, services channels, service content, interaction times, interaction friendliness, electricity consumption, electricity consumption behavioural analysis, industrial electrical equipment energy
The level of effect, industrial electric behavioural analysis, payment credit, payment amount of money, payment channel.
Wherein, in the step S1, the specific dimension of building efficiency customer grouping label includes electricity consumption behavior type, electricity consumption
Energy consumption level, electricity consumption efficiency are horizontal, credit worthiness of paying the fees, channel preference, interaction liveness, interaction friendliness；
Electricity consumption behavior type: including continuing smooth electricity consumption, lasting regular fluctuating electricity consumption, the lasting smooth electricity consumption of irregularities, holding
Continuous irregularities fluctuating electricity consumption, the smooth electricity consumption of interruption regularity, the regular fluctuating electricity consumption of interruption, interruption irregularities are smoothly used
Electricity, interruption irregularities fluctuating electricity consumption etc.；
Electricity consumption is horizontal: business big customer, business common customer, commercial mini client, industrial big customer, the general visitor of industry
Family, the small-sized client of industry etc.；
Electricity consumption efficiency is horizontal: being classified according to power factor (PF) and industry, mainly includes high, medium and low three categories；
Payment credit worthiness: including very good, good, general, poor, poor；
Channel preference: including website, the palm Room, phone etc.；
Interaction liveness: including very active, active, general active, inactive, very inactive；
Interaction friendliness: including very good, good, general, poor, poor.
Wherein, in the step S1, the energy value index constructed in energy value index system includes following index:
Value index: it should collect charges for electricity, charging category, average electricity price, business handling total amount, credit rating；
Economic impact and population impact power index: whether the big electricity consumption top 100 enterprises, whether big electricity consumption manufacturing industry, electricity ring
Compare gaining rate；
Whether society and national security index: being differentiated service object.
Wherein, in the step S1, it is specifically to high value customer potential demand that Indentification model is excavated in building energy demand
It is excavated and is analyzed, comprising:
Purchase sale of electricity demand: it is carried out with it with energy aggregate demand index, the relationship of peeling off of electricity consumption increment index based on similar client's electricity charge
Analysis.
Efficiency value-added service: the relationship of peeling off based on indexs such as the every standard unit's conversion electricity consumptions of similar client is divided
Analysis；
Other value-added services: the data such as the negative control terminal of fusion metering and marketing, voltage monitoring terminal, marketing archives carry out visitor
The reactive requirement at family, power quality characteristic, power supply sensitivity analysis research, comprehensive assessment voltage supplied, frequency and reliability aspect
The special value-added service demand of client.
Wherein, the separate service view includes client's essential information, electricity consumption behavioural information of the client in the scope of business
With electric energy information, trade information.
Wherein, the unified view of customers includes two large divisions, and first part is the personal essential information of client, and second
The record that part is the client that is made of all data services in each data service dimension.
Wherein, the step S9 is specifically included: using client's power marketing archive information as base table, according to customer number and
Stoichiometric point is numbered to be associated with other data in service view.
Wherein, in step S13, by the step S11 generate characterization rules collection be converted to customers characteristic information it
Before, will also judge in sample data, whether the result drawn by the characterization rules collection consistent with actual result, or
Person's accuracy is not less than 95%.
Wherein, the ratio section of the primary sources and secondary sources be 1:1-1:4, the third class data with
The ratio section of 4th class data is 1:1-1:4.
The beneficial effect of the embodiment of the present invention is: comprehensive energy service market status and data with existing assets are based on,
Eye constructs customer value index system, building client point in the current value of client and the following potential value and credit standing
Analysis divides group, realizes the precise positioning of high value customer, provides branch with precision marketing for client's positioning of comprehensive energy service enterprise
Support.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of process of the customer analysis grouping method based on client's energy value index system of the embodiment of the present invention
Schematic diagram.
Specific embodiment
The explanation of following embodiment be with reference to attached drawing, can be to the specific embodiment implemented to the example present invention.
It please refers to shown in Fig. 1, the embodiment of the present invention provides a kind of customer analysis based on client's energy value index system
Grouping method, comprising:
The full dimension archives of client are established in step S1, analysis, construct efficiency customer grouping label, building energy value index system and
It constructs energy demand and excavates Indentification model；
Step S2 is carried out in conjunction with each system that the step S1 is constructed from each system of comprehensive energy service by ETL tool
The extraction of data, cleaning and processing；
Step S3 audits each field using Data Mining Tools, and Check sees the distribution and quality of its data；According to business demand, really
Determine the critical field of separate service view, and for statistical analysis in the dimension of critical field, determines point of critical field data
Cloth situation；
Step S4, sampling belong to the primary sources of specific a certain business and do not meet the primary sources decimation rule
Secondary sources；
Step S5 carries out data prediction to data source and establishes each separate service view according to demand；
Step S6 audits each field information in each separate service view using Data Mining Tools, check its data distribution and
Quality；
Step S7 determines the critical field in each separate service view, determined and closed based on statistical analysis to critical field
The distribution situation of data in key field；
Step S8 is divided in critical field according to the statistical result of the step S7, thus in critical field dimension
Each separate service view is subjected to a point group；
Step S9 determines the field information of unified view of customers, establishes unified view of customers；
Step S10 unifies the third class data that sampling in Client view belongs to a group of specific a certain business from client, and
The 4th class data of the third class data pick-up rule are not met；
Step S11 models the step S10 data sampled using sorting algorithm, and generation belongs to some client
The characterization rules collection of group；
Step S12 is assessed using test data set come the model established to the step S11, the accuracy of comparison model,
Choose optimal model and publication；
The step S11 characterization rules collection generated is converted to the characteristic information of customers, and is added to client by step S13
The group character description section of group.
Specifically, in step S1, it is specific as follows that the full dimension archives of client are established in analysis:
Demand is provided for the receipts of efficiency service, based on system datas such as marketing, metering, customer services, the full dimension archives of client is carried out and sets
Meter, specifically include geographical location, building type and price, unit/industry attribute, services channels, service content, interaction times,
Interaction friendliness, electricity consumption behavioural analysis, industrial electrical equipment efficiency level, industrial electric behavioural analysis, payment credit, is paid electricity consumption
Take the amount of money, payment channel.
It is specific as follows to construct efficiency customer grouping label:
Construct efficiency customer grouping label, specific dimension include electricity consumption behavior type, electricity consumption is horizontal, electricity consumption efficiency is horizontal,
Payment credit worthiness, channel preference, interaction liveness, interaction friendliness:
Electricity consumption behavior type: including continuing smooth electricity consumption, lasting regular fluctuating electricity consumption, the lasting smooth electricity consumption of irregularities, holding
Continuous irregularities fluctuating electricity consumption, the smooth electricity consumption of interruption regularity, the regular fluctuating electricity consumption of interruption, interruption irregularities are smoothly used
Electricity, interruption irregularities fluctuating electricity consumption etc.；
Electricity consumption is horizontal: business big customer, business common customer, commercial mini client, industrial big customer, the general visitor of industry
Family, the small-sized client of industry etc.；
Electricity consumption efficiency is horizontal: being classified according to power factor (PF) and industry, mainly includes high, medium and low three categories；
Payment credit worthiness: including very good, good, general, poor, poor；
Channel preference: including website, the palm Room, phone etc.；
Interaction liveness: including very active, active, general active, inactive, very inactive；
Interaction friendliness: including very good, good, general, poor, poor.
It is specific as follows to construct energy value index system:
In conjunction with customer value critical parameter, energy value index system is constructed, energy value index includes following index:
Value index: it should collect charges for electricity, charging category, average electricity price, business handling total amount, credit rating etc..
Economic impact and population impact power index: whether the big electricity consumption top 100 enterprises, whether big electricity consumption manufacturing industry, electricity
Ring is measured than gaining rate etc..
Whether society and national security index: being differentiated service object.
Judged by These parameters, for example each index is 1 to 15 points and differs, and gives a mark respectively, finally according to sample
Data determine threshold values, for example higher than 85 points are exactly high value customer, to provide support to segment to outbid to be worth customers.
It constructs energy demand and excavates Indentification model, high value customer potential demand is excavated and analyzed:
Purchase sale of electricity demand: based on similar client's electricity charge and its with the indexs such as energy aggregate demand index, electricity consumption increment peel off relationship into
Row analysis.
Efficiency value-added service: based on the every standard unit of similar client (enterprise's output value, construction area etc.) conversion electricity consumption etc.
The relationship of peeling off of index is analyzed.
Other value-added services: the data such as the negative control terminal of fusion metering and marketing, voltage monitoring terminal, marketing archives are opened
Open up the reactive requirement, power quality characteristic, power supply sensitivity analysis research of client, comprehensive assessment voltage supplied, frequency and reliability
Etc. the special value-added service demand of client.
Step S2 is by the abbreviation of ETL(English Extract-Transform-Load, for describing data from source terminal
By extraction (extract), transposition (transform), load (load) to destination process) tool, in conjunction with above-mentioned system,
The extraction of data, cleaning and processing are carried out from systems such as metering automation, marketing, customer services.
In step S3, each field is audited using Data Mining Tools, Check sees the distribution and quality of its data；According to business need
It asks, determines the critical field of separate service view, and for statistical analysis in the dimension of critical field, determine critical field data
Distribution situation；The data include the power marketing information of each client, electric energy information and other related informations (such as
It manages position, building type and price, unit/industry attribute, services channels, service content, interaction times, interaction friendliness, use
Electricity, electricity consumption behavioural analysis, industrial electrical equipment efficiency level, industrial electric behavioural analysis, payment credit, payment amount of money, payment canal
Road) etc., the record in each data service dimension is closed by the customer number of client and metering point number, electric energy meter asset number etc.
Connection.
In step S4, two class data, the two classes data are sampled are as follows: primary sources a belongs to specific a certain business number
According to this partial data meets the statistical rules of this business；Secondary sources b, this partial data are not meet primary sources a
Decimation rule data.The ratio section of primary sources a and secondary sources b is 1:1-1:4.It is calculated using multiple classification
Method models the data of sampling；Optimal parameter is set for each model；Then model evaluation is carried out, is generated according to each model
Estimate parameter and accuracy to carry out the evaluation and test of model, select current optimal model；The popularization of model, model is applied to
Entire data set judges the rule set generated, if having actual meaning (i.e. in sample data, to obtain by this rule set
Whether rule not less than 95%), is then converted to customers to result out by or accuracy consistent with actual result
Characteristic information is added to the special description section of each separate service view；The foreground of model shows, and creates table one and table two, respectively
It is used to store characteristic information and belongs to the customer information of this feature.
Step S5 establishes each separate service view.Data Mart is made of several separate service views and unified view of customers
, separate service view is showing to comprehensive attribute of specific data service, and separate service view includes that personal (client) is basic
Information, personal electricity consumption behavioural information and electric energy information, trade information etc. in the scope of business；In data source
The type of business datum has very much, and required field is selected according to the theme of data mining；ETL personnel will be to data source
It carries out data prediction and to establish each separate service view according to demand, be embodied using storing process, and automatically generate
Separate service view.
Step S6 comprehensively audits the information of each field in each separate service view using Data Mining Tools, checks
The distribution of its data and the quality of data.It should be noted that step S3 determines critical field, unite to critical field
Meter and quality analysis, there is no the divisions for carrying out separate service view；Step S6 is then after establishing separate service view, to each point
The quality of data of service view is audited.
Step S7 determines the critical field in each separate service view according to data mining theme, carries out base to critical field
In statistical analysis, the distribution situation of data in critical field is determined.
Step S8, which will be realized, divides group based on statistical result, be according to point of data in actual separate service view
Cloth feature determines the rule of point group, the rule of group will be divided to put in order, so as to automatic processing.According to statistical result come in key
It is reasonably divided in field, so that separate service view is carried out a point group in critical field dimension.
Step S9 will determine that the field information of unified view of customers, separate service view reflect client in individual data business
Personal essential information in dimension, behavioural information, cost information, separate service view can on single business dimension to client into
Row divides the operation such as group and the description of group's information characteristics.But this operation is only limited on single business dimension, if to carry out
On all business dimensions customer grouping and customer grouping feature description etc. operation when, will meet difficulty, must so having
Establish the unified view of customers totally according to business dimension；Unified view of customers includes two large divisions, and first part is client's
Personal essential information, second part are the record of the client that is made of all data services in each data service dimension.
Data set can be divided into three layers: unified view of customers-" client's separate service view-" customer grouping view；Client's system
One view refers to the set of the separate service view of some client's multi-service dimension.
Step S9 will establish unified view of customers, the strategy used be using client's power marketing archive information as base table,
It is associated according to customer number and stoichiometric point number with other data in service view, in addition also to carry out processing empty value,
Null value is assigned a value of zero, and renames field to avoid the duplication of name field in multilist.
Step S10 will randomly select part sample from unified Client view, this sample includes two class data, third class number
According to c: belonging to the data of a group of specific a certain business, this partial data meets the statistical rules of this group；4th class data
D: this partial data is not meet the data of third class data c decimation rule.The ratio section of data c and data d is (1:1-
1:4), specific ratio selection will see the assessment result of model.
Step S11 models sample data using sorting algorithm, is generated using sorting algorithm and belongs to some client
The characterization rules of group.Parameter is set according to data model, and sorting algorithm should be carried out using a variety of sorting algorithms come to sample
Data modeling, and corresponding parameter is used, obtain model in terms of parameter setting optimal, so as to the assessment of the model of next step
It is used.
The assessment that step S12 carries out model assesses model including the use of test data set, and comparison model is just
True rate therefrom chooses optimal model.The publication of model includes that data set will be divided into it by rule derived from model to belong to
Group, then will Clustering information be written foreground display data library in.
The characterization rules collection that step S13 generates model, business personnel will explain, and it is actual to see whether rule has
Meaning, the characteristic information for then converting it into customers are added to each group of group spy's description section；By repetition training and
Optimization, which allows, analyzes result more closing to reality business.Similarly, if having actual meaning i.e. in sample data, pass through this
Whether or accuracy consistent with actual result is not less than 95% to the result that characterization rules collection is drawn.
By above description it is found that the beneficial effect of the embodiment of the present invention is, it is based on comprehensive energy service market status
With data with existing assets, the current value and the following potential value and credit standing, building customer value for being conceived to client refer to
Mark system, building customer analysis divide group, realize the precise positioning of high value customer, are that the client of comprehensive energy service enterprise positions
Support is provided with precision marketing.
The above disclosure is only the preferred embodiments of the present invention, cannot limit the right model of the present invention with this certainly
It encloses, therefore equivalent changes made in accordance with the claims of the present invention, is still within the scope of the present invention.
Claims (10)
1. a kind of customer analysis grouping method based on client's energy value index system, comprising:
The full dimension archives of client are established in step S1, analysis, construct efficiency customer grouping label, building energy value index system and
It constructs energy demand and excavates Indentification model；
Step S2 is carried out in conjunction with each system that the step S1 is constructed from each system of comprehensive energy service by ETL tool
The extraction of data, cleaning and processing；
Step S3 audits each field using Data Mining Tools, and Check sees the distribution and quality of its data；According to business demand, really
Determine the critical field of separate service view, and for statistical analysis in the dimension of critical field, determines point of critical field data
Cloth situation；
Step S4, sampling belong to the primary sources of specific a certain business and do not meet the primary sources decimation rule
Secondary sources；
Step S5 carries out data prediction to data source and establishes each separate service view according to demand；
Step S6 audits each field information in each separate service view using Data Mining Tools, check its data distribution and
Quality；
Step S7 determines the critical field in each separate service view, determined and closed based on statistical analysis to critical field
The distribution situation of data in key field；
Step S8 is divided in critical field according to the statistical result of the step S7, thus in critical field dimension
Each separate service view is subjected to a point group；
Step S9 determines the field information of unified view of customers, establishes unified view of customers；
Step S10 unifies the third class data that sampling in Client view belongs to a group of specific a certain business from client, and
The 4th class data of the third class data pick-up rule are not met；
Step S11 models the step S10 data sampled using sorting algorithm, and generation belongs to some client
The characterization rules collection of group；
Step S12 is assessed using test data set come the model established to the step S11, the accuracy of comparison model,
Choose optimal model and publication；
The step S11 characterization rules collection generated is converted to the characteristic information of customers, and is added to client by step S13
The group character description section of group.
2. the method according to claim 1, wherein client is complete, and dimension archives specifically include in the step S1
Geographical location, building type and price, unit/industry attribute, services channels, service content, interaction times, interaction friendliness,
Electricity consumption, electricity consumption behavioural analysis, industrial electrical equipment efficiency level, industrial electric behavioural analysis, payment credit, payment amount of money, payment
Channel.
3. the method according to claim 1, wherein constructing efficiency customer grouping label in the step S1
Specific dimension includes electricity consumption behavior type, electricity consumption is horizontal, electricity consumption efficiency is horizontal, payment credit worthiness, channel preference, interaction
Liveness, interaction friendliness；
Electricity consumption behavior type: including continuing smooth electricity consumption, lasting regular fluctuating electricity consumption, the lasting smooth electricity consumption of irregularities, holding
Continuous irregularities fluctuating electricity consumption, the smooth electricity consumption of interruption regularity, the regular fluctuating electricity consumption of interruption, interruption irregularities are smoothly used
Electricity, interruption irregularities fluctuating electricity consumption etc.；
Electricity consumption is horizontal: business big customer, business common customer, commercial mini client, industrial big customer, the general visitor of industry
Family, the small-sized client of industry etc.；
Electricity consumption efficiency is horizontal: being classified according to power factor (PF) and industry, mainly includes high, medium and low three categories；
Payment credit worthiness: including very good, good, general, poor, poor；
Channel preference: including website, the palm Room, phone etc.；
Interaction liveness: including very active, active, general active, inactive, very inactive；
Interaction friendliness: including very good, good, general, poor, poor.
4. the method according to claim 1, wherein being constructed in energy value index system in the step S1
Energy value index include following index:
Value index: it should collect charges for electricity, charging category, average electricity price, business handling total amount, credit rating；
Economic impact and population impact power index: whether the big electricity consumption top 100 enterprises, whether big electricity consumption manufacturing industry, electricity ring
Compare gaining rate；
Whether society and national security index: being differentiated service object.
5. the method according to claim 1, wherein building energy demand, which is excavated, judges body in the step S1
System is specifically that high value customer potential demand is excavated and analyzed, comprising:
Purchase sale of electricity demand: it is carried out with it with energy aggregate demand index, the relationship of peeling off of electricity consumption increment index based on similar client's electricity charge
Analysis；
Efficiency value-added service: the relationship of peeling off based on indexs such as the every standard unit's conversion electricity consumptions of similar client is analyzed；
Other value-added services: the data such as the negative control terminal of fusion metering and marketing, voltage monitoring terminal, marketing archives carry out visitor
The reactive requirement at family, power quality characteristic, power supply sensitivity analysis research, comprehensive assessment voltage supplied, frequency and reliability aspect
The special value-added service demand of client.
6. the method according to claim 1, wherein the separate service view includes client's essential information, client
Electricity consumption behavioural information and electric energy information, trade information in the scope of business.
7. the method according to claim 1, wherein the unified view of customers includes two large divisions, first
It is divided into the personal essential information of client, second part is the client that is made of all data services in each data service dimension
Record.
8. the method according to claim 1, wherein the step S9 is specifically included: with client's power marketing shelves
Case information is base table, is associated according to customer number and stoichiometric point number with other data in service view.
9. the method according to claim 1, wherein the feature for generating the step S11 is advised in step S13
Then collection be converted to before the characteristic information of customers, will also judge in sample data, drawn by the characterization rules collection
Result whether or accuracy consistent with actual result be not less than 95%.
10. the method according to claim 1, wherein the ratio area of the primary sources and secondary sources
Between be 1:1-1:4, the ratio section of the third class data and the 4th class data is 1:1-1:4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910598659.4A CN110427418A (en) | 2019-07-04 | 2019-07-04 | A kind of customer analysis grouping method based on client's energy value index system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910598659.4A CN110427418A (en) | 2019-07-04 | 2019-07-04 | A kind of customer analysis grouping method based on client's energy value index system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110427418A true CN110427418A (en) | 2019-11-08 |
Family
ID=68408937
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910598659.4A Pending CN110427418A (en) | 2019-07-04 | 2019-07-04 | A kind of customer analysis grouping method based on client's energy value index system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110427418A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112100246A (en) * | 2020-09-22 | 2020-12-18 | 国网辽宁省电力有限公司电力科学研究院 | Customer electricity value mining method based on multi-dimensional graph code label |
| CN112102003A (en) * | 2020-09-18 | 2020-12-18 | 国网辽宁省电力有限公司电力科学研究院 | Big data platform-based electricity customer core resource management system and method |
| CN113590607A (en) * | 2021-09-29 | 2021-11-02 | 国网江苏省电力有限公司营销服务中心 | Electric power marketing report realization method and system based on report factor |
| CN114238615A (en) * | 2021-12-14 | 2022-03-25 | 淄博天大创新科技服务有限公司 | Enterprise service achievement data processing method and system |
| CN115081893A (en) * | 2022-06-27 | 2022-09-20 | 国网湖北省电力有限公司电力科学研究院 | User electricity consumption data analysis method and device, electronic equipment and readable storage medium |
| CN117132025A (en) * | 2023-10-26 | 2023-11-28 | 国网山东省电力公司泰安供电公司 | Power consumption monitoring and early warning system based on multisource data fusion |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050108023A1 (en) * | 2003-11-13 | 2005-05-19 | Chris Hemmings | Methods and systems for producing and/or distributing electronic publications |
| CN101620599A (en) * | 2008-06-30 | 2010-01-06 | 上海全成通信技术有限公司 | Method for building unified view of customers of mobile communication data service |
| CN101621823A (en) * | 2008-06-30 | 2010-01-06 | 上海全成通信技术有限公司 | Method for accurately building customer portrait of mobile communication data service |
| CN108764939A (en) * | 2018-05-11 | 2018-11-06 | 深圳供电局有限公司 | A kind of electric power enterprise CRM system and its method |
-
2019
- 2019-07-04 CN CN201910598659.4A patent/CN110427418A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050108023A1 (en) * | 2003-11-13 | 2005-05-19 | Chris Hemmings | Methods and systems for producing and/or distributing electronic publications |
| CN101620599A (en) * | 2008-06-30 | 2010-01-06 | 上海全成通信技术有限公司 | Method for building unified view of customers of mobile communication data service |
| CN101621823A (en) * | 2008-06-30 | 2010-01-06 | 上海全成通信技术有限公司 | Method for accurately building customer portrait of mobile communication data service |
| CN108764939A (en) * | 2018-05-11 | 2018-11-06 | 深圳供电局有限公司 | A kind of electric power enterprise CRM system and its method |
Non-Patent Citations (1)
| Title |
|---|
| 张世强: "《中国智能金融产业蓝皮书》", 31 March 2018, 中国发展出版社 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102003A (en) * | 2020-09-18 | 2020-12-18 | 国网辽宁省电力有限公司电力科学研究院 | Big data platform-based electricity customer core resource management system and method |
| CN112100246A (en) * | 2020-09-22 | 2020-12-18 | 国网辽宁省电力有限公司电力科学研究院 | Customer electricity value mining method based on multi-dimensional graph code label |
| CN113590607A (en) * | 2021-09-29 | 2021-11-02 | 国网江苏省电力有限公司营销服务中心 | Electric power marketing report realization method and system based on report factor |
| CN114238615A (en) * | 2021-12-14 | 2022-03-25 | 淄博天大创新科技服务有限公司 | Enterprise service achievement data processing method and system |
| CN115081893A (en) * | 2022-06-27 | 2022-09-20 | 国网湖北省电力有限公司电力科学研究院 | User electricity consumption data analysis method and device, electronic equipment and readable storage medium |
| CN117132025A (en) * | 2023-10-26 | 2023-11-28 | 国网山东省电力公司泰安供电公司 | Power consumption monitoring and early warning system based on multisource data fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110427418A (en) | A kind of customer analysis grouping method based on client's energy value index system | |
| US11699198B2 (en) | Methods and systems for machine-learning for prediction of grid carbon emissions | |
| CN106651424B (en) | Power user portrait establishing and analyzing method based on big data technology | |
| CN106780140B (en) | Power credit evaluation method based on big data | |
| WO2011152087A1 (en) | Economic activity index presenting system | |
| CN108764984A (en) | A kind of power consumer portrait construction method and system based on big data | |
| CN108280541A (en) | Customer service strategies formulating method, device based on random forest and decision tree | |
| CN107958043B (en) | Automatic generation method for power grid engineering budget list | |
| CN106570778A (en) | Big data-based data integration and line loss analysis and calculation method | |
| Li et al. | Risk dependence between energy corporations: A text-based measurement approach | |
| Tomita et al. | An algorithm for locating logic design errors | |
| CN108154311A (en) | Top-tier customer recognition methods and device based on random forest and decision tree | |
| ElBahrawy et al. | Wikipedia and cryptocurrencies: interplay between collective attention and market performance | |
| CN112116256A (en) | Data asset management method | |
| CN108280562A (en) | A kind of method of specification electric power enterprise data resource | |
| CN115456745A (en) | Small and micro enterprise portrait construction method and device | |
| CN110188255A (en) | Power consumer Behavior mining method and system based on the shared fusion of business datum | |
| CN115130811A (en) | Method and device for establishing power user portrait and electronic equipment | |
| CN110222180A (en) | A kind of classification of text data and information mining method | |
| Lu et al. | Customer segmentation algorithm based on data mining for electric vehicles | |
| Hu | Predicting and improving invoice-to-cash collection through machine learning | |
| CN109767333A (en) | Select based method, device, electronic equipment and computer readable storage medium | |
| CN112258067A (en) | Low-voltage user payment behavior classification method based on Gaussian mixture model clustering algorithm | |
| CN116187808A (en) | Electric power package recommendation method based on virtual power plant user-package label portrait | |
| CN115860312A (en) | Electric power marketing digital on-line service system and construction method thereof |
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 |
Application publication date: 20191108 |
|
| RJ01 | Rejection of invention patent application after publication |