CN106373026A - User portrait construction method for power industry - Google Patents
User portrait construction method for power industry Download PDFInfo
- Publication number
- CN106373026A CN106373026A CN201610713004.3A CN201610713004A CN106373026A CN 106373026 A CN106373026 A CN 106373026A CN 201610713004 A CN201610713004 A CN 201610713004A CN 106373026 A CN106373026 A CN 106373026A
- Authority
- CN
- China
- Prior art keywords
- user
- order
- generate
- nearly
- behavior
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 31
- 230000006399 behavior Effects 0.000 claims abstract description 282
- 230000005611 electricity Effects 0.000 claims description 105
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 12
- 230000006855 networking Effects 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims 1
- 238000000034 method Methods 0.000 abstract description 4
- 238000005265 energy consumption Methods 0.000 abstract 1
- 230000002452 interceptive effect Effects 0.000 abstract 1
- 230000003993 interaction Effects 0.000 description 15
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 8
- 230000004069 differentiation Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000011038 discontinuous diafiltration by volume reduction Methods 0.000 description 4
- 230000002045 lasting effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000001934 delay Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000000205 computational method Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000007418 data mining Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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 invention discloses a user portrait construction method for a power industry. The method comprises the steps of generating basic attribute tags of a user according to fields in a database, wherein basic attributes of the user include an area, a voltage grade, an industry, a power utilization type, a network access duration, whether energy consumption is high or not, and whether the user is a third-party user or not; and/or, generating basic behavior tags of the user based on a power utilization behavior, a paying behavior and an interactive behavior respectively. According to the user portrait construction method for the power industry, provided by an embodiment of the invention, the frequency, degree and recent prediction of the user behaviors of the power industry are combined and behavior characteristics of power utilization customers of different attributes can be described multi-dimensionally, thereby effectively assisting business personnel of power companies to provide differential value-added services according to states of the power utilization customers.
Description
Technical field
The present invention relates to data mining technology field, particularly to a kind of user's portrait construction method of power industry.
Background technology
User's Portrait brand technology has been the technology of a relative maturity, has been obtained for widely in finance, telecommunications industry
With.Perfect with China market economic structure, electric power enterprise needs to excavate the need of user according to the different characteristics of user
Ask, and then differentiation value-added service is provided.Therefore, in the value-added service system of power industry, accurately and comprehensively understand and " use
Family behavior " is very necessary.
At present, it is more to build user to be worth subdivision system in power industry, obtain the Electricity customers of different value
Afterwards, provide value-added service further according to some quantitative indexs.However, such method has the disadvantage in that not by qualitative number
Combine according to quantitative data, the interpretability of the conclusion obtaining is not high, thus user behavior can not clear, comprehensively be described
Specific features.
Therefore, the correlation technique that user's portrait of power industry builds need to improve.
Content of the invention
It is contemplated that at least solving one of technical problem in above-mentioned technology to a certain extent.For this reason, the present invention
Purpose is to propose a kind of user's portrait construction method of power industry, by the frequency of the user behavior of power industry, degree, near
Phase prediction combines, and is capable of the behavior characteristicss of multi-faceted description Electricity customers, thus the business personnel of effective auxiliary power company
Situation according to Electricity customers provides differentiation value-added service.
For reaching above-mentioned purpose, embodiments of the invention propose a kind of user's portrait construction method of power industry, bag
Include: generate the base attribute label of user according to the field in data base, the base attribute of wherein said user includes area, electricity
Pressure grade, industry, electricity consumption classification, networking duration, whether be highly energy-consuming, whether be tripartite user;And/or, based on electricity consumption behavior,
Paying behaviors and interbehavior generate the basic act label of user respectively.
User's portrait construction method of power industry according to embodiments of the present invention, by the frequency of the user behavior of power industry
Degree, degree, last-period forecast combine, and are capable of the behavior characteristicss of the Electricity customers of multi-faceted description different attribute, thus effectively auxiliary
The business personnel helping Utilities Electric Co. provides differentiation value-added service according to the situation of Electricity customers.
In addition, according to the above embodiment of the present invention propose power industry user portrait construction method can also have as
Lower additional technical characteristic:
Specifically, included based on the basic act label that described electricity consumption behavior generates user: based on safety utilization of electric power behavior, different
The behavior of conventional electricity, change electricity consumption behavior, normal electricity consumption behavior build the second order behavior label system of user respectively.
According to one embodiment of present invention, the second order behavior label system of user is built based on described safety utilization of electric power behavior
Including: generate in order to describe the second order behavior label of described safety utilization of electric power behavior, wherein, described in order to describe described safety utilization of electric power
The second order behavior label of behavior includes: electrical equipment is safe, electrical equipment safety is low, Electrical Safety operating capability high,
Electrical Safety operating capability is low.
According to one embodiment of present invention, user's portrait construction method of described power industry also includes: generates and uses
To describe the high/low three-level behavior label of described electrical equipment safety, wherein, described in order to describe described electrical equipment safety
The high/low three-level behavior label of property includes: frequently occur potential safety hazard, occur once in a while potential safety hazard, from occur without potential safety hazard,
Severe compromise once occurred, severe compromise, the low and potential safety utilization of electric power risk of potential safety utilization of electric power risk had not occurred
High.
According to one embodiment of present invention, generate the three-level behavior high/low in order to describe described electrical equipment safety
Label includes: obtains nearly 3 years potential safety hazard total degrees of user from power utility check table, and it is hidden to calculate nearly 3 years accordingly safety
Suffer from frequency;If described nearly 3 years potential safety hazard frequencies are higher than industry monthly average potential safety hazard frequency, frequently occur described in generation
The three-level behavior label of potential safety hazard, otherwise generate described in potential safety hazard occurs once in a while or described from occurring without the three of potential safety hazard
Level behavior label;Once occurred according to the potential safety hazard type of described electrical equipment generates severe compromise or described not
The three-level behavior label of severe compromise occurs;Obtain user's potential safety hazard of nearly March always secondary from described power utility check table
Number, and calculate nearly March potential safety hazard frequency accordingly;If described nearly March potential safety hazard frequency is higher than predeterminated frequency threshold value,
Generate the high three-level behavior label of potential safety utilization of electric power risk, otherwise generate the low three-level behavior mark of potential safety utilization of electric power risk
Sign.
According to one embodiment of present invention, user's portrait construction method of described power industry, also includes: generate and use
To describe the high/low three-level behavior label of described Electrical Safety operating capability, wherein, described in order to describe described Electrical Safety pipe
The high/low three-level behavior label of reason ability includes: power consumption efficiency is high, power consumption efficiency is low, safety management consciousness is strong, safety management meaning
Know weak.
According to one embodiment of present invention, generate the three-level row high/low in order to describe described Electrical Safety operating capability
Include for label: obtain nearly 3 years capacity of idle power summations and nearly 3 years line loss electricity summations from electricity charge tablet menu respectively, and
Nearly three annual capacity of idle power accountings and nearly three annual line loss electricity accountings were respectively obtained according to nearly 3 years total electricity consumptions;By institute
State the difference that nearly three annual capacity of idle power accountings deduct industry average capacity of idle power accounting and be multiplied by the first default weight to obtain
Varmeter value;The difference that described nearly three annual line loss electricity accountings are deducted industry average line loss electricity accounting is multiplied by second
Default weight is to obtain line loss variable;If described varmeter value and described line loss variable and be positive number, generate and use
The low three-level behavior label of electrical efficiency, otherwise generates the high three-level behavior label of power consumption efficiency;Near according to power utility check table statistics
3 years all there is the number of times of potential safety hazard in double power utility check;If nearly 3 years double power utility checks of statistics all exist
The number of times of potential safety hazard is higher than industry average time, then generate the weak three-level behavior label of safety management consciousness, otherwise generate peace
The complete strong three-level behavior label of management awareness.
According to one embodiment of present invention, the described second order behavior label of user is built based on described abnormal electricity consumption behavior
System includes: generate in order to describe the second order behavior label of described abnormal electricity consumption behavior, wherein, described in order to describe described exception
The second order behavior label of electricity consumption behavior includes: promise breaking risk is high, promise breaking risk is low, stealing risk is high, stealing risk
Low.
According to one embodiment of present invention, user's portrait construction method of described power industry also includes: generates and uses
To describe the described promise breaking high/low three-level behavior label of risk, wherein, described in order to describe described promise breaking risk
High/low three-level behavior label includes: frequently promise breaking, once in a while promise breaking, never promise breaking, in the recent period frequently promise breaking, in the recent period slightly promise breaking,
Never promise breaking, grave breach of contract, slight promise breaking in the recent period.
According to one embodiment of present invention, generate the three-level behavior mark high/low in order to describe described promise breaking risk
Sign and include: obtain nearly 3 years promise breaking total degrees from promise breaking stealing information table, and calculate nearly three annual promise breaking frequencies;If described
Nearly three annuals break a contract frequencies be located at of the same trade with capacity averagely break a contract frequency from big to small after 25% ranking in, then generate institute
State promise breaking or the described three-level behavior label never broken a contract once in a while, otherwise generate the three-level behavior label of described frequent promise breaking;From
Obtaining user's nearly March in described promise breaking stealing information table break a contract total degree, and calculates nearly three monthly average and break a contract frequencies;If described
In front from big to small 25% ranking positioned at frequency of averagely breaking a contract with capacity of the same trade for nearly three monthly average promise breaking frequencies, then generate
The three-level behavior label of described frequently promise breaking in the recent period;Otherwise generate described slight in the recent period promise breaking or described never break a contract in the recent period three
Level behavior label;Obtain nearly 3 years promise breaking total amounts from described promise breaking stealing information table, and calculate the monthly average promise breaking amount of money;Root
Calculate the average grave breach of contract amount of money according to the nearly amount of money of in monthly, 3 breaking a contract;Described monthly average is broken a contract the amount of money and described averagely seriously disobey
About the amount of money carries out equal rights calculating to obtain promise breaking total score;If described promise breaking total score is located at industry promise breaking total score from big to small front 25%
Ranking in, then generate the three-level behavior label of described grave breach of contract, otherwise generate the three-level behavior label of described slight promise breaking.
According to one embodiment of present invention, described power industry user portrait construction method also include: be in order to
Describe the high/low three-level behavior label of described promise breaking risk and give corresponding weight respectively;According to described in order to describe
State the high/low three-level behavior label of promise breaking risk and corresponding weight calculation three-level behavior label score;If described three-level
Behavior label score is higher than default score threshold, then generate the promise breaking high second order behavior label of risk, otherwise, generates described
The promise breaking low second order behavior label of risk.
According to one embodiment of present invention, user's portrait construction method of described power industry also includes: generates and uses
To describe the high/low three-level behavior label of described stealing risk, wherein, described high/low in order to describe described stealing risk three
Level behavior label includes: frequently stealing, once in a while stealing, never stealing, in the recent period frequently stealing, slight stealing in the recent period, no steal in the recent period
Electric, serious stealing, slight stealing.
According to one embodiment of present invention, generate the three-level behavior label bag high/low in order to describe described stealing risk
Include: obtain nearly 3 years stealing total degrees from promise breaking stealing information table, and calculate nearly three annual stealing frequencies;If described nearly three
Annual stealing frequency is located at the same industry with rear 70% ranking from big to small of capacity average stealing frequency, then generate described
The never three-level behavior label of stealing or described stealing once in a while;Otherwise generate the three-level behavior label of described frequent stealing;From institute
State in promise breaking stealing information table and obtain nearly March stealing total degree, and calculate nearly three monthly average stealing frequencies;If described nearly March
Average stealing frequency is located at of the same trade described recent with capacity average stealing frequency from big to small front 30% ranking, then generating
The frequently three-level behavior label of stealing;Otherwise generate the three-level behavior mark of described slight in the recent period stealing or described no stealing in the recent period
Sign;Obtain nearly 3 years stealing total amounts from described promise breaking stealing information table, calculate the monthly average stealing amount of money;Every according to nearly 3 years
The averagely serious stealing amount of money of moon stealing amount of money calculating;The described monthly average stealing amount of money and the described averagely serious stealing amount of money are carried out
Equal rights calculate to obtain stealing total score;If described stealing total score, in industry total score from big to small front 25% ranking, is given birth to
Become the three-level behavior label of described serious stealing, otherwise generate the three-level behavior label of described slight stealing.
According to one embodiment of present invention, described power industry user portrait construction method also include: be in order to
Describe the high/low three-level behavior label of described stealing risk and give corresponding weight respectively;According to described in order to steal described in describing
The high/low three-level behavior label of risk and corresponding weight calculation three-level behavior label score;If described three-level behavior label
Score is higher than default score threshold, then generate the high second order behavior label of stealing risk, otherwise, generates described stealing risk low
Second order behavior label.
According to one embodiment of present invention, the described second order behavior label of user is built based on described change electricity consumption behavior
System includes: generate in order to describe described change electricity consumption behavior second order behavior label, wherein, described in order to describe described change
The second order behavior label of electricity consumption behavior includes: volume reduction in the recent period, recent increase-volume, cycle capacity change, lasting increase-volume, lasting volume reduction.
According to one embodiment of present invention, the described second order behavior label of user is built based on described normal electricity consumption behavior
System includes: generates in order to describe the second order behavior label of described normal electricity consumption behavior, wherein, described described normal in order to describe
The second order behavior label of electricity consumption behavior includes: policy needs electricity price, policy eliminates electricity price, Price Sensitive, price are insensitive, sale of electricity
Average price is high, average electric sales rate is low, power consumption is big, power consumption is little, recent electricity consumption increases, recent power consumption is stable, recent electricity consumption reduces,
Old user, new user.
According to one embodiment of present invention, generate in order to describe the second order behavior label bag of described normal electricity consumption behavior
Include: described policy is generated according to the field in data base and needs electricity price and the second order behavior label of the superseded electricity price of described policy;If
Averagely the moon, crest segment power consumption accounted for the accounting of total electricity consumption more than or equal to 30%, then generate the insensitive second order behavior of described price
Label, otherwise generates the second order behavior label of described Price Sensitive;If the average electric sales rate of user be located at electricity price of the same trade from big to
In little front 40% ranking, then generate the high second order behavior label of average electric sales rate, otherwise generate the low second order behavior of average electric sales rate
Label;If the networking duration of user is more than 3 years, generate the second order behavior label of described old user;If the networking duration of user
Less than 6 months, then generate the second order behavior label of new user.
According to one embodiment of present invention, included based on the basic act label that described interbehavior generates user: raw
Become in order to describe the second order behavior label of subscriber data integrity degree, wherein, described in order to describe described subscriber data integrity degree
Second order behavior label includes: complete data and data be not complete;And/or, generate in order to describe the second order behavior label of frequency of interaction,
Wherein, the described second order behavior label in order to describe described frequency of interaction includes: no interactions behavior and interaction are frequently.
According to one embodiment of present invention, generate and include in order to describe the second order behavior label of subscriber data integrity degree:
Data field accounting is determined according to customer profile hollow field quantity;If described data field accounting is less than 90%, generate institute
The infull second order behavior label of data of stating, otherwise generates the second order behavior label of described complete data;Generate described in order to describe
The second order behavior label of frequency of interaction includes: if client exceedes predetermined value with the number of times of predetermined telephone communication, generates described friendship
Mutual frequently second order behavior label;Otherwise generate the second order behavior label of described no interactions behavior.
According to one embodiment of present invention, included based on the basic act label that described paying behaviors generate user: raw
Become the second order behavior label in order to describe described payment duration, wherein, in order to describe the second order behavior label of described payment duration
Including: payment delays with payment in time;And/or, generate the second order behavior label in order to describe described payment channel preference, its
In, the second order behavior label in order to describe described payment channel preference includes: intelligent electric meter, prepayment, financial institution withhold and electricity
Force mechanisms are sat and are received.
According to one embodiment of present invention, generate and include in order to the second order behavior label describing described payment duration: if
User the moon total electricity bill payment duration be more than similar average payment duration, then generate described payment delay second order behavior mark
Sign;If it is not, then generating payment timely second order behavior label;Generate the second order behavior mark in order to describe described payment channel preference
Sign and include: generate two grades in order to describe described payment channel preference according to the information of the payment channel field in payment information table
Behavior label.
Brief description
Fig. 1 is the flow chart of user's portrait construction method of the power industry according to one embodiment of the invention.
Specific embodiment
Embodiments of the invention are described below in detail, the example of described embodiment is shown in the drawings, wherein from start to finish
The element that same or similar label represents same or similar element or has same or like function.Below with reference to attached
The embodiment of figure description is exemplary it is intended to be used for explaining the present invention, and is not considered as limiting the invention.
User's portrait construction method of the power industry of the embodiment of the present invention to be described below in conjunction with the accompanying drawings.
As shown in figure 1, embodiments of the invention propose a kind of user's portrait construction method of power industry, comprising:
S11: generate the base attribute label of user, the base attribute bag of wherein said user according to the field in data base
Include area, electric pressure, industry, electricity consumption classification, networking duration, whether be highly energy-consuming, whether be tripartite user;And/or,
S12: generate the basic act label of user based on electricity consumption behavior, interbehavior and paying behaviors respectively.
User's portrait construction method of power industry according to embodiments of the present invention, by the frequency of the user behavior of power industry
Degree, degree, last-period forecast combine, and are capable of the behavior characteristicss of multi-faceted description Electricity customers, thus effective auxiliary power company
Business personnel provide differentiation value-added service according to the situation of Electricity customers.
Table 1 is for describing the logical relation of the label of user's portrait according to the embodiment of the present invention.Specifically, as table 1
Shown, included based on the basic act label that described electricity consumption behavior generates user: based on safety utilization of electric power behavior, abnormal electricity consumption row
For, change electricity consumption behavior, normal electricity consumption behavior build the second order behavior label system of user respectively.
Table 1
First, electricity consumption behavior
1.1 safety utilization of electric power behaviors
Preferably, included based on the second order behavior label system that described safety utilization of electric power behavior builds user: generate in order to retouch
State the second order behavior label of described safety utilization of electric power behavior.Wherein, the described second order behavior in order to describe described safety utilization of electric power behavior
Label includes: electrical equipment is safe, electrical equipment safety is low, Electrical Safety operating capability high, Electrical Safety management energy
Power is low.
Further, user's portrait construction method of described power industry also includes: generates in order to describe described " electricity consumption
Device security height " or the three-level behavior label of " electrical equipment safety is low ";And/or, generate in order to describe described " electricity consumption peace
Full operating capability height " or the three-level behavior label of " Electrical Safety operating capability is low ".
Wherein, in order to describe the three-level behavior label of described " electrical equipment is safe " or " electrical equipment safety is low "
Can include herein below: frequently occur potential safety hazard, occur once in a while potential safety hazard, from occur without potential safety hazard, once occurred tight
Weigh potential safety hazard, severe compromise, potential safety utilization of electric power risk low and potential safety utilization of electric power risk height had not occurred.
In order to describe the three-level behavior label of described " Electrical Safety operating capability is high " or " Electrical Safety operating capability is low "
Herein below can be included: power consumption efficiency is high, power consumption efficiency is low, safety management consciousness is strong, safety management consciousness is weak.
Specifically, generate the three-level row in order to describe described " electrical equipment is safe " or " electrical equipment safety is low "
Include for label:
(1) nearly 3 years potential safety hazard total degrees of user are obtained in the power utility check table from power industry data base;By institute
State nearly 3 years potential safety hazard total degrees divided by 36 (months), to obtain nearly 3 years potential safety hazard frequencies accordingly;If described nearly three
Year, potential safety hazard frequency was higher than monthly average potential safety hazard frequency of the same trade, the then three-level of generation described " frequently occurring potential safety hazard "
Behavior label, otherwise generates the three-level behavior mark of described " potential safety hazard once in a while " or described " from occurring without potential safety hazard "
Sign.
(2) " severe compromise once occurred " or described according to the potential safety hazard type generation of described electrical equipment
The three-level behavior label of " severe compromise had not occurred ".Herein, described potential safety hazard type is carried out by experts in the industry
Pre-set.
(3) obtain user's potential safety hazard total degree of nearly March from described power utility check table;Will be hidden safely for described nearly March
Suffer from total degree divided by 3 (months), to calculate nearly March potential safety hazard frequency accordingly;If described nearly March potential safety hazard frequency is high
In predeterminated frequency threshold value, then generate the three-level behavior label of " potential safety utilization of electric power risk is high ", otherwise generate " potential safety utilization of electric power
Risk is low " three-level behavior label.
Specifically, generation is in order to describe the three of described " Electrical Safety operating capability is high " or " Electrical Safety operating capability is low "
Level behavior label includes:
(1) nearly 3 years capacity of idle power summations and nearly 3 years line loss electricity summations are obtained from electricity charge tablet menu respectively, will
Described nearly 3 years capacity of idle power summations divided by nearly 3 years total electricity consumptions, will be total divided by nearly 3 years for described nearly 3 years line loss electricity summations
Power consumption, respectively obtaining " nearly three annual capacity of idle power accountings " and " nearly three annual line loss electricity accountings ";Will be described " near
The difference that three annual capacity of idle power accountings " deduct industry average capacity of idle power accounting is multiplied by the first default weight to obtain " no
Work(variable ";The difference that described " nearly three annual line loss electricity accountings " are deducted industry average line loss electricity accounting is multiplied by
Two default weights are to obtain " line loss variable ";Described if " varmeter value " and described " line loss variable " and be positive number,
Then generate the three-level behavior label of " power consumption efficiency is low ", otherwise generate the three-level behavior label of " power consumption efficiency is high ".Herein, described
First default weight and described second default weight can flexibly be arranged according to actual count situation and demand respectively.
(2) nearly 3 years double power utility checks are counted according to power utility check table and all there is the number of times of potential safety hazard;If system
The number of times that nearly 3 years double power utility checks of meter all have potential safety hazard is higher than industry average time, then generate described " peace
Full management awareness is weak " three-level behavior label, otherwise generate the three-level behavior label of described " safety management consciousness is strong ".
1.2 abnormal electricity consumption behaviors
Preferably, included based on the described second order behavior label system that described abnormal electricity consumption behavior builds user: generate and use
To describe the second order behavior label of described abnormal electricity consumption behavior.Wherein, described in order to describe described abnormal electricity consumption behavior two grades
Behavior label includes: promise breaking risk is high, promise breaking risk is low, stealing risk is high, stealing risk is low.
Further, user's portrait construction method of described power industry also includes: generates in order to describe described " promise breaking
High with risk " or " promise breaking is low with risk " three-level behavior label;And/or, generate in order to describe described " stealing risk
Height " or the three-level behavior label of " stealing risk is low ".
Wherein, the described three-level behavior label in order to describe described " promise breaking risk is high " or " promise breaking risk is low "
Can include following: frequently promise breaking, once in a while promise breaking, never promise breaking, in the recent period frequently promise breaking, in the recent period slightly promise breaking, never disobey in the recent period
About, grave breach of contract, slight promise breaking.
Wherein, described include in order to describe described " stealing risk is high " or the three-level behavior label of " stealing risk is low ": frequently
Numerous stealing, once in a while stealing, never stealing, in the recent period frequently stealing, slight stealing in the recent period, in the recent period no stealing, serious stealing, slight steal
Electricity.
Specifically, generate and include in order to describe the high/low three-level behavior label of described promise breaking risk:
(1) obtain nearly 3 years promise breaking total degrees from promise breaking stealing information table, and described nearly 3 years promise breaking total degrees are removed
With 36 (months) to calculate nearly three annual promise breaking frequencies;If described nearly three annual promise breaking frequencies are located at of the same trade flat with capacity
Frequency of all breaking a contract from big to small in rear 25% ranking, then generates described " breaking a contract once in a while " or the three-level row of described " never promise breaking "
For label, otherwise generate the three-level behavior label of described " frequently breaking a contract ".Herein, the rank threshold of " 25% " can be according to reality
Situation is modified.For example, if the degree requirement to promise breaking is more relaxed, rank threshold can be set to 40%, that is, " if institute
State nearly three annuals break a contract frequencies be located at of the same trade with capacity averagely break a contract frequency from big to small after 40% ranking in, then generate
Described " breaking a contract once in a while " or the three-level behavior label of described " never breaking a contract ".
(2) obtaining user's nearly March from described promise breaking stealing information table break a contract total degree, and by described nearly March promise breaking
Total degree is divided by 3 (months) to calculate nearly three monthly average promise breaking frequencies;If described nearly three monthly average promise breaking frequencies are located at the same industry
With capacity averagely break a contract frequency front from big to small 25% ranking in, then generate the three-level behavior of described " frequently breaking a contract in the recent period "
Label;Otherwise generate described " slightly breaking a contract in the recent period " or the three-level behavior label of described " never breaking a contract in the recent period ".
(3) nearly 3 years promise breaking total amounts are obtained from described promise breaking stealing information table, and will be always golden for promise breaking in described nearly 3 years
Volume is divided by 36 (months) to calculate the monthly average promise breaking amount of money;The amount of money of in monthly, 3 breaking a contract for nearly is ranked up from high in the end, will be front
The promise breaking amount of money in 30% electricity consumption month (i.e. 36*30%=10.8) carries out additional calculation, and by the summation after calculating divided by 30%
Electricity consumption month, to obtain the average grave breach of contract amount of money;The described monthly average promise breaking amount of money and the described average grave breach of contract amount of money are entered
Row equal rights calculate to obtain promise breaking total score;If described promise breaking total score be located at promise breaking total score of the same trade from big to small front 25% ranking
In, then generate the three-level behavior label of described " grave breach of contract ", otherwise generate the three-level behavior label of described " slightly breaking a contract ".
The calculating process of for example bright below " the average grave breach of contract amount of money " is it is assumed that break a contract the moon after sorting from high to low
The amount of money (RMB) is as follows respectively:
(1)80、(2)75、(3)70、(4)65、(5)60、(6)55、(7)50、(8)45、(9)40、(10)35、(11)30、
(12)25……
So, the average grave breach of contract amount of money of described first 10.8 months is
(80+75+70+65+60+55+50+45+40+35+30*0.8)/10.8=55
So-called equal rights calculate, that is, described monthly average break a contract the amount of money and the described average grave breach of contract amount of money respectively account for 50% power
Weight.
In addition, the second order behavior label of " promise breaking risk is high/low " and the pass in order to describe its three-level behavior label
System is described as follows:
It is respectively the weight that " promise breaking frequency ", " promise breaking degree " and " degree of breaking a contract in the recent period " gives 0.2,0.5 and 0.3;
For example, if having " frequently breaking a contract ", " grave breach of contract ", the three-level behavior label of " frequently breaking a contract in the recent period ",
The weight of " promise breaking frequency ", " promise breaking degree " and " degree of breaking a contract in the recent period " is respectively 0.2,0.5 and 0.3;If have " disobeying once in a while
About ", the three-level behavior label of " grave breach of contract ", " break a contract in the recent period serious ", then " promise breaking frequency ", " promise breaking degree " and " disobey in the recent period
The weight of about degree " is respectively 0,0.5 and 0.3;If have " once in a while break a contract ", " grave breach of contract ", the three of " never breaking a contract in the recent period "
Level behavior label, then the weight respectively 0,0.5 and 0 of " promise breaking frequency ", " promise breaking degree " and " degree of breaking a contract in the recent period ";
If score is higher than 0.5, stamp the label of " promise breaking risk is high ", otherwise, stamp " promise breaking risk is low "
Label.
Specifically, generate and include in order to describe described " stealing risk is high " or the three-level behavior label of " stealing risk is low ":
(1) nearly 3 years stealing total degrees are obtained from promise breaking stealing information table, stealing total degree is divided by the 36 (moons within nearly 3 years
Part) to calculate nearly three annual stealing frequencies;If described nearly three annual stealing frequencies are located at the same industry with the average stealing of capacity
In rear 70% ranking from big to small of frequency, then generate the three-level behavior mark of described " never stealing " or described " stealing once in a while "
Sign;Otherwise generate the three-level behavior label of described " frequent stealing ".Herein, when described nearly three annual stealing frequencies are zero, that is,
Generate the three-level behavior label of described " never stealing ".
(2) obtain nearly March stealing total degree from described promise breaking stealing information table, nearly March stealing total degree is divided by 3
(month) is to calculate nearly three monthly average stealing frequencies;If described nearly three monthly average stealing frequencies are located at the same industry and averagely steal with capacity
Electric frequency from big to small in front 30% ranking, then generates the three-level behavior label of described " frequently stealing in the recent period ";Otherwise generate
Described " slight stealing in the recent period " or the three-level behavior label of described " no stealing in the recent period ".
(3) obtain nearly 3 years stealing total amounts from described promise breaking stealing information table, calculate the monthly average stealing amount of money;Nearly
In monthly, 3 the stealing amount of money be ranked up from high in the end, by the stealing amount of money summation in front 30% electricity consumption month divided by the 30% electricity consumption moon
Part, to obtain the averagely serious stealing amount of money;The described monthly average stealing amount of money and the described averagely serious stealing amount of money are carried out equal rights
Calculate to obtain stealing total score;If described stealing total score is in industry total score from big to small front 25% ranking, generate institute
State the three-level behavior label of " serious stealing ", otherwise generate the three-level behavior label of described " slight stealing ".Herein, with regard to described
The computational methods of the averagely serious stealing amount of money are similar with the computational methods of " the average grave breach of contract amount of money ", are referred to carry out, this
Place repeats no more.
In addition, the second order behavior label of " stealing risk is high/low " and saying in order to describe the relation of its three-level behavior label
Bright as follows:
It is respectively the weight that " stealing frequency ", " stealing degree " and " recent stealing degree " gives 0.2,0.5 and 0.3;
For example, if having " frequent stealing ", " serious stealing ", the three-level behavior label of " frequently stealing in the recent period ",
The weight of " stealing frequency ", " stealing degree " and " recent stealing degree " is respectively 0.2,0.5 and 0.3;If have " stealing once in a while
Electricity ", " serious stealing ", the three-level behavior label of " in the recent period frequently stealing ", then " promise breaking frequency ", " promise breaking degree " and " disobey in the recent period
The weight of about degree " is respectively 0,0.5 and 0.3;If having " stealing once in a while ", " serious stealing ", the three-level of " no stealing in the recent period "
Behavior label, then the weight respectively 0,0.5 and 0 of " promise breaking frequency ", " promise breaking degree " and " degree of breaking a contract in the recent period ";
If score is higher than 0.5, stamp the label of " stealing risk is high ", otherwise, stamp the label of " stealing risk is low ".
In the metering of abnormal electricity consumption behavior, rank threshold equally can be carried out flexibly according to actual count situation and needs
Setting.
1.3 change electricity consumption behaviors
Preferably, included based on the described second order behavior label system that described change electricity consumption behavior builds user: generate and use
To describe the second order behavior label of described change electricity consumption behavior.
Wherein, the described second order behavior label in order to describe described change electricity consumption behavior includes: volume reduction in the recent period, in the recent period increasing
Appearance, cycle capacity change, lasting increase-volume, lasting volume reduction.
1.4 normal electricity consumption behaviors
Preferably, included based on the described second order behavior label system that described normal electricity consumption behavior builds user: generate and use
To describe the second order behavior label of described normal electricity consumption behavior.
Wherein, the described second order behavior label in order to describe described normal electricity consumption behavior includes: policy needs electricity price, policy
Superseded electricity price, Price Sensitive, price are insensitive, average electric sales rate is high, average electric sales rate is low, power consumption is big, power consumption is little, recent electricity consumption
Increase, recent power consumption is stable, recent electricity consumption minimizing, old user, new user.
Specifically, generate and include in order to describe the second order behavior label of described normal electricity consumption behavior:
(1) two grades of " policy needs electricity price " and described " policy eliminates electricity price " according to the field in data base generates
Behavior label.
(2) if average moon crest segment power consumption is more than or equal to 30% with the ratio of total electricity consumption, generate that described " price is not
The second order behavior label of sensitivity ", otherwise generates the second order behavior label of described " Price Sensitive ".It is herein, described that " price is unwise
The second order behavior label of sense " means that user does not especially avoid the peak of power consumption period, namely the accounting for of the power consumption of peak period
Ratio is bigger, and user is insensitive to electricity rates.
(3) if the average electric sales rate of user, in electricity price of the same trade from big to small front 40% ranking, generates sale of electricity equal
The high second order behavior label of valency, otherwise generates the low second order behavior label of average electric sales rate.
(4) if the networking duration of user is more than 3 years, generate the second order behavior label of described old user;If user enters
Net duration is less than 6 months, then generate the second order behavior label of new user.Herein, for the time threshold judging differentiation old and new users
Value flexibly can be arranged according to actual count situation and needs.
In the metering of normal electricity consumption behavior, rank threshold equally can be carried out flexibly according to actual count situation and needs
Setting.
2nd, interbehavior
Preferably, included based on the basic act label that described interbehavior generates user: generate in order to describe user's money
The second order behavior label of material integrity degree;And/or, generate in order to describe the second order behavior label of frequency of interaction.
Wherein, the second order behavior label in order to describe described subscriber data integrity degree includes: complete data and data be not complete.
Second order behavior label in order to describe described frequency of interaction includes: no interactions behavior and interaction are frequently.
Specifically, generate and include in order to describe the second order behavior label of subscriber data integrity degree:
Data field accounting is determined according to customer profile hollow field quantity;If described data field accounting is less than 90%,
Then generate the second order behavior label of described " data is not complete ", otherwise generate the second order behavior label of described " complete data ".Herein,
Judge that the field accounting of the integrated degree of subscriber data can flexibly be arranged, e.g., if require higher to complete data degree, permissible
The threshold value of field accounting is set to 100%, even described data field accounting is less than 100%, then described in generation, " data is not
Second order behavior label entirely ", otherwise generates the second order behavior label of described " complete data ".
Generate and include in order to describe the second order behavior label of described frequency of interaction:
If client exceedes predetermined value with the number of times of predetermined telephone communication, generate the second order behavior mark of described " interaction is frequently "
Sign;Otherwise generate the second order behavior label of described " no interactions behavior ".For example, dialed the average moon according to user in data base
The number of times of 95588 hot lines, more than 10 times, then for the second order behavior label of this user setup " interaction is frequently ", otherwise, setting is " no
The second order behavior label of interbehavior ".
3rd, paying behaviors
Preferably, included based on the basic act label that described paying behaviors generate user: generate in order to pay described in describing
The second order behavior label of time-consuming length;And/or, generate the second order behavior label in order to describe described payment channel preference.
Wherein, the second order behavior label in order to describe described payment duration includes: payment delays with payment in time;In order to retouch
The second order behavior label stating described payment channel preference includes: intelligent electric meter, prepayment, financial institution withhold and sit with electric power mechanism
Receive.
Specifically, generate and include in order to the second order behavior label describing described payment duration: if the moon total electricity bill of user
Payment duration is more than similar average payment duration, then generate the second order behavior label of described " payment delays ";If it is not, then generating
The second order behavior label of " payment is in time ".
Generate and include in order to the second order behavior label describing described payment channel preference: according to the payment in payment information table
The information of channel field generates the second order behavior label in order to describe described payment channel preference.
In describing the invention it is to be understood that term " " center ", " longitudinal ", " horizontal ", " length ", " width ",
" thickness ", " on ", D score, "front", "rear", "left", "right", " vertical ", " level ", " top ", " bottom ", " interior ", " outward ", " up time
The orientation of instruction such as pin ", " counterclockwise ", " axial ", " radially ", " circumferential " or position relationship be based on orientation shown in the drawings or
Position relationship, is for only for ease of the description present invention and simplifies description, rather than the device of instruction or hint indication or element must
Must have specific orientation, with specific azimuth configuration and operation, be therefore not considered as limiting the invention.
Additionally, term " first ", " second " are only used for describing purpose, and it is not intended that indicating or hint relative importance
Or the implicit quantity indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can express or
Implicitly include one or more this feature.In describing the invention, " multiple " are meant that two or more,
Unless otherwise expressly limited specifically.
In the present invention, unless otherwise clearly defined and limited, term " installation ", " being connected ", " connection ", " fixation " etc.
Term should be interpreted broadly, for example, it may be being fixedly connected or being detachably connected or integral;Can be that machinery connects
Connect or electrically connect;Can be to be joined directly together it is also possible to be indirectly connected to by intermediary, can be in two elements
The connection in portion or the interaction relationship of two elements.For the ordinary skill in the art, can be according to concrete feelings
Condition understands above-mentioned term concrete meaning in the present invention.
In the present invention, unless otherwise clearly defined and limited, fisrt feature second feature " on " or D score permissible
It is the first and second feature directly contacts, or the first and second features pass through intermediary mediate contact.And, fisrt feature exists
Second feature " on ", " top " and " above " but fisrt feature are directly over second feature or oblique upper, or be merely representative of
Fisrt feature level height is higher than second feature.Fisrt feature second feature " under ", " lower section " and " below " can be
One feature is immediately below second feature or obliquely downward, or is merely representative of fisrt feature level height and is less than second feature.
In the description of this specification, reference term " embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy describing with reference to this embodiment or example
Point is contained at least one embodiment or the example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.And, the specific features of description, structure, material or feature can be in office
Combine in an appropriate manner in one or more embodiments or example.Additionally, in the case of not conflicting, the skill of this area
The feature of the different embodiments described in this specification or example and different embodiment or example can be tied by art personnel
Close and combine.
Although embodiments of the invention have been shown and described above it is to be understood that above-described embodiment is example
Property it is impossible to be interpreted as limitation of the present invention, those of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, changes, replacing and modification.
Claims (10)
1. a kind of user's portrait construction method of power industry is it is characterised in that include:
Generate the base attribute label of user according to the field in data base, the base attribute of wherein said user include area,
Electric pressure, industry, electricity consumption classification, networking duration, whether be highly energy-consuming, whether be tripartite user;And/or
Generate the basic act label of user based on electricity consumption behavior, paying behaviors and interbehavior respectively.
2. user's portrait construction method of power industry as claimed in claim 1 is it is characterised in that be based on described electricity consumption behavior
The basic act label generating user includes:
Build two grades of user based on safety utilization of electric power behavior, abnormal electricity consumption behavior, change electricity consumption behavior, normal electricity consumption behavior respectively
Behavior label system.
3. user's portrait construction method of power industry as claimed in claim 2 is it is characterised in that be based on described safety utilization of electric power
The second order behavior label system that behavior builds user includes:
Generate in order to describe the second order behavior label of described safety utilization of electric power behavior,
Wherein, the described second order behavior label in order to describe described safety utilization of electric power behavior includes: electrical equipment is safe, electricity consumption
Device security is low, Electrical Safety operating capability high, Electrical Safety operating capability is low.
4. power industry as claimed in claim 3 user portrait construction method it is characterised in that also including: generate in order to
The high/low three-level behavior label of described electrical equipment safety is described,
Wherein, described include in order to describe the high/low three-level behavior label of described electrical equipment safety: frequently occur safety hidden
Suffer from, occur once in a while potential safety hazard, from occur without potential safety hazard, once occurred severe compromise, do not occurred severe compromise,
The low and potential safety utilization of electric power risk of potential safety utilization of electric power risk is high.
5. user's portrait construction method of power industry as claimed in claim 4 is it is characterised in that generate described in order to describe
The high/low three-level behavior label of electrical equipment safety includes:
Obtain nearly 3 years potential safety hazard total degrees of user from power utility check table, and calculate nearly 3 years accordingly potential safety hazard frequencies
Rate;If described nearly 3 years potential safety hazard frequencies are higher than industry monthly average potential safety hazard frequency, described in generation, frequently occur safety
The three-level behavior label of hidden danger, otherwise generate described in potential safety hazard occurs once in a while or described from the three-level row occurring without potential safety hazard
For label;
Once occurred according to the potential safety hazard type of described electrical equipment generates severe compromise or described do not occurred tight
The three-level behavior label of weight potential safety hazard;
Obtain user's potential safety hazard total degree of nearly March from described power utility check table, and calculate nearly March potential safety hazard accordingly
Frequency;If described nearly March potential safety hazard frequency is higher than predeterminated frequency threshold value, generate the high three-level of potential safety utilization of electric power risk
Behavior label, otherwise generates the low three-level behavior label of potential safety utilization of electric power risk.
6. power industry as claimed in claim 3 user portrait construction method it is characterised in that also including: generate in order to
The high/low three-level behavior label of described Electrical Safety operating capability is described,
Wherein, described include in order to describe the high/low three-level behavior label of described Electrical Safety operating capability:
Power consumption efficiency is high, power consumption efficiency is low, safety management consciousness is strong, safety management consciousness is weak.
7. user's portrait construction method of power industry as claimed in claim 6 is it is characterised in that generate described in order to describe
The high/low three-level behavior label of Electrical Safety operating capability includes:
Nearly 3 years capacity of idle power summations and nearly 3 years line loss electricity summations is obtained respectively from electricity charge tablet menu, and according to nearly three
Year total electricity consumption respectively obtains nearly three annual capacity of idle power accountings and nearly three annual line loss electricity accountings;By described nearly 3 years
The difference that average capacity of idle power accounting deducts industry average capacity of idle power accounting is multiplied by the first default weight to obtain reactive measurement
Value;The difference that described nearly three annual line loss electricity accountings are deducted industry average line loss electricity accounting is multiplied by the second default weight
To obtain line loss variable;If described varmeter value and described line loss variable and be positive number, generate power consumption efficiency low
Three-level behavior label, otherwise generate the high three-level behavior label of power consumption efficiency;
Nearly 3 years double power utility checks are counted according to power utility check table and all there is the number of times of potential safety hazard;If nearly the three of statistics
Year all there is the number of times of potential safety hazard higher than industry average time in double power utility check, then generate safety management consciousness weak
Three-level behavior label, otherwise generates the strong three-level behavior label of safety management consciousness.
8. user's portrait construction method of power industry as claimed in claim 2 is it is characterised in that be based on described abnormal electricity consumption
The described second order behavior label system that behavior builds user includes:
Generate in order to describe the second order behavior label of described abnormal electricity consumption behavior,
Wherein, the described second order behavior label in order to describe described abnormal electricity consumption behavior includes: promise breaking risk is high, promise breaking is used
Risk is low, stealing risk high, stealing risk is low.
9. power industry as claimed in claim 8 user portrait construction method it is characterised in that also including: generate in order to
The description described promise breaking high/low three-level behavior label of risk,
Wherein, described include in order to describe the high/low three-level behavior label of described promise breaking risk: frequently promise breaking, disobey once in a while
About, never promise breaking, in the recent period frequently promise breaking, in the recent period slightly promise breaking, in the recent period never promise breaking, grave breach of contract, slight promise breaking.
10. user's portrait construction method of power industry as claimed in claim 9 is it is characterised in that generate in order to describe
State the high/low three-level behavior label of promise breaking risk to include:
Obtain nearly 3 years promise breaking total degrees from promise breaking stealing information table, and calculate nearly three annual promise breaking frequencies;If described near
Three annuals break a contract frequencies be located at of the same trade with capacity averagely break a contract frequency from big to small after 25% ranking in, then generate described
Promise breaking or the described three-level behavior label never broken a contract, otherwise generate the three-level behavior label of described frequent promise breaking once in a while;
Obtaining user's nearly March from described promise breaking stealing information table break a contract total degree, and calculates nearly three monthly average and break a contract frequencies;
In front from big to small 25% ranking positioned at frequency of averagely breaking a contract with capacity of the same trade for the frequency if described nearly three monthly average are broken a contract,
Then generate the three-level behavior label of described frequently promise breaking in the recent period;Otherwise generate described slight in the recent period promise breaking or described never disobey in the recent period
Three-level behavior label about;
Obtain nearly 3 years promise breaking total amounts from described promise breaking stealing information table, and calculate the monthly average promise breaking amount of money;According to nearly three
The amount of money of monthly breaking a contract in year calculates the average grave breach of contract amount of money;By the described monthly average promise breaking amount of money and the described average grave breach of contract amount of money
Carry out equal rights to calculate to obtain promise breaking total score;If described promise breaking total score be located at industry break a contract total score from big to small front 25% ranking
In, then generate the three-level behavior label of described grave breach of contract, otherwise generate the three-level behavior label of described slight promise breaking.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610713004.3A CN106373026A (en) | 2016-08-24 | 2016-08-24 | User portrait construction method for power industry |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610713004.3A CN106373026A (en) | 2016-08-24 | 2016-08-24 | User portrait construction method for power industry |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106373026A true CN106373026A (en) | 2017-02-01 |
Family
ID=57878215
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610713004.3A Pending CN106373026A (en) | 2016-08-24 | 2016-08-24 | User portrait construction method for power industry |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106373026A (en) |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106909676A (en) * | 2017-03-02 | 2017-06-30 | 国家电网公司 | The analysis method and device of user power utilization behavior |
CN107145586A (en) * | 2017-05-10 | 2017-09-08 | 中国电力科学研究院 | A kind of label output method and apparatus based on power marketing data |
CN107180392A (en) * | 2017-05-18 | 2017-09-19 | 北京科技大学 | A kind of electric power enterprise tariff recovery digital simulation method |
CN107315810A (en) * | 2017-06-27 | 2017-11-03 | 济南浪潮高新科技投资发展有限公司 | A kind of internet of things equipment behavior portrait method |
CN107358269A (en) * | 2017-07-12 | 2017-11-17 | 广州天源信息科技有限公司 | A kind of construction method of telecommunication user consumption portrait towards precision marketing |
CN108536701A (en) * | 2017-03-02 | 2018-09-14 | 塞纳德(北京)信息技术有限公司 | A kind of user's portrait structure and content recommendation method based on page marking |
CN108764939A (en) * | 2018-05-11 | 2018-11-06 | 深圳供电局有限公司 | Power enterprise customer relationship management system and method thereof |
CN109242309A (en) * | 2018-09-05 | 2019-01-18 | 广州视源电子科技股份有限公司 | Participated user portrait generation method and device, intelligent conference equipment and storage medium |
CN109961197A (en) * | 2017-12-22 | 2019-07-02 | 中国电力科学研究院有限公司 | A kind of regional complex electricity consumption evaluation method and system based on power consumer label |
WO2019140703A1 (en) * | 2018-01-22 | 2019-07-25 | 华为技术有限公司 | Method and device for generating user profile picture |
CN110119998A (en) * | 2019-03-27 | 2019-08-13 | 广东浩迪创新科技有限公司 | Rental house approaches to IM and system based on intelligent electric meter |
CN110163621A (en) * | 2018-02-10 | 2019-08-23 | 广州供电局有限公司 | A kind of electric power customer service big data DSS |
CN110196849A (en) * | 2019-06-05 | 2019-09-03 | 普元信息技术股份有限公司 | It realizes that user draws a portrait based on big data Treatment process and constructs the system and method for processing |
CN110309932A (en) * | 2018-03-21 | 2019-10-08 | 国网浙江省电力公司湖州供电公司 | A kind of power customer resource fine-grained management method based on TEM |
CN111105248A (en) * | 2019-12-03 | 2020-05-05 | 广东电网有限责任公司 | Client appeal automatic early warning system based on client portrait |
CN111126880A (en) * | 2020-01-02 | 2020-05-08 | 浙江吉利新能源商用车集团有限公司 | User portrait generation method, device and equipment |
CN111967723A (en) * | 2020-07-24 | 2020-11-20 | 南昌大学 | User peak regulation potential analysis method based on data mining |
CN112150267A (en) * | 2020-09-14 | 2020-12-29 | 深圳供电局有限公司 | Computer equipment and enterprise power consumption analysis system |
CN112184313A (en) * | 2020-09-28 | 2021-01-05 | 国网上海市电力公司 | Power marketing business application system based on client portrait data |
CN112835882A (en) * | 2021-01-29 | 2021-05-25 | 北京百家科技集团有限公司 | Information prediction method, information prediction device, electronic equipment and storage medium |
CN114417955A (en) * | 2021-12-02 | 2022-04-29 | 国网浙江省电力有限公司 | Power index portrait real-time generation method and device suitable for villages and storage medium |
-
2016
- 2016-08-24 CN CN201610713004.3A patent/CN106373026A/en active Pending
Cited By (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108536701A (en) * | 2017-03-02 | 2018-09-14 | 塞纳德(北京)信息技术有限公司 | A kind of user's portrait structure and content recommendation method based on page marking |
CN106909676A (en) * | 2017-03-02 | 2017-06-30 | 国家电网公司 | The analysis method and device of user power utilization behavior |
CN107145586A (en) * | 2017-05-10 | 2017-09-08 | 中国电力科学研究院 | A kind of label output method and apparatus based on power marketing data |
CN107145586B (en) * | 2017-05-10 | 2021-10-29 | 中国电力科学研究院 | Label output method and device based on electric power marketing data |
CN107180392A (en) * | 2017-05-18 | 2017-09-19 | 北京科技大学 | A kind of electric power enterprise tariff recovery digital simulation method |
CN107315810A (en) * | 2017-06-27 | 2017-11-03 | 济南浪潮高新科技投资发展有限公司 | A kind of internet of things equipment behavior portrait method |
CN107315810B (en) * | 2017-06-27 | 2020-04-21 | 浪潮集团有限公司 | Internet of things equipment behavior portrait method |
CN107358269A (en) * | 2017-07-12 | 2017-11-17 | 广州天源信息科技有限公司 | A kind of construction method of telecommunication user consumption portrait towards precision marketing |
CN107358269B (en) * | 2017-07-12 | 2020-10-02 | 广州天源信息科技股份有限公司 | Construction method of telecom user consumption portrait for precise marketing |
CN109961197B (en) * | 2017-12-22 | 2021-08-27 | 中国电力科学研究院有限公司 | Regional comprehensive power utilization evaluation method and system based on power user label |
CN109961197A (en) * | 2017-12-22 | 2019-07-02 | 中国电力科学研究院有限公司 | A kind of regional complex electricity consumption evaluation method and system based on power consumer label |
WO2019140703A1 (en) * | 2018-01-22 | 2019-07-25 | 华为技术有限公司 | Method and device for generating user profile picture |
CN110163621A (en) * | 2018-02-10 | 2019-08-23 | 广州供电局有限公司 | A kind of electric power customer service big data DSS |
CN110309932A (en) * | 2018-03-21 | 2019-10-08 | 国网浙江省电力公司湖州供电公司 | A kind of power customer resource fine-grained management method based on TEM |
CN108764939A (en) * | 2018-05-11 | 2018-11-06 | 深圳供电局有限公司 | Power enterprise customer relationship management system and method thereof |
CN109242309A (en) * | 2018-09-05 | 2019-01-18 | 广州视源电子科技股份有限公司 | Participated user portrait generation method and device, intelligent conference equipment and storage medium |
CN110119998B (en) * | 2019-03-27 | 2023-04-28 | 广东浩迪创新科技有限公司 | Renting house information management method and system based on intelligent ammeter |
CN110119998A (en) * | 2019-03-27 | 2019-08-13 | 广东浩迪创新科技有限公司 | Rental house approaches to IM and system based on intelligent electric meter |
CN110196849A (en) * | 2019-06-05 | 2019-09-03 | 普元信息技术股份有限公司 | It realizes that user draws a portrait based on big data Treatment process and constructs the system and method for processing |
CN111105248A (en) * | 2019-12-03 | 2020-05-05 | 广东电网有限责任公司 | Client appeal automatic early warning system based on client portrait |
CN111126880A (en) * | 2020-01-02 | 2020-05-08 | 浙江吉利新能源商用车集团有限公司 | User portrait generation method, device and equipment |
CN111967723B (en) * | 2020-07-24 | 2022-05-20 | 南昌大学 | User peak regulation potential analysis method based on data mining |
CN111967723A (en) * | 2020-07-24 | 2020-11-20 | 南昌大学 | User peak regulation potential analysis method based on data mining |
CN112150267A (en) * | 2020-09-14 | 2020-12-29 | 深圳供电局有限公司 | Computer equipment and enterprise power consumption analysis system |
CN112184313A (en) * | 2020-09-28 | 2021-01-05 | 国网上海市电力公司 | Power marketing business application system based on client portrait data |
CN112835882A (en) * | 2021-01-29 | 2021-05-25 | 北京百家科技集团有限公司 | Information prediction method, information prediction device, electronic equipment and storage medium |
CN112835882B (en) * | 2021-01-29 | 2024-02-02 | 北京百家科技集团有限公司 | Information prediction method, device, electronic equipment and storage medium |
CN114417955A (en) * | 2021-12-02 | 2022-04-29 | 国网浙江省电力有限公司 | Power index portrait real-time generation method and device suitable for villages and storage medium |
CN114417955B (en) * | 2021-12-02 | 2023-10-31 | 国网浙江省电力有限公司 | Method, device and storage medium for generating power index image suitable for village in real time |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106373026A (en) | User portrait construction method for power industry | |
Smith | Electricity theft: a comparative analysis | |
Holmberg et al. | The supply function equilibrium and its policy implications for wholesale electricity auctions | |
Tewari et al. | An assessment of South African prepaid electricity experiment, lessons learned, and their policy implications for developing countries | |
Alam et al. | Power sector reform in Bangladesh: Electricity distribution system | |
CN106920110A (en) | A kind of evaluation method of power customer credit and arrears risk | |
Narayan | Foreign exchange markets and oil prices in Asia | |
Fares et al. | Trends in transmission, distribution, and administration costs for US investor-owned electric utilities | |
Malama et al. | The effects of the introduction of prepayment meters on the energy usage behaviour of different housing consumer groups in Kitwe, Zambia | |
CN104021454A (en) | Capital account data monitoring method and system for group enterprise | |
CN108596467B (en) | Market operation simulation transaction simulation system suitable for electricity selling company | |
CN108681891A (en) | A kind of Multiple Currencies tranaction costs collection methods based on block chain | |
US20130179202A1 (en) | Method and system for analysis of infrastructure | |
CN108647849A (en) | A kind of distributed generation resource Credit Evaluation of Power Consumers method based on grey relational grade | |
CN109697574A (en) | Small customer electricity Risk Identification Method in a kind of electric power | |
Alahmed et al. | Integrating distributed energy resources: Optimal prosumer decisions and impacts of net metering tariffs | |
Blank et al. | Residential winners and losers behind the energy versus customer charge debate | |
Horlick | How the GATT Became Protectionist-An Analysis of the Uruguay Round Draft Final Antidumping Code | |
CN106600151A (en) | Power big data credit reporting analysis method and apparatus | |
Papadimitriou et al. | Non-technical losses: detection methods and regulatory aspects overview | |
Tauhidi et al. | The conundrum of circular debt | |
CN110599059A (en) | Incremental power distribution network user-oriented electricity selling decision method and system | |
CN113379541B (en) | Comprehensive settlement system and method for retail power consumption and damage | |
CN204990496U (en) | Unmanned many varieties of theft protection vegetables food retail trade equipment | |
Audinet | Electricity prices in India |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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: 20170201 |