CN106846163A - A kind of electric power payment channel overall analysis system - Google Patents
A kind of electric power payment channel overall analysis system Download PDFInfo
- Publication number
- CN106846163A CN106846163A CN201610525389.0A CN201610525389A CN106846163A CN 106846163 A CN106846163 A CN 106846163A CN 201610525389 A CN201610525389 A CN 201610525389A CN 106846163 A CN106846163 A CN 106846163A
- Authority
- CN
- China
- Prior art keywords
- channel
- payment
- data
- user
- layer
- 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 67
- 238000010276 construction Methods 0.000 claims abstract description 18
- 238000011161 development Methods 0.000 claims abstract description 14
- 238000004088 simulation Methods 0.000 claims abstract description 13
- 238000012800 visualization Methods 0.000 claims abstract description 6
- 238000007726 management method Methods 0.000 claims description 38
- 238000000034 method Methods 0.000 claims description 22
- 230000009471 action Effects 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 12
- 238000011084 recovery Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000008878 coupling Effects 0.000 claims description 3
- 238000010168 coupling process Methods 0.000 claims description 3
- 238000005859 coupling reaction Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 230000003542 behavioural effect Effects 0.000 claims description 2
- 230000008859 change Effects 0.000 claims description 2
- 230000010354 integration Effects 0.000 claims description 2
- 230000000153 supplemental effect Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 10
- 238000011156 evaluation Methods 0.000 abstract description 7
- 230000006399 behavior Effects 0.000 abstract description 6
- 230000005611 electricity Effects 0.000 abstract description 5
- 238000007418 data mining Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 10
- 238000012360 testing method Methods 0.000 description 9
- 238000002922 simulated annealing Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 230000007704 transition Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000000137 annealing Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000013209 evaluation strategy Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 241000257303 Hymenoptera Species 0.000 description 1
- HUTDUHSNJYTCAR-UHFFFAOYSA-N ancymidol Chemical compound C1=CC(OC)=CC=C1C(O)(C=1C=NC=NC=1)C1CC1 HUTDUHSNJYTCAR-UHFFFAOYSA-N 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000008260 defense mechanism Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Landscapes
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of electric power payment channel overall analysis system, including payment channel information management module, channel payment condition managing module, user preference analysis module, channel geographical distribution management module and channel simulation implementation management module.The present invention combines the idea of development in current " big data " epoch, data mining technology is introduced to be analyzed a large amount of payment data of Electricity customers, improved KNN algorithms are used in terms of evaluation index selection, construct client's paying behaviors analysis model, channel simulation construction model and the visualization site selection model based on GIS, and the exploitation based on this of novelty complete to be based on the payment channel overall analysis system of big data.
Description
Technical field
The present invention relates to communication of power system field, more particularly to a kind of electric power payment channel overall analysis system.
Background technology
With payment channel building variation, the development of way to pay dues diversification, the payment of business office of original electric power mechanism
" single to pay dues " pattern is broken, but in real life, the head when payment of electric power mechanism is still users' electricity payment
Mode is selected, it is overstaffed during indivedual business office's payment peaks.Between subscriber payment custom, payment demand and payment channel building
Contradiction is highlighted, and tariff recovery hidden danger, electric service hidden danger, is gradually manifested the problems such as human resource distribution is unreasonable.
Chinese Government proposes in the U.S.《Big data research and development plan》Also reply " 12 states housekeeping in 2012
Business informatization project planning ", using big data as constructing emphases, gross investment is estimated hundreds of hundred million.Issue within 2013《In
State's electric power big data development white paper》, it is proposed that electric power big data is the necessarily mistake of power industry technologies innovation in energy revolution
Journey, rather than simple technology category.Electric power big data is not only technological progress, is even more related to whole power system counting greatly
It is that intelligent electric Force system of future generation exists according to the major transformation of the aspect such as idea of development, management system and technology path under the epoch
The form of value rises under the big data epoch.
The Specific Principles that system architecture design is followed are as follows：
(1) autgmentability principle, system is provided in terms of scalability can dynamically be dismantled, the machine based on component model upgraded
System, takes into full account the expansible demand to business breadth and depth.(2) principle of sound accounting, system Construction is followed strictly《State's household electrical appliances
The application software universal safety requirement of net company》Specified in every security strategy, and combine business characteristic and strengthen information security and prevent
Shield.Safe and reliable defense mechanism, comprehensive guarantor are set up in terms of transmission control, storage control, operation control, access control four
Hinder information security, the data safety of user.(3) reliability, open principle, system design not only meet current business
Need, it is also contemplated that system stability reliably and with long-term, will not decline because system operation time and data volume increase.(4) specification
Change principle, system design follows associated international standards, national standard, professional standard and company standard, Uniting, unitized overall development
And application.(5) Supreme principle, using multi-layer framework designing technique, keeps technological precedence.It is high concurrent control in system, fast
The aspects such as speed calculating construct advanced technical system.
Therefore, excavated by subscriber payment data, premised on business-driven, for the purpose of practical application, set up
Corresponding business model, channel analysis business structure of paying the fees forms a perfect electric power payment channel overall analysis system and shows
Obtain particularly important.
The content of the invention
In order to solve the above technical problems, being analyzed according to existing finding and Current Situation, key index is summarized, formulated
Corresponding Evaluation Strategy method, mainly includes that channel payment situation evaluation of programme, terminal operating situation evaluation of programme, terminal are paid
Take situation evaluation of programme, the electricity charge and account situation evaluation of programme and distributor's traffic-operating period evaluation of programme.
It is an object of the invention to provide one kind in electric power payment channel analysis, can formulate different for different value customers
Power supply mode provides marketing decision-making and supports, and makes the electric power payment channel comprehensive analysis system that anticipation forms payment channel optimization
System.
For achieving the above object, the technical scheme of present invention offer is：
A kind of electric power payment channel overall analysis system, including payment channel information management module, channel payment situation pipe
Reason module, user preference analysis module, channel geographical distribution management module and channel simulation implementation management module, wherein,
Payment channel information management module integrates electric power payment channel, site, terminal construction and payment terminal in region
The data of service ability, according to Data Comparison, each payment terminal is utilized situation；
Channel payment each channel payment amount of money of condition managing module management and stroke count data, according to payment amount of money and stroke count
Data judge channel development trend, analyze the tariff recovery situation of each time period, obtain subscriber payment custom and tariff recovery rate
Data；
User preference analysis module analyzes service condition of the different characteristic user to channel, grasps user preference；
Channel geographical distribution management module is based on the distributed data of management map payment site and payment terminal, analysis payment
The data of channel site covering radius, service ability, operation and equipment operation, obtain payment channel coverage blind area；
Channel simulates implementation management module on the basis of payment channel coverage blind area, and optimization channel is distributed.
Further, the displaying of payment channel information and payment terminal service energy are included in payment channel information management module
Power analyzes two parts, and payment channel information illustrates payment channel composition, quantity and the construction data of time of putting into operation, energy
Enough inquiries completed by region channel entirety construction situation；
The analysis of payment terminal service ability obtains the data of payment terminal working time, every Business Processing speed, calculates
Electric power payment terminal handles the bearing capacity of the business of paying dues, with according to equipment operation ratio, the index of Day Trading stroke count analyzes payment terminal
Service ability.
Further, pay dues situation statistics, subscriber payment action trail point are included in channel payment condition managing module
Paid dues day after analysis, channel distribution and managed and four parts of channel trend analysis,
Wherein, situation of paying dues is counted according to power supply unit, time of paying dues, channel grouped data, there is provided statistics and inquiry work(
Can, including stroke count of paying dues, the pay dues amount of money and proportion；
The action trail of paying dues of subscriber payment action trail analysis analysis user, concludes receivable information data and user pays dues
Information data, forms action trail figure of paying dues；
Paid dues day after channel distribution daily pay dues stroke count, value data of paying dues after the distribution of management integration channel, obtain user
Paying behaviors feature；
Channel distribution after pay dues day each channel of administrative analysis pay dues stroke count, the amount of money of paying dues on year-on-year basis with sequential growth rate result,
Judge following payment channel development trend.
Further, user preference analysis module is analyzed including user preference, and user's personal feature is managed and payment canal
Three parts of road positioning analysis,
Wherein, user preference analysis forms user with reference to personal feature, behavior of paying dues, the customer satisfaction data of user
Channel preference data；
The management of user's personal feature carries out maintenance management to user's personal feature data, to user's personal feature data dimension
It is modified and inquires about；
Payment channel positioning analysis reflection channel and the mapping relations of user, it is by clustering methodology that user is different individual
Body characteristicses data are combined, and generate the mapping relations of different crowd user preference data, construction feature user and channel.
Further, channel geographical distribution management module includes payment terminal monitoring, site information and position distribution inquiry
And dot area coverage analyzes three parts,
Wherein payment terminal monitors the distribution of information display terminal position according to the map, and function includes：Payment terminal is set
Standby state is monitored, the data of the normal operation terminal of display and failed terminals；The transaction business for monitoring payment terminal handles feelings
Condition, judges whether normally provide service；
Site information and position distribution inquire about the distribution situation for showing site information on map, single according to power supply
Position, channel classification and site type, show each dot location, and can show that site includes pay dues situation and equipment on map
The essential information of running status；
Dot area coverage analysis can show each site coverage condition on map, according to network point distribution and covering radius
Setting, the overlay area to site in GIS map marks display.
Further, channel simulation implementation management module includes existing channel optimization, channel simulation planning construction and channel
Coefficient sets three parts,
Wherein, existing channel optimization optimizes existing network point distribution situation on map, adjusts dot location and covering radius；
Channel simulate planning construction on the basis of the map on combine supply capacity, channel coverage blind spot and simulation and build net
Point data, carries out visualization addressing, and generation is following to build distribution displaying figure；
Set by channel coefficient, be site, payment terminal covering radius default settings.
Further, the data transfer mode of the electric power payment channel overall analysis system is, data Layer and application layer,
Application layer carries out data transmission respectively with represent layer, represent layer and client layer；
The data Layer is responsible for receiving the data call of application layer and result set being returned into application layer；
Coupling system service logic does corresponding treatment after the application layer receives the instruction that user operates；
The represent layer gets the authority of active user from client layer, represent in systems module under the authority with
Data after business and treatment are presented to user by function, represent layer in the form of chart word；
In the client layer, by web browser sign-on access system, client layer judges the account of user's distribution
The authority of currently logged on user is simultaneously transmitted to represent layer.
Further, the application layer is also divided into operation layer and logical layer, operation layer receiving front-end request type and parameter
Data, so that the corresponding interface service of corresponding calling logic layer；
The logical layer is responsible for the combination of the business and data of function under standalone module, and the parameter that operation layer is transmitted through is done
Data analysis, calls the corresponding data-interface of data Layer to return to operation layer to realize business demand data.
Using above-mentioned technical proposal, the present invention has the advantages that：
First, the present invention forms a set of standard payment channel index definition, and base values and meter are divided into according to index source
Index is calculated, and defines threshold value.According to desired value, corresponding Evaluation Strategy method is formulated, made the data display of system accurate, canal
Road optimization is effective.
Second, the present invention combines the idea of development in current " big data " epoch, is firstly introduced data mining technology to electricity consumption
A large amount of payment data of client are analyzed, and improved KNN algorithms are used in terms of evaluation index selection, and novelty is constructed
Client's paying behaviors analysis model, channel simulation construction model and the visualization site selection model based on GIS, and open based on this
Distribute into the payment channel overall analysis system based on big data.
Brief description of the drawings
Fig. 1 is electric power payment channel overall analysis system structural representation of the present invention；
Fig. 2 is present system data framework schematic diagram.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, below in conjunction with the accompanying drawings and embodiment, it is right
The present invention is further elaborated.It should be appreciated that structure chart described herein and specific embodiment are only used to explain this
Invention, is not intended to limit the present invention.
Embodiment 1
Fig. 1 is electric power payment channel overall analysis system structural representation of the present invention, as shown in figure 1, the invention provides
A kind of electric power payment channel overall analysis system, including payment channel information management module, channel payment condition managing module, use
Family preference analysis module, channel geographical distribution management module and channel simulation implementation management module, wherein,
Payment channel information management module integrates electric power payment channel, site, terminal construction and payment terminal in region
The data of service ability, according to Data Comparison, each payment terminal is utilized situation；
Channel payment each channel payment amount of money of condition managing module management and stroke count data, according to payment amount of money and stroke count
Data judge channel development trend, analyze the tariff recovery situation of each time period, obtain subscriber payment custom and tariff recovery rate
Data；
User preference analysis module analyzes service condition of the different characteristic user to channel, grasps user preference；
Channel geographical distribution management module is based on the distributed data of management map payment site and payment terminal, analysis payment
The data of channel site covering radius, service ability, operation and equipment operation, obtain payment channel coverage blind area；
Channel simulates implementation management module on the basis of payment channel coverage blind area, and optimization channel is distributed.
Embodiment 2
The type matrix block structure of modules is as shown in Figure 1.
Wherein, 1) payment channel information displaying
Show channel building situation of paying dues, including channel composition, quantity, put into operation the time etc..There is provided according to belonging to city simultaneously
Each area is inquired about, and shows the channel entirety construction situation in the area.
2) terminal service capability analysis
Displaying terminal working time, every Business Processing speed, calculate the carrying that electric power payment terminal handles the business of paying dues
Amount, and considers equipment operation ratio, day the index, analysing terminal service ability such as real trade stroke count.
3) situation of paying dues is counted
Show situation of paying dues, according to power supply unit, time of paying dues, channel classification, there is provided statistics and query function, including hand over
Take stroke count, the pay dues amount of money and proportion.
4) subscriber payment action trail analysis
Show the action trail of paying dues of user, with the time as transverse axis, the longitudinal axis shows receivable information (including amount receivable and electricity
Expense classification) and user's paying information (information such as including the amount of money of paying dues, the way to pay dues for using), form action trail figure of paying dues.
5) paid dues day situation after issuing
After displaying distribution, stroke count of paying dues daily, the amount of money of paying dues understand subscriber payment behavioral characteristic, for optimization is serviced, improve
User satisfaction provides reference.
6) channel trend analysis
Show each channel pay dues stroke count, the amount of money of paying dues on year-on-year basis with sequential growth rate result, judge following channel development trend,
For following channel building variation tendency quantitatively provides foundation.
7) user preference analysis
Displaying user preference, personal feature, behavior of paying dues with reference to user, CSAT, the channel for forming user is inclined
It is good.
8) user's personal feature management
Maintenance management is carried out for user's personal feature, the increasing to user's personal feature dimension is supported, is deleted, changes, looking into operation.
9) channel positioning analysis
User's Different Individual combinations of features is formed different people by displaying channel and the mapping relations of user, clustering methodology
Group's user preference, forms the mapping relations of different characteristic user and channel.For each power supply unit is formulated according to oneself user situation
Channel adjustment scheme provides foundation.
10) payment terminal monitoring
Displaying terminal position distribution on map, information includes：The SOT state of termination is monitored：Terminal unit status is monitored,
The situation of the normal operation terminal of display and failed terminals；Terminal transaction situation is monitored：The transaction business of monitor terminal handles situation,
Whether service can be provided normally.
11) site information and position distribution
Distribution situation of the displaying site information on map:According to power supply unit, channel classification, site type, in map
Upper each site address of display.The site on map is clicked on, the site essential information, including the operation of situation of paying dues, equipment can be shown
State etc..
12) site covering analyzing
Show each site coverage condition on map, set according to network point distribution and covering radius, to site in GIS map
Overlay area mark display.
13) existing channel operation optimization
Optimize existing network point distribution situation on map, dot location, covering radius can be adjusted according to actual conditions.
Make current channel distribution and coverage condition more accurate, basis is provided to be accurately positioned future plan.
14) channel simulation planning construction
Whether matched with reference to supply capacity on map, with reference to channel coverage blind spot, site is built in simulation.Carried out based on GIS
Visualization addressing, simulates future plan, and generation is following to build distribution displaying figure.Later site coverage is blueness, newly-increased
Site coverage is red, and each planning chart can preserve scheme.Can be to having preserved proposal inquiry, editor, deletion action.
15) channel coefficient is set
Define site, the system default value of terminal covering radius.
Embodiment 3
Fig. 2 is present system data framework schematic diagram, as shown in Fig. 2 client layer：The account of user's distribution passes through
Web browser sign-on access system, this layer judges the authority of currently logged on user and informs represent layer；Use the technology for arriving：
HTML user be presented to user-friendly login page, SESSION user storage User logs in after deposit user profile container,
EL labels are that the information of the page does not leak effectively, play a part of protection, javascript do page data simple process,
Jquery is some special efficacys for doing the page.
Represent layer：The authority of active user is got from client layer, module and function under the authority is represented in systems,
Data after business and treatment are presented to user by represent layer in the form of chart word, are whole systems most direct with user interaction
Effective level；Used technology has：HTML user is presented to user-friendly login page, SESSION user's storage and uses
Family is deposited the information that the container of user profile, EL labels are the pages and is not leaked effectively after logging in, play a part of protection,
It is to do some special efficacys of the page that javascript does the simple process of page data, jquery；Easyui is whole system leading portion
The framework of the page, it is that the framework for representing chart to user includes that it is responsible for the layout of the page, echarts：But post figure, multicolumn
Figure, pie chart, radar map etc., echart and can say system data privacy functions, freemarker Page Templates effect be
Reuse the page and save the page jump time.
Application layer：Coupling system service logic does corresponding treatment, application after application layer receives the instruction that user operates
Layer can be divided into operation layer, logical layer again；Operation layer：Operation layer is mainly receiving front-end request type and parameter, so that accordingly
The calling logic corresponding interface service of layer, Business Processing is not done in the layer, and simply a front end and business link bridge and number
According to transfer；
Logical layer：The most strong level with business association, the knot of the business of function and data under this layer of responsible standalone module
Close, the parameter that operation layer is transmitted through is done data analysis, call the corresponding data-interface of data Layer to realize business demand data
Return to operation layer.The technology being directed to has：Java agent technologies, springMVC system bodies architecture framework, hadoop do
The main framework of Data Analysis Services, development system platform are the distinctive analysis of big data and disposal ability, and can be to magnanimity number
According to efficient Treatment Analysis.
Data Layer：The layer is responsible for reception application layer and calls and result set is returned into application layer, and mysql databases are for propping up
The storehouse of development platform is supportted, oracle is the storehouse of data source；The major technique being related to has the number that hibernate partial functions are used
According to storing framework.
Wherein, the algorithm on data mining, it is preferred to use certain methods.
K arest neighbors (k-Nearest Neighbor, KNN) sorting algorithm, according to some sample instances and other examples it
Between similitude classified.KNN algorithms can be not only used for classification, can be also used for returning, and is one and compares into theory
Ripe method, is also one of simplest machine learning algorithm.The thinking of the method is：If a sample is in feature space
K most like (i.e. closest in feature space) sample in it is most of belong to some classification, then the sample falls within
This classification.In KNN algorithms, selected neighbours are the objects correctly classified.The method on class decision-making is determined only according to
The classification belonging to sample to be divided is determined according to the classification of one or several closest samples.Although KNN methods are from principle
Limit theorem is also relied on, but in classification decision-making, it is only relevant with minimal amount of adjacent sample.Because KNN methods are mainly by week
The neighbouring sample of limit is with, generic is determined rather than the method by differentiation class field, therefore for the intersection of class field
Or for the more sample set to be divided of overlap, KNN methods are more suitable for compared with other method.Specifically by finding out sample
K nearest-neighbors, the sample is assigned to by the average value of the attribute of these neighbours, so as to obtain the attribute of the sample.KNN algorithm streams
Journey figure is as shown in Figure 2.
According to traditional vector space model, sample by formalize be characterized in space weighted feature vector, i.e. D=D
(T1, W1；T2,W2；…；Tn,Wn).For a test sample, the similarity that it concentrates each sample with training sample is calculated,
The most like samples of K are found out, the classification according to Weighted distance and belonging to judging test sample.The test sample is calculated with training
The similarity of each sample, computing formula is concentrated to be:
In formula:diIt is the characteristic vector of test sample, djIt is the center vector of jth class；M is characterized the dimension of vector；WkFor
The kth dimension of vector.The determination of k values typically first uses an initial value, then the result adjustment K values according to experiment test K, typically
Initial value is set to tens to hundreds of.
Simulated annealing is a kind of random optimizing algorithm based on Monte-Carlo iterative strategies, its starting point
It is the similitude between annealing process and general combinatorial optimization problem based on solid matter in physics.Simulated annealing from certain
One initial temperature higher is set out, and with the continuous decline of temperature parameter, join probability kick characteristic is random in solution space to find target
The globally optimal solution of function, i.e., probability can jump out and finally tend to global optimum in locally optimal solution.Simulated annealing
Starting is first made with arbitrfary point in search space, each step first selects one " neighbours ", then calculate again from existing position to
Up to the probability of " neighbours ".
The algorithm model of simulated annealing is as follows：
That annealing algorithm (SA) access is modeled in the iteration is solution j, and is modeled in (k+1) secondary iteration and moved back
What fiery algorithm (SA) accessed is the probability for solving j.It is made up of two independent probability distribution, is produced from solution i in kth time iteration
The probability g of solutionij(T), wherein gij(T) it is required to meet normalizing condition:
Solve received probability λij(T) temperature when, T is kth time iteration here, during for i ≠ j, transition probability
Expression formula it is as follows
Because λij(T) it is not always equivalent to, therefore new explanation has not received possibility, the probability that algorithm rests on solution i is
Because Ω is a countable set, therefore the random process representated by the stochastic variable of simulated annealing generation is one
Markov chain, one walks transition probability two formulas more than and defines, and one step transition probability of note is：
Then k steps transition probability is
Wherein I is unit matrix, TtRepresent temperature value during the t times iteration.The implication of its matrix element is
Pij(m, m+k)=Pr{Xm+k=j | Xm=i }
State i is in by m iteration, the m+k times iteration is in the probability of state j.
Iteration tuning index weights parameter, so that for channel planning provides index weights reference.It is randomly provided each attribute
Initial weight；Set test set is divided based on sample data set, k nearest neighbor classified calculating, every number in traversal test set is carried out
According to, closest preceding K datas are extracted from training set, compare with the actual value of test data, and statistical error；Missed
Difference compares, and adjusts the weight of each attribute, if error is less than threshold value, obtains the weight of each attribute, otherwise, adjustment attribute
Weight, is iterated test, obtains the weight of each attribute.
Cluster analysis
The target of cluster is to distinguish and extract important distinguishing cluster in potential data set, up to the present studies people
Member develops five kinds of basic clustering methods, partition clustering, hierarchical clustering, density clustering, based on Grid Clustering and
Cluster based on model.Wherein, the thought based on the k-means algorithms for dividing due to algorithm in itself is simple, implements and compares
Easily, it is widely used.But, k-means algorithms are sensitive to exceptional value, and need to determine k values in advance.Therefore use
The improved customer behavior analysis algorithm based on swarm intelligence, the algorithm is the naive model with the classification of ant colony cooperation ant nest as base
Plinth, analyze customer action a kind of Self-organization clustering algorithm, the method can make data be easier visualization, it highlight induce one it is emerging
The feature of interest.The number of cluster centre is automatically generated from data.
Assuming that only a kind of object, all of object is all randomly dispersed in above two-dimentional lattice, and each lattice point only includes one
Object, ant is placed on two-dimentional lattice at random, and every time along random one lattice of direction movement, every time after movement, if phase
The lattice point answered has if object, and the ant without burden determines that giving following probability picks up an object：
Wherein, λ ants feel to obtain object number, and γ around it1＞ 0.When only a small amount of object is in ant week
When enclosing, i.e. λ ＜ ＜ γ1, then PpClose to 1；Therefore, object has larger probability to be lifted, on the other hand, if ant is perceived
To many object γ ＞ ＞ γ1, then PpClose to 0, the probability that object is lifted is just smaller.
The probability that the ant often only born puts down born object is given by following formula：
Wherein, should ensure that given corresponding lattice point is empty, γ2＞ 0, if ant finds substantial amounts of object, i.e. λ around
＞ ＞ γ2, then PdClose to 1, the probability for putting down object is very big.If λ ＜ ＜ γ2, then PdClose to 0, the probability for putting down almost does not have
Have.
Be generalized to BM with actual element to gather by the basic model (BM) based on ant colony clustering algorithm, Lumer and Faieta
Class data vector, proposes famous LF algorithms.A similar density function is introduced in LF algorithms to weigh two data objects
Between similarity degree.
In LF algorithms, data vector is laid randomly on two-dimentional lattice, and n is referred to as in observationNPathIndividually
During point peripheral region, ant randomly moves about in lattice, and moving area is exactly a square fieldI.e. ant is worked as
N around the i of front positionN×nNIndividual place, it is assumed that ant is located at position i in time t, finds data vector Oi, in ant field
Interior data vector Oi" part " density f (Oi) computing formula it is as follows：
In formula, α ＞ 0 define data vector OiAnd OjDistinctiveness ratio scope.Constant α determines that two objects when should
Or should not put together, be one regulation data vector between averag density coefficient, if α is too small, can be formed many it is small
The object for belonging to same group, is gathered different groups by group, if α is too big, is likely to result in obscuring between each group, not belonging to
Gather together in same group of object.So the number of clusters of the α on being formed has directly influence.
Using measuring similarity f (Oi), pick up and abandon probability and be defined as follows：
Embodiment described above only expresses embodiments of the present invention, and its description is more specific and detailed, but can not
Therefore it is interpreted as the limitation to the scope of the claims of the present invention.It should be pointed out that for the person of ordinary skill of the art,
Without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection model of the invention
Enclose.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (8)
1. a kind of electric power payment channel overall analysis system, including payment channel information management module, channel payment condition managing
Module, user preference analysis module, channel geographical distribution management module and channel simulation implementation management module, it is characterised in that
Wherein,
Payment channel information management module integrates electric power payment channel, site, terminal construction and payment terminal service in region
The data of ability, according to Data Comparison, each payment terminal is utilized situation；
Channel payment each channel payment amount of money of condition managing module management and stroke count data, according to payment amount of money and stroke count data
Judge channel development trend, analyze the tariff recovery situation of each time period, obtain subscriber payment custom and tariff recovery rate data；
User preference analysis module analyzes service condition of the different characteristic user to channel, grasps user preference；
Channel geographical distribution management module is based on the distributed data of management map payment site and payment terminal, analysis payment channel
The data of site covering radius, service ability, operation and equipment operation, obtain payment channel coverage blind area；
Channel simulates implementation management module on the basis of payment channel coverage blind area, and optimization channel is distributed.
2. electric power payment channel overall analysis system according to claim 1, it is characterised in that in payment channel information pipe
Reason module includes the displaying of payment channel information and payment terminal service ability analyzes two parts, payment channel information displaying exhibition
Payment channel composition, quantity and the construction data of time of putting into operation are shown, looking into by region channel entirety construction situation can have been completed
Ask；
The analysis of payment terminal service ability obtains the data of payment terminal working time, every Business Processing speed, calculates electric power
Payment terminal handles the bearing capacity of the business of paying dues, with according to equipment operation ratio, the index of Day Trading stroke count analyzes payment terminal service
Ability.
3. electric power payment channel overall analysis system according to claim 1, it is characterised in that paid the fees situation pipe in channel
Reason module includes paying dues pay dues day after situation statistics, the analysis of subscriber payment action trail, channel distribution management and channel develops
Four parts of trend analysis,
Wherein, situation of paying dues is counted according to power supply unit, time of paying dues, channel grouped data, there is provided statistics and query function, bag
Stroke count of paying dues is included, the pay dues amount of money and proportion；
The action trail of paying dues of subscriber payment action trail analysis analysis user, concludes receivable information data and user's paying information
Data, form action trail figure of paying dues；
Paid dues day after channel distribution daily pay dues stroke count, value data of paying dues after the distribution of management integration channel, obtain subscriber payment
Behavioural characteristic；
Channel distribution after pay dues day each channel of administrative analysis pay dues stroke count, the amount of money of paying dues on year-on-year basis with sequential growth rate result, judge
Future payment channel development trend.
4. electric power payment channel overall analysis system according to claim 1, it is characterised in that user preference analysis module
Including user preference analysis, user's personal feature is managed and three parts of payment channel positioning analysis,
Wherein, user preference analysis forms the canal of user with reference to personal feature, behavior of paying dues, the customer satisfaction data of user
Road preference data；
The management of user's personal feature carries out maintenance management to user's personal feature data, and user's personal feature data dimension is carried out
Change and inquiry；
The mapping relations of payment channel positioning analysis reflection channel and user, by clustering methodology by user's Different Individual feature
Data are combined, and generate the mapping relations of different crowd user preference data, construction feature user and channel.
5. electric power payment channel overall analysis system according to claim 1, it is characterised in that channel geographical distribution is managed
Module includes that payment terminal monitoring, site information and position distribution inquiry and dot area coverage analyze three parts,
Wherein payment terminal monitors the distribution of information display terminal position according to the map, and function includes：To payment terminal equipment shape
State is monitored, the data of the normal operation terminal of display and failed terminals；The transaction business for monitoring payment terminal handles situation, sentences
It is disconnected whether normally to provide service；
Site information and position distribution inquire about the distribution situation for showing site information on map, according to power supply unit, canal
Road is classified and site type, each dot location is shown on map, and can show that site includes pay dues situation and equipment operation
The essential information of state；
Dot area coverage analysis can show each site coverage condition on map, according to setting for network point distribution and covering radius
Fixed, the overlay area to site in GIS map marks display.
6. electric power payment channel overall analysis system according to claim 1, it is characterised in that channel simulates implementation management
Module includes that existing channel optimization, channel simulation planning construction and channel coefficient set three parts,
Wherein, existing channel optimization optimizes existing network point distribution situation on map, adjusts dot location and covering radius；
Channel simulate planning construction on the basis of the map on combine supply capacity, channel coverage blind spot and simulation and build net number
According to, visualization addressing is carried out, generation is following to build distribution displaying figure；
Set by channel coefficient, be site, payment terminal covering radius default settings.
7. electric power payment channel overall analysis system according to claim 1, it is characterised in that the electric power payment channel
The data transfer mode of overall analysis system is that data Layer is distinguished with application layer, application layer and represent layer, represent layer and client layer
Carry out data transmission；
The data Layer is responsible for receiving the data call of application layer and result set being returned into application layer；
Coupling system service logic does corresponding treatment after the application layer receives the instruction that user operates；
The represent layer gets the authority of active user from client layer, and module and work(under the authority are represented in systems
Can, data after business and treatment are presented to user by represent layer in the form of chart word；
In the client layer, by web browser sign-on access system, client layer judges current the account of user's distribution
The authority of login user is simultaneously transmitted to represent layer.
8. electric power payment channel overall analysis system according to claim 7, it is characterised in that the application layer is also divided into
Operation layer and logical layer, operation layer receiving front-end request type and supplemental characteristic, so as to corresponding calling logic layer is corresponding connect
Oral business；
The logical layer is responsible for the combination of the business and data of function under standalone module, and the parameter that operation layer is transmitted through is done data
Analysis, calls the corresponding data-interface of data Layer to return to operation layer to realize business demand data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610525389.0A CN106846163A (en) | 2016-07-05 | 2016-07-05 | A kind of electric power payment channel overall analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610525389.0A CN106846163A (en) | 2016-07-05 | 2016-07-05 | A kind of electric power payment channel overall analysis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106846163A true CN106846163A (en) | 2017-06-13 |
Family
ID=59145294
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610525389.0A Pending CN106846163A (en) | 2016-07-05 | 2016-07-05 | A kind of electric power payment channel overall analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106846163A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107909288A (en) * | 2017-12-05 | 2018-04-13 | 国网内蒙古东部电力有限公司电力科学研究院 | Paying behaviors analysis method based on SOM neural network clustering algorithms |
| CN109597840A (en) * | 2018-12-06 | 2019-04-09 | 珠海格力电器股份有限公司 | Data display method, system and energy management back-end platform |
| CN110111124A (en) * | 2019-03-21 | 2019-08-09 | 贵州电网有限责任公司 | Power customer service preference methods and system based on channel preference and business preference |
| CN110136002A (en) * | 2019-03-21 | 2019-08-16 | 阿里巴巴集团控股有限公司 | Payment based reminding method and device calculate equipment and computer readable storage medium |
| CN110633082A (en) * | 2019-09-26 | 2019-12-31 | 山东浪潮商用系统有限公司 | Dynamic data display method and system combining echart and html |
| CN110750248A (en) * | 2018-07-23 | 2020-02-04 | 贵州白山云科技股份有限公司 | Method and device for transmitting extension information of existing component |
| CN111221868A (en) * | 2018-11-26 | 2020-06-02 | 国网上海市电力公司 | Data mining and analyzing method applied to channel preference of power customer |
| CN111489087A (en) * | 2020-04-13 | 2020-08-04 | 广东卓维网络有限公司 | Power grid strategic operation control method and system |
| CN112488837A (en) * | 2020-12-11 | 2021-03-12 | 四川川能智网实业有限公司 | Comprehensive energy service electric power transaction system |
| CN112594937A (en) * | 2020-12-16 | 2021-04-02 | 珠海格力电器股份有限公司 | Control method and device of water heater, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104077719A (en) * | 2014-07-08 | 2014-10-01 | 国家电网公司 | Electric power payment branch value analyzing system |
| CN104125090A (en) * | 2013-04-28 | 2014-10-29 | 国际商业机器公司 | Method and apparatus for managing communication channel |
| CN105260815A (en) * | 2015-09-18 | 2016-01-20 | 国网辽宁省电力有限公司鞍山供电公司 | Electric power system payment channel evaluating method based on large data |
| CN105303470A (en) * | 2015-11-26 | 2016-02-03 | 国网辽宁省电力有限公司大连供电公司 | Electric power project planning and construction method based on big data |
-
2016
- 2016-07-05 CN CN201610525389.0A patent/CN106846163A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104125090A (en) * | 2013-04-28 | 2014-10-29 | 国际商业机器公司 | Method and apparatus for managing communication channel |
| CN104077719A (en) * | 2014-07-08 | 2014-10-01 | 国家电网公司 | Electric power payment branch value analyzing system |
| CN105260815A (en) * | 2015-09-18 | 2016-01-20 | 国网辽宁省电力有限公司鞍山供电公司 | Electric power system payment channel evaluating method based on large data |
| CN105303470A (en) * | 2015-11-26 | 2016-02-03 | 国网辽宁省电力有限公司大连供电公司 | Electric power project planning and construction method based on big data |
Non-Patent Citations (1)
| Title |
|---|
| 宁卜 等: "基于GIS的电力缴费渠道一体化管理平台", 《华北电业》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107909288A (en) * | 2017-12-05 | 2018-04-13 | 国网内蒙古东部电力有限公司电力科学研究院 | Paying behaviors analysis method based on SOM neural network clustering algorithms |
| CN110750248A (en) * | 2018-07-23 | 2020-02-04 | 贵州白山云科技股份有限公司 | Method and device for transmitting extension information of existing component |
| CN111221868A (en) * | 2018-11-26 | 2020-06-02 | 国网上海市电力公司 | Data mining and analyzing method applied to channel preference of power customer |
| CN109597840A (en) * | 2018-12-06 | 2019-04-09 | 珠海格力电器股份有限公司 | Data display method, system and energy management back-end platform |
| CN110111124A (en) * | 2019-03-21 | 2019-08-09 | 贵州电网有限责任公司 | Power customer service preference methods and system based on channel preference and business preference |
| CN110136002A (en) * | 2019-03-21 | 2019-08-16 | 阿里巴巴集团控股有限公司 | Payment based reminding method and device calculate equipment and computer readable storage medium |
| CN110136002B (en) * | 2019-03-21 | 2023-09-12 | 创新先进技术有限公司 | Payment reminding method and device, computing equipment and computer readable storage medium |
| CN110633082A (en) * | 2019-09-26 | 2019-12-31 | 山东浪潮商用系统有限公司 | Dynamic data display method and system combining echart and html |
| CN111489087A (en) * | 2020-04-13 | 2020-08-04 | 广东卓维网络有限公司 | Power grid strategic operation control method and system |
| CN112488837A (en) * | 2020-12-11 | 2021-03-12 | 四川川能智网实业有限公司 | Comprehensive energy service electric power transaction system |
| CN112488837B (en) * | 2020-12-11 | 2024-03-12 | 四川川能智网实业有限公司 | Comprehensive energy service electric power transaction system |
| CN112594937A (en) * | 2020-12-16 | 2021-04-02 | 珠海格力电器股份有限公司 | Control method and device of water heater, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106846163A (en) | A kind of electric power payment channel overall analysis system | |
| Malczewski | Integrating multicriteria analysis and geographic information systems: the ordered weighted averaging (OWA) approach | |
| CN106650763A (en) | Calculating method of index selection, weight optimization and channel planning of electric power payment channel analysis | |
| CN109711865A (en) | A method of prediction is refined based on the mobile radio communication flow that user behavior excavates | |
| CN101894134B (en) | Spatial layout-based fishing webpage detection and implementation method | |
| CN109377265A (en) | Site selecting method, device, equipment and storage medium | |
| CN105184455A (en) | High dimension visualized analysis method facing urban electric power data analysis | |
| CN107146089A (en) | The single recognition methods of one kind brush and device, electronic equipment | |
| CN103020302A (en) | Academic core author excavation and related information extraction method and system based on complex network | |
| CN103176985A (en) | Timely and high-efficiency crawling method for internet information | |
| CN108023768A (en) | Network event chain establishment method and network event chain establish system | |
| Yuan et al. | Regional land-use allocation using a coupled MAS and GA model: From local simulation to global optimization, a case study in Caidian District, Wuhan, China | |
| Feng et al. | Design and simulation of human resource allocation model based on double-cycle neural network | |
| CN110297990A (en) | The associated detecting method and system of crowdsourcing marketing microblogging and waterborne troops | |
| CN110009416A (en) | A kind of system based on big data cleaning and AI precision marketing | |
| Yang et al. | Evaluation of integrative hierarchical stepwise sampling for digital soil mapping | |
| CN106296315A (en) | Context aware systems based on user power utilization data | |
| CN104363104A (en) | User-requirement-oriented mass multivariate data situation displaying system and method | |
| Dassisti et al. | Net modelling of energy mix among European Countries: A proposal for ruling new scenarios | |
| CN108733747A (en) | Map retrieval method based on cloud computing and its system | |
| CN108416524A (en) | Estate planning based on a figure general framework refines deciphering method | |
| Yiping et al. | An improved multi-view collaborative fuzzy C-means clustering algorithm and its application in overseas oil and gas exploration | |
| CN107767280A (en) | A kind of high-quality node detecting method based on element of time | |
| Hung et al. | Investigating uncertainties in human adaptation and their impacts on water scarcity in the Colorado river Basin, United States | |
| CN104703059B (en) | A kind of method and device for planning of broadband access network |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170613 |
|
| WD01 | Invention patent application deemed withdrawn after publication |