CN109087127A - A kind of the behavioural characteristic analysis method and device of electric car charge user - Google Patents
A kind of the behavioural characteristic analysis method and device of electric car charge user Download PDFInfo
- Publication number
- CN109087127A CN109087127A CN201810755332.9A CN201810755332A CN109087127A CN 109087127 A CN109087127 A CN 109087127A CN 201810755332 A CN201810755332 A CN 201810755332A CN 109087127 A CN109087127 A CN 109087127A
- Authority
- CN
- China
- Prior art keywords
- electric car
- user
- charge user
- car charge
- charging
- 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
- 230000003542 behavioural effect Effects 0.000 title claims abstract description 40
- 238000004458 analytical method Methods 0.000 title claims abstract description 22
- 238000011160 research Methods 0.000 claims abstract description 52
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 27
- 230000006399 behavior Effects 0.000 claims description 41
- 230000005611 electricity Effects 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 235000012054 meals Nutrition 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 230000009897 systematic effect Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000000034 method Methods 0.000 abstract description 14
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 239000012141 concentrate Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 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
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of behavioural characteristic analysis method of electric car charge user and devices, are related to electric car charging technique field.Method includes: to obtain the related data of each electric car charge user in research range, and be standardized to each project in the related data, obtains standardized data；According to Model tying algorithm, the standardized data is handled, each electric car charge user in research range is divided into multiple user behavior characteristics classes.The present invention is arranged by the related data to electric car charge user, and is analyzed by the behavioural characteristic that the clustering algorithm of big data technology (such as K-means) can conveniently carry out electric car charge user.
Description
Technical field
The present invention relates to electric car charging technique field more particularly to a kind of behavioural characteristics of electric car charge user
Analysis method and device.
Background technique
Currently, electric car has occupied certain ratio in people's trip mode with the gradually development of new energy technology
Example.And during trip, electric car is frequently necessary to charge, to supplement the electric power energy of electric car.Therefore, in electricity
Electrical automobile is widely used regional (such as China Ji Beidiqu), needs that the facilities such as charging pile largely are arranged.
In order to meet the user demand of each department, the charging enterprise of electric car needs to be grasped the charge data of user, because
This needs to carry out charge user behavioural characteristic research, and current main research means are to rely on from car networking management platform and extract
Data, including charging pile archives, each department charging transaction data etc..These data generally pertain only to the recharged card of user
Number, charge volume, transaction amount, mode of doing business, exchange hour, transaction pile No. etc., be short of and charge the accurate description of behavior to user.
Currently, correctly identifying the behavioural characteristic of charging station user or automobile user, efficiency of operation is improved for operation enterprise, is promoted
O&M service quality, guidance user's charging behavior, are all of great significance.And how conveniently to carry out electric car charging
The behavioural characteristic analysis of user has become a urgent problem to be solved.
Summary of the invention
The embodiment of the present invention provides the behavioural characteristic analysis method and device of a kind of electric car charge user, to realize
Conveniently carry out the behavioural characteristic analysis of electric car charge user.
In order to achieve the above objectives, the present invention adopts the following technical scheme:
A kind of behavioural characteristic analysis method of electric car charge user, comprising:
The related data of each electric car charge user in research range is obtained, and to each in the related data
Project is standardized, and obtains standardized data；
According to Model tying algorithm, the standardized data is handled, each electric car in research range is filled
Electric user is divided into multiple user behavior characteristics classes.
Further, the behavioural characteristic analysis method of the electric car charge user, further includes:
User into different user behavior characteristics classes pushes pre-set electric car charging service content, so as to
Business handling and acquisition of information are carried out according to electric car charging service content in electric car charge user.
Specifically, the related data for obtaining each electric car charge user in research range, and to the correlation
Each project in data is standardized, and obtains standardized data, comprising:
Obtain the related data of each electric car charge user in research range, each project in the related data
It include: the charging total electricity in a predetermined period, charging total degree, in the charging times, on weekdays of each default website
Charging times, the charging times at weekend, the charging times in festivals or holidays and the charging times in daily each preset time period；
Obtain the maximum value S of the project in the related data in each electric car charge usermaxWith minimum value Smin；
According to the maximum value SmaxWith minimum value SminBy one in the related data in each electric car charge user
Purpose value SIt is formerIt is standardized, obtains SIt is formerCorresponding standardized data SStandard；Wherein,
Specifically, described handled the standardized data according to Model tying algorithm, it will be each in research range
Electric car charge user is divided into multiple user behavior characteristics classes, comprising:
Each electric car charge user is divided into pre-set K class by step 1；
Step 2, according to the standardized data of each electric car charge user, seek the average value of pre-set K class
Wherein,Wherein,For the standardization of each electric car charge user
The average value of i-th of project in data, p are the project sum in the standardized data of electric car charge user；N is research
Electric car charge user sum in range；xjiFor i-th in the standardized data of j-th of electric car charge user
Purpose value；
The standardized data x of step 3, each electric car charge user of traversalj=(xj1,xj2,...,xjp), it is each to determine
The standardized data x of electric car charge userj=(xj1,xj2,...,xjp) and each pre-set K classEuclidean away from
From；
Each electric car charge user is re-assigned in the smallest one kind of Euclidean distance, and recalculates K by step 4
The average value of class；3 are returned to step after step 4, until the Euclidean of class that is currently located of each electric car charge user away from
From minimum；
If the electric car charge user in step 5, one kind accounts for the electric car charge user sum in survey region
Percentage is less than pre-set percentage threshold, then deletes such, retains electric car charge user and accounts in survey region
The percentage of electric car charge user sum is more than or equal to the class of pre-set percentage threshold, as user behavior characteristics
Class.
In addition, the user into different user behavior characteristics classes pushes pre-set electric car charging service
Content, in order to which electric car charge user carries out business handling and acquisition of information, packet according to electric car charging service content
It includes:
User into different user behavior characteristics classes pushes different electric car charging service contents；It is described electronic
Automobile charging service content includes the preferential service content of charging pricing for segment, electric car charging set meal service content, neighbouring scape
Area's information, periphery adequate and systematic service information, nearby one of charge station information and newly-increased website situation information or a variety of on the way.
A kind of behavioural characteristic analytical equipment of electric car charge user, comprising:
Data normalization processing unit, for obtaining the related data of each electric car charge user in research range,
And each project in the related data is standardized, obtain standardized data；
Cluster cell will be in research range for handling the standardized data according to Model tying algorithm
Each electric car charge user is divided into multiple user behavior characteristics classes.
Further, the behavioural characteristic analytical equipment of the electric car charge user, further includes:
Service content push unit, it is pre-set electronic for user's push into different user behavior characteristics classes
Automobile charging service content, in order to electric car charge user according to electric car charging service content carry out business handling and
Acquisition of information.
In addition, the data normalization processing unit, is specifically used for:
Obtain the related data of each electric car charge user in research range, each project in the related data
It include: the charging total electricity in a predetermined period, charging total degree, in the charging times, on weekdays of each default website
Charging times, the charging times at weekend, the charging times in festivals or holidays and the charging times in daily each preset time period；
Obtain the maximum value S of the project in the related data in each electric car charge usermaxWith minimum value Smin；
According to the maximum value SmaxWith minimum value SminBy one in the related data in each electric car charge user
Purpose value SIt is formerIt is standardized, obtains SIt is formerCorresponding standardized data SStandard；Wherein,
In addition, the cluster cell, is specifically used for:
Each electric car charge user is divided into pre-set K class by step 1；
Step 2, according to the standardized data of each electric car charge user, seek the average value of pre-set K class
Wherein,Wherein,For the standardization of each electric car charge user
The average value of i-th of project in data, p are the project sum in the standardized data of electric car charge user；N is research
Electric car charge user sum in range；xjiFor i-th in the standardized data of j-th of electric car charge user
Purpose value；
The standardized data x of step 3, each electric car charge user of traversalj=(xj1,xj2,...,xjp), it is each to determine
The standardized data x of electric car charge userj=(xj1,xj2,...,xjp) and each pre-set K classEuclidean away from
From；
Each electric car charge user is re-assigned in the smallest one kind of Euclidean distance, and recalculates K by step 4
The average value of class；3 are returned to step after step 4, until the Euclidean of class that is currently located of each electric car charge user away from
From minimum；
If the electric car charge user in step 5, one kind accounts for the electric car charge user sum in survey region
Percentage is less than pre-set percentage threshold, then deletes such, retains electric car charge user and accounts in survey region
The percentage of electric car charge user sum is more than or equal to the class of pre-set percentage threshold, as user behavior characteristics
Class.
In addition, the service content push unit, is specifically used for:
User into different user behavior characteristics classes pushes different electric car charging service contents；It is described electronic
Automobile charging service content includes the preferential service content of charging pricing for segment, electric car charging set meal service content, neighbouring scape
Area's information, periphery adequate and systematic service information, nearby one of charge station information and newly-increased website situation information or a variety of on the way.
A kind of computer readable storage medium, is stored thereon with computer program, realization when which is executed by processor
Following steps:
The related data of each electric car charge user in research range is obtained, and to each in the related data
Project is standardized, and obtains standardized data；
According to Model tying algorithm, the standardized data is handled, each electric car in research range is filled
Electric user is divided into multiple user behavior characteristics classes.
A kind of computer equipment including memory, processor and is stored in the meter that storage is upper and can run on a processor
Calculation machine program, the processor perform the steps of when executing described program
The related data of each electric car charge user in research range is obtained, and to each in the related data
Project is standardized, and obtains standardized data；
According to Model tying algorithm, the standardized data is handled, each electric car in research range is filled
Electric user is divided into multiple user behavior characteristics classes.
The behavioural characteristic analysis method and device of a kind of electric car charge user provided in an embodiment of the present invention, are obtained first
The related data of each electric car charge user in research range is taken, and each project in the related data is marked
Quasi-ization processing, obtains standardized data；Later, according to Model tying algorithm, the standardized data is handled, will be studied
Each electric car charge user in range is divided into multiple user behavior characteristics classes.As it can be seen that the present invention passes through to electric car
The related data of charge user is arranged, and can be convenient and efficient by the clustering algorithm of big data technology (such as K-means)
Progress electric car charge user behavioural characteristic analysis.
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 without any creative labor, may be used also for those of ordinary skill in the art
To obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart of the behavioural characteristic analysis method of electric car charge user provided in an embodiment of the present invention
One；
Fig. 2 is a kind of flow chart of the behavioural characteristic analysis method of electric car charge user provided in an embodiment of the present invention
Two；
Fig. 3 is that a kind of structure of the behavioural characteristic analytical equipment of electric car charge user provided in an embodiment of the present invention is shown
It is intended to.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
As shown in Figure 1, the embodiment of the present invention provides a kind of behavioural characteristic analysis method of electric car charge user, packet
It includes:
Step 101, the related data for obtaining each electric car charge user in research range, and to the related data
In each project be standardized, obtain standardized data.
Step 102, according to Model tying algorithm, the standardized data is handled, by each electricity in research range
Electrical automobile charge user is divided into multiple user behavior characteristics classes.
Model tying algorithm involved in the embodiment of the present invention can use K-means clustering algorithm, and K-means cluster is calculated
Method is hard clustering algorithm, is the representative of the typically objective function clustering method based on prototype, it is data point to certain of prototype
Objective function of the kind distance as optimization obtains the adjustment rule of interative computation using the method that function seeks extreme value.
A kind of behavioural characteristic analysis method of electric car charge user provided in an embodiment of the present invention obtains research first
The related data of each electric car charge user in range, and place is standardized to each project in the related data
Reason, obtains standardized data；Later, according to Model tying algorithm, the standardized data is handled, it will be in research range
Each electric car charge user be divided into multiple user behavior characteristics classes.As it can be seen that the present invention is used by charging to electric car
The related data at family is arranged, and can conveniently be carried out by the clustering algorithm of big data technology (such as K-means)
The behavioural characteristic of electric car charge user is analyzed.
In order to make those skilled in the art be better understood by the present invention, a more detailed embodiment is set forth below,
As shown in Fig. 2, the embodiment of the present invention provides a kind of behavioural characteristic analysis method of electric car charge user, comprising:
Step 201, the related data for obtaining each electric car charge user in research range, in the related data
Each project include: a predetermined period charging total electricity, charging total degree, each default website charging times,
Workaday charging times, the charging times at weekend, charging times in festivals or holidays and in daily each preset time period
Charging times.
Each electric car charge user in research range herein generally refers to the public group such as private car, and simultaneously non-electrical
Electric bus user, because bus charging does not have representativeness.For example, using September 1 day to 2017 October in 2016 herein
The transaction data of the electric car charge user (not including public transport charging station) of 30 backlands Ji area.
Each project in the related data can be as shown in table 1 below comprising: in the charging total electricity of a predetermined period
Dl, charging total degree Dc, in the charging times of each default website, (such as each high speed website Zg, city website Zs, Beijing are related
Website Zb, Chengde website Zc, intercity high speed website Zj, Langfang City website Zl, Qinhuangdao website Zq, Tangshan City website Zt,
Zhangjiakou City website Zz can also include a lot of other default websites, details are not described herein again herein only by taking above-mentioned website as an example),
(such as Spring Festival holiday fills by charging times Tg on weekdays, the charging times Tz at weekend, the charging times Tj in festivals or holidays
Electric number, the charging times etc. of vacation on National Day) and daily each preset time period charging times (for example, 00 in daily:
00 to 03:59,04:00 to 07:59,08:00 to 11:59,12:00 to 15:59,16:00 to 19:59 and 20:00 to 23:59's
Charging times).
Table 1:
The maximum value S of the project in related data in step 202, each electric car charge user of acquisitionmaxAnd minimum
Value Smin。
Step 203, according to the maximum value SmaxWith minimum value SminBy the related data in each electric car charge user
In a project value SIt is formerIt is standardized, obtains SIt is formerCorresponding standardized data SStandard。
Wherein,
It is handled by standardized data, such as the dimension of the data of projects in above-mentioned table 1 can be carried out to unification, avoided
Inaccuracy caused by when data between different number grade are clustered.
Each electric car charge user is divided into pre-set K class by step 204.
For example, can enable K=1 by the way of exhaustion, and be gradually increased K value, carry out clustering respectively, finally may be used
Obtain the suitable class quantity in electric vehicle charging field.
Step 205, according to the standardized data of each electric car charge user, seek the average value of pre-set K class
Wherein,Wherein,It charges and uses for each electric car
The average value of i-th of project in the standardized data at family, p are that the project in the standardized data of electric car charge user is total
Number；N is the electric car charge user sum in research range；xjiFor the standardized data of j-th of electric car charge user
In i-th of project value.
The standardized data x of step 206, each electric car charge user of traversalj=(xj1,xj2,...,xjp), with determination
The standardized data x of each electric car charge userj=(xj1,xj2,...,xjp) and each pre-set K classEuclidean away from
From.
Each electric car charge user is re-assigned in the smallest one kind of Euclidean distance, and recalculates by step 207
The average value of K class.
206 are returned to step after step 207, until the Euclidean of class that is currently located of each electric car charge user away from
From minimum.
If the electric car charge user in step 208, one kind accounts for the electric car charge user sum in survey region
Percentage be less than pre-set percentage threshold, then delete such, retain electric car charge user account in survey region
Electric car charge user sum percentage be more than or equal to pre-set percentage threshold class, as user behavior spy
Levy class.
For example, if there is 16012 electric car charge users, wherein 1 class is 5497,2 classes are 4769 when K=6
A, 3 classes are 5744, and 4 classes are 1, and 5 classes are 1, and 6 classes are 0, then the apparent 4th, 5, the number of users very little in 6 classes,
It can be ignored, 4,5,6 classes are above-mentioned, only retain 1,2,3 classes.
The percentage threshold can choose 1%, 2%, 3% etc., but be not only limited to this.
Step 209, the user into different user behavior characteristics classes push different electric car charging service contents；
The electric car charging service content is including in the preferential service content of charging pricing for segment, electric car charging set meal service
Appearance, neighbouring scenic spot information, periphery adequate and systematic service information, nearby on the way in charge station information and newly-increased website situation information one
Kind is a variety of.
A detailed data instance is set forth below:
K- is used by the standardization of data based in October, 2016 to the Ji of in September, 2017 north transaction data
Means model carries out clustering using 16012 users of overcharge stake in Ji Beidiqu.It the setting of K and finally answers
The generation how many classes are a problems of any Clustering Model.One feasible method is carried out in fact to the value of one group of given K
It tests, so that the element number in class relatively balances, final class number is selected in conjunction with professional knowledge.
Preliminary K-means cluster result:
In order to cover potential class number, we carry out K-means clustering to K=1 to 15, and final choice K=6's is poly-
Class is as a result, further determine final class number.The cluster result of K=6 such as table 2.
2 preliminary clusters classification of table and number of users
| Classification | 1 | 2 | 3 | 4 | 5 | 6 |
| Number of members | 5497 | 4769 | 5744 | 1 | 1 | 0 |
From the point of view of preliminary clusters result, the number of members that classification 4,5,6 includes only has 1 or does not have, can for this 3 classifications
Not go to pay close attention to.Therefore, the classification 1,2,3 of 3 comparisons balance is tentatively obtained.Separately below from high speed use, charge volume, charging
Compare this 3 classifications in terms of number, charging time.
3 three classes user of table compares
As shown in Table 3, the 1st, 2 class user's high speed station charging uses are more frequent, and the 3rd class user is rarely employed high speed station and fills
Electricity.Therefore, this 3 classifications of preliminary definition are respectively high speed primary client, high speed second level client, urban customers.1st, 3 class users
Year per capita charge capacity be much higher than the 2nd user.But the average charge amount of three classes user is all mainly than the more significant, charging time
It concentrates between 8:00-20:00, needs further to pay close attention to.
First kind user is high speed primary user, shares 5497 people, accounts for about the 34.33% of Ji north user group, most of to use
Family high speed utilization rate is high and access times are high.Quantity dimension per capita, uses at a high speed relatively high for year；Charge capacity and charging times
The highest in three classes user, it is micro- to be higher than third class user.
Second class user is high speed secondary user, accounts for about the 29.78% of Ji north user group, most of user's high speed utilization rate
Height, but access times are low, share 4769 people.Quantity dimension per capita, uses at a high speed than high for year；Charge capacity and charging times exist
It is minimum in three classes user, and it is far below other classes user.
Third class user is urban subscriber, accounts for about the 35.87% of Ji north user group, and most of user's high speed utilization rate is low,
But access times are high, share 5744 people.Quantity dimension per capita, uses at a high speed than low, close to 0 for year；Charge capacity and charging
Number is similar to first kind user, micro- to be lower than first kind user.
4 three classes client's festivals or holidays of table, website compare:
From table 4, it can be seen that high speed primary user job day access times: weekend access times: red-letter day access times ≈
3.3:2.0:1；8-19:59 period access times are high；Website service condition, the related high speed in Beijing are much higher than other station types.
High speed secondary user working day access times: weekend access times: red-letter day access times ≈ 3.7:2.3:1；8-19:
59 period access times are high；Website service condition, the related high speed in Beijing are much higher than other station types.
Urban subscriber's working day access times: weekend access times: red-letter day access times ≈ 10.6:4.9:1；12-19:59
Period access times are high；Website service condition, Langfang City website are much higher than other station types.
User characteristics:
For example, above-mentioned ultimately form the different user behavior characteristics class of 3 classes:
High speed primary client, majority are across city office users.Its behavior of charging is mainly characterized by Beijing-tianjin-hebei Region work
It is larger and charging times are more to make day charge capacity, charging station uses frequent crowd, and in Beijing associated stations, intercity high speed
Website often has charging.For high speed primary client, pricing for segment service content or set meal service content can be pushed to it.By dividing
It is period, the combined set meal for dividing the diversified forms such as location or festivals or holidays on working day, a degree of preferential to client's offer, come more
Attracts clients, and improves service quality.
High speed second level client, majority is the user that passes by one's way, play user.It is characterized in that charge volume, charging times are little, but fill
The website distribution of electricity is relatively uniform, disperses.For high speed second level client, nearby scenic spot information, ambient services (food and drink can be pushed
Deng), neighbouring charging station on the way.To herein can from the point of interest of client, not only can effectively services client, can also
To cooperate with periphery scenic spot and other service trades, new-type service mode is found.
Urban customers, substantially city dweller user, with office worker on city.Its main feature is that working day charging times are opposite
It is more, but charging station is less uniform.For urban customers, neighbouring low frequency can be pushed using website and give preferential, push newly
Increase website situation etc..Client can be guided to use low frequency website at a reduced price in this manner, it is particularly recommended that near some
Newly-increased website.This can not only reduce client's waiting time, also sufficiently use charging network resource.
In addition, the behavioural characteristic of the electric car charge user provided according to embodiments of the present invention is analyzed, can charge
Around the city website of high frequency, increase charging station.In entire charging network system kind, the use frequency difference of each website is very
Greatly.For example, the website access times of Langfang Prefecture are much higher than other websites.This just needs to increase near the high frequency website of this area
If new site, so that site network topology is more reasonable.
A kind of behavioural characteristic analysis method of electric car charge user provided in an embodiment of the present invention obtains research first
The related data of each electric car charge user in range, and place is standardized to each project in the related data
Reason, obtains standardized data；Later, according to Model tying algorithm, the standardized data is handled, it will be in research range
Each electric car charge user be divided into multiple user behavior characteristics classes.As it can be seen that the present invention is used by charging to electric car
The related data at family is arranged, and can conveniently be carried out by the clustering algorithm of big data technology (such as K-means)
The behavioural characteristic of electric car charge user is analyzed.
Corresponding to above-mentioned Fig. 1 and embodiment of the method shown in Fig. 2, as shown in figure 3, the embodiment of the present invention also provides a kind of electricity
The behavioural characteristic analytical equipment of electrical automobile charge user, comprising:
Data normalization processing unit 31, for obtaining the dependency number of each electric car charge user in research range
According to, and each project in the related data is standardized, obtain standardized data.
Cluster cell 32 will be in research range for handling the standardized data according to Model tying algorithm
Each electric car charge user be divided into multiple user behavior characteristics classes.
Further, as shown in figure 3, the behavioural characteristic analytical equipment of the electric car charge user, further includes:
Service content push unit 33 pushes pre-set electricity for the user into different user behavior characteristics classes
Electrical automobile charging service content, in order to which electric car charge user carries out business handling according to electric car charging service content
And acquisition of information.
In addition, the data normalization processing unit 31, is specifically used for:
Obtain the related data of each electric car charge user in research range, each project in the related data
It include: the charging total electricity in a predetermined period, charging total degree, in the charging times, on weekdays of each default website
Charging times, the charging times at weekend, the charging times in festivals or holidays and the charging times in daily each preset time period.
Obtain the maximum value S of the project in the related data in each electric car charge usermaxWith minimum value Smin。
According to the maximum value SmaxWith minimum value SminBy one in the related data in each electric car charge user
Purpose value SIt is formerIt is standardized, obtains SIt is formerCorresponding standardized data SStandard；Wherein,
In addition, the cluster cell 32, is specifically used for executing:
Each electric car charge user is divided into pre-set K class by step 1.
Step 2, according to the standardized data of each electric car charge user, seek the average value of pre-set K class
Wherein,Wherein,For the standardization of each electric car charge user
The average value of i-th of project in data, p are the project sum in the standardized data of electric car charge user；N is research
Electric car charge user sum in range；xjiFor i-th in the standardized data of j-th of electric car charge user
Purpose value.
The standardized data x of step 3, each electric car charge user of traversalj=(xj1,xj2,...,xjp), it is each to determine
The standardized data x of electric car charge userj=(xj1,xj2,...,xjp) and each pre-set K classEuclidean away from
From.
Each electric car charge user is re-assigned in the smallest one kind of Euclidean distance, and recalculates K by step 4
The average value of class；3 are returned to step after step 4, until the Euclidean of class that is currently located of each electric car charge user away from
From minimum.
If the electric car charge user in step 5, one kind accounts for the electric car charge user sum in survey region
Percentage is less than pre-set percentage threshold, then deletes such, retains electric car charge user and accounts in survey region
The percentage of electric car charge user sum is more than or equal to the class of pre-set percentage threshold, as user behavior characteristics
Class.
In addition, the service content push unit 33, is specifically used for:
User into different user behavior characteristics classes pushes different electric car charging service contents；It is described electronic
Automobile charging service content includes the preferential service content of charging pricing for segment, electric car charging set meal service content, neighbouring scape
Area's information, periphery adequate and systematic service information, nearby one of charge station information and newly-increased website situation information or a variety of on the way.
A kind of behavioural characteristic analytical equipment of electric car charge user provided in an embodiment of the present invention obtains research first
The related data of each electric car charge user in range, and place is standardized to each project in the related data
Reason, obtains standardized data；Later, according to Model tying algorithm, the standardized data is handled, it will be in research range
Each electric car charge user be divided into multiple user behavior characteristics classes.As it can be seen that the present invention is used by charging to electric car
The related data at family is arranged, and can conveniently be carried out by the clustering algorithm of big data technology (such as K-means)
The behavioural characteristic of electric car charge user is analyzed.
In addition, the embodiment of the present invention also provides a kind of computer readable storage medium, it is stored thereon with computer program, it should
It is performed the steps of when program is executed by processor
The related data of each electric car charge user in research range is obtained, and to each in the related data
Project is standardized, and obtains standardized data.
According to Model tying algorithm, the standardized data is handled, each electric car in research range is filled
Electric user is divided into multiple user behavior characteristics classes.
In addition, the embodiment of the present invention also provides a kind of computer equipment, including memory, processor and it is stored in storage
And the computer program that can be run on a processor, the processor perform the steps of when executing described program
The related data of each electric car charge user in research range is obtained, and to each in the related data
Project is standardized, and obtains standardized data.
According to Model tying algorithm, the standardized data is handled, each electric car in research range is filled
Electric user is divided into multiple user behavior characteristics classes.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Specific embodiment is applied in the present invention, and principle and implementation of the present invention are described, above embodiments
Explanation be merely used to help understand method and its core concept of the invention；At the same time, for those skilled in the art,
According to the thought of the present invention, there will be changes in the specific implementation manner and application range, in conclusion in this specification
Appearance should not be construed as limiting the invention.
Claims (12)
1. a kind of behavioural characteristic analysis method of electric car charge user characterized by comprising
The related data of each electric car charge user in research range is obtained, and to each project in the related data
It is standardized, obtains standardized data；
According to Model tying algorithm, the standardized data is handled, each electric car in research range is charged and is used
Family is divided into multiple user behavior characteristics classes.
2. the behavioural characteristic analysis method of electric car charge user according to claim 1, which is characterized in that also wrap
It includes:
User into different user behavior characteristics classes pushes pre-set electric car charging service content, in order to electricity
Electrical automobile charge user carries out business handling and acquisition of information according to electric car charging service content.
3. the behavioural characteristic analysis method of electric car charge user according to claim 2, which is characterized in that described to obtain
The related data of each electric car charge user in research range is taken, and each project in the related data is marked
Quasi-ization processing, obtains standardized data, comprising:
Obtain the related data of each electric car charge user in research range, each project packet in the related data
It includes: charging total electricity, charging total degree, the charging times in each default website, filling on weekdays in a predetermined period
Electric number, the charging times at weekend, the charging times in festivals or holidays and the charging times in daily each preset time period；
Obtain the maximum value S of the project in the related data in each electric car charge usermaxWith minimum value Smin；
According to the maximum value SmaxWith minimum value SminBy the project in the related data in each electric car charge user
Value SIt is formerIt is standardized, obtains SIt is formerCorresponding standardized data SStandard；Wherein,
4. the behavioural characteristic analysis method of electric car charge user according to claim 3, which is characterized in that described
According to Model tying algorithm, the standardized data is handled, each electric car charge user in research range is divided
For multiple user behavior characteristics classes, comprising:
Each electric car charge user is divided into pre-set K class by step 1；
Step 2, according to the standardized data of each electric car charge user, seek the average value of pre-set K classWherein,Wherein,For the standardized data of each electric car charge user
In i-th of project average value, p be electric car charge user standardized data in project sum；N is research range
Interior electric car charge user sum；xjiFor i-th of project in the standardized data of j-th of electric car charge user
Value；
The standardized data x of step 3, each electric car charge user of traversalj=(xj1,xj2,...,xjp), with each electronic vapour of determination
The standardized data x of vehicle charge userj=(xj1,xj2,...,xjp) and each pre-set K classEuclidean distance；
Each electric car charge user is re-assigned in the smallest one kind of Euclidean distance, and recalculates K class by step 4
Average value；3 are returned to step after step 4, until the Euclidean distance for the class that each electric car charge user is currently located is most
It is small；
If the electric car charge user in step 5, one kind accounts for the percentage of the electric car charge user sum in survey region
Than being less than pre-set percentage threshold, then such is deleted, reservation electric car charge user accounts for electronic in survey region
The percentage of automobile charge user sum is more than or equal to the class of pre-set percentage threshold, as user behavior characteristics class.
5. the behavioural characteristic analysis method of electric car charge user according to claim 4, which is characterized in that difference
User behavior characteristics class in user push pre-set electric car charging service content, in order to electric car charging
User carries out business handling and acquisition of information according to electric car charging service content, comprising:
User into different user behavior characteristics classes pushes different electric car charging service contents；The electric car
Charging service content includes the preferential service content of charging pricing for segment, electric car charging set meal service content, neighbouring scenic spot letter
Breath, periphery adequate and systematic service information, nearby one of charge station information and newly-increased website situation information or a variety of on the way.
6. a kind of behavioural characteristic analytical equipment of electric car charge user characterized by comprising
Data normalization processing unit, for obtaining the related data of each electric car charge user in research range, and it is right
Each project in the related data is standardized, and obtains standardized data；
Cluster cell, for handling the standardized data, by each electricity in research range according to Model tying algorithm
Electrical automobile charge user is divided into multiple user behavior characteristics classes.
7. the behavioural characteristic analytical equipment of electric car charge user according to claim 6, which is characterized in that also wrap
It includes:
Service content push unit pushes pre-set electric car for the user into different user behavior characteristics classes
Charging service content, in order to which electric car charge user carries out business handling and information according to electric car charging service content
It obtains.
8. the behavioural characteristic analytical equipment of electric car charge user according to claim 7, which is characterized in that the number
According to standardization unit, it is specifically used for:
Obtain the related data of each electric car charge user in research range, each project packet in the related data
It includes: charging total electricity, charging total degree, the charging times in each default website, filling on weekdays in a predetermined period
Electric number, the charging times at weekend, the charging times in festivals or holidays and the charging times in daily each preset time period；
Obtain the maximum value S of the project in the related data in each electric car charge usermaxWith minimum value Smin；
According to the maximum value SmaxWith minimum value SminBy the project in the related data in each electric car charge user
Value SIt is formerIt is standardized, obtains SIt is formerCorresponding standardized data SStandard；Wherein,
9. the behavioural characteristic analytical equipment of electric car charge user according to claim 8, which is characterized in that described poly-
Class unit, is specifically used for:
Each electric car charge user is divided into pre-set K class by step 1；
Step 2, according to the standardized data of each electric car charge user, seek the average value of pre-set K classWherein,Wherein,For the standardized data of each electric car charge user
In i-th of project average value, p be electric car charge user standardized data in project sum；N is research range
Interior electric car charge user sum；xjiFor i-th of project in the standardized data of j-th of electric car charge user
Value；
The standardized data x of step 3, each electric car charge user of traversalj=(xj1,xj2,...,xjp), with each electronic vapour of determination
The standardized data x of vehicle charge userj=(xj1,xj2,...,xjp) and each pre-set K classEuclidean distance；
Each electric car charge user is re-assigned in the smallest one kind of Euclidean distance, and recalculates K class by step 4
Average value；3 are returned to step after step 4, until the Euclidean distance for the class that each electric car charge user is currently located is most
It is small；
If the electric car charge user in step 5, one kind accounts for the percentage of the electric car charge user sum in survey region
Than being less than pre-set percentage threshold, then such is deleted, reservation electric car charge user accounts for electronic in survey region
The percentage of automobile charge user sum is more than or equal to the class of pre-set percentage threshold, as user behavior characteristics class.
10. the behavioural characteristic analytical equipment of electric car charge user according to claim 9, which is characterized in that described
Service content push unit, is specifically used for:
User into different user behavior characteristics classes pushes different electric car charging service contents；The electric car
Charging service content includes the preferential service content of charging pricing for segment, electric car charging set meal service content, neighbouring scenic spot letter
Breath, periphery adequate and systematic service information, nearby one of charge station information and newly-increased website situation information or a variety of on the way.
11. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
It is performed the steps of when execution
The related data of each electric car charge user in research range is obtained, and to each project in the related data
It is standardized, obtains standardized data；
According to Model tying algorithm, the standardized data is handled, each electric car in research range is charged and is used
Family is divided into multiple user behavior characteristics classes.
12. a kind of computer equipment including memory, processor and is stored in the calculating that storage is upper and can run on a processor
Machine program, which is characterized in that the processor performs the steps of when executing described program
The related data of each electric car charge user in research range is obtained, and to each project in the related data
It is standardized, obtains standardized data；
According to Model tying algorithm, the standardized data is handled, each electric car in research range is charged and is used
Family is divided into multiple user behavior characteristics classes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810755332.9A CN109087127A (en) | 2018-07-11 | 2018-07-11 | A kind of the behavioural characteristic analysis method and device of electric car charge user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810755332.9A CN109087127A (en) | 2018-07-11 | 2018-07-11 | A kind of the behavioural characteristic analysis method and device of electric car charge user |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109087127A true CN109087127A (en) | 2018-12-25 |
Family
ID=64837603
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810755332.9A Pending CN109087127A (en) | 2018-07-11 | 2018-07-11 | A kind of the behavioural characteristic analysis method and device of electric car charge user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109087127A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934473A (en) * | 2019-02-28 | 2019-06-25 | 深圳智链物联科技有限公司 | Charge health index methods of marking, device, terminal device and storage medium |
| CN110263069A (en) * | 2019-05-27 | 2019-09-20 | 华东师范大学 | The temporal aspect of new energy usage behavior implies factor extraction and depicting method and system |
| CN111680933A (en) * | 2020-06-29 | 2020-09-18 | 北京中电普华信息技术有限公司 | Method and device for analyzing power consumption behavior, readable medium and equipment |
| CN112036602A (en) * | 2020-07-24 | 2020-12-04 | 国网安徽省电力有限公司经济技术研究院 | 5G electric vehicle charging prediction method and system integrating human-computer intelligence |
| CN113544009A (en) * | 2019-04-05 | 2021-10-22 | 矢崎总业株式会社 | Charging device reservation system, communication terminal, and server device |
| CN113723993A (en) * | 2021-08-17 | 2021-11-30 | 广东新能通科技有限公司 | Charging pile electronic coupon issuing method, device and system |
| CN114261312A (en) * | 2020-09-16 | 2022-04-01 | 蓝谷智慧(北京)能源科技有限公司 | Power battery charging process monitoring method, device and equipment |
| CN116756638A (en) * | 2023-08-17 | 2023-09-15 | 广东电网有限责任公司汕头供电局 | Method, device, equipment and storage medium for detecting electric load demand of electric vehicle |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105825232A (en) * | 2016-03-15 | 2016-08-03 | 国网北京市电力公司 | Classification method and device for electromobile users |
-
2018
- 2018-07-11 CN CN201810755332.9A patent/CN109087127A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105825232A (en) * | 2016-03-15 | 2016-08-03 | 国网北京市电力公司 | Classification method and device for electromobile users |
Non-Patent Citations (2)
| Title |
|---|
| 李东东 等: "共享模式下的充电桩引导与充电价格研究", 《电网技术》 * |
| 李雪梅 等: "电动汽车充电用户行为特征研究", 《中国市场》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934473A (en) * | 2019-02-28 | 2019-06-25 | 深圳智链物联科技有限公司 | Charge health index methods of marking, device, terminal device and storage medium |
| CN113544009A (en) * | 2019-04-05 | 2021-10-22 | 矢崎总业株式会社 | Charging device reservation system, communication terminal, and server device |
| CN110263069A (en) * | 2019-05-27 | 2019-09-20 | 华东师范大学 | The temporal aspect of new energy usage behavior implies factor extraction and depicting method and system |
| CN111680933A (en) * | 2020-06-29 | 2020-09-18 | 北京中电普华信息技术有限公司 | Method and device for analyzing power consumption behavior, readable medium and equipment |
| CN111680933B (en) * | 2020-06-29 | 2023-04-18 | 北京中电普华信息技术有限公司 | Method and device for analyzing power consumption behavior, readable medium and equipment |
| CN112036602A (en) * | 2020-07-24 | 2020-12-04 | 国网安徽省电力有限公司经济技术研究院 | 5G electric vehicle charging prediction method and system integrating human-computer intelligence |
| CN114261312A (en) * | 2020-09-16 | 2022-04-01 | 蓝谷智慧(北京)能源科技有限公司 | Power battery charging process monitoring method, device and equipment |
| CN113723993A (en) * | 2021-08-17 | 2021-11-30 | 广东新能通科技有限公司 | Charging pile electronic coupon issuing method, device and system |
| CN116756638A (en) * | 2023-08-17 | 2023-09-15 | 广东电网有限责任公司汕头供电局 | Method, device, equipment and storage medium for detecting electric load demand of electric vehicle |
| CN116756638B (en) * | 2023-08-17 | 2023-11-14 | 广东电网有限责任公司汕头供电局 | Method, device, equipment and storage medium for detecting electric load demand of electric vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109087127A (en) | A kind of the behavioural characteristic analysis method and device of electric car charge user | |
| Faridimehr et al. | A stochastic programming approach for electric vehicle charging network design | |
| CN109359682B (en) | A kind of Shuttle Bus candidate's website screening technique based on F-DBSCAN iteration cluster | |
| DE102013202059B4 (en) | CHARGER INFRASTRUCTURE FOR ELECTRIC VEHICLES (EVs) WITH OPTIMUM LOCATION SELECTION FOR CHARGING STATIONS | |
| Li et al. | Estimating a transit passenger trip origin-destination matrix using automatic fare collection system | |
| CN110225081A (en) | Information of charging pile supplying system and method | |
| He et al. | Evaluation of city-scale built environment policies in New York City with an emerging-mobility-accessible synthetic population | |
| Abdalrahman et al. | A survey on PEV charging infrastructure: Impact assessment and planning | |
| KR20190054122A (en) | Method, apparatus, device and computer storage medium for shuttle bus route | |
| Hung et al. | Optimal routing for electric vehicle service systems | |
| CN109697637A (en) | Object type determines method, apparatus, electronic equipment and computer storage medium | |
| US20180349412A1 (en) | Non-linear systems and methods for destination selection | |
| CN103634807A (en) | WIFI data hotspot cell data monitoring method and WLAN deployment ordering method and device | |
| Eisel et al. | Finding suitable locations for charging stations | |
| Lu et al. | Charging and relocating optimization for electric vehicle car-sharing: an event-based strategy improvement approach | |
| CN111311193B (en) | Method and device for configuring public service resources | |
| Jung et al. | Effects of charging infrastructure and non-electric taxi competition on electric taxi adoption incentives in New York City | |
| Yang et al. | Fleet sizing and charging infrastructure design for electric autonomous mobility-on-demand systems with endogenous congestion and limited link space | |
| CN110427442A (en) | The information query method and device of new energy vehicle record of charging | |
| Lu et al. | Demand-responsive transport for students in rural areas: A case study in vulkaneifel, germany | |
| CN106850777A (en) | The method and apparatus of pushed information | |
| CN107493579B (en) | Method and device for wireless network pre-construction planning in colleges and universities | |
| Moradipari et al. | Pricing differentiated services in an electric vehicle public charging station network | |
| von Meier | Ev infrastructure planning and grid impact assessment: a case for Mexico | |
| Bhundar et al. | Using EV charging control to provide building load flexibility |
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: 20181225 |
|
| RJ01 | Rejection of invention patent application after publication |