CN110111124A - Power customer service preference methods and system based on channel preference and business preference - Google Patents
Power customer service preference methods and system based on channel preference and business preference Download PDFInfo
- Publication number
- CN110111124A CN110111124A CN201910215906.8A CN201910215906A CN110111124A CN 110111124 A CN110111124 A CN 110111124A CN 201910215906 A CN201910215906 A CN 201910215906A CN 110111124 A CN110111124 A CN 110111124A
- Authority
- CN
- China
- Prior art keywords
- channel
- preference
- frequency
- service
- customer
- 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
- 238000000034 method Methods 0.000 title claims abstract description 18
- 239000011159 matrix material Substances 0.000 claims abstract description 21
- 230000001186 cumulative effect Effects 0.000 claims abstract description 6
- 108091006146 Channels Proteins 0.000 claims description 150
- 230000000694 effects Effects 0.000 claims description 74
- 238000004364 calculation method Methods 0.000 claims description 16
- 230000005611 electricity Effects 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 4
- 235000021167 banquet Nutrition 0.000 abstract 1
- 241001122767 Theaceae Species 0.000 description 9
- 238000004891 communication Methods 0.000 description 3
- 238000012546 transfer Methods 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000011272 standard treatment Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
-
- 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)
- Finance (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (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 belongs to grid service technical fields, and in particular to power customer service preference methods and system based on channel preference and business preference.Step 1 counts power grid client for the cumulative contact frequency X of different grid service channels1Frequency X is handled with for the accumulative of different electrical network business2；Step 2, respectively to power grid client for the cumulative contact frequency X of different grid service channels1Frequency X is handled with for the accumulative of different electrical network business2It is weighted；Step 3 is standardized the obtained different grid service channels weighting frequency, the different business weighting frequency after weighting, the channel liveness matrix for calculating the channel liveness of client according to liveness formula and being considered based on business respectively；Step 4, according to the value of power grid client's channel liveness, determine the preferred service channel of power grid user.The application can meet customer service and attend a banquet and fast, accurately and comprehensively understand customer priorities according to client's liveness, when customer in response demand.
Description
Technical Field
The invention belongs to the technical field of power grid service, and particularly relates to a power customer service preference method and system based on channel preference and business preference.
Background
The electric power hotline service system provides professional services such as business consultation, business acceptance and complaint suggestion related to business or work for the client in modes of manual work, automatic voice, short message, E-mail and the like, and is an exchange channel for external services of a company. The electric power hotline service provides service functions such as power failure information inquiry, fault repair, electricity charge inquiry and payment, business handling, business consultation, complaint report, manual service and the like. The customer service work faces thousands of households, the customer group is large and complex, and is limited by factors such as customer quality, communication modes and the like, and the customer service seat cannot quickly, accurately and comprehensively know the customer preference and cannot timely respond to the customer appeal.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides the power customer service preference method and the power customer service preference system based on channel preference and business preference, which can meet the requirements that a customer service agent can quickly, accurately and comprehensively know the customer preference and respond to the customer demands.
In order to realize the purpose, the invention is realized by the following technical scheme:
the invention provides a power customer service preference method based on channel preference and business preference, which is characterized in that:
step 1, counting accumulated contact frequency X of power grid customers to different power grid service channels1And accumulated transaction frequency X for different power grid services2；
Step 2, calculating time dimension weighting weight, and respectively carrying out cumulative contact frequency X on different power grid service channels by power grid customers1And accumulated transaction frequency X for different power grid services2Carrying out weighting;
step 3, respectively carrying out standardization processing on the weighted frequencies of the different power grid service channels and the weighted frequencies of the different services, and calculating the channel activity of the customer and a channel activity matrix based on service consideration according to an activity formula;
step 4, determining a preference service channel of the power grid user according to the value of the channel activity of the power grid customer; and determining the preference degrees of the customers to different channels under the premise of considering the business according to the channel activity degree matrix, wherein the channel with the maximum activity degree value is used as the preference service channel of the customers.
Further, in step 1, cumulative contact frequency of the grid customer to different grid service channels is counted to form X in a set form1Wherein X is1＝{x11,x12,x13......,x1nAnd counting the accumulated transaction frequency of the grid customers for different grid services to form X in a set form2Wherein X is2＝{x21,x22,x23......,x2n}。
Further, according to different filing times of different power grid customers, calculating a time dimension weighting weight:
further, the history record starting month is a time threshold, the current month is a handling time, and the filing month is before the handling time or on the same day.
Inquiring the customer filing time through the customer file information, respectively calculating the frequency of the power grid service channel and the service handling frequency of the customer according to the time threshold,
under the condition that the handling time is less than or equal to the time threshold, the weighting frequency of the client is the actual frequency;
under the condition that the handling time is greater than the time threshold, the weighting frequency of the client is the ratio of the actual frequency multiplied by the difference between the current time and the time threshold to the difference between the current month and the time threshold, and then the weighting frequency of the client is obtained;
recording weighted frequency X 'of different power grid service channels'1＝{x’11,x’12,x’13,......,x’1nX 'and different grid business weighted frequencies'2＝{x'21,x'22,x'23,......,x'2nX 'therein'1iAnd x'2jThe weighted frequencies of the 1i channel and the 2j traffic are respectively represented (i, j ═ 1,2,3,... times, n is a natural number).
Further, the mean value mu and the standard deviation sigma of each channel and business weighting frequency are calculated,
according to a standardized formulaTo the weighted frequency X'1＝{x’11,x’12,x’13,......,x’1nAnd X'2＝{x'21,x'22,x'23,......,x'2nStandardizing, wherein the values of X are respectively X'1、X'2The weighted frequency of (1); obtaining the normalized frequency X "1＝{x”11,x”12,x”13,......,x”1nAnd X "2＝{x”21,x”22,x”23,......,x”2n}。
Further, using liveness formulasCalculating the activity of a customer channel and the activity of a service of the power grid, wherein H represents the activity, x 'represents the standardized weighted frequency, and x'minRepresents the normalized weighted frequency minimum, x "maxRepresents a normalized weighted frequency maximum, (i ═ 1,2,3,. · m }, j ═ 1,2,3,... ·, n }, m, n are natural numbers);
integrating the service preference and channel preference of the customer to obtain an activity matrix D of the customer preference as follows,
wherein,Hijliveness, x, indicating the use of channels of the jth type for handling businesses of the ith type "ijNormalized weighted frequency, x' representing transacting ith traffic using jth channel "(ij)minNormalized weighted frequency minimum, x', representing all traffic transacted using channel j "(ij)maxThe normalized weighted frequency maximum of all traffic is handled using the jth channel, (i ═ 1,2, 3.·, m }, j ═ 1,2, 3.·, n }, m, n are natural numbers).
The invention also provides an electric power customer service preference analysis system based on channel preference and business preference, which is characterized in that:
the statistical module is used for counting the accumulated contact frequency of the power grid customer to different power grid service channels and the accumulated transaction frequency of different power grid services;
the data weighting module is used for weighting the accumulated contact frequency of the power grid customer channel and the accumulated handling frequency of the power grid business by using the time dimension weighting weight;
the data standardization module is used for carrying out standardization processing on the weighted frequency;
the activity calculation module is used for calculating the activity of the channel and the service activity of the power grid customer by using an activity formula and integrating the channel activity and the service activity results to generate an activity matrix;
and the preference determining module is used for determining the preference of the client according to the activity.
Further, the activity calculation module includes:
an acquisition unit for counting the contact frequency X of all users to different service channels1And different business handling frequency X2And all customers use the power grid service channel and handle the mean value mu and the standard deviation sigma of different businesses; a first calculating unit for calculating a weighted frequency X 'of the channel by using the weighted weight of the time dimension'1＝{x’11,x’12,x’13,......,x’1nAnd different traffic weighted frequencies X'2＝{x'21,x'22,x'23,......,x'2nX 'therein'1iAnd x'2jRespectively representing the weighted frequency of the 1i channel and the weighted frequency of the 2j service (i, j ═ 1,2,3,... times, n is a natural number);
a second calculation unit for calculating a second calculation value based on the normalization formulaTo the weighted frequency X'1＝{x’11,x’12,x’13,......,x’1nAnd X'2＝{x'21,x'22,x'23,......,x'2nStandardizing; wherein X is X'1、X'2The weighted frequency of (1); obtaining the normalized frequency X "1＝{x”11,x”12,x”13,......,x”1nAnd X "2＝{x”21,x”22,x”23,......,x”2n}；
A third computing unit using liveness formulaAnd calculating the channel activity and the service activity of the power grid customer.
Further, the preference determination module includes:
an output unit for outputting the activity data table of all users in different channels and the activity matrix D of different channels based on business consideration, as follows,
wherein,Hijindicating the liveness, x, of handling the ith service using the jth channelij"normalized weighted frequency, x, for handling ith traffic using jth channel"(ij)minNormalized weighted frequency minimum, x', representing all traffic transacted using channel j "(ij)maxUsing a normalized weighted frequency maximum for all traffic handled in a jth channel, (i ═ 1,2, 3.· m }, j ═ 1,2, 3.· n., n }, m, n are natural numbers);
the preference determining unit is used for determining a specific preferred channel according to the liveness of the user in different channels; the method is used for determining the preference degrees of the customers for different channels in the same service according to the channel activity matrix based on the service.
Compared with the prior art, the invention has the advantages that: the customer service preference is analyzed by utilizing big data, a data mining technology, customer electricity utilization behaviors, power grid production and operation activities and the correlation among customers, and intelligent information support is provided for a front-line customer service seat. Through the analysis of the user preference, when customer service personnel provide service for the customers, the customers can be quickly, accurately and comprehensively known, the customer demands can be responded in time, and the working efficiency is improved. The efficiency and the communication quality of the customer service and the customer are improved, the time cost of communication is reduced, and the working pressure of the customer service is reduced. Therefore, the electric power customer service preference analysis model based on the channel preference and the business preference can guide the customer to transfer the service channel, and the service cost of the electric power service channel is reduced; through the comparison and analysis of the electric power service channel deviation degree data tables corresponding to the business type customers, the electric power service channels preferred by the business type customers are found out, and therefore a strategy for guiding the customers to transfer to the low-cost service channels is formulated.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings.
The method for analyzing the service preference of the power customer comprises the following steps:
step 1, counting the contact frequency X of all users to different service channels1And different business handling frequency X2And all customers use the mean value mu and the standard deviation sigma of the power grid service channel and the business channel;
step 2, determining a weighted frequency X 'for calculating a channel by utilizing a time dimension weighted weight'1＝{x’11,x’12,x’13,......,x’1nAnd different traffic weighted frequencies X'2＝{x'21,x'22,x'23,......,x'2nX 'therein'1iAnd x'2jRespectively representing the weighted frequency of the 1i channel and the weighted frequency of the 2j service (i, j ═ 1,2,3,... times, n is a natural number);
step 3, is used for according to the standardized formulaTo the weighted frequency X'1＝{x’11,x’12,x’13,......,x’1nAnd X'2＝{x'21,x'22,x'23,......,x'2nStandardizing, wherein the values of X are respectively X'1、X'2The weighted frequency of (1); obtaining the normalized frequency X "1＝{x”11,x”12,x”13,......,x”1nAnd X "2＝{x”21,x”22,x”23,......,x”2n}；
Step 4, utilizing the liveness formulaCalculating the activity of a customer channel and the activity of a service of the power grid, wherein H represents the activity, x 'represents the standardized weighted frequency, and x'minRepresents the normalized weighted frequency minimum, x "maxRepresents a normalized weighted frequency maximum, (i ═ 1,2,3,. · m }, j ═ 1,2,3,... ·, n }, m, n are natural numbers);
and 5, repeating the processes from 1 to 4, calculating the activity indexes of all channels and services of all customers, and integrating the service activity indexes and the channel activity indexes to obtain a customer activity preference matrix.
The principle and the steps are explained in detail by embodiments:
step 1: inquiring the filing time of the client according to the client file information;
step 2: counting the contact frequency of each channel of all customers and the transaction frequency of each business through the detail information, 95598 incoming call information and payment information of the historical business transaction of the customers, and counting the effective initial month 201601 of the historical record;
and step 3: because some users are filed after 201601, the transaction frequency of channel contact services among all users is different based on time span, and the customer preference degree cannot be normally reflected when the customer preference is calculated, so the frequency of all users is weighted according to the time span;
and 4, step 4: calculating the mean value mu and the standard deviation sigma of each channel and business weighting frequency;
and 5: for according to a standardised formulaTo the weighted frequency X'1＝{x’11,x’12,x’13,......,x’1nAnd
X'2＝{x'21,x'22,x'23,......,x'2nthe standardization treatment is carried out, and the standard treatment is carried out,
step 6:
using formula of livenessAnd calculating the channel activity and the service activity of the power grid customer.
And 7: the integrated service liveness index and channel liveness index obtain a customer preference matrix D, as follows,
wherein,Hijindicating the liveness, x, of handling the ith service using the jth channelij"normalized weighted frequency, x, for handling ith traffic using jth channel"(ij)minNormalized weighted frequency minimum, x', representing all traffic transacted using channel j "(ij)maxThe normalized weighted frequency maximum of all traffic is handled using the jth channel, (i ═ 1,2, 3.·, m }, j ═ 1,2, 3.·, n }, m, n are natural numbers).
The technical scheme of the invention is explained through specific data description, and the specific analysis of customers is as follows:
given the customer base information data prior to analysis, the history records the starting month: 201601, current month, i.e. the time of transaction: 201810, overall time span 201810-.
The client profiling time is as follows in table 1. TABLE 1
| Customer | Filing month |
| Zhang three | 201505 |
| Li four | 201102 |
| Wangwu tea | 201706 |
The time span for calculating the customer history data is shown in table 2 below.
TABLE 2
| Customer | Time span (moon) |
| Zhang three | 34 |
| Li four | 34 |
| Wangwu tea | 17 |
Calculating the activity of a user channel
For the user channel liveness calculation, the customer channel exposure frequency is as follows in table 3.
TABLE 3
| Customer | Online business hall | 95598 | Business hall |
| Zhang three | 10 | 2 | 10 |
| Li four | 9 | 10 | 3 |
| Wangwu tea | 5 | 4 | 1 |
Step 1: calculating the contact weighted frequency of the customer channels:
taking the online business hall channels as an example, the filing time of Zhang III and Liqu are both earlier than the historical record starting month 201601, and the weighting frequency of the online business hall channels of Zhang III and Liqu is equal to the frequency;
the profiling time of Wang is later than the historical starting month 201601, and the weighted frequency is calculated as follows:
for example, the weighting frequency of the channels of the Wang Wu online business hall is
Through calculation, the weighting frequency table of each channel of the user is as follows:
| customer | Online business hall | 95598 | Business hall |
| Zhang three | 10 | 2 | 10 |
| Li four | 9 | 10 | 3 |
| Wangwu tea | 10 | 8 | 2 |
Step 2: the average value and the standard deviation of the weighted frequency of each channel are calculated, the calculation of the average value and the standard deviation is a conventional method in the field, a calculation formula is not separately given, and the obtained result is as follows:
| online business hall | 95598 | Business hall | |
| Mean value | 9.67 | 6.67 | 5 |
| Standard deviation of | 0.47 | 3.4 | 3.56 |
And step 3: normalized formula based on mean and varianceCarrying out weighted frequency normalization treatment:
and 4, step 4: calculating the liveness to obtain a liveness matrix
| Customer | Online business hall | 95598 | Business hall |
| Zhang three | 74.14 | 32.54 | 88.1 |
| Li four | 31.72 | 79.61 | 48.76 |
| Wangwu tea | 74.14 | 67.84 | 43.14 |
Secondly, calculating the channel liveness based on the business
Customer channel contact frequency
| Customer | Class of service | Online business hall | 95598 | Business hall |
| Zhang three | Paying fee | 10 | 2 | 10 |
| Zhang three | Inquiring electricity charge | 9 | 10 | 3 |
| Zhang three | Power off for consultation | 5 | 4 | 1 |
| Zhang three | Repair reporting device | 0 | 1 | 1 |
| Li four | Paying fee | 20 | 3 | 2 |
| Li four | Inquiring electricity charge | 5 | 5 | 0 |
| Li four | Power off for consultation | 0 | 1 | 2 |
| Li four | Repair reporting device | 1 | 0 | 0 |
| Wangwu tea | Paying fee | 11 | 0 | 0 |
| Wangwu tea | Inquiring electricity charge | 3 | 1 | 3 |
| Wangwu tea | Power off for consultation | 9 | 4 | 5 |
| Wangwu tea | Repair reporting device | 0 | 0 | 0 |
Step 1: counting the contact times of various services in each channel
| Class of service | Online business hall | 95598 | Business hall |
| Paying fee | 41 | 5 | 12 |
| Inquiring electricity charge | 17 | 16 | 6 |
| Power off for consultation | 14 | 9 | 8 |
| Repair reporting device | 1 | 1 | 1 |
Step 2: the mean and standard deviation of the weighted frequency of each channel are calculated, and the result is as follows
| Online business hall | 95598 | Business hall | |
| Mean value | 18.25 | 7.75 | 6.75 |
| Standard deviation of | 16.68 | 6.4 | 4.57 |
The traffic class does not need to consider the time span, so the degree of deviation is directly calculated.
And step 3: calculating the degree of deviation
| Class of service | Online business hall | 95598 | Business hall |
| Paying fee | 1.36 | -0.43 | 1.15 |
| Inquiring electricity charge | -0.07 | 1.29 | -0.16 |
| Power off for consultation | -0.25 | 0.2 | 0.27 |
| Repair reporting device | -1.03 | -1.06 | -1.26 |
And 4, step 4: calculating liveness
According to the channel activity matrix based on the service, the highest activity of the channels of the online business hall is found in the payment service, and the preferred channel is judged to be the online business hall when the client handles the payment service; the same can be obtained, the preference channel when the client transacts the service of inquiring the electric charge is 95598; when the client transacts the consultation power failure service, the preferred channel is a business hall; the preferred channel is the online business hall when the client transacts the repair business. Therefore, according to the channel activity matrix based on the service, the preference channel when the client transacts different services can be directly judged.
For the electric power customer service preference analysis model based on channel preference and business preference, the electric power customer service preference analysis model comprises the following steps:
the statistical module is used for counting the accumulated contact frequency of the power grid customer to different power grid service channels and the accumulated transaction frequency of different power grid services;
the data weighting module is used for weighting the accumulated contact frequency of the power grid customer channel and the accumulated handling frequency of the power grid business by using the time dimension weighting weight;
the data standardization module is used for carrying out standardization processing on the weighted frequency;
the activity calculation module is used for calculating the activity of the channel and the service activity of the power grid customer by using an activity formula and integrating the channel activity and the service activity results to generate an activity matrix;
and the preference determining module is used for determining the preference of the client according to the activity.
The liveness calculation module comprises:
an acquisition unit for counting the contact frequency X of all users to different service channels1And different business handling frequency X2And all customers use the power grid service channel and handle the mean value mu and the standard deviation sigma of different businesses; a first calculating unit for calculating a weighted frequency X 'of the channel by using the weighted weight of the time dimension'1＝{x’11,x’12,x’13,......,x’1nAnd different traffic weighted frequencies X'2＝{x'21,x'22,x'23,......,x'2nX 'therein'1iAnd x'2jRespectively representing the weighted frequency of the 1i channel and the weighted frequency of the 2j service (i, j ═ 1,2,3,... times, n is a natural number);
a second calculation unit for calculating a second calculation value based on the normalization formulaTo the weighted frequency X'1＝{x’11,x’12,x’13,......,x’1nAnd X'2＝{x'21,x'22,x'23,......,x'2nStandardizing; wherein X is X'1、X'2The weighted frequency of (1); obtaining the normalized frequency X "1＝{x”11,x”12,x”13,......,x”1nAnd X "2＝{x”21,x”22,x”23,......,x”2n}；
A third computing unit using liveness formulaAnd calculating the channel activity and the service activity of the power grid customer.
The preference determination module includes:
an output unit for outputting the activity data table of all users in different channels and the activity matrix D of different channels based on business consideration, as follows,
wherein,Hijindicating the liveness, x, of handling the ith service using the jth channelij"normalized weighted frequency, x, for handling ith traffic using jth channel"(ij)minNormalized weighted frequency minimum, x', representing all traffic transacted using channel j "(ij)maxUsing a normalized weighted frequency maximum for all traffic handled in a jth channel, (i ═ 1,2, 3.· m }, j ═ 1,2, 3.· n., n }, m, n are natural numbers);
the preference determining unit is used for determining a specific preferred channel according to the liveness of the user in different channels; the method is used for determining the preference degrees of the customers for different channels in the same service according to the channel activity matrix based on the service.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain a separate embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (9)
1. The electric power customer service preference method based on channel preference and business preference is characterized in that:
step 1, counting accumulated contact frequency X of power grid customers to different power grid service channels1And accumulated transaction frequency X for different power grid services2；
Step 2, calculating time dimension weighting weight, and respectively carrying out cumulative contact frequency X on different power grid service channels by power grid customers1And accumulated transaction frequency X for different power grid services2Carrying out weighting;
step 3, respectively carrying out standardization processing on the weighted frequencies of the different power grid service channels and the weighted frequencies of the different services, and calculating the channel activity of the customer and a channel activity matrix based on service consideration according to an activity formula;
step 4, determining a preference service channel of the power grid user according to the value of the channel activity of the power grid customer; and determining the preference degrees of the customers to different channels under the premise of considering the business according to the channel activity degree matrix, wherein the channel with the maximum activity degree value is used as the preference service channel of the customers.
2. The method of claim 1 for electricity customer service preference based on channel preference and business preference, wherein:
in step 1, cumulative contact frequency of the grid customer to different grid service channels is counted to form X in a set form1Wherein X is1＝{x11,x12,x13......,x1nAnd counting the accumulated transaction frequency of the grid customers for different grid services to form X in a set form2Wherein X is2＝{x21,x22,x23......,x2n}。
3. The method of claim 2 for electricity customer service preference based on channel preference and business preference, wherein:
according to different filing times of different power grid customers, calculating a time dimension weighting weight:
。
4. the method of claim 3 for electricity customer service preference based on channel preference and business preference, wherein:
the historical record starting month is a time threshold, the current month is a transaction time, and the filing month is before or on the day of the transaction time.
Inquiring the customer filing time through the customer file information, respectively calculating the frequency of the power grid service channel and the service handling frequency of the customer according to the time threshold,
under the condition that the handling time is less than or equal to the time threshold, the weighting frequency of the client is the actual frequency;
under the condition that the handling time is greater than the time threshold, the weighting frequency of the client is the ratio of the actual frequency multiplied by the difference between the current time and the time threshold to the difference between the current month and the time threshold, and then the weighting frequency of the client is obtained;
recording weighted frequency X 'of different power grid service channels'1＝{x′11,x′12,x′13,......,x′1nX 'and different grid business weighted frequencies'2＝{x'21,x'22,x'23,......,x'2nX 'therein'1iAnd x'2jThe weighted frequencies of the 1i channel and the 2j traffic are respectively represented (i, j ═ 1,2,3,... times, n is a natural number).
5. The method of claim 4 for electricity customer service preference based on channel preference and business preference, wherein: calculating the mean value mu and the standard deviation sigma of each channel and business weighting frequency,
according to a standardized formulaTo the weighted frequency X'1＝{x′11,x′12,x′13,......,x′1nAnd X'2＝{x'21,x'22,x'23,......,x'2nStandardizing, wherein the values of X are respectively X'1、X'2The weighted frequency of (1); obtaining the normalized frequency X "1＝{x″11,x″12,x″13,......,x″1nAnd X ″)2＝{x″21,x″22,x″23,......,x″2n}。
6. The method of claim 5 for electricity customer service preference based on channel preference and business preference, wherein: using formula of livenessCalculating the activity of a customer channel and the activity of a service of the power grid, wherein H represents the activity, x 'represents the standardized weighted frequency, and x'minRepresents the normalized weighted frequency minimum, x "maxRepresents a normalized weighted frequency maximum, (i ═ 1,2,3,. · m }, j ═ 1,2,3,... ·, n }, m, n are natural numbers);
integrating the service preference and channel preference of the customer to obtain an activity matrix D of the customer preference as follows,
wherein,Hijindicating the liveness, x, of handling the ith service using the jth channelij"normalized weighted frequency, x, for handling ith traffic using jth channel"(ij)minNormalized weighted frequency minimum, x', representing all traffic transacted using channel j "(ij)maxThe normalized weighted frequency maximum of all traffic is handled using the jth channel, (i ═ 1,2, 3.·, m }, j ═ 1,2, 3.·, n }, m, n are natural numbers).
7. An electric power customer service preference analysis system based on channel preference and business preference is characterized in that:
the statistical module is used for counting the accumulated contact frequency of the power grid customer to different power grid service channels and the accumulated transaction frequency of different power grid services;
the data weighting module is used for weighting the accumulated contact frequency of the power grid customer channel and the accumulated handling frequency of the power grid business by using the time dimension weighting weight;
the data standardization module is used for carrying out standardization processing on the weighted frequency;
the activity calculation module is used for calculating the activity of the channel and the service activity of the power grid customer by using an activity formula and integrating the channel activity and the service activity results to generate an activity matrix;
and the preference determining module is used for determining the preference of the client according to the activity.
8. The power customer service preference analysis system based on channel preferences and business preferences of claim 7 wherein:
the liveness calculation module comprises:
an acquisition unit for counting the contact frequency X of all users to different service channels1And different business handling frequency X2And all customers use the power grid service channel and handle the mean value mu and the standard deviation sigma of different businesses; a first calculating unit for calculating a weighted frequency X 'of the channel by using the weighted weight of the time dimension'1＝{x′11,x′12,x′13,......,x′1nAnd different traffic weighted frequencies X'2＝{x'21,x'22,x'23,......,x'2nX 'therein'1iAnd x'2jRespectively representing the weighted frequency of the 1i channel and the weighted frequency of the 2j service (i, j ═ 1,2,3,... times, n is a natural number);
a second calculation unit for calculating a second calculation value based on the normalization formulaTo the weighted frequency X'1＝{x′11,x′12,x′13,......,x′1nAnd X'2＝{x'21,x'22,x'23,......,x'2nStandardizing; wherein X is X'1、X'2The weighted frequency of (1); obtaining the normalized frequency X "1＝{x″11,x″12,x″13,......,x″1nAnd X ″)2＝{x″21,x″22,x″23,......,x″2n}；
A third computing unit using liveness formulaAnd calculating the channel activity and the service activity of the power grid customer.
9. The power customer service preference analysis system based on channel preferences and business preferences of claim 8 wherein:
the preference determination module includes:
an output unit for outputting the activity data table of all users in different channels and the activity matrix D of different channels based on business consideration, as follows,
wherein,Hijindicating the liveness, x, of handling the ith service using the jth channelij"normalized weighted frequency, x, for handling ith traffic using jth channel"(ij)minNormalized weighted frequency minimum, x', representing all traffic transacted using channel j "(ij)maxUsing a normalized weighted frequency maximum for all traffic handled in a jth channel, (i ═ 1,2, 3.· m }, j ═ 1,2, 3.· n., n }, m, n are natural numbers);
the preference determining unit is used for determining a specific preferred channel according to the liveness of the user in different channels; the method is used for determining the preference degrees of the customers for different channels in the same service according to the channel activity matrix based on the service.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910215906.8A CN110111124A (en) | 2019-03-21 | 2019-03-21 | Power customer service preference methods and system based on channel preference and business preference |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910215906.8A CN110111124A (en) | 2019-03-21 | 2019-03-21 | Power customer service preference methods and system based on channel preference and business preference |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110111124A true CN110111124A (en) | 2019-08-09 |
Family
ID=67484486
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910215906.8A Pending CN110111124A (en) | 2019-03-21 | 2019-03-21 | Power customer service preference methods and system based on channel preference and business preference |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110111124A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113435918A (en) * | 2020-03-19 | 2021-09-24 | 杭州大搜车汽车服务有限公司 | Method and device for determining maintenance strategy, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096825A (en) * | 2016-06-03 | 2016-11-09 | 广东电网有限责任公司 | A kind of electrical power services channel analysis method and system |
| CN106846163A (en) * | 2016-07-05 | 2017-06-13 | 国网内蒙古东部电力有限公司 | A kind of electric power payment channel overall analysis system |
| CN108898429A (en) * | 2018-06-19 | 2018-11-27 | 平安科技（深圳）有限公司 | Electronic device, preference tendency prediction technique and computer readable storage medium |
| CN111221868A (en) * | 2018-11-26 | 2020-06-02 | 国网上海市电力公司 | Data mining and analyzing method applied to channel preference of power customer |
-
2019
- 2019-03-21 CN CN201910215906.8A patent/CN110111124A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106096825A (en) * | 2016-06-03 | 2016-11-09 | 广东电网有限责任公司 | A kind of electrical power services channel analysis method and system |
| CN106846163A (en) * | 2016-07-05 | 2017-06-13 | 国网内蒙古东部电力有限公司 | A kind of electric power payment channel overall analysis system |
| CN108898429A (en) * | 2018-06-19 | 2018-11-27 | 平安科技（深圳）有限公司 | Electronic device, preference tendency prediction technique and computer readable storage medium |
| CN111221868A (en) * | 2018-11-26 | 2020-06-02 | 国网上海市电力公司 | Data mining and analyzing method applied to channel preference of power customer |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113435918A (en) * | 2020-03-19 | 2021-09-24 | 杭州大搜车汽车服务有限公司 | Method and device for determining maintenance strategy, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110110881B (en) | Power customer demand prediction analysis method and system | |
| CN110020777A (en) | A kind of power customer business worksheet system and method | |
| CN105760449B (en) | A kind of cloud method for pushing towards multi-source heterogeneous data | |
| WO2018209913A1 (en) | Distribution network station area power shortage prediction method based on voltage quality | |
| WO2008131656A1 (en) | Service processing method, apparatus of charging system and charging system | |
| CN111626614A (en) | User classification method based on electric charge recovery | |
| CN102487523A (en) | User compliant analysis method and device | |
| CN109993380A (en) | A kind of information processing method, device and computer readable storage medium | |
| CN111583008A (en) | Intelligent automatic charge cancellation system and method for electricity consumption customers | |
| CN114398941A (en) | User payment behavior classification method, device, equipment and readable storage medium | |
| CN111797145A (en) | Power customer tolerance evaluation classification method | |
| CN110111124A (en) | Power customer service preference methods and system based on channel preference and business preference | |
| CN114706827A (en) | Automatic generation method and device for transaction link topology | |
| CN110675069A (en) | Real estate industry client signing risk early warning method, server and storage medium | |
| CN114401158A (en) | Flow charging method and device, electronic equipment and storage medium | |
| CN113411453A (en) | Intelligent management method and device of outbound object, medium and computing equipment | |
| CN110705916B (en) | Method and system for judging small and micro load electric quantity of transformer | |
| CN115623130B (en) | Agent conversation service business distribution method and system | |
| CN115170153B (en) | Work order processing method and device based on multidimensional attribute and storage medium | |
| CN108985822A (en) | A kind of used equipment marketing price index generation method | |
| US8510152B1 (en) | System for capability assessment and development | |
| CN107580305A (en) | A kind of consumer member purity analysis method and system | |
| CN109359825B (en) | Bank digital operation product value analysis method | |
| WO2014094302A1 (en) | Method and device for judging user repeatedly accessing network | |
| CN112750020A (en) | Automatic tax guiding system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190809 |
|
| RJ01 | Rejection of invention patent application after publication |