CN107730269A - A kind of Electricity customers portrait method of Behavior-based control analysis - Google Patents
A kind of Electricity customers portrait method of Behavior-based control analysis Download PDFInfo
- Publication number
- CN107730269A CN107730269A CN201710600570.8A CN201710600570A CN107730269A CN 107730269 A CN107730269 A CN 107730269A CN 201710600570 A CN201710600570 A CN 201710600570A CN 107730269 A CN107730269 A CN 107730269A
- Authority
- CN
- China
- Prior art keywords
- behavior
- class label
- electricity customers
- class
- client
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of Electricity customers portrait method of Behavior-based control analysis, specific steps include:1) customer action feature is extracted;2) class label designs;3) score is calculated;4) Electricity customers class label is generated.Through the above way, a kind of Electricity customers portrait method of Behavior-based control analysis of the present invention, this method carries out quantification treatment by characteristic indexs such as the credit rating to Electricity customers, power failure susceptibility, price sensitivity, make the class label dynamic change of Electricity customers, allow power supply enterprise more realistically to understand demand of the client to various different services, realize fast accurate service.
Description
Technical field
The present invention relates to a kind of customer portrait method, is drawn a portrait more particularly, to a kind of Electricity customers of Behavior-based control analysis
Method.
Background technology
Customer portrait is the important application of big data technology, and its target is to establish to be directed to client in many dimensions
Descriptive label attribute, so as to be sketched the contours using these tag attributes true personal characteristics many to client, and then,
Customer portrait can be utilized to excavate customer demand, analyze customer priorities, and be supplied to client more efficient by matching customer portrait
With more targeted information conveyance and the customer experience closer to personal habits.
With the progress and development of society, the individual demand of client becomes increasingly conspicuous, and Electricity customers are no exception.Electricity consumption
Client has no longer met for the simple electricity consumption requirements of support, and also price, information, technology, energy-conservation, safety utilization of electric power etc. are carried
Higher level demand is gone out, with the reform of client's system, the developing direction of power supply enterprise is increasingly turned to the marketization, power supply
The service theory of enterprise also turns to " customer experience guiding " from " customer demand orientation ", and power supply enterprise needs effectively to use number
Itself marketing ability and level of customer service are lifted according to technical methods such as drivings, it is poor from service content diversification, method of service
Alienation angle, differentiated service is provided to different clients colony.
But the change of Electricity customers consumption habit so that power supply enterprise can not really recognize client.Electricity customers exist
Constantly change, enterprise is also required to change pattern, it is thus understood that the real demand of client.Enterprise needs to be finely divided client, is
Different types of client development deisgn product.Power supply enterprise is needed by customer portrait, is comprehensively understood client, is found target
Client, different clients are realized with the service of differentiation, realizes precision marketing.
The problem of existing customer's division methods are present:
(1) label is closed, and so-called closing refers to that number of tags is limited and fixed;
(2) customer portrait renewal hysteresis, it is impossible to the newest transition of reflection client in real time.
The content of the invention
The present invention solves the technical problem of a kind of Electricity customers portrait method for providing Behavior-based control analysis, energy
It is enough to allow the information labels of client by building Electricity customers class label, comprehensive displaying Electricity customers information, power supply
Enterprise can realize fast accurate service.
In order to solve the above technical problems, one aspect of the present invention is:A kind of electricity consumption of Behavior-based control analysis
Customer portrait method, specific steps include:A kind of Electricity customers portrait method of Behavior-based control analysis, specific steps include:
1) customer action feature is extracted:Client's call list in 95598 work order informations, outage information, power information
Customer action is analyzed with payment information, assigns each customer action specific weights, the set of whole customer actions, which is formed, to be used
Electric customer action database, a client can have a variety of behavioural characteristics, i.e. attribute, and customer action is stored with four-tuple;
2) class label designs:To customer action database quantitative analysis, class label is designed, and give each classification mark
Label assign a class label weights (empirical value), and whole class labels form class label database;
3) score is calculated:Class label weights are obtained from class label database, from Electricity customers behavior database
The behavior weights of corresponding behavior are obtained, class label weights are multiplied with behavior weights, obtain behavior score value, by the specific visitor
Behavior score value under the same category label of family is added, and obtains classification score value of the particular customer on such distinguishing label, and repeating should
Step, until obtaining the classification score value of the particular customer all categories label;
4) Electricity customers class label is generated:The behavior score value for choosing particular customer class label is more than some of threshold value
Behavior, so as to calculate the Electricity customers class label, as representation data.
In a preferred embodiment of the present invention, the structure of four-tuple is (client, attribute, to be worth, OK in the step 1)
For weights).
In a preferred embodiment of the present invention, the behavior weights P is as follows by formula (1) calculation formula:
Wherein Y includes resident and non-resident two kinds, Y (resident)=a+b electricity consumption classification+c contract capacity+d history
Power off time+x Very Important Person mark+f cities and towns/rural area+g age+h power supply type+i credit grades+j
95598 link up number (non-power failure class consulting), Y (non-resident)=a+b electricity consumption classification+c contract capacity+d categorys of employment
+ x history power off time+f voltage class+g client's classifications+h95598 links up number (non-power failure class consulting), wherein
Coefficient a, b, c, d, x, f, g, h, i, j are calculated by regression equation, and x is the bottom of natural logrithm.
In a preferred embodiment of the present invention, in the step 3), the higher expression of classification score value of a certain class label
The client is higher for the attention rate of such distinguishing label.
In a preferred embodiment of the present invention, representation data is stored as chart-pattern in the step 4).
In a preferred embodiment of the present invention, the representation data T7 of user is calculated in the step 4) by formula (2)
[i,j]:
After wherein T4 [i, j] represents that the value that the i-th row j is arranged in class label property data base, T6 [1, j] represent filtering
The behavior score value that the 1st row jth arranges in behavior score value.
The beneficial effects of the invention are as follows:A kind of Electricity customers portrait method of Behavior-based control analysis of the present invention, this method are led to
Cross the characteristic indexs such as the credit rating to Electricity customers, power failure susceptibility, price sensitivity and carry out quantification treatment, make Electricity customers
Class label dynamic change, allow power supply enterprise more realistically to understand demands of the client to various different services, realize quick essence
Quasi- service.
Brief description of the drawings
Fig. 1 is a kind of structural representation of the Electricity customers portrait method of Behavior-based control analysis.
Fig. 2 is a kind of chart-pattern schematic diagram of the Electricity customers portrait embodiment of the method 1 of Behavior-based control analysis.
Embodiment
Presently preferred embodiments of the present invention is described in detail below in conjunction with the accompanying drawings, so that advantages and features of the invention
It can be easier to be readily appreciated by one skilled in the art, apparent clearly be defined so as to be made to protection scope of the present invention.
As shown in figure 1,1) extract customer action feature:Client in 95598 work order informations converses, and single, have a power failure letter
Breath, power information and payment information analyze customer action, assign each customer action specific weights, whole customer actions
Set form Electricity customers behavior database, a client can have a variety of behavioural characteristics, i.e. attribute, be deposited with four-tuple
Customer action is stored up, the structure of four-tuple is (client, attribute, value, behavior weights), the advantages of storage using four-tuple:First, category
Property can constantly expand, edit, realize the dynamic management of label, with client properties constantly enrich, portrait system can be deep
Carve ground and understand client, so as to move towards to understand the ultimate aim of client;Second, the chart-pattern of ensuing representation data is facilitated to store.
The behavior weights P is as follows by formula (1) calculation formula:
Wherein Y includes resident and non-resident two kinds, Y (resident)=a+b electricity consumption classification+c contract capacity+d history
Power off time+x Very Important Person mark+f cities and towns/rural area+g age+h power supply type+i credit grades+j
95598 link up number (non-power failure class consulting), Y (non-resident)=a+b electricity consumption classification+c contract capacity+d categorys of employment
+ x history power off time+f voltage class+g client's classifications+h95598 links up number (non-power failure class consulting), wherein
Coefficient a, b, c, d, x, f, g, h, i, j are calculated by regression equation, and x is the bottom of natural logrithm.
95598 work order data, for building the data source of representation data, including:Work order is accepted, telephone counseling, work order are superintended and directed
Do, power-off event, the information such as troubleshooting;
The work order of table 1 accepts information
The telephone counseling information table of table 2
2) class label designs:To customer action database quantitative analysis, class label is designed, such as:Eventful type, enjoyment
Type, hesitation type etc., and a class label weights (empirical value) is assigned to each class label, whole class labels form class
Distinguishing label database, class label database are mapping of the user behavior to class label.
3) score is calculated:Class label weights are obtained from class label database, from Electricity customers behavior database
The behavior weights of corresponding behavior are obtained, class label weights are multiplied with behavior weights, obtain behavior score value, by the specific visitor
Behavior score value under the same category label of family is added, and obtains classification score value of the particular customer on such distinguishing label, and repeating should
Step, until obtaining the classification score value of the particular customer all categories label, during concrete operations, choose a certain particular customer one
The behavior of section time, the class label analyzed characteristic point therein and be mapped on this feature point, is obtained by above-mentioned steps
The classification score value of all categories label, the classification score value of a certain class label is higher to represent the client for such distinguishing label
Attention rate is higher, such as eventful type client often more lays particular stress on price sensitivity, and enjoying type client often more lays particular stress on Service Quality
Amount.
4) Electricity customers class label is generated:The behavior score value for choosing particular customer class label is more than some of threshold value
Behavior, so as to calculate the Electricity customers class label, as representation data, the setting of threshold value can be relatively low by a large amount of scores
Behavior filter, obtain some behaviors representative, that score is higher be used for client characteristics are described.
Representation data is stored as chart-pattern, and the benefit that representation data is stored with chart-pattern is to reflect client most in real time
New state.
Embodiment 1:Give certain colleges and universities' Electricity customers portrait
Step 1) is performed to 95598 data and obtains colleges and universities' client portion behavioural characteristic (four-tuple), is arranged as shown in table 3,
Wherein, power failure susceptibility OS, price sensitivity PS, monthly power consumption MP, Peak power use accounting pxak, credit worthiness crxdit, the moon
Accept work order accounting MW, town and country classification locatx (urban district of 1 rural area, 2 suburb 3), the electricity consumption classification typx (business of 1 resident, 2 cause 3
The industry of industry 4).
Certain the colleges and universities' client portion behavioural characteristic of table 3
Designed through step 2) class label, class label characteristic such as table 4 is obtained by machine learning.
The class label property data base of table 4
Through step 3) calculating score such as table 5
The behavior score value of certain colleges and universities of table 5
Table 5 is the class label weights * behavior weights of behavior score value=character pair of table 3 of certain colleges and universities, for example, certain is high
School feature OS score value=0.8 × 0.10=0.08.
Assuming that threshold value is 0.005, the MW of table 5 is less than threshold value, then can be filtered, so as to obtain table 6
The behavior score value of certain colleges and universities after the filtering of table 6
It is convenient in order to calculate representation data, to two marks, the value of the row j of T4 [i, j] --- table 4 i-th row, for example, T4
[1,1]=[0.05,0.1], T6 [1, j] --- the behavior score value of table 6 the 1st row jth row is represented, such as T6 [1,2]=0.006, this
The representation data of sample table 7 is calculated as follows:
For example, T7 [1,1]=(0.08-0.05)/(0.1-0.05)=0.6.
Certain the colleges and universities' representation data of table 7
Table 8 is conventional class label weights, i.e. empirical value.
The class label weights of table 8
Often row is added after table 7 is multiplied with the corresponding element of table 8, you can determines the classification score value of given client.
Such as eventful type classification score value=0.6*0.1+0*0.1+0*0.05+0*0.1+0*0.5+1*0.05=0.11
In the present embodiment, certain the colleges and universities' classification score value calculated is table 9:
Certain the colleges and universities' classification score value of table 9
So certain colleges and universities portrait such as Fig. 2.
Compared with prior art, the Electricity customers portrait method of a kind of Behavior-based control analysis of the present invention, it is right that this method passes through
The characteristic indexs such as the credit ratings of Electricity customers, power failure susceptibility, price sensitivity carry out quantification treatment, make the class of Electricity customers
Distinguishing label dynamic change, allow power supply enterprise more realistically to understand demand of the client to various different services, realize that fast accurate takes
Business.
Embodiments of the invention are the foregoing is only, are not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow conversion that bright specification and accompanying drawing content are made, or directly or indirectly it is used in other correlations
Technical field, it is included within the scope of the present invention.
Claims (6)
1. a kind of Electricity customers portrait method of Behavior-based control analysis, it is characterised in that:Specific steps include:
1) customer action feature is extracted:Client in 95598 work order informations, which converses, list, outage information, power information and to pay
Charge information analyzes customer action, assigns each customer action specific weights, and the set of whole customer actions forms electricity consumption visitor
Family behavior database, a client can have a variety of behavioural characteristics, i.e. attribute, and customer action is stored with four-tuple;
2) class label designs:To customer action database quantitative analysis, class label is designed, and assign to each class label
One class label weights (empirical value), whole class labels form class label database;
3) score is calculated:Class label weights are obtained from class label database, are obtained from Electricity customers behavior database
The behavior weights of corresponding behavior, class label weights are multiplied with behavior weights, obtain behavior score value, and the particular customer is same
Behavior score value under class label is added, and obtains classification score value of the particular customer on such distinguishing label, repeats the step, directly
To obtaining the classification score value of the particular customer all categories label;
4) Electricity customers class label is generated:The behavior score value for choosing particular customer class label is more than some behaviors of threshold value,
So as to calculate the Electricity customers class label, as representation data.
A kind of 2. Electricity customers portrait method of Behavior-based control analysis according to claim 1, it is characterised in that the step
It is rapid 1) in four-tuple structure for (client, attribute, value, behavior weights).
A kind of 3. Electricity customers portrait method of Behavior-based control analysis according to claim 1, it is characterised in that the row
It is as follows by formula (1) calculation formula for weights P:
<mrow>
<mi>P</mi>
<mo>=</mo>
<mfrac>
<msup>
<mi>e</mi>
<mi>Y</mi>
</msup>
<mrow>
<mn>1</mn>
<mo>+</mo>
<msup>
<mi>e</mi>
<mi>Y</mi>
</msup>
</mrow>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein Y includes resident and non-resident two kinds, Y (resident)=a+b electricity consumption classification+c contract capacity+d history power failure
Time+x Very Important Person mark+f cities and towns/rural area+g age+h power supply type+i credit grade+j95598 ditches
Logical number (non-power failure class consulting), Y (non-resident)=a+b electricity consumption classification+c contract capacity+d category of employment+x history
Power off time+f voltage class+g client's classifications+h95598 communications number (non-power failure class consulting), wherein coefficient a, b,
C, d, x, f, g, h, i, j are calculated by regression equation, and x is the bottom of natural logrithm.
A kind of 4. Electricity customers portrait method of Behavior-based control analysis according to claim 1, it is characterised in that the step
It is rapid 3) in, the classification score value of a certain class label is higher to represent that the client is higher for the attention rate of such distinguishing label.
A kind of 5. Electricity customers portrait method of Behavior-based control analysis according to claim 1, it is characterised in that the step
It is rapid 4) in representation data be stored as chart-pattern.
A kind of 6. Electricity customers portrait method of Behavior-based control analysis according to claim 1, it is characterised in that the step
It is rapid 4) in by formula (2) calculate user representation data T7 [i, j]:
Wherein T4 [i, j] represents the value that the i-th row j is arranged in class label property data base, and T6 [1, j] represents the behavior point after filtering
The behavior score value that the 1st row jth arranges in value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710600570.8A CN107730269A (en) | 2017-07-21 | 2017-07-21 | A kind of Electricity customers portrait method of Behavior-based control analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710600570.8A CN107730269A (en) | 2017-07-21 | 2017-07-21 | A kind of Electricity customers portrait method of Behavior-based control analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107730269A true CN107730269A (en) | 2018-02-23 |
Family
ID=61201122
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710600570.8A Pending CN107730269A (en) | 2017-07-21 | 2017-07-21 | A kind of Electricity customers portrait method of Behavior-based control analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107730269A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108564262A (en) * | 2018-03-31 | 2018-09-21 | 甘肃万维信息技术有限责任公司 | Enterprise's portrait big data model system based on big data analysis |
CN108764663A (en) * | 2018-05-15 | 2018-11-06 | 广东电网有限责任公司信息中心 | A kind of power customer portrait generates the method and system of management |
CN108764939A (en) * | 2018-05-11 | 2018-11-06 | 深圳供电局有限公司 | A kind of electric power enterprise CRM system and its method |
CN109685567A (en) * | 2018-12-20 | 2019-04-26 | 长沙理工大学 | It is a kind of to be drawn a portrait new method based on convolutional neural networks and the Electricity customers of fuzzy clustering |
CN109934273A (en) * | 2019-03-01 | 2019-06-25 | 长沙理工大学 | It is a kind of based on the fault characteristic of DML-KNN algorithm and active damage repair technology draw a portrait new method |
CN109949004A (en) * | 2019-03-01 | 2019-06-28 | 长沙理工大学 | A kind of Electricity customers portrait new method of the positioning of client's fast failure and clustering algorithm |
CN111145288A (en) * | 2019-12-27 | 2020-05-12 | 杭州利伊享数据科技有限公司 | Target customer virtual imaging method |
CN112132631A (en) * | 2020-09-29 | 2020-12-25 | 国网上海市电力公司 | Label electricity utilization management method based on power customer portrait |
CN112286921A (en) * | 2020-10-29 | 2021-01-29 | 海南大学 | Multi-source heterogeneous data-based dynamic enterprise portrait generation method |
CN112417308A (en) * | 2020-12-17 | 2021-02-26 | 国网河北省电力有限公司营销服务中心 | User portrait label generation method based on electric power big data |
CN112579638A (en) * | 2019-09-29 | 2021-03-30 | 北京国双科技有限公司 | Behavior tag information processing method and device, computer equipment and storage medium |
CN114219241A (en) * | 2021-12-01 | 2022-03-22 | 深圳供电局有限公司 | Customer electricity consumption behavior analysis method and system |
CN116401601A (en) * | 2023-04-14 | 2023-07-07 | 国网浙江省电力有限公司 | Power failure sensitive user preferential treatment method based on logistic regression model |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106056407A (en) * | 2016-06-03 | 2016-10-26 | 北京网智天元科技股份有限公司 | Online banking user portrait drawing method and equipment based on user behavior analysis |
CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
CN106557882A (en) * | 2016-11-29 | 2017-04-05 | 国网山东省电力公司电力科学研究院 | Power consumer screening technique and system based on various dimensions Risk Evaluation Factors |
CN106651424A (en) * | 2016-09-28 | 2017-05-10 | 国网山东省电力公司电力科学研究院 | Electric power user figure establishment and analysis method based on big data technology |
-
2017
- 2017-07-21 CN CN201710600570.8A patent/CN107730269A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
CN106056407A (en) * | 2016-06-03 | 2016-10-26 | 北京网智天元科技股份有限公司 | Online banking user portrait drawing method and equipment based on user behavior analysis |
CN106651424A (en) * | 2016-09-28 | 2017-05-10 | 国网山东省电力公司电力科学研究院 | Electric power user figure establishment and analysis method based on big data technology |
CN106557882A (en) * | 2016-11-29 | 2017-04-05 | 国网山东省电力公司电力科学研究院 | Power consumer screening technique and system based on various dimensions Risk Evaluation Factors |
Non-Patent Citations (1)
Title |
---|
严宇平 等: ""基于数据挖掘技术的客户停电敏感度研究与应用"", 《新技术新工艺》 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108564262A (en) * | 2018-03-31 | 2018-09-21 | 甘肃万维信息技术有限责任公司 | Enterprise's portrait big data model system based on big data analysis |
CN108764939A (en) * | 2018-05-11 | 2018-11-06 | 深圳供电局有限公司 | A kind of electric power enterprise CRM system and its method |
CN108764663A (en) * | 2018-05-15 | 2018-11-06 | 广东电网有限责任公司信息中心 | A kind of power customer portrait generates the method and system of management |
CN108764663B (en) * | 2018-05-15 | 2020-10-16 | 广东电网有限责任公司信息中心 | Method and system for generating and managing power customer portrait |
CN109685567A (en) * | 2018-12-20 | 2019-04-26 | 长沙理工大学 | It is a kind of to be drawn a portrait new method based on convolutional neural networks and the Electricity customers of fuzzy clustering |
CN109934273A (en) * | 2019-03-01 | 2019-06-25 | 长沙理工大学 | It is a kind of based on the fault characteristic of DML-KNN algorithm and active damage repair technology draw a portrait new method |
CN109949004A (en) * | 2019-03-01 | 2019-06-28 | 长沙理工大学 | A kind of Electricity customers portrait new method of the positioning of client's fast failure and clustering algorithm |
CN112579638A (en) * | 2019-09-29 | 2021-03-30 | 北京国双科技有限公司 | Behavior tag information processing method and device, computer equipment and storage medium |
CN112579638B (en) * | 2019-09-29 | 2024-02-13 | 北京国双科技有限公司 | Behavior tag information processing method and device, computer equipment and storage medium |
CN111145288A (en) * | 2019-12-27 | 2020-05-12 | 杭州利伊享数据科技有限公司 | Target customer virtual imaging method |
CN112132631A (en) * | 2020-09-29 | 2020-12-25 | 国网上海市电力公司 | Label electricity utilization management method based on power customer portrait |
CN112286921A (en) * | 2020-10-29 | 2021-01-29 | 海南大学 | Multi-source heterogeneous data-based dynamic enterprise portrait generation method |
CN112417308A (en) * | 2020-12-17 | 2021-02-26 | 国网河北省电力有限公司营销服务中心 | User portrait label generation method based on electric power big data |
CN114219241A (en) * | 2021-12-01 | 2022-03-22 | 深圳供电局有限公司 | Customer electricity consumption behavior analysis method and system |
CN116401601A (en) * | 2023-04-14 | 2023-07-07 | 国网浙江省电力有限公司 | Power failure sensitive user preferential treatment method based on logistic regression model |
CN116401601B (en) * | 2023-04-14 | 2023-09-15 | 国网浙江省电力有限公司 | Power failure sensitive user handling method based on logistic regression model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107730269A (en) | A kind of Electricity customers portrait method of Behavior-based control analysis | |
CN106651424B (en) | Power user portrait establishing and analyzing method based on big data technology | |
CN103714139B (en) | Parallel data mining method for identifying a mass of mobile client bases | |
Lam | Neural network techniques for financial performance prediction: integrating fundamental and technical analysis | |
Harrington et al. | Industrial location: Principles, practice and policy | |
CN110796354A (en) | Enterprise electric charge recovery risk portrait method and system | |
Tapp et al. | Direct and database marketing and customer relationship management in recruiting students for higher education | |
CN106557882A (en) | Power consumer screening technique and system based on various dimensions Risk Evaluation Factors | |
CN107507038A (en) | A kind of electricity charge sensitive users analysis method based on stacking and bagging algorithms | |
CN108596443A (en) | A kind of Electricity customers method for evaluating credit rating based on multi-dimensional data | |
CN108388955A (en) | Customer service strategies formulating method, device based on random forest and logistic regression | |
CN109325799A (en) | Power customer reserve value assessment method based on cloud model | |
Joachain et al. | Emerging trend of complementary currencies systems for environmental purposes: changes ahead | |
Bastan et al. | Revenue structure of mobile banking: a system dynamics model | |
Deepa et al. | A study on customer’s awareness on green banking in selected public and private sector banks with reference to Tirupur | |
Cung | Gross domestic product and foreign direct investment: Empirical evidence from Vietnam | |
Almansoori | The mediating role of sustainability between strategic planning and the performance of governmental organizations | |
Schneider | Economic principles and problems: a pluralist introduction | |
Šimelytė | The role of investment promotion in attracting FDI: Evidence from the Baltic States | |
Hasibuan et al. | Determinants of Palm Oil Productivity in North Sumatra Province | |
Chandar et al. | Integrating accounting and statistics: forecasting, budgeting and production planning at the American Telephone and Telegraph Company during the 1920s | |
Rodger | Putting the economy back in to the city | |
Robkob et al. | Antecedents and consequences of voluntary disclosure of environmental accounting: An empirical study of foods and beverage firms in Thailand | |
Vydhyam et al. | A study on green banking initiatives of selected private and public sector banks in chittoor (dt.), andhra pradesh | |
Zarghamfard et al. | Low-income housing policy in Iran (1990–2020): lessons and modifications |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180223 |