CN111415060A - Complaint risk analysis method based on customer label - Google Patents

Complaint risk analysis method based on customer label Download PDF

Info

Publication number
CN111415060A
CN111415060A CN202010070843.4A CN202010070843A CN111415060A CN 111415060 A CN111415060 A CN 111415060A CN 202010070843 A CN202010070843 A CN 202010070843A CN 111415060 A CN111415060 A CN 111415060A
Authority
CN
China
Prior art keywords
complaint
customer
initial
distance
customers
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
Application number
CN202010070843.4A
Other languages
Chinese (zh)
Other versions
CN111415060B (en
Inventor
吕斌斌
王国帮
吴健
陆生兵
吴伟强
张旭东
陈昊
王龙
张明乐
邵力
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Tailun Power Group Co ltd
Changxing Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Original Assignee
Zhejiang Tailun Power Group Co ltd
Changxing Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang Tailun Power Group Co ltd, Changxing Power Supply Co of State Grid Zhejiang Electric Power Co Ltd filed Critical Zhejiang Tailun Power Group Co ltd
Priority to CN202010070843.4A priority Critical patent/CN111415060B/en
Publication of CN111415060A publication Critical patent/CN111415060A/en
Application granted granted Critical
Publication of CN111415060B publication Critical patent/CN111415060B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • 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
    • G06Q30/00—Commerce
    • G06Q30/01—Customer relationship services
    • G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
    • G06Q30/016—After-sales
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply

Abstract

The invention relates to the technical field of power system operation and maintenance, in particular to a complaint risk analysis method based on a customer label, which comprises the following steps: A) collecting customer data; B) collecting complaint data of all the years; C) clustering n customers, and associating a complaint type label for each cluster; D) sequentially calculating the distances from the user to the k class clusters; E) taking the reciprocal of the distance minimum as the initial risk of the customer for initiating complaints, and calculating the mean value mu and the variance sigma of the initial risk of all the customers; F) the risk of customer complaints is
Figure DDA0002377278820000011
The complaint type is predicted to be a complaint type associated with the class cluster. The substantial effects of the invention are as follows: the risk of customer complaints can be predicted, high-risk customers are found, and faults corresponding to the customers are preferably checked, so that the total number of complaints is reduced, the overall satisfaction degree of power grid customers is improved, the overall operation reliability of a power grid is improved, and the allocation of operation and maintenance resources is optimized.

Description

Complaint risk analysis method based on customer label
Technical Field
The invention relates to the technical field of operation and maintenance of power systems, in particular to a complaint risk analysis method based on a customer label.
Background
With the development of economy, the scale of the power grid is continuously enlarged, the number of power grid customers is rapidly increased, and the power consumption is also greatly increased. With the increase of enterprises, the load of the power grid is greatly increased, and meanwhile, higher requirements are placed on the power supply quality and stability of the power grid. In the process of greatly enlarging the power grid, the operation and maintenance resources of the power grid are relatively short, the operation and maintenance of partial equipment in the power grid are not timely, and the power supply abnormality of the user is caused. And the shortage of maintenance resources can lead to slow troubleshooting progress, and further lead to complaints of customers on the power grid. In order to improve the satisfaction degree of customers to the whole power grid, a method is needed for analyzing the faults or abnormalities which need to be processed most urgently, users which are most likely to initiate complaints are selected, and operation and maintenance resources are preferentially satisfied with the customers, so that the reliability of power supply of the power grid is improved on the whole, and the satisfaction degree of the customers is improved.
For example, chinese patent CN105095588B, published 2018, 7, month 3, a method and apparatus for predicting complaints of mobile internet users, the method comprising: acquiring internet surfing data records of a mobile internet user to be predicted in a statistical period; calculating a traffic usage data record corresponding to a mobile internet user to be predicted according to the internet access data record; calculating the complaint related characteristics corresponding to the mobile internet user to be predicted according to the flow usage record, the historical complaint data record, the package and the service order data record corresponding to the mobile internet user to be predicted in the statistical period; inputting the relevant complaint characteristics into the verified complaint prediction model, and acquiring a complaint risk value of the mobile internet user to be predicted; and outputting the complaint risk value and the complaint related characteristics of the mobile internet user to be predicted. The method and the system reduce the number of complaints of the mobile internet users, predict the possible complaint content of each complaint user and accelerate the complaint processing speed. It is not suitable for complaint prediction of grid customers.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the technical problem of the prior complaint prediction method for power grid customers is lacked. The method can predict the risk of customer complaint initiation and possible complaint types, so that reference is provided for complaint handling, complaint handling is accelerated, and the overall satisfaction degree of power grid customers is improved.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: the complaint risk analysis method based on the customer label comprises the following steps: A) customer data is collected, each customer being represented by a vector x ═ a1,a2,…,ad) Description, d is the customer label dimension; B) collecting complaint data of all years, wherein n customers x1,…xnComplaints have been made about power supply services; C) clustering n customers to obtain C1,…CkK types of clusters are provided, and complaint type labels are associated with each class cluster; D) for any one client xi,i∈[1,n]Sequentially calculating xiDistance to k clusters of classes
Figure BDA0002377278800000021
E) Will be provided with
Figure BDA0002377278800000027
Reciprocal of minimum value of (1)
Figure BDA0002377278800000022
Figure BDA0002377278800000023
As a client xiAn initial risk of initiating a complaint; the initial risk of complaints from all customers is f1,f2,…,fnCalculating the mean value mu and the variance sigma thereof; F) customer xiThe risk of initiating a complaint is
Figure BDA0002377278800000024
The complaint type is predicted to
Figure BDA0002377278800000025
Cluster the associated complaint type for the smallest value of (1).
Preferably, in the step a), the customer vector is customer type, annual power consumption, annual average load rate of the local area, power failure times, power failure loss degree and historical payment data.
Preferably, in the step a), the customer vector further includes a urbanization rate, a car retention rate and a number of tourists in the area where the customer is located.
Preferably, in step C), the method for clustering n customers includes: C1) randomly extracting m sample points from all data points to form a sampling data set; C2) estimating an optimized density parameter d using a sampled data setc(ii) a C3) Carrying out grid division on the space by a set scale; C4) calculating the local density of all data points; C5) calculating the high density of all sample points according to the sequence of the local density from large to smallNearest neighbor distance; C6) determining a subset of samples representing a cluster center; C7) and iteratively dividing all the non-central sample points to corresponding clustering centers along the nearest neighbor direction of the density estimation value increment, thereby realizing the division of the data into a plurality of clusters.
Preferably, step C3), to
Figure BDA0002377278800000026
The space is gridded for scale.
Preferably, in step C5), the method for calculating the high-density nearest neighbor distances of all the sample points includes: C51) determining a local high density center; C52) and calculating the distance between each sample point and the local high-density center thereof, namely the high-density nearest neighbor distance thereof.
Preferably, in step C51), the method for determining the local high-density center includes: C511) randomly selecting the sample points with the distance less than a set first threshold dsThe plurality of sample points of (2) constitute an initial part; C512) calculating the central point x 'of the initial part, wherein the mean value Ψ of the distances from the central point x' of the initial part to each sample point in the initial part is the minimum, and the obtained mean value is denoted as Ψ0(ii) a C513) Taking the central point x ' of the initial local part as the center, selecting the distance between the central point x ' of the initial local part and the central point x ' of the initial local part to be less than a set second threshold value daSequentially adding sample points to calculate a distance mean psi according to the sequence of the distance from the near to the far from the initial local central point x'; C514) if a sample point is added, the mean Ψ exceeds the threshold k Ψ0K is a threshold coefficient, k>1, all the points participating in the mean calculation are included in the initial part, the step C512) is returned to re-determine the central point x ' of the initial part, and the steps C513) to C514) are re-executed until the distance from the central point x ' of the initial part to the central point x ' of the initial part is less than the set second threshold d)aWhen all the sample points participate in calculating the distance mean, the mean Ψ does not exceed the threshold k Ψ0The initial local center point x' at this time is set as a local high-density center.
Preferably, in step C), the method for associating the complaint type label for each cluster is as follows: and counting historical complaint data of all sample points in the cluster, wherein the complaint type with the most complaint types is the complaint type associated with the cluster.
Preferably, in step C), the complaint types include: power supply business, power supply service, power supply quality, power outage and transmission complaints, service complaints, power grid construction and business complaints.
Preferably, in step D), x is calculatediTo cluster Cj,j∈[1,k]Distance d ofijThe method comprises the following steps:
Figure BDA0002377278800000031
wherein, dist (x)i,yi) Is xiAnd yiThe euclidean distance of (c).
The substantial effects of the invention are as follows: the risk of customer complaints can be predicted, high-risk customers are found, and faults corresponding to the customers are preferably checked, so that the total number of complaints is reduced, the overall satisfaction degree of power grid customers is improved, the overall operation reliability of a power grid is improved, and the allocation of operation and maintenance resources is optimized.
Drawings
FIG. 1 is a flow chart of a complaint risk analysis method according to an embodiment.
FIG. 2 is a block diagram illustrating a clustering method according to an embodiment.
Fig. 3 is a block diagram of a high density nearest neighbor distance method according to an embodiment.
FIG. 4 is a flowchart illustrating a method for determining a local high density center according to an embodiment.
Detailed Description
The following provides a more detailed description of the present invention, with reference to the accompanying drawings.
The first embodiment is as follows:
as shown in fig. 1, the method for analyzing complaint risk based on a customer label includes the following steps: A) customer data is collected, each customer being represented by a vector x ═ a1,a2,…,ad) Description, d is the customer label dimension; B) collecting complaint data of all years, wherein n customers x1,…xnComplaints have been made about power supply services; C) clustering n customers to obtain C1,…CkK types of clusters are provided, and complaint type labels are associated with each class cluster; D) for any one client xi,i∈[1,n]Sequentially calculating xiDistance to k clusters of classes
Figure BDA0002377278800000032
E) Will be provided with
Figure BDA0002377278800000046
Reciprocal of minimum value of (1)
Figure BDA0002377278800000041
As a client xiAn initial risk of initiating a complaint; the initial risk of complaints from all customers is f1,f2,…,fnCalculating the mean value mu and the variance sigma thereof; F) customer xiThe risk of initiating a complaint is
Figure BDA0002377278800000042
The complaint type is predicted to
Figure BDA0002377278800000045
Cluster the associated complaint type for the smallest value of (1). In step D), x is calculatediTo cluster Cj,j∈[1,k]Distance d ofijThe method comprises the following steps:
Figure BDA0002377278800000043
wherein, dist (x)i,yi) Is xiAnd yiThe euclidean distance of (c).
In the step A), the customer vector is customer type, annual power consumption, annual average load rate of a platform area, power failure times, power failure loss degree, historical payment data, urbanization rate of the area where the customer is located, automobile retention rate and tourist number proportion.
As shown in fig. 2, in step C), the method for clustering n customers includes: C1) randomly extracting m sample points from all data points to form a sampling data set; C2) estimation with sampled data setsOptimizing the Density parameter dc(ii) a C3) To be provided with
Figure BDA0002377278800000044
Meshing the space for a scale; C4) calculating the local density of all data points; C5) calculating the high-density nearest neighbor distances of all the sample points according to the sequence of the local densities from large to small; C6) determining a subset of samples representing a cluster center; C7) and iteratively dividing all the non-central sample points to corresponding clustering centers along the nearest neighbor direction of the density estimation value increment, thereby realizing the division of the data into a plurality of clusters. The method for associating the complaint type label for each cluster comprises the following steps: and counting historical complaint data of all sample points in the cluster, wherein the complaint type with the most complaint types is the complaint type associated with the cluster. The complaint types include: power supply business, power supply service, power supply quality, power outage and transmission complaints, service complaints, power grid construction and business complaints.
As shown in fig. 3, in step C5), the method for calculating the high-density nearest neighbor distances of all the sample points includes: C51) determining a local high density center; C52) and calculating the distance between each sample point and the local high-density center thereof, namely the high-density nearest neighbor distance thereof.
As shown in fig. 4, in step C51), the method for determining the local high-density center includes: C511) randomly selecting the sample points with the distance less than a set first threshold dsThe plurality of sample points of (2) constitute an initial part; C512) calculating the central point x 'of the initial part, wherein the mean value Ψ of the distances from the central point x' of the initial part to each sample point in the initial part is the minimum, and the obtained mean value is denoted as Ψ0(ii) a C513) Taking the central point x ' of the initial local part as the center, selecting the distance between the central point x ' of the initial local part and the central point x ' of the initial local part to be less than a set second threshold value daSequentially adding sample points to calculate a distance mean psi according to the sequence of the distance from the near to the far from the initial local central point x'; C514) if a sample point is added, the mean Ψ exceeds the threshold k Ψ0K is a threshold coefficient, k>1, all the points participating in the mean calculation are included in the initial part, the step C512) is returned to determine the central point x' of the initial part again, and the steps C513) to C514 are executed again) Until the distance x' from the central point of the initial part is smaller than a set second threshold daWhen all the sample points participate in calculating the distance mean, the mean Ψ does not exceed the threshold k Ψ0The initial local center point x' at this time is set as a local high-density center.
The above-described embodiments are only preferred embodiments of the present invention, and are not intended to limit the present invention in any way, and other variations and modifications may be made without departing from the spirit of the invention as set forth in the claims.

Claims (8)

1. The complaint risk analysis method based on the customer label is characterized in that,
the method comprises the following steps:
A) customer data is collected, each customer being represented by a vector x ═ a1,a2,…,ad) Description, d is the customer label dimension;
B) collecting complaint data of all years, wherein n customers x1,…xnComplaints have been made about power supply services;
C) clustering n customers to obtain C1,…CkK types of clusters are provided, and complaint type labels are associated with each class cluster;
D) for any one client xi,i∈[1,n]Sequentially calculating xiDistance to k clusters of classes
Figure FDA0002377278790000011
E) Will be provided with
Figure FDA0002377278790000012
Reciprocal of minimum value of (1)
Figure FDA0002377278790000013
As a client xiAn initial risk of initiating a complaint;
the initial risk of complaints from all customers is f1,f2,…,fnCalculating the mean value mu and the variance sigma thereof;
F) customerxiThe risk of initiating a complaint is
Figure FDA0002377278790000014
The complaint type is predicted to
Figure FDA0002377278790000015
Cluster the associated complaint type for the smallest value of (1).
2. The customer label-based complaint risk analysis method according to claim 1,
in the step A), the customer vector is customer type, annual power consumption, annual average load rate of a transformer area, power failure times, power failure loss degree and historical payment data.
3. The customer label-based complaint risk analysis method according to claim 1 or 2,
in the step C), the method for clustering n customers comprises the following steps:
C1) randomly extracting m sample points from all data points to form a sampling data set;
C2) estimating an optimized density parameter d using a sampled data setc；
C3) Carrying out grid division on the space by a set scale;
C4) calculating the local density of all data points;
C5) calculating the high-density nearest neighbor distances of all the sample points according to the sequence of the local densities from large to small;
C6) determining a subset of samples representing a cluster center;
C7) and iteratively dividing all the non-central sample points to corresponding clustering centers along the nearest neighbor direction of the density estimation value increment, thereby realizing the division of the data into a plurality of clusters.
4. The customer label-based complaint risk analysis method according to claim 3,
in step C3), in order to
Figure FDA0002377278790000016
The space is gridded for scale.
5. The customer label-based complaint risk analysis method according to claim 3,
in step C5), the method for calculating the high-density nearest neighbor distances of all the sample points includes:
C51) determining a local high density center;
C52) and calculating the distance between each sample point and the local high-density center thereof, namely the high-density nearest neighbor distance thereof.
6. The customer label-based complaint risk analysis method according to claim 5,
in step C51), the method for determining the local high-density center includes:
C511) randomly selecting the sample points with the distance less than a set first threshold dsThe plurality of sample points of (2) constitute an initial part;
C512) calculating the position of the central point x 'of the initial part, wherein the value of the mean value Ψ of the distances from the central point x' of the initial part to each sample point in the initial part is minimum, and the obtained mean value is recorded as Ψ0；
C513) Taking the central point x ' of the initial local part as the center, selecting the distance between the central point x ' of the initial local part and the central point x ' of the initial local part to be less than a set second threshold value daSequentially adding sample points to calculate a distance mean psi according to the sequence of the distance from the near to the far from the initial local central point x';
C514) if a sample point is added, the mean Ψ exceeds the threshold k Ψ0K is a threshold coefficient, k>1, all the points participating in the mean calculation are included in the initial part, the step C512) is returned to re-determine the central point x ' of the initial part, and the steps C513) to C514) are re-executed until the distance from the central point x ' of the initial part to the central point x ' of the initial part is less than the set second threshold d)aWhen all the sample points participate in calculating the distance mean, the mean psi is not exceededPassing threshold k Ψ0The initial local center point x' at this time is set as a local high-density center.
7. The method for complaint risk analysis based on customer labels as claimed in claim 1 or 2, wherein in step C), the method for associating a complaint type label for each cluster is as follows:
and counting historical complaint data of all sample points in the cluster, wherein the complaint type with the most complaint types is the complaint type associated with the cluster.
8. Customer label based complaint risk analysis method according to claim 1 or 2, characterized in that in step D) x is calculatediTo cluster Cj,j∈[1,k]Distance d ofijThe method comprises the following steps:
Figure FDA0002377278790000021
wherein, dist (x)i,yi) Is xiAnd yiThe euclidean distance of (c).
CN202010070843.4A 2020-01-21 2020-01-21 Complaint risk analysis method based on customer label Active CN111415060B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010070843.4A CN111415060B (en) 2020-01-21 2020-01-21 Complaint risk analysis method based on customer label

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010070843.4A CN111415060B (en) 2020-01-21 2020-01-21 Complaint risk analysis method based on customer label

Publications (2)

Publication Number Publication Date
CN111415060A true CN111415060A (en) 2020-07-14
CN111415060B CN111415060B (en) 2022-07-29

Family

ID=71493986

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010070843.4A Active CN111415060B (en) 2020-01-21 2020-01-21 Complaint risk analysis method based on customer label

Country Status (1)

Country Link
CN (1) CN111415060B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104484345A (en) * 2014-11-28 2015-04-01 广东工业大学 K-means cluster based extraction method of 3D scanning module of flame forming plate
CN106529804A (en) * 2016-11-09 2017-03-22 国网江苏省电力公司南京供电公司 Client complaint early-warning monitoring analyzing method based on text mining technology
CN106779497A (en) * 2017-01-25 2017-05-31 国家电网公司 Complaint risk appraisal procedure caused by a kind of fare payment system is out of service
CN107203916A (en) * 2016-03-17 2017-09-26 阿里巴巴集团控股有限公司 A kind of user credit method for establishing model and device
CN107220732A (en) * 2017-05-31 2017-09-29 福州大学 A kind of power failure complaint risk Forecasting Methodology based on gradient boosted tree
US20190050368A1 (en) * 2016-04-21 2019-02-14 Sas Institute Inc. Machine learning predictive labeling system
CN110348488A (en) * 2019-06-19 2019-10-18 华中科技大学 A kind of modal identification method based on local density's peak value cluster

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104484345A (en) * 2014-11-28 2015-04-01 广东工业大学 K-means cluster based extraction method of 3D scanning module of flame forming plate
CN107203916A (en) * 2016-03-17 2017-09-26 阿里巴巴集团控股有限公司 A kind of user credit method for establishing model and device
US20190050368A1 (en) * 2016-04-21 2019-02-14 Sas Institute Inc. Machine learning predictive labeling system
CN106529804A (en) * 2016-11-09 2017-03-22 国网江苏省电力公司南京供电公司 Client complaint early-warning monitoring analyzing method based on text mining technology
CN106779497A (en) * 2017-01-25 2017-05-31 国家电网公司 Complaint risk appraisal procedure caused by a kind of fare payment system is out of service
CN107220732A (en) * 2017-05-31 2017-09-29 福州大学 A kind of power failure complaint risk Forecasting Methodology based on gradient boosted tree
CN110348488A (en) * 2019-06-19 2019-10-18 华中科技大学 A kind of modal identification method based on local density's peak value cluster

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李硕: "聚类算法的研究与改进", 《中国优秀硕士学位论文数据库 信息科技辑》 *

Also Published As

Publication number Publication date
CN111415060B (en) 2022-07-29

Similar Documents

Publication Publication Date Title
CN110147803B (en) User loss early warning processing method and device
CN101110699B (en) System with network satisfaction degree estimation and early warning function and implementing method thereof
CN108345670B (en) Service hotspot discovery method for 95598 power work order
CN114048436A (en) Construction method and construction device for forecasting enterprise financial data model
CN110991527A (en) Similarity threshold determination method considering voltage curve average fluctuation rate
CN111415060B (en) Complaint risk analysis method based on customer label
CN113033909A (en) Portable user analysis method, device, equipment and computer storage medium
US20060136293A1 (en) System and method for predictive product requirements analysis
CN107590747A (en) Power grid asset turnover rate computational methods based on the analysis of comprehensive energy big data
CN116662860A (en) User portrait and classification method based on energy big data
CN111797145A (en) Power customer tolerance evaluation classification method
CN114912854B (en) Subway train operation adjusting method and device, electronic equipment and storage medium
CN115935076A (en) Travel service information pushing method and system based on artificial intelligence
CN114372835B (en) Comprehensive energy service potential customer identification method, system and computer equipment
CN115689016A (en) Power consumption prediction method and device for business expansion new installation customer
CN110727910B (en) Method and system for realizing copying and collecting risk prediction and business linkage
CN114491971A (en) Travel behavior modeling method based on mixed Logit model and Bayesian model average and application
CN116308190B (en) Work order full life cycle monitoring method based on energy Internet of things service system
CN112712194A (en) Electric quantity prediction method and device for power consumption cost intelligent optimization analysis
CN113537671A (en) Sorting timeliness prediction method and device, storage medium and electronic equipment
CN110992087A (en) Method and device for differentiating customer electricity consumption behavior areas
CN109684549A (en) Target data prediction technique, device, electronic equipment and computer storage medium
CN115203344B (en) Method for establishing power grid big data warehouse based on CIM model
CN114219369B (en) Prediction model training method and device, and user category prediction method and device
CN115860411A (en) Method for predicting user demand based on power user behavior

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