CN115456210A - Power utilization complaint early warning method based on cascade logistic regression Bayesian algorithm - Google Patents
Power utilization complaint early warning method based on cascade logistic regression Bayesian algorithm Download PDFInfo
- Publication number
- CN115456210A CN115456210A CN202211006404.2A CN202211006404A CN115456210A CN 115456210 A CN115456210 A CN 115456210A CN 202211006404 A CN202211006404 A CN 202211006404A CN 115456210 A CN115456210 A CN 115456210A
- Authority
- CN
- China
- Prior art keywords
- complaint
- information
- user
- fault
- time
- 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
- 238000007477 logistic regression Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012216 screening Methods 0.000 claims abstract description 11
- 230000005611 electricity Effects 0.000 claims description 28
- 230000008569 process Effects 0.000 claims description 12
- 238000011084 recovery Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
- G06Q10/20—Administration of product repair or maintenance
-
- 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
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention provides a power consumption complaint early warning method based on a cascade logistic regression Bayesian algorithm, which comprises the following steps: acquiring the power failure time of a power grid and the complaint time of a user, calculating a power failure forgetting index of the user, and screening out the complaint information of the user in an effective complaint range according to the power failure forgetting index; acquiring fault basic information and fault associated information corresponding to the screened user complaint information, extracting basic features based on the fault basic information and the user complaint information, and extracting additional features based on the fault associated information; the power failure forgetting index, the basic features and the additional features are jointly used as final feature sets, and the final feature sets are respectively input into a trained logistic regression model and a naive Bayes model; and cascading results output by the logistic regression model and the naive Bayes model to obtain a power utilization complaint early warning result. The method and the system realize the discrimination of potential complaint users, more accurate early warning of the power consumption complaint risks and can effectively reduce the workload of basic level personnel.
Description
Technical Field
The invention belongs to the field of big data analysis, and particularly relates to a power consumption complaint early warning method based on a cascade logistic regression Bayesian algorithm.
Background
When a power grid enterprise provides power service for users, if facilities such as a power distribution network and a power transmission line have faults, complaints of power utilization users are likely to be caused, and for the power grid enterprise, how to reduce complaints of the users in the power utilization process becomes important content in improving power supply quality. At present, power supply enterprises optimize power supply and distribution capacity continuously through canceling power failure operation and popularizing live working, power supply reliability is improved, risks of power utilization complaints are early warned in advance according to fault conditions through simple rules, and then manual notification is carried out on users affected by power failure, so that customer power utilization satisfaction is improved.
However, equipment failure and power failure maintenance can be inevitably caused in the power transmission and distribution process, and for areas with wider power distribution scale and higher power supply quality requirement, the early warning range of power consumption complaint risks of power grid enterprises is too large, so that the first power consumption complaint risks of users are difficult to accurately early warn, and the workload of staff at the front line of the basic level is huge, but the customer satisfaction degree is improved very limitedly.
Disclosure of Invention
The invention provides an electricity consumption complaint early warning method based on a cascade logistic regression Bayesian algorithm, aiming at solving the problems that electricity consumption complaint risks of users are difficult to accurately early warn in power grid enterprises and the workload of first-line staff at the basic level is large.
The invention provides a power consumption complaint early warning method based on a cascade logistic regression Bayesian algorithm, which comprises the following steps:
acquiring the power failure time of a power grid and the complaint time of a user, calculating a power failure forgetting index of the user, and screening out the complaint information of the user in an effective complaint range according to the power failure forgetting index;
acquiring fault basic information and fault associated information corresponding to the screened user complaint information, extracting basic features based on the fault basic information and the user complaint information, and extracting additional features based on the fault associated information;
the power failure forgetting index, the basic features and the additional features are jointly used as final feature sets, and the final feature sets are respectively input into a trained logistic regression model and a naive Bayes model;
and cascading results output by the logistic regression model and the naive Bayes model to obtain a power utilization complaint early warning result.
Optionally, the obtaining of the power failure time of the power grid and the complaint time of the user, calculating a power failure forgetting index of the user, and screening out the power consumption complaint information in the effective complaint range according to the power failure forgetting index includes:
acquiring power failure time corresponding to the power grid fault, and respectively calculating time difference t between complaint time of a user i and power failure time of the power grid fault;
calculating a user power failure forgetting index T = Σ e according to the time difference T -t/α Alpha is a preset unit conversion coefficient;
judging whether the power failure forgetting index of the user is in a preset range, if so, screening out a user i corresponding to the power failure forgetting index of the user, and judging that the power utilization complaint information of the user i is in an effective complaint range.
Optionally, the obtaining of the basic fault information and the fault associated information corresponding to the screened power consumption complaint information includes: acquiring a distribution transformer power failure list in an SQL (structured query language) database, and acquiring a platform area corresponding to a power failure line in the distribution transformer power failure list;
matching the transformer area with the user house name by taking the user house name in the electricity complaint information as a key, and taking the fault section data of the matched transformer area as fault basic information;
and using the electric quantity information and the weather information corresponding to the matched transformer area as fault correlation information.
Optionally, after the matching the distribution area with the user username, the method further includes:
and deleting the duplicate user name and the electricity consumption complaint information corresponding to the user name in the user names matched to the same distribution area.
Optionally, the basic features extracted based on the basic fault information include a fault line name, fault studying and judging time, fault recovery time, and fault date property.
Optionally, the basic features extracted based on the electricity complaint information include complaint time, complaint content, user account number, user classification, and user standing duration.
Optionally, the additional features include influence time, a power failure forgetting index of the user, a peak-to-valley power consumption of the user, a power consumption of the user in the last month and the last day, weather of the day of the fault, and air temperature.
Optionally, the calculating process of the influence time includes:
acquiring fault study and judgment time and fault recovery time in the fault basic information and complaint time in the electricity utilization complaint information; and respectively calculating the difference values of the complaint time and the fault studying and judging time and the difference values of the fault recovery time and the fault studying and judging time, and taking the minimum value in the difference values as the influence time.
Optionally, the cascading is performed on the result output by the logistic regression model and the naive bayes model to obtain the result of the electricity complaint early warning, and the method includes:
and taking an intersection of output results of the logistic regression model and the naive Bayesian model, and generating electricity complaint risk early warning aiming at the users in the intersection.
The technical scheme provided by the invention has the following beneficial effects:
according to the technical scheme provided by the invention, the information related to the fault and the user complaint is subjected to learning analysis, and the complaint information is preliminarily screened according to the timeliness of the complaint by learning historical data, so that the data volume of two learning models, namely the input logistic regression model and the Bayesian algorithm, is reduced. In addition, two learning models of logistic regression and Bayesian algorithm are adopted to realize the discrimination of potential complaint users, so that the users can be effectively communicated, and the working satisfaction of the customers is improved.
Compared with a conventional working method, the technical scheme realizes more accurate early warning of the complaint risk of power utilization, so that the workload of basic-level personnel can be effectively reduced to a certain extent.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a power consumption complaint early warning method based on a cascade logistic regression bayesian algorithm according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating a corresponding relationship between the user complaint information, the basic failure information, and the associated failure information according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein.
It should be understood that, in various embodiments of the present invention, the sequence numbers of the processes do not mean the execution sequence, and the execution sequence of the processes should be determined by the functions and the internal logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
It should be understood that in the present application, "comprising" and "having" and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that, in the present invention, "a plurality" means two or more. "and/or" is merely an association describing an associated object, meaning that three relationships may exist, for example, and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "comprising a, B and C", "comprising a, B, C" means that all three of a, B, C are comprised, "comprising a, B or C" means comprising one of a, B, C, "comprising a, B and/or C" means comprising any 1 or any 2 or 3 of a, B, C.
It should be understood that in the present invention, "B corresponding to a", "a corresponds to B", or "B corresponds to a" means that B is associated with a, and B can be determined from a. Determining B from a does not mean determining B from a alone, but may be determined from a and/or other information. And the matching of A and B means that the similarity of A and B is greater than or equal to a preset threshold value.
As used herein, the term "if" may be interpreted as "at \8230; …" or "in response to a determination" or "in response to a detection" depending on the context.
The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
The embodiment is as follows:
as shown in fig. 1, the present embodiment provides a power consumption complaint early warning method based on a cascade logistic regression bayesian algorithm, including:
s1: acquiring the power failure time of a power grid and the complaint time of a user, calculating a power failure forgetting index of the user, and screening out power utilization complaint information in an effective complaint range according to the power failure forgetting index;
s2: acquiring fault basic information and fault associated information corresponding to the screened power consumption complaint information, extracting basic features based on the fault basic information and the power consumption complaint information, and extracting additional features based on the fault basic information, the fault associated information and the power consumption complaint information;
s3: the power failure forgetting index, the basic features and the additional features are used as final feature sets together, and the final feature sets are respectively input into a trained logistic regression model and a naive Bayes model;
s4: and cascading results output by the logistic regression model and the naive Bayes model to obtain a power utilization complaint early warning result.
This embodiment aims at accurate judgement user's power consumption complaint risk, reduces basic level first-line personnel work load. The power utilization complaint information and the associated fault basic information and fault associated information are obtained, the power utilization complaint information primary screening combined with external factor data is realized, then a cascading algorithm of a logistic regression model and a naive Bayesian model is applied, the range of potential power utilization complaint users is searched, and the searched users are communicated through telephone, short messages and the like after power failure, so that complaints are reduced, and the customer satisfaction is improved.
In order to preliminarily screen power consumption complaint information in an effective complaint range and avoid interference of invalid information with long complaint time, in this embodiment, the obtaining power failure time of a power grid and complaint time of a user, calculating a power failure forgetting index of the user, and screening the power consumption complaint information in the effective complaint range according to the power failure forgetting index includes:
acquiring power failure time corresponding to the power grid fault, and respectively calculating time difference t between complaint time of a user i and the power failure time of the power grid fault;
calculating a user power failure forgetting index T = Σ e according to the time difference T -t/α α is a predetermined unit transformation systemCounting;
judging whether the power failure forgetting index of the user is in a preset range, if so, screening out a user i corresponding to the power failure forgetting index of the user, and judging that the power utilization complaint information of the user i is in an effective complaint range.
Specifically, in the present embodiment, the unit of T is second, and α is 3600/24/10, that is, in the present embodiment, the user power failure forgetting index T = Σ e -t/3600/24/10 。
In this embodiment, the preset range is a range larger than the preset index threshold, that is, the electricity consumption complaint information of the complaint time after a certain time is screened out, so that interference of the electricity consumption complaint information at an earlier time on the current early warning analysis is avoided, and preliminary screening of potential complaint users is realized.
In this embodiment, in order to combine the electricity complaint information with other external information for early warning analysis, in this embodiment, the acquiring basic fault information and relevant fault information corresponding to the screened electricity complaint information includes:
acquiring a distribution transformer power failure list in an SQL (structured query language) database, and acquiring a platform area corresponding to a power failure line in the distribution transformer power failure list;
matching the transformer area with the user house name by taking the user house name in the power consumption complaint information as a key, and taking the fault section data of the matched transformer area as fault basic information;
and using the electric quantity information and the weather information corresponding to the matched transformer area as fault correlation information.
The corresponding relation between the electricity consumption complaint information and the basic fault information and the relevant fault information is shown in fig. 2, and the basic fault information is fault section data which comprises a power failure number, fault studying and judging time, fault recovery time and a line name; weather information is used as one of fault associated information and comprises date, temperature and weather conditions; the management and distribution link is a system for acquiring other fault care information, the stored data comprises equipment codes, circuits and station area codes, and the power consumption condition of each user in the station area can be acquired; the electricity complaint information comprises a complaint number, a complaint time, complaint content and a user number.
And by taking the user number as a key, firstly determining the station area code corresponding to the user number to realize matching, thereby realizing matching of electricity complaint information and marketing and distribution through related information, matching fault section data corresponding to the line name through the line to which the electricity complaint information belongs, and finally matching corresponding weather information through fault research and judgment time.
In this embodiment, considering that there may be power consumption complaint information that some users frequently initiate complaints and generate power consumption complaint information for the power consumption complaint information, and affecting the early warning analysis efficiency, after matching the distribution room with the user names, the method further includes: and deleting the duplicate user name and the electricity consumption complaint information corresponding to the user name in the user names matched to the same distribution area.
As can be seen from fig. 2, in this embodiment, the basic features extracted based on the basic failure information include a failure line name, failure study time, failure recovery time, and failure date properties, where the failure date properties include a working day, a double holiday, and a holiday.
The basic features extracted based on the electricity complaint information comprise complaint time, complaint content, user number, user classification and user standing time.
The additional characteristics comprise influence time, a power failure forgetting index of the user, the peak-to-valley electricity quantity of the user, the electricity consumption of the user in the last month and the day, the weather of the fault day and air temperature.
Wherein the calculation process of the influence time comprises the following steps:
acquiring fault study and judgment time and fault recovery time in the fault basic information and complaint time in the electricity utilization complaint information; and respectively calculating the difference values of the complaint time and the fault studying and judging time and the difference values of the fault recovery time and the fault studying and judging time, and taking the minimum value in the difference values as the influence time.
Finally, the basic features and the additional features are spliced into a final feature set and are respectively input into a trained logistic regression model and a naive Bayes model. Therefore, the characteristic data input into the logistic regression model and the naive Bayesian model in the embodiment is fused with the multidimensional characteristics including the power failure duration, the weather condition, the date attribute, the complaint attribute and the like, and the early warning analysis accuracy of potential complaint users can be further improved.
In this embodiment, the logistic regression model is a conventional classification regression model, which can be implemented by a perceptron substantially, and is used for determining whether a currently occurring fault causes a complaint of a user and a level of a complaint amount caused by the currently occurring fault. The naive Bayes model is a conventional classification model based on Bayes theorem and independent hypothesis of characteristic conditions, and realizes classification through probability analysis.
In order to improve the accuracy of the power consumption complaint early warning result, the results output by the logistic regression model and the naive bayes model are cascaded to obtain the power consumption complaint early warning result, which includes:
and taking an intersection of output results of the logistic regression model and the naive Bayesian model, and generating electricity complaint risk early warning for users in the intersection.
The sequence numbers in the above embodiments are merely for description, and do not represent the sequence of the assembly or the use of the components.
The above description is only exemplary of the present invention and should not be taken as limiting the invention, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. A power consumption complaint early warning method based on a cascade logistic regression Bayesian algorithm is characterized by comprising the following steps:
acquiring the power failure time of a power grid and the complaint time of a user, calculating a power failure forgetting index of the user, and screening out power utilization complaint information in an effective complaint range according to the power failure forgetting index;
acquiring basic fault information and relevant fault information corresponding to the screened electricity consumption complaint information, extracting basic features based on the basic fault information and the electricity consumption complaint information, and extracting additional features based on the basic fault information, the relevant fault information and the electricity consumption complaint information;
the power failure forgetting index, the basic features and the additional features are used as final feature sets together, and the final feature sets are respectively input into a trained logistic regression model and a naive Bayes model;
and cascading results output by the logistic regression model and the naive Bayesian model to obtain a power utilization complaint early warning result.
2. The power consumption complaint early warning method based on the cascade logistic regression Bayesian algorithm as recited in claim 1, wherein the power failure time of the power grid and the complaint time of the user are obtained, the power failure forgetting index of the user is calculated, and the power consumption complaint information in the effective complaint range is screened out according to the power failure forgetting index, and the power consumption complaint early warning method comprises the following steps:
acquiring power failure time corresponding to the power grid fault, and respectively calculating time difference t between complaint time of a user i and power failure time of the power grid fault;
calculating a user power failure forgetting index T = Σ e according to the time difference T -t/α Alpha is a preset unit conversion coefficient;
judging whether the power failure forgetting index of the user is in a preset range, if so, screening out a user i corresponding to the power failure forgetting index of the user, and judging that the power utilization complaint information of the user i is in an effective complaint range.
3. The power consumption complaint early warning method based on the cascading logistic regression Bayesian algorithm as recited in claim 1, wherein the step of obtaining basic fault information and relevant fault information corresponding to the screened power consumption complaint information comprises the steps of:
acquiring a distribution transformer power failure list in an SQL (structured query language) database, and acquiring a platform area corresponding to a power failure line in the distribution transformer power failure list;
matching the transformer area with the user house name by taking the user house name in the power consumption complaint information as a key, and taking the fault section data of the matched transformer area as fault basic information;
and using the electric quantity information and the weather information corresponding to the matched transformer area as fault correlation information.
4. The power consumption complaint early warning method based on the cascading logistic regression Bayesian algorithm as recited in claim 3, further comprising, after the matching of the transformer area and the user username:
and deleting the duplicate user account name and the electricity consumption complaint information corresponding to the user account name in the user account names matched to the same distribution area.
5. The power consumption complaint early warning method based on the cascading logistic regression Bayesian algorithm as recited in claim 1, wherein basic features extracted based on the basic fault information comprise fault line names, fault studying and judging time, fault recovery time and fault date properties.
6. The power consumption complaint early warning method based on the cascading logistic regression Bayesian algorithm as recited in claim 1, wherein basic features extracted based on the power consumption complaint information include complaint time, complaint content, user number, user classification and household standing time.
7. The power consumption complaint early warning method based on the cascading logistic regression Bayesian algorithm as claimed in claim 1, wherein the additional characteristics comprise influence time, a power failure forgetting index of a user, the peak-valley power of the user in the previous month, the power consumption of the user in the previous month, the weather of the day of the failure and air temperature.
8. The electric complaint early warning method based on the cascading logistic regression Bayesian algorithm as recited in claim 7, wherein the calculation process of the influence time comprises the following steps:
acquiring fault study and judgment time and fault recovery time in the fault basic information and complaint time in the electricity utilization complaint information;
and respectively calculating the difference values of the complaint time and the fault studying and judging time and the difference values of the fault recovery time and the fault studying and judging time, and taking the minimum value in the difference values as the influence time.
9. The power consumption complaint early warning method based on the cascade logistic regression Bayesian algorithm as claimed in claim 1, wherein the cascade of the results output by the logistic regression model and the naive Bayesian model to obtain the power consumption complaint early warning result comprises:
and taking an intersection of output results of the logistic regression model and the naive Bayesian model, and generating electricity complaint risk early warning aiming at the users in the intersection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211006404.2A CN115456210B (en) | 2022-08-22 | 2022-08-22 | Power consumption complaint early warning method based on cascading logistic regression Bayesian algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211006404.2A CN115456210B (en) | 2022-08-22 | 2022-08-22 | Power consumption complaint early warning method based on cascading logistic regression Bayesian algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115456210A true CN115456210A (en) | 2022-12-09 |
| CN115456210B CN115456210B (en) | 2024-04-12 |
Family
ID=84298227
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211006404.2A Active CN115456210B (en) | 2022-08-22 | 2022-08-22 | Power consumption complaint early warning method based on cascading logistic regression Bayesian algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115456210B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101719147A (en) * | 2009-11-23 | 2010-06-02 | 合肥兆尹信息科技有限责任公司 | Rochester model-naive Bayesian model-based data classification system |
| CN109410089A (en) * | 2018-12-29 | 2019-03-01 | 广州供电局有限公司 | Low-voltage tripping and customer complaint prediction technique, device and storage medium |
| CN109447364A (en) * | 2018-11-08 | 2019-03-08 | 国网湖南省电力有限公司 | Power customer based on label complains prediction technique |
| US20190114677A1 (en) * | 2017-10-13 | 2019-04-18 | Yahoo Holdings, Inc. | Systems and Methods for User Propensity Classification and Online Auction Design |
| 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 |
| CN111723519A (en) * | 2020-05-29 | 2020-09-29 | 国网四川省电力公司电力科学研究院 | Transformer fault diagnosis device and method based on logistic regression and naive Bayes |
| CN111860940A (en) * | 2020-06-02 | 2020-10-30 | 山西潞安环保能源开发股份有限公司 | Coal mine distribution network power failure accident prediction method based on logistic regression algorithm |
-
2022
- 2022-08-22 CN CN202211006404.2A patent/CN115456210B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101719147A (en) * | 2009-11-23 | 2010-06-02 | 合肥兆尹信息科技有限责任公司 | Rochester model-naive Bayesian model-based data classification system |
| US20190114677A1 (en) * | 2017-10-13 | 2019-04-18 | Yahoo Holdings, Inc. | Systems and Methods for User Propensity Classification and Online Auction Design |
| CN109447364A (en) * | 2018-11-08 | 2019-03-08 | 国网湖南省电力有限公司 | Power customer based on label complains prediction technique |
| CN109410089A (en) * | 2018-12-29 | 2019-03-01 | 广州供电局有限公司 | Low-voltage tripping and customer complaint prediction technique, device and storage medium |
| 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 |
| CN111723519A (en) * | 2020-05-29 | 2020-09-29 | 国网四川省电力公司电力科学研究院 | Transformer fault diagnosis device and method based on logistic regression and naive Bayes |
| CN111860940A (en) * | 2020-06-02 | 2020-10-30 | 山西潞安环保能源开发股份有限公司 | Coal mine distribution network power failure accident prediction method based on logistic regression algorithm |
Non-Patent Citations (3)
| Title |
|---|
| VIET-HA NHU等: "Shallow Landslide Susceptibility Mapping: A Comparison between Logistic Model Tree, Logistic Regression, Naïve Bayes Tree, Artificial Neural Network, and Support Vector Machine Algorithms", 《INT.J.ENVIRON.RES.PUBLIC HEALTH》, 16 April 2020 (2020-04-16) * |
| 梁景舒: "机器学习经典算法在无线设备故障预警用户投诉行为的应用", 《信息科技》 * |
| 梁景舒;顾俊峰;李江;黄伟锋;李土光;: "机器学习经典算法在无线设备故障预警用户投诉行为的应用", 中国新通信, no. 08, 20 April 2018 (2018-04-20) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115456210B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109165763B (en) | Method and device for evaluating potential complaints of power grid customer service work order | |
| CN106570778A (en) | Big data-based data integration and line loss analysis and calculation method | |
| CN110689385A (en) | Power customer service user portrait construction method based on knowledge graph | |
| US20230247138A1 (en) | Methods and internet of things systems for gas operation based on call centers of smart gas | |
| CN108470022A (en) | A kind of intelligent work order quality detecting method based on operation management | |
| CN111291076A (en) | Abnormal water use monitoring and alarming system based on big data and construction method thereof | |
| CN115423429A (en) | Multimode integrated distribution network operation system based on image and sound information | |
| CN112052966A (en) | Power customer satisfaction analysis system and method based on site emergency repair work order | |
| CN111612230A (en) | Client appeal trend early warning analysis method | |
| CN112862172A (en) | State network 95598 power failure complaint prediction method and device, computer equipment and storage medium | |
| CN113379313A (en) | Intelligent preventive test operation management and control system | |
| CN110751317A (en) | Power load prediction system and prediction method | |
| CN116843162B (en) | Contradiction reconciliation scheme recommendation and scoring system and method | |
| CN116955445A (en) | Complaint event data mining analysis method and system based on information extraction | |
| CN115456210A (en) | Power utilization complaint early warning method based on cascade logistic regression Bayesian algorithm | |
| WO2020010531A1 (en) | Fault detection method and device | |
| CN113379432B (en) | Sales system customer matching method based on machine learning | |
| CN115358755A (en) | Method and device for fine layering of grids | |
| CN111400567B (en) | AI-based user data processing method, device and system | |
| CN111427936B (en) | Report generation method and device, computer equipment and storage medium | |
| Li | Implementation of a community data processing system based on data mining | |
| CN117829435B (en) | Urban data quality management method and system based on big data | |
| CN110866173B (en) | Remote signaling combing method based on deep learning | |
| CN118052448A (en) | Power failure early warning method and system based on multidimensional sensitivity influence factor analysis | |
| WO2024065776A1 (en) | Method for data processing, apparatus for data processing, electronic device, and storage medium |
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 |