CN109165763A - A kind of potential complained appraisal procedure and device of 95598 customer service work order - Google Patents
A kind of potential complained appraisal procedure and device of 95598 customer service work order Download PDFInfo
- Publication number
- CN109165763A CN109165763A CN201810610029.XA CN201810610029A CN109165763A CN 109165763 A CN109165763 A CN 109165763A CN 201810610029 A CN201810610029 A CN 201810610029A CN 109165763 A CN109165763 A CN 109165763A
- Authority
- CN
- China
- Prior art keywords
- work order
- complaint
- customer
- potential
- order data
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 230000006399 behavior Effects 0.000 claims abstract description 62
- 238000004458 analytical method Methods 0.000 claims abstract description 42
- 238000010276 construction Methods 0.000 claims abstract description 22
- 230000005611 electricity Effects 0.000 claims description 25
- 238000005457 optimization Methods 0.000 claims description 13
- 238000007726 management method Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 230000003542 behavioural effect Effects 0.000 claims description 4
- 230000006855 networking Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 238000013499 data model Methods 0.000 claims description 2
- 230000004069 differentiation Effects 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 abstract description 2
- 238000007405 data analysis Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000009467 reduction 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses the potential complained appraisal procedures and device of a kind of 95598 customer service work orders, are related to electric power customer service job evaluation technical field, comprising the following steps: first choose work order label and user tag；It is matched to obtain 95598 work order integrated information label systems according to work order label and user tag customer name corresponding with 95598 work order data；According to the customer complaint Analysis model of network behaviors of 95598 work order integrated information label system construction, 95598 work order data；Customer complaint Analysis model of network behaviors optimized regression coefficient based on 95598 work order data obtains optimum regression coefficient, the customer complaint Analysis model of network behaviors of optimal 95598 work order data is constructed based on optimum regression coefficient, scoring and divided rank are carried out to 95598 customer service work orders using the customer complaint Analysis model of network behaviors of optimal 95598 work order data, score value and the divided rank judgement obtained by scoring can generate the probability of subsequent complaint, thus the differentiation value-added service that the business personnel of effectively auxiliary power company provides according to 95598 different work orders.
Description
Technical field
The present invention relates to electric power customer service job evaluation technical fields, more particularly to a kind of potential quilt of 95598 customer service work orders
The appraisal procedure and device of complaint.
Background technique
With increasing for 95598 customer service traffic quantity of Utilities Electric Co., protection growth, visitor is quantitatively presented in business datum
Complain pressure also growing day by day in family.However, remaining one in major part grid company customer service operating analysis at present
Fixed problem: intelligent analysis means are insufficient, and artificial subjective factor influences more；Internal and external factor analysis to customer service analysis
Deficiency, can not quantization influence degree and duration, client can not further be complained behavior do one prediction in time
Adjust differentiation customer service measure.In order to improve the limitation of existing customer service analysis prediction, the level of prediction is analyzed in promotion,
A reasonable prediction is done to customer complaint behavior according to customer complaint content in time, it is full to improve customer service using the service of differentiation
Meaning degree reduces the behavior that Electricity customers are further complained, and the invention proposes a kind of the potential complained of 95598 customer service work orders
Appraisal procedure and device.
Summary of the invention
The purpose of the present invention is to provide the potential complained appraisal procedure and device of a kind of 95598 customer service work orders, from
And solving the disadvantage that power supply company can not objectively give a forecast to the complaint behavior of client according to 95598 work order data.
To achieve the above object, the present invention provides a kind of potential complained appraisal procedure of 95598 customer service work orders, packets
Include following steps:
S10, the work order label that user power utilization behavior can be embodied from 95598 work order data decimations；
S20, selection can embody user power utilization behavior from the power consumer database of power marketing management information system
User tag；
S30, it is carried out according to the work order label and corresponding with the 95598 work order data customer name of user tag
With obtaining 95598 work order integrated information label systems；
S40, according to the customer complaint behavior of 95598 work order integrated information label system construction, the 95598 work order data
Analysis model；
S50, the customer complaint Analysis model of network behaviors optimized regression coefficient based on the 95598 work order data obtain optimal time
Return coefficient, the customer complaint Analysis model of network behaviors of optimal 95598 work order data is constructed based on optimum regression coefficient, utilization is optimal
The customer complaint Analysis model of network behaviors of 95598 work order data carries out scoring and divided rank to 95598 customer service work orders, passes through scoring
Obtained score value and divided rank judgement can generate the probability of subsequent complaint.
Further, the work order label includes: work order class of service, work order second level classification, work order three-level classification, electricity consumption
Season, electricity consumption weather, electricity consumption there and then temperature and TT processing duration.
Further, the user tag includes: address section, voltage class, electricity consumption classification, line name, platform area name
Title and networking duration.
Further, obtain 95598 work order v's according to the customer complaint Analysis model of network behaviors of the 95598 work order data
Complain marking L:
In formula (1), L is the complaint marking value of 95598 work order v, and M is marking factor set；ε is independent departure；Xj
It is the scoring of the grading factor j of 95598 work order v；βjIt is recurrence corresponding to the grading factor j using spline curve smooth treatment
The calculating of coefficient, the regression coefficient is as follows:
In formula (2) and formula (3),It is the base for indicating linear spline function, k is the segments of linear spline function,It is the functional value of rightmost side point in the range of linear spline function,
βj1And βjKIt is the value of the left and right ends in section where linear spline function, k-s3Be piecewise function subtract one it is normal less than 1
Number, s3It is a constant between [0,1], k-sKβIt is that segments subtracts a constant less than 1, sKβBe one between [0,1] often
Number.
Further, the calculating process of the optimum regression coefficient are as follows: pass through the customer complaint of the 95598 work order data
Analysis model of network behaviors obtains the grading stability goal function and 95598 work order numbers of the customer complaint behavior of 95598 work order data
According to customer complaint behavior grading otherness objective function；According to the grading stability goal function and grading otherness mesh
Scalar functions form multi-objective constrained optimization problem；Single goal is converted by the multi-objective constrained optimization problem by optimization algorithm
Optimization problem, to obtain optimum regression coefficient.
Further, the grading stability goal function is as follows:
In formula (4),The grading stationary value that a possibility that complaint potential for work order grades, N are the works assessed
Odd number amount,Indicating being averaged for N number of number, L is the complaint marking value of 95598 work order v,It is the phase of the 95598 potential complaints of work order v
Prestige value；
The grading otherness objective function is as follows:
In formula (5),The difference value that a possibility that being work order potential complaint grades, N is the work order number assessed
Amount,Indicating being averaged for N-1 number, L is the complaint marking value of 95598 work order v,It is that the potential complaint of 95598 work order v may
The average value of property,It is average valueSquare；
The multi-objective constrained optimization problem are as follows:
In formula (6),The grading stationary value that a possibility that complaint potential for work order grades,For the potential complaint of work order
The difference value of possibility grading, β are optimum regression coefficient.
A kind of potential complained assessment device of 95598 customer service work order, comprising:
Work order label model, for the work order label of user power utilization behavior can be embodied from 95598 work order data decimations；
User tag module can be embodied for choosing from the power consumer database of power marketing management information system
The user tag of user power utilization behavior；
System construction module, for corresponding with the 95598 work order data according to the work order label and user tag
Customer name is matched to obtain 95598 work order integrated information label systems；
Model construction module, for according to 95598 work order integrated information label system construction, the 95598 work order data
Customer complaint Analysis model of network behaviors；And
Optimized model constructs module, for being optimized according to the customer complaint Analysis model of network behaviors of the 95598 work order data
Regression coefficient obtains optimum regression coefficient, and the customer complaint behavior of optimal 95598 work order data is constructed based on optimum regression coefficient
Analysis model, using optimal 95598 work order data customer complaint Analysis model of network behaviors to 95598 customer service work orders carry out scoring and
Divided rank, the score value obtained by scoring and divided rank judgement can generate the probability of subsequent complaint.
Compared with prior art, the invention has the following beneficial effects:
The potential complained appraisal procedure and device of a kind of 95598 customer service work order provided by the present invention, pass through 95598
Work order data decimation can embody the work order label of user power utilization behavior；Pass through the power consumer of power marketing management information system
The user tag that can embody user power utilization behavior is chosen in database；Pass through work order label and user tag and 95598 work orders
The corresponding customer name of data is matched to obtain 95598 work order integrated information label systems, which includes a variety of label energy
More than enough orientation describes the behavioural characteristic of Electricity customers；Further according to 95598 work order integrated information label system construction, 95598 work
The customer complaint Analysis model of network behaviors of forms data；By optimized regression coefficient, keep model more accurate, is based on optimized regression coefficient
The customer complaint Analysis model of network behaviors of optimal 95598 work order data is obtained, the customer complaint of optimal 95598 work order data is utilized
Analysis model of network behaviors carries out scoring and divided rank to 95598 customer service work orders and predicts 95598 work order by divided rank
The probability of subsequent complaint behavior is generated, so that the business personnel of effectively auxiliary power company generates according to 95598 different work orders
The probability of subsequent complaint behavior, the value-added service of a kind of differentiation provided, to promote Electricity customers service level, further
Reduction by 95598 client service center of power supply company, which is repeated the probability of complaint and reduces power customer, further dials 12398 Electricity Monitoring Commissions
A possibility that phone call for appeal.
Detailed description of the invention
It, below will be to attached drawing needed in embodiment description in order to illustrate more clearly of technical solution of the present invention
It is briefly described, it should be apparent that, the accompanying drawings in the following description is only one embodiment of the present of invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart of the potential complained appraisal procedure of 95598 customer service work orders of the invention；
Fig. 2 is a kind of structural schematic diagram of the potential complained assessment device of 95598 customer service work orders of the invention；
Wherein: 101- work order label model, 102- user tag module, 103- system construction module, 104- model construction
Module, 105- Optimized model construct module.
Specific embodiment
With reference to the attached drawing in the embodiment of the present invention, the technical solution in the present invention is clearly and completely described,
Obviously, described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Based in the present invention
Embodiment, those of ordinary skill in the art's every other embodiment obtained without creative labor,
It shall fall within the protection scope of the present invention.
As shown in Figure 1, a kind of potential complained appraisal procedure of 95598 customer service work order provided by the present invention include with
Lower step:
S10, the work order label that user power utilization behavior can be embodied from 95598 work order data decimations, work order label includes: work
Single class of service, work order second level classification, work order three-level classification, electricity consumption season, electricity consumption weather, electricity consumption there and then temperature are (Celsius
Degree) and TT processing duration (minute).
Work order class of service include: electricity consumption business, consulting inquiry, subscription information, troublshooting, it is other, suggest, praise,
Complaint, report and opinion.
Work order second level classification includes: that work order is pressed, demand cancellation, general demand work order, inquires and stop power transmission, recording, checking, and charging, electricity
Energy metering, power grid construction and safety, services channels, the inquiry of client's essential information, arrearage power failure, industry expand business, subscription information, take
Disappear subscription, low pressure power failure, electric voltage exception, high pressure power failure, power supply facilities failure, other repairing business, return visit client, internal connection
Press, interior business link up, other, power grid construction, power supply safety, customer service, other suggestion, new energy, business business, take
Business attitude, efficiency of service, other, professional skill, meter reading charging, electrical energy measurement, power grid construction, appeal of service, power supply safety, confession
Electricity quality, the repairing that has a power failure, Business Process System, other report, stealing, promise breaking (confession) electricity, power grid construction, power supply safety, power supply matter
Amount pays a return visit opinion, customer service, stops power transmission opinion and business business.
Work order three-level classification include: outlet consulting, forward call/user get the wrong number, without contact client processing,
Client pay a return visit successfully, need to contact client's subsequent processing, the electricity price electricity charge, quality of voltage, industry expand work order returns visit, new clothes increase-volume, power
Facility, power supply reliability need to contact client's subsequent processing, electrical energy measurement and electricity consumption change.
The summary table of work order class of service, work order second level classification and work order three-level classification is as shown in table 1.
Table 1: the summary table of work order class of service, work order second level classification and work order three-level classification
S20, selection can embody user power utilization behavior from the power consumer database of power marketing management information system
User tag, user tag include: address section, voltage class (volt), electricity consumption classification, line name, platform area title and
Networking duration (year).
S30, it is carried out according to the work order label and corresponding with the 95598 work order data customer name of user tag
With obtaining 95598 work order integrated information label systems.95598 work order integrated information label system tables are as shown in table 2.
Table 2:95598 work order integrated information label system table
S40, according to the customer complaint behavior of 95598 work order integrated information label system construction, the 95598 work order data
Analysis model obtains the complaint marking L of 95598 work order v according to the customer complaint Analysis model of network behaviors of 95598 work order data:
In formula (1), L is the complaint marking value of 95598 work order v, and M is marking factor set；ε is independent departure；Xj
It is the scoring of the grading factor j of 95598 work order v；βjIt is recurrence corresponding to the grading factor j using spline curve smooth treatment
The calculating of coefficient, the regression coefficient is as follows:
In formula (2) and formula (3),It is the base for indicating linear spline function, k is the segments of linear spline function,It is the functional value of rightmost side point in the range of linear spline function,
βj1And βjKIt is the value of the left and right ends in section where linear spline function, k-s3Be piecewise function subtract one it is normal less than 1
Number, s3It is a constant between [0,1], k-sKβIt is that segments subtracts a constant less than 1, sKβBe one between [0,1] often
Number.
S50, the customer complaint Analysis model of network behaviors optimized regression coefficient based on 95598 work order data obtain optimum regression system
Number, optimum regression coefficient calculate as follows:
S501, the user that 95598 work order data are obtained according to the customer complaint Analysis model of network behaviors of 95598 work order data throw
Tell that the grading stability goal function of behavior, grading stability goal function are as follows:
In formula (4),The grading stationary value that a possibility that complaint potential for work order grades, N are the works assessed
Odd number amount,Indicating being averaged for N number of number, L is the complaint marking value of 95598 work order v,It is the phase of the 95598 potential complaints of work order v
Prestige value；
S502, the user that 95598 work order data are obtained according to the customer complaint Analysis model of network behaviors of 95598 work order data throw
Tell that the grading otherness objective function of behavior, grading otherness objective function are as follows:
In formula (5),The difference value that a possibility that being work order potential complaint grades, N is the work order number assessed
Amount,Indicating being averaged for N-1 number, L is the complaint marking value of 95598 work order v,It is that the potential complaint of 95598 work order v may
The average value of property,It is average valueSquare；
S503, multi-objective constrained optimization is formed according to the grading stability goal function and grading otherness objective function
Problem, multi-objective constrained optimization problem are as follows:
In formula (6),The grading stationary value that a possibility that complaint potential for work order grades,For the potential complaint of work order
The difference value of possibility grading, β are optimum regression coefficient；
S504, single-object problem is converted for multi-objective constrained optimization problem by optimization algorithm, to obtain most
Excellent regression coefficient β；
The customer complaint Analysis model of network behaviors that optimal 95598 work order data are constructed based on optimum regression coefficient, is made optimal
The customer complaint Analysis model of network behaviors of 95598 work order data makes more acurrate, utilizes the customer complaint row of optimal 95598 work order data
95598 customer service work orders are scored to obtain real-time score value for analysis model；The customer complaint row of optimal 95598 work order data
Divided rank is carried out to score value in advance for analysis model, four grades are divided into according to score value from high to low: very satisfied,
It is satisfied, be satisfied in the main and be unsatisfied with, and each grade corresponds to the probability that client can further complain, very satisfied, ratio
Probability that is relatively satisfactory, being satisfied in the main and be unsatisfied with the corresponding client of this corresponding work order of four grades and can further complain successively rises
It is high；Grade where real-time score value is divided by the customer complaint Analysis model of network behaviors of optimal 95598 work order data, passes through division
A possibility that grade can determine the probability that can generate subsequent complaint, i.e., user generates subsequent complaint.
As shown in Fig. 2, the potential complained assessment device of the present invention 95598 customer service work orders of one kind, comprising: work order label
Module 101, user tag module 102, system construction module 103, model construction module 104 and Optimized model construct module
105.In the potential complained assessment to 95598 customer service work orders, firstly, work order label model 101 is from 95598 work order data
Choose the work order label that can embody user power utilization behavior, electricity of the user tag module 102 from power marketing management information system
The user tag that can embody user power utilization behavior is chosen in power customer data base；Secondly, system construction module 103 is according to work order
Label and user tag customer name corresponding with 95598 work order data are matched to obtain 95598 work order integrated information labels
System；Then, model construction module 104 is according to the users of 95598 work order integrated information label system construction, 95598 work order data
Complain Analysis model of network behaviors；Finally, Optimized model constructs module 105 according to the customer complaint behavioural analysis of 95598 work order data
Model optimization regression coefficient obtains optimum regression coefficient, and the user of optimal 95598 work order data is constructed based on optimum regression coefficient
Complain Analysis model of network behaviors, using optimal 95598 work order data customer complaint Analysis model of network behaviors to 95598 customer service work orders into
Row scoring and divided rank, the score value obtained by scoring and divided rank judgement can generate the probability of subsequent complaint.Specifically
, the specific works content of modules, refers to the content of corresponding embodiment of the method in the present embodiment, no longer superfluous herein
It states.
Above disclosed is only a specific embodiment of the invention, but scope of protection of the present invention is not limited thereto,
Anyone skilled in the art in the technical scope disclosed by the present invention, can readily occur in variation or modification,
It is covered by the protection scope of the present invention.
Claims (7)
1. a kind of potential complained appraisal procedure of 95598 customer service work orders, it is characterised in that: the following steps are included:
S10, the work order label that user power utilization behavior can be embodied from 95598 work order data decimations；
S20, the use that can embody user power utilization behavior is chosen from the power consumer database of power marketing management information system
Family label；
S30, match according to the work order label and user tag customer name corresponding with the 95598 work order data
To 95598 work order integrated information label systems；
S40, according to the customer complaint behavioural analysis of 95598 work order integrated information label system construction, the 95598 work order data
Model；
S50, the customer complaint Analysis model of network behaviors optimized regression coefficient based on the 95598 work order data obtain optimum regression system
Number, the customer complaint Analysis model of network behaviors of optimal 95598 work order data is constructed based on optimum regression coefficient, utilizes optimal 95598
The customer complaint Analysis model of network behaviors of work order data carries out scoring and divided rank to 95598 customer service work orders, is obtained by scoring
Score value and divided rank judgement can generate the probability of subsequent complaint.
2. the potential complained appraisal procedure of 95598 customer service work order according to claim 1, it is characterised in that: described
Work order label includes: that work order class of service, work order second level classification, work order three-level classification, electricity consumption season, electricity consumption weather, electricity consumption are worked as
When local temperature and TT processing duration.
3. the potential complained appraisal procedure of 95598 customer service work order according to claim 1, it is characterised in that: described
User tag includes: address section, voltage class, electricity consumption classification, line name, platform area title and networking duration.
4. the potential complained appraisal procedure of 95598 customer service work order according to claim 1, it is characterised in that: according to
The customer complaint Analysis model of network behaviors of the 95598 work order data obtains the complaint marking L of 95598 work order v:
In formula (1), L is the complaint marking value of 95598 work order v, and M is marking factor set；ε is independent departure；XjIt is
The scoring of the grading factor j of 95598 work order v；βjIt is recurrence system corresponding to the grading factor j using spline curve smooth treatment
Number, the calculating of the regression coefficient are as follows:
In formula (2) and formula (3),It is the base for indicating linear spline function, k is the segments of linear spline function, It is the functional value of rightmost side point in the range of linear spline function, βj1
And βjKIt is the value of the left and right ends in section where linear spline function, k-s3It is that piecewise function subtracts a constant less than 1,
s3It is a constant between [0,1], k-sKβIt is that segments subtracts a constant less than 1, sKβIt is a constant between [0,1].
5. the potential complained appraisal procedure of 95598 customer service work order according to claim 1, it is characterised in that: described
The calculating process of optimum regression coefficient are as follows: obtain 95598 by the customer complaint Analysis model of network behaviors of the 95598 work order data
The grading of the customer complaint behavior of the grading stability goal function of the customer complaint behavior of work order data and 95598 work order data
Otherness objective function；It is excellent that multi-objective restriction is formed according to the grading stability goal function and grading otherness objective function
Change problem；Single-object problem is converted by the multi-objective constrained optimization problem by optimization algorithm, to obtain optimal
Regression coefficient.
6. the potential complained appraisal procedure of 95598 customer service work order according to claim 5, it is characterised in that:
The grading stability goal function is as follows:
In formula (4),The grading stationary value that a possibility that complaint potential for work order grades, N are the work order numbers assessed
Amount,Indicating being averaged for N number of number, L is the complaint marking value of 95598 work order v,It is the expectation of the 95598 potential complaints of work order v
Value；
The grading otherness objective function is as follows:
In formula (5),The difference value that a possibility that being work order potential complaint grades, N is the work order quantity assessed,Indicating being averaged for N-1 number, L is the complaint marking value of 95598 work order v,It is the potential complaint possibility of 95598 work order v
Average value,It is average valueSquare；
The multi-objective constrained optimization problem are as follows:
In formula (6),The grading stationary value that a possibility that complaint potential for work order grades,For the possibility of the potential complaint of work order
Property grading difference value, β be optimum regression coefficient.
7. a kind of potential complained assessment device of 95598 customer service work orders, it is characterised in that: include:
Work order label model, for the work order label of user power utilization behavior can be embodied from 95598 work order data decimations；
User tag module can embody user for choosing from the power consumer database of power marketing management information system
The user tag of electricity consumption behavior；
System construction module, for according to the work order label and user tag client corresponding with the 95598 work order data
Title is matched to obtain 95598 work order integrated information label systems；
Model construction module, for the user according to 95598 work order integrated information label system construction, the 95598 work order data
Complain Analysis model of network behaviors；And
Optimized model constructs module, for the customer complaint Analysis model of network behaviors optimized regression according to the 95598 work order data
Coefficient obtains optimum regression coefficient, and the customer complaint behavioural analysis of optimal 95598 work order data is constructed based on optimum regression coefficient
Model is scored and is divided to 95598 customer service work orders using the customer complaint Analysis model of network behaviors of optimal 95598 work order data
Grade, the score value obtained by scoring and divided rank judgement can generate the probability of subsequent complaint.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810610029.XA CN109165763B (en) | 2018-06-13 | 2018-06-13 | Method and device for evaluating potential complaints of power grid customer service work order |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810610029.XA CN109165763B (en) | 2018-06-13 | 2018-06-13 | Method and device for evaluating potential complaints of power grid customer service work order |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109165763A true CN109165763A (en) | 2019-01-08 |
| CN109165763B CN109165763B (en) | 2021-12-07 |
Family
ID=64897087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810610029.XA Active CN109165763B (en) | 2018-06-13 | 2018-06-13 | Method and device for evaluating potential complaints of power grid customer service work order |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109165763B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110414819A (en) * | 2019-07-19 | 2019-11-05 | 中国电信集团工会上海市委员会 | A kind of work order methods of marking |
| CN111126783A (en) * | 2019-11-29 | 2020-05-08 | 广东电网有限责任公司 | Customer complaint risk rating method and device based on big data |
| CN111178957A (en) * | 2019-12-23 | 2020-05-19 | 广西电网有限责任公司 | Method for early warning sudden increase of electric quantity of electricity consumption customer |
| CN111353792A (en) * | 2020-05-25 | 2020-06-30 | 广东电网有限责任公司惠州供电局 | Client portrait system with visual display and data analysis functions |
| CN111489095A (en) * | 2020-04-15 | 2020-08-04 | 腾讯科技（深圳）有限公司 | Risk user management method and device, computer equipment and storage medium |
| CN112446615A (en) * | 2020-11-26 | 2021-03-05 | 深圳供电局有限公司 | Method for evaluating priority of uninterrupted operation |
| CN112529630A (en) * | 2020-12-17 | 2021-03-19 | 国网河北省电力有限公司营销服务中心 | Construction method of multi-dimensional informatization label system of power consumer |
| CN112991049A (en) * | 2021-04-13 | 2021-06-18 | 重庆度小满优扬科技有限公司 | Loan information processing method and electronic device |
| CN113254644A (en) * | 2021-06-07 | 2021-08-13 | 成都数之联科技有限公司 | Model training method, non-complaint work order processing method, system, device and medium |
| CN114240225A (en) * | 2021-12-23 | 2022-03-25 | 国网山东省电力公司东营供电公司 | Power system operation evaluation method and system under source network load storage multivariate cooperative interaction |
| CN115481925A (en) * | 2022-10-12 | 2022-12-16 | 中邮消费金融有限公司 | Customer service early warning method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104680428A (en) * | 2015-03-16 | 2015-06-03 | 朗新科技股份有限公司 | Construction method of power grid customer satisfaction model |
| CN107240033A (en) * | 2017-06-07 | 2017-10-10 | 国家电网公司客户服务中心 | The construction method and system of a kind of electric power identification model |
| CN107437124A (en) * | 2017-07-20 | 2017-12-05 | 大连大学 | A kind of operator based on big data analysis complains and trouble correlation analytic method |
| CN107992609A (en) * | 2017-12-15 | 2018-05-04 | 广东电网有限责任公司信息中心 | A kind of complaint tendency determination methods based on Text Classification and decision tree |
-
2018
- 2018-06-13 CN CN201810610029.XA patent/CN109165763B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104680428A (en) * | 2015-03-16 | 2015-06-03 | 朗新科技股份有限公司 | Construction method of power grid customer satisfaction model |
| CN107240033A (en) * | 2017-06-07 | 2017-10-10 | 国家电网公司客户服务中心 | The construction method and system of a kind of electric power identification model |
| CN107437124A (en) * | 2017-07-20 | 2017-12-05 | 大连大学 | A kind of operator based on big data analysis complains and trouble correlation analytic method |
| CN107992609A (en) * | 2017-12-15 | 2018-05-04 | 广东电网有限责任公司信息中心 | A kind of complaint tendency determination methods based on Text Classification and decision tree |
Non-Patent Citations (1)
| Title |
|---|
| ALIREZA FAED .ETC: "Intelligent customer complaint handling utilising principal component and data envelopment analysis", 《APPLIED SOFT COMPUTING》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110414819B (en) * | 2019-07-19 | 2023-05-26 | 中国电信集团工会上海市委员会 | Work order scoring method |
| CN110414819A (en) * | 2019-07-19 | 2019-11-05 | 中国电信集团工会上海市委员会 | A kind of work order methods of marking |
| CN111126783A (en) * | 2019-11-29 | 2020-05-08 | 广东电网有限责任公司 | Customer complaint risk rating method and device based on big data |
| CN111178957B (en) * | 2019-12-23 | 2023-04-14 | 广西电网有限责任公司 | Method for early warning sudden increase of electric quantity of electricity consumption customer |
| CN111178957A (en) * | 2019-12-23 | 2020-05-19 | 广西电网有限责任公司 | Method for early warning sudden increase of electric quantity of electricity consumption customer |
| CN111489095A (en) * | 2020-04-15 | 2020-08-04 | 腾讯科技（深圳）有限公司 | Risk user management method and device, computer equipment and storage medium |
| CN111489095B (en) * | 2020-04-15 | 2023-07-25 | 腾讯科技（深圳）有限公司 | Risk user management method, apparatus, computer device and storage medium |
| CN111353792A (en) * | 2020-05-25 | 2020-06-30 | 广东电网有限责任公司惠州供电局 | Client portrait system with visual display and data analysis functions |
| CN112446615A (en) * | 2020-11-26 | 2021-03-05 | 深圳供电局有限公司 | Method for evaluating priority of uninterrupted operation |
| CN112446615B (en) * | 2020-11-26 | 2023-10-20 | 深圳供电局有限公司 | Uninterrupted operation priority evaluation method |
| CN112529630A (en) * | 2020-12-17 | 2021-03-19 | 国网河北省电力有限公司营销服务中心 | Construction method of multi-dimensional informatization label system of power consumer |
| CN112991049A (en) * | 2021-04-13 | 2021-06-18 | 重庆度小满优扬科技有限公司 | Loan information processing method and electronic device |
| CN113254644A (en) * | 2021-06-07 | 2021-08-13 | 成都数之联科技有限公司 | Model training method, non-complaint work order processing method, system, device and medium |
| CN113254644B (en) * | 2021-06-07 | 2021-09-17 | 成都数之联科技有限公司 | Model training method, non-complaint work order processing method, system, device and medium |
| CN114240225A (en) * | 2021-12-23 | 2022-03-25 | 国网山东省电力公司东营供电公司 | Power system operation evaluation method and system under source network load storage multivariate cooperative interaction |
| CN115481925A (en) * | 2022-10-12 | 2022-12-16 | 中邮消费金融有限公司 | Customer service early warning method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109165763B (en) | 2021-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109165763A (en) | A kind of potential complained appraisal procedure and device of 95598 customer service work order | |
| CN105811402B (en) | A kind of Electric Load Prediction System and its Forecasting Methodology | |
| US7409303B2 (en) | Identifying energy drivers in an energy management system | |
| CN101266674A (en) | Method and system for determination of an appropriate strategy for supply of renewal energy onto a power grid | |
| Gerbec et al. | An approach to customers daily load profile determination | |
| JP2012010489A (en) | Simultaneous commensurate device, its control method, and its program | |
| CN113469486A (en) | Line negative loss and high loss analysis method | |
| JP2006011715A (en) | Estimation method for resource consumption, and device | |
| Alvisi et al. | Using water consumption smart metering for water loss assessment in a DMA: a case study | |
| Harder | Key performance indicators for smart grids master thesis on performance measurement for smart grids | |
| CN116611862A (en) | Prediction method for monthly marketized purchase electric quantity of power supply company | |
| Kühnbach et al. | How much energy autonomy can decentralised photovoltaic generation provide? A case study for Southern Germany | |
| CN104252647B (en) | Electro-load forecast method based on anti-distance weighting interpolation method | |
| CN116777616A (en) | Probability density distribution-based future market new energy daily transaction decision method | |
| JP2016213987A (en) | Electric power retailing charge menu planning apparatus | |
| Uppal et al. | Short term load forecasting through heat index biasing approach for smart grid sustainability | |
| CN112001551A (en) | Method for predicting electricity sales amount of power grid in city based on electricity information of large users | |
| CN116070781B (en) | Electric energy metering equipment demand prediction method and device and computer equipment | |
| CN117495429A (en) | Electricity selling management system for predicting electric quantity and method for predicting electric quantity | |
| CN107590571A (en) | A kind of power predicating method based on user behavior analysis | |
| JP2018156540A (en) | Prediction apparatus and prediction method | |
| Thackray et al. | THE SEVERN-TRENT STUDIES OF INDUSTRIAL WATER USE. | |
| Miller | Understanding how hourly approaches to emissions accounting and voluntary energy procurement can accelerate the decarbonization of the electric grid | |
| Pratt et al. | DSO+ T: Valuation Methodology and Economic Metrics (DSO+ T Study: Volume 4) | |
| Islam | Scrutiny of electricity data for consumption and load forecasting |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |