CN109615089A - Power information acquires the generation method of label and the work order distributing method based on this - Google Patents
Power information acquires the generation method of label and the work order distributing method based on this Download PDFInfo
- Publication number
- CN109615089A CN109615089A CN201811193733.6A CN201811193733A CN109615089A CN 109615089 A CN109615089 A CN 109615089A CN 201811193733 A CN201811193733 A CN 201811193733A CN 109615089 A CN109615089 A CN 109615089A
- Authority
- CN
- China
- Prior art keywords
- label
- work order
- failure
- model
- power information
- 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
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
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to label generating method, in particular to the generation method of a kind of power information acquisition label and the work order distributing method based on this.Label object includes work order object, user object, platform area object, terminal object and tagged object;Tag types include manual label, regular label and model label;Generating mode, which is divided into, to be manually generated and automatically generates, and is automatically generated and is generated and model generation including rule;Include but is not limited to remotely processing using link, scene feedback, O&M feedback, file and send work.The present invention generates model label by machine learning techniques combination tag library system automation, realizes automatically generating and updating for label;According to the abnormal cause prediction label of generation and work order composite rating label, judge whether worksheet processing and worksheet processing priority, overcomes the case where original worksheet processing mode easily leads to repetition worksheet processing, invalid worksheet processing, worksheet processing inefficiency.
Description
Technical field
The present invention relates to label generating method, in particular to a kind of power information acquires the generation method of label and is based on this
Work order distributing method.
Background technique
Under the overall background and trend that power information acquisition system is widelyd popularize, power information acquisition scale is increasingly huge,
Data strengthened research is constantly reinforced, and also expands therewith to the operation and maintenance of system, at present the average event generated daily of the whole province
Hindering work order is more than 7000, far beyond the current ability to work for being equipped with operation maintenance personnel, urgent acquisition O&M demand with relatively
The contradiction of low acquisition O&M efficiency is increasingly prominent, is mainly reflected in the following aspects:
(1) same to anomaly exist repetition and send work;
(2) exist and send work in vain;
(3) analysis is abnormal, it is big to distribute work order magnitude of the operation;
(4) lack guiding processing function, keep abnormal worksheet problem more passive;
(5) manual intervention is more, and system automation processing is horizontal low.
Summary of the invention
It is an object of the present invention to solve above-mentioned repetition of the existing technology to send work, worksheet processing automatization level low
Problem provides a kind of generation method of power information acquisition label and the work order distributing method based on this.
The technical solution adopted by the present invention to solve the technical problems is: a kind of power information acquisition label, including label
Object, bookmark name, tag types, generating mode and apply link;
The label object includes work order object, user object, platform area object, terminal object and tagged object;It is described
Tag types include manual label, regular label and model label;The generating mode, which is divided into, to be manually generated and automatically generates, institute
It states to automatically generate to generate including rule and be generated with model;The application link includes but is not limited to long-range processing, scene feedback, fortune
Work is filed and sent to dimension feedback.
The present invention also provides a kind of power information acquisition labels to manually generate method, feeds back to label object by scene
Label is manually generated, generated label is manual label.
The present invention also provides a kind of power informations to acquire label rule generating method, comprising: establishes system database, uses
In the characteristic information for storing manual label, and by characteristic information data;Business rule is established, converts data for business rule
Rule;The corresponding manual label of digitization characteristic information for meeting a certain data rule is searched in system database;For the hand
The corresponding label object of work label carries out business rule label, if the business rule marker number note on label object is more than default
Value, then system database is that the label object generates label automatically, and generated label is regular label.
The present invention also provides a kind of power informations to acquire label model generation method, comprising: collects historical failure work order
Fault message;Machine learning model is obtained by machine learning algorithm training;When label object generates new failure, event is read
Hinder information, inputs the machine learning model, machine learning model output model calculated result, then the model calculation is generated
For label;Generated label is model label.
Further, the fault message includes but is not limited to fault type, failure exception phenomenon, failure cause, failure
Material needed for coverage, fault handling time, troubleshooting.
The present invention also provides a kind of work order distributing methods based on power information acquisition label, are acquired according to power information
Label model generation method establishes failure cause prediction model, and the failure exception phenomenon and failure cause of historical failure work order is defeated
Enter failure cause prediction model, generates abnormal cause prediction label;Label model generation method is acquired according to power information to establish
Historical failure work order and work order standard diagrams are inputted work order composite rating model, it is comprehensive to generate work order by work order composite rating model
Close rating tab;Judge whether to distribute work order according to abnormal cause prediction label;Work order is judged according to work order composite rating label
The priority distributed.
Further, the work order standard diagrams include:
(1) failure disturbance degree: according to failure exception phenomenon, fault object, route relationship assessment failure coverage, and
Whether have Very Important Person, carry out metrization to the influence that failure generates if comprehensively considering;
(2) troubleshooting difficulty: modeling analysis is carried out from failure self attributes and historical failure worksheet situation, to not
Processing difficulty with characteristic fault is predicted;
(3) fault handling time: in conjunction with history trouble ticket disposition, analyzing the processing time of fault ticket, real
Now to the prediction of each fault ticket handling duration.
Substantial effect of the invention: the present invention generates model by machine learning techniques combination tag library system automation
Label realizes automatically generating and updating for label;According to the abnormal cause prediction label of generation and work order composite rating label, sentence
It is disconnected whether worksheet processing and worksheet processing priority, overcome original worksheet processing mode and easily lead to repetition worksheet processing, invalid worksheet processing, worksheet processing inefficiency
The case where.
Detailed description of the invention
Fig. 1 is the model label generating process schematic diagram of the embodiment of the present invention four.
Fig. 2 is that the abnormal cause prediction label of the embodiment of the present invention four generates schematic diagram.
Fig. 3 is that the work order overall merit label of the embodiment of the present invention four generates schematic diagram.
Fig. 4 is that the work order of the embodiment of the present invention five distributes process.
Specific embodiment
Below by specific embodiment, and in conjunction with attached drawing, technical scheme of the present invention will be further explained in detail.
Embodiment one:
A kind of power information acquisition label, including but not limited to label object, bookmark name, tag types, generating mode
And apply link.Label object includes work order object, user object, platform area object, terminal object and tagged object.Using
Link includes but is not limited to long-range processing, scene feedback, O&M feedback, filing and sends work.Power information acquires label design
The considerations of factor include label object, tag types, service attribute, generate link, using link, i.e., each power information is adopted
Collect label, all should include the information of these dimensions.Wherein: power information acquires the corresponding " user-platform area-terminal-table of label
Five label objects of meter-work order ", work order label include: abnormal cause prediction, work order importance and processing priority.
1 power information of table acquires label information table
Tag types: label can be divided into manual label, regular label and model label three types according to generating mode.
Wherein regular label and model label are system automatically generated label, the mark that can be directly generated by simple or complicated calculating
Label.Wherein, the rule-based definition of regular label is inquired all objects for meeting rule definition by SQL statement and marked
The upper label;Model label is then to carry out the label that analysis mining obtains to acquisition big data with machine learning related algorithm,
Such as abnormal cause prediction judges that fault ticket priority is model label.
Generate link: the generation link of manual label is concentrated mainly on long-range processing, scene feedback, regular label and model
The generation link of label is that the label scheduling of system executes the time, can the customized update cycle.
Using link: the application link of label design, including acquisition O&M whole process generates extremely, long-range processing, scene
Feedback and O&M feedback.In conjunction with the characteristics of each traffic flow, specific label is applied to corresponding process.
Embodiment two:
A kind of power information acquisition label manually generates method, feeds back to label object by scene and manually generates label,
Generated label is manual label.Manual label is static labels, i.e., can not be judged by the data in system, is needed by existing
Field feeds back to the label of object tag.Such as " long Qimen closes " label, when O&M is fed back at the scene, if it find that the user meets
Attributive character described in this label, then by operation maintenance personnel in systems by hand to the label in this user's mark.Label
The user " will bind " this label before the deadline afterwards, later in all information related with the user of system queries, all
It will be able to see that this label.
Embodiment three:
A kind of power information acquisition label rule generating method, comprising: system database is established, for storing manual label
Characteristic information, and by characteristic information data;Business rule is established, converts data rule for business rule;
The corresponding manual label of digitization characteristic information for meeting a certain data rule is searched in system database;For this
The corresponding label object of manual label carries out business rule label, if the business rule mark quantity note on label object is more than default
Value, then system database is that the label object generates label automatically, and generated label is regular label.
According to data with existing source in system database, business rule is designed according to the meaning of label, and by system maintenance people
Business rule is converted data rule by member, goes out to meet the subject population of the data rule by data query, and right to these
As marking the label in batches.The process to label to legal object implementatio8 is realized by tag library system platform.For example it " tears open
Move user's white list " label, it is previous to need by declaring white list, it, can be according to rule from system number by tag library platform
According to these users are found out in table, the label is stamped automatically.Corresponding functional module is developed in tag library system, is supported direct
Simple SQL statement and selection scheduling period are filled in by front end, then the object that system periodically can directly meet the rule is beaten
Upper label.The service generation process of regular label is label requirements to be proposed by business personnel or system operation maintenance personnel, by system
Operation maintenance personnel creation generates label.
Example IV:
A kind of power information acquisition label model generation method, comprising: collect the fault message of historical failure work order;Pass through
Machine learning algorithm training obtains machine learning model;When label object generates new failure, read failure information, described in input
Machine learning model, machine learning model output model calculated result, then the model calculation is generated as label;Generate mark
Label are model label.
For needing the label that depth is excavated, height is refined, for example, " prediction clock of power meter abnormal ", " worksheet is excellent
The labels such as first grade height ", " fault incidence is wide ", can not be directly obtained by the data in system, be needed with machine learning
Algorithm establishes model and generates label.Model label automatically generates process as shown in Figure 1, first by historical data and machine
Learning algorithm, training obtain machine learning machine learning model;When label object generates new failure, read failure information input
In machine learning model, output model calculated result is stored in result table, and finally by tag library platform, model result is turned
Turn to label, the generation of implementation model label.Model label is directed to different themes, needs to establish different models.
Model foundation process: model label is generated by machine learning method, the algorithm of use includes factorial analysis, association
It is main to cover data prediction (data cleansing, dimensionality reduction etc.), cluster, each son for rule, deep neural network, support vector machines etc.
The algorithm that topic prediction modeling may relate to.By machine learning algorithm, final training obtains the model result of theme demand, and will
The parameter input model of object, automatically derives prediction result, so that final implementation model label automatically generates.
Include the following contents by the process that machine learning algorithm realizes that label automatically generates:
A) index system establishment constructs the index system of model according to theme;
B) machine learning algorithm selects, and is calculated using machine learning such as correlation rule, support vector machines, deep neural networks
Method at least selects two kinds or more suitable algorithms for the same theme, and is compared to result and selects the final mould of choosing selection
Type result;
C) deep learning frame selects: when selected depth learning algorithm is modeled, because algorithm calculation amount is excessive, needing
Existing deep learning frame is selected, including TensorFlow, Caffe, Keras, MXNet etc.;
D) algorithmic tool selects, and according to real data environment, selects corresponding algorithm development solution, is such as based on
Oralce, by Data Mining Tools R/PYTHON, by ODBC/JDBC interfacing data library, complete algorithm operation and
Read-write operation;Hadoop big data platform is such as netted based on state, then selects SparkR or Rhive solution.Specific scheme choosing
It selects, is determined according to project reality;
E) label generates, the model obtained by machine learning algorithm, after data input model, automatically derives model output
As a result, and automatically generate label, existing tag library table is written, is shown and calls for tag library system, to realize height
Grade label automatically generates.
Embodiment five:
A method of the work order based on power information acquisition label distributes, and acquires label model according to power information and generates
Method establishes failure cause prediction model, and the phenomenon of the failure of historical failure work order and failure cause input fault reason are predicted mould
Type generates abnormal cause prediction label, as Fig. 2 shows.Label model generation method, which is acquired, according to power information establishes work order synthesis
Historical failure work order and work order standard diagrams are inputted work order composite rating model, generate work order composite rating mark by rating model
Label, as Fig. 3 shows.Judge whether to distribute work order according to abnormal cause prediction label;Work order is judged according to work order composite rating label
The priority distributed.
According to statistics, acquisition failure exception phenomenon 59 kinds of totally seven major class at present, 98 kinds of failure cause.Accident analysis positions very
Difficulty, common operation maintenance personnel do not have positioning failure reason usually and determine the technical capability of defect elimination scheme.Knowledge base provides
For different abnormal phenomenon, which the failure cause that may cause has, but lists all failure causes, O&M people
Member needs to exclude one by one, it is difficult to be accurately positioned, the same problem lower in face of efficiency.Acquire the failure of fault ticket in history
The factors such as material needed for type, failure exception phenomenon, failure cause, fault incidence, fault handling time, troubleshooting,
Label model generation method is acquired according to power information and generates failure cause prediction model, when new fault ticket generates, is led to
It crosses and reads relevant fault message, model, which is given, judges possible failure cause, by model output as a result, generating abnormal former
Because predicting class label, such as " scene is without electric energy meter ", " clock of power meter is abnormal ", " batch failure ".By label in work order
Direct remarks realize the purpose of precise positioning failure cause, improve maintenance work efficiency conscientiously.
By machine learning algorithm, composite rating, such as " work order importance is high " or " work are carried out to acquisition fault ticket
Single importance rate is 5 grades " or " priority processing rank is high ".Fault ticket carries out failure shadow of the composite rating from fault ticket
Comprehensively considered in terms of loudness and troubleshooting difficulty two.If Fig. 3 shows, work order composite rating index includes but is not limited to:
(1) failure disturbance degree: according to failure exception phenomenon, fault object, route relationship assessment failure coverage, and
Whether have Very Important Person, carry out metrization to the influence that failure generates if comprehensively considering;
(2) troubleshooting difficulty: modeling analysis is carried out from failure self attributes and historical failure worksheet situation, to not
Processing difficulty with characteristic fault is predicted;
(3) fault handling time: in conjunction with history trouble ticket disposition, analyzing the processing time of fault ticket, real
Now to the prediction of each fault ticket handling duration.
Failure disturbance degree and troubleshooting difficulty can also be carried out to registration division, form label, such as " fault incidence
Greatly ", the labels such as " fault incidence is small ", " troubleshooting difficulty is high ", " troubleshooting difficulty is low ".
If Fig. 4 shows, without label information in original process flow, exception generally directly distributes at work order when occurring
Situations such as managing, being easy to cause repetition worksheet processing, invalid worksheet processing appearance.By label information, worksheet processing process can be optimized, such as:
Work order 1 shows " arrearage power failure ", " removal is demolished squatter buildings " label, and distributing treatment measures is to distribute link in work order not to send
Work effectively reduces invalid O&M;
The display of work order 2 " industry expands process conflict " distributes treatment measures as according to this type of information, judgement should not file this work
Single to hang up, work order, which corresponds to equipment, in certain time will not generate exception, avoid reprocessing;
Work order 3 increases " priority processing rank is high " label, illustrates that the exception work order is extremely important, preferentially distributes and handle the work
Singly, situations such as so just avoiding repetition worksheet processing, invalid worksheet processing appearance.
Embodiment described above is a kind of preferable scheme of the invention, not makees limit in any form to the present invention
System, there are also other variants and remodeling on the premise of not exceeding the technical scheme recorded in the claims.
Claims (7)
1. a kind of power information acquires label, which is characterized in that including label object, bookmark name, tag types, generating mode
And apply link;
The label object includes work order object, user object, platform area object, terminal object and tagged object;
The tag types include manual label, regular label and model label;
The generating mode, which is divided into, to be manually generated and automatically generates, and described automatically generate generates and model generation including rule;
The application link includes but is not limited to long-range processing, scene feedback, O&M feedback, filing and sends work.
2. a kind of power information acquisition label manually generates method, which is characterized in that
Label object is fed back to by scene and manually generates label, and generated label is manual label.
3. a kind of power information acquires label rule generating method characterized by comprising
System database is established, for storing the characteristic information of manual label, and by characteristic information data;
Business rule is established, converts data rule for business rule;
The corresponding manual label of digitization characteristic information for meeting a certain data rule is searched in system database;
Business rule label is carried out for the corresponding label object of the craft label,
If the business rule marker number note on label object is more than preset value, system database is that the label object is raw automatically
At label, generated label is regular label.
4. a kind of power information acquires label model generation method characterized by comprising
Collect the fault message of historical failure work order;
Machine learning model is obtained by machine learning algorithm training;
When label object generates new failure, read failure information inputs the machine learning model, machine learning model output
The model calculation, then the model calculation is generated as label;
Generated label is model label.
5. a kind of power information as claimed in claim 4 acquires label model generation method, which is characterized in that
The fault message includes but is not limited to fault type, failure exception phenomenon, failure cause, fault incidence, failure
Material needed for handling time, troubleshooting.
6. a kind of work order distributing method based on power information acquisition label, which is characterized in that
Label model generation method is acquired according to power information and establishes failure cause prediction model, by the failure of historical failure work order
Abnormal phenomenon and failure cause input fault reason prediction model generate abnormal cause prediction label;
Label model generation method is acquired according to power information and establishes work order composite rating model, by historical failure work order and work order
Standard diagrams input work order composite rating model, generate work order composite rating label;
Judge whether to distribute work order according to abnormal cause prediction label;
The priority that work order distributes is judged according to work order composite rating label.
7. a kind of work order distributing method based on power information acquisition label as claimed in claim 6, which is characterized in that described
Work order standard diagrams include:
(1) failure disturbance degree: according to failure exception phenomenon, fault object, route relationship assessment failure coverage, and it is comprehensive
It has considered whether Very Important Person, metrization is carried out to the influence that failure generates;
(2) troubleshooting difficulty: modeling analysis is carried out from failure self attributes and historical failure worksheet situation, to different spies
The processing difficulty of sign failure is predicted;
(3) fault handling time: in conjunction with history trouble ticket disposition, analyzing the processing time of fault ticket, realization pair
The prediction of each fault ticket handling duration.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811193733.6A CN109615089A (en) | 2018-10-12 | 2018-10-12 | Power information acquires the generation method of label and the work order distributing method based on this |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811193733.6A CN109615089A (en) | 2018-10-12 | 2018-10-12 | Power information acquires the generation method of label and the work order distributing method based on this |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109615089A true CN109615089A (en) | 2019-04-12 |
Family
ID=66002377
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811193733.6A Pending CN109615089A (en) | 2018-10-12 | 2018-10-12 | Power information acquires the generation method of label and the work order distributing method based on this |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109615089A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110363382A (en) * | 2019-06-03 | 2019-10-22 | 华东电力试验研究院有限公司 | Almightiness type Township Merging integrated business integration technology |
CN110489463A (en) * | 2019-08-26 | 2019-11-22 | 广东电网有限责任公司 | A kind of multiple information acquisition system of garden integrated energy system |
CN110650052A (en) * | 2019-09-26 | 2020-01-03 | 科大国创软件股份有限公司 | Customer reason fault identification processing method and system based on intelligent algorithm |
CN111242325A (en) * | 2019-12-31 | 2020-06-05 | 中国电力科学研究院有限公司 | Secondary label generation method for power acquisition equipment |
CN111310782A (en) * | 2019-12-31 | 2020-06-19 | 国网浙江省电力有限公司电力科学研究院 | Label generation method for operation and maintenance of power acquisition equipment |
CN111817265A (en) * | 2020-06-29 | 2020-10-23 | 北京智芯微电子科技有限公司 | Low-voltage transformer area power distribution protection method and system |
CN113919936A (en) * | 2021-09-22 | 2022-01-11 | 百融至信(北京)征信有限公司 | Sample data processing method and device |
CN117350521A (en) * | 2023-12-05 | 2024-01-05 | 江苏臻云技术有限公司 | Operation and maintenance duty management system and method based on big data analysis |
CN117851443A (en) * | 2024-03-07 | 2024-04-09 | 北京偶数科技有限公司 | SQL rule tag generation method based on artificial intelligence and readable storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103091112A (en) * | 2013-01-31 | 2013-05-08 | 林惠堂 | Method and device of car emission fault detection and diagnosis based on fuzzy reasoning and self-learning |
CN104270779A (en) * | 2014-10-17 | 2015-01-07 | 浪潮通信信息***有限公司 | Wireless network fault cause preprocessing method and wireless network fault work order dispatching system |
CN104698343A (en) * | 2015-03-26 | 2015-06-10 | 广东电网有限责任公司电力调度控制中心 | Method and system for judging power grid faults based on historical recording data |
CN105893407A (en) * | 2015-11-12 | 2016-08-24 | 乐视云计算有限公司 | Individual user portraying method and system |
CN106296445A (en) * | 2016-08-01 | 2017-01-04 | 国网浙江省电力公司 | A kind of power customer label construction method |
CN106803125A (en) * | 2016-12-08 | 2017-06-06 | 国网浙江省电力公司 | A kind of acquisition abnormity urgency level computational methods based on the conversion of standard electricity consumer |
-
2018
- 2018-10-12 CN CN201811193733.6A patent/CN109615089A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103091112A (en) * | 2013-01-31 | 2013-05-08 | 林惠堂 | Method and device of car emission fault detection and diagnosis based on fuzzy reasoning and self-learning |
CN104270779A (en) * | 2014-10-17 | 2015-01-07 | 浪潮通信信息***有限公司 | Wireless network fault cause preprocessing method and wireless network fault work order dispatching system |
CN104698343A (en) * | 2015-03-26 | 2015-06-10 | 广东电网有限责任公司电力调度控制中心 | Method and system for judging power grid faults based on historical recording data |
CN105893407A (en) * | 2015-11-12 | 2016-08-24 | 乐视云计算有限公司 | Individual user portraying method and system |
CN106296445A (en) * | 2016-08-01 | 2017-01-04 | 国网浙江省电力公司 | A kind of power customer label construction method |
CN106803125A (en) * | 2016-12-08 | 2017-06-06 | 国网浙江省电力公司 | A kind of acquisition abnormity urgency level computational methods based on the conversion of standard electricity consumer |
Non-Patent Citations (2)
Title |
---|
张凌倩 等: "《杭州电信年鉴 2005》", 31 October 2005, 方志出版社 * |
韦鹏程 等: "《基于R语言数据挖掘的统计与分析》", 31 December 2017, 电子科技大学出版社 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110363382A (en) * | 2019-06-03 | 2019-10-22 | 华东电力试验研究院有限公司 | Almightiness type Township Merging integrated business integration technology |
CN110489463B (en) * | 2019-08-26 | 2023-05-02 | 广东电网有限责任公司 | Multi-element information acquisition system of park comprehensive energy system |
CN110489463A (en) * | 2019-08-26 | 2019-11-22 | 广东电网有限责任公司 | A kind of multiple information acquisition system of garden integrated energy system |
CN110650052A (en) * | 2019-09-26 | 2020-01-03 | 科大国创软件股份有限公司 | Customer reason fault identification processing method and system based on intelligent algorithm |
CN111242325A (en) * | 2019-12-31 | 2020-06-05 | 中国电力科学研究院有限公司 | Secondary label generation method for power acquisition equipment |
CN111310782A (en) * | 2019-12-31 | 2020-06-19 | 国网浙江省电力有限公司电力科学研究院 | Label generation method for operation and maintenance of power acquisition equipment |
CN111817265A (en) * | 2020-06-29 | 2020-10-23 | 北京智芯微电子科技有限公司 | Low-voltage transformer area power distribution protection method and system |
CN113919936A (en) * | 2021-09-22 | 2022-01-11 | 百融至信(北京)征信有限公司 | Sample data processing method and device |
CN113919936B (en) * | 2021-09-22 | 2022-08-05 | 百融至信(北京)征信有限公司 | Sample data processing method and device |
CN117350521A (en) * | 2023-12-05 | 2024-01-05 | 江苏臻云技术有限公司 | Operation and maintenance duty management system and method based on big data analysis |
CN117350521B (en) * | 2023-12-05 | 2024-02-13 | 江苏臻云技术有限公司 | Operation and maintenance duty management system and method based on big data analysis |
CN117851443A (en) * | 2024-03-07 | 2024-04-09 | 北京偶数科技有限公司 | SQL rule tag generation method based on artificial intelligence and readable storage medium |
CN117851443B (en) * | 2024-03-07 | 2024-05-14 | 北京偶数科技有限公司 | SQL rule tag generation method based on artificial intelligence and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109615089A (en) | Power information acquires the generation method of label and the work order distributing method based on this | |
US7739138B2 (en) | Automated utility supply management system integrating data sources including geographic information systems (GIS) data | |
CN106570778B (en) | A kind of method that data integration based on big data is calculated with line loss analyzing | |
CN101872166B (en) | Process simulation utilizing component-specific consumption data | |
CN109711865A (en) | A method of prediction is refined based on the mobile radio communication flow that user behavior excavates | |
CN110046718A (en) | A kind of intelligent operation platform based on BIM and RFID | |
CN106951694A (en) | A kind of secondary equipment in power system on-line monitoring system adaptive modeling method | |
CN104769582A (en) | Real-time data management for a power grid | |
CN109615088A (en) | A kind of processing operation/maintenance work orders based on power information acquisition label | |
CN111125236B (en) | Three-dimensional dynamic information physical system based on GIS | |
CN112183379A (en) | Report-oriented multi-dimensional management analysis method and system | |
CN110633839A (en) | Kneading algorithm-based power failure maintenance plan analysis and optimization system | |
CN111311133B (en) | Monitoring system applied to power grid production equipment | |
CN105205185B (en) | The method of data interaction and data modeling between monitoring system and management information system | |
CN110490361A (en) | The digital emergency planning system and its design method of urban distribution network contingency management | |
CN104778551A (en) | Designing and analyzing method of visualization grid | |
CN108225439A (en) | A kind of electronic communication environment monitoring system | |
CN113627784A (en) | Enterprise asset management intelligent decision-making system based on industrial internet | |
CN112861494A (en) | Road network data-based visual report generation method, equipment and storage medium | |
CN110058126A (en) | Distribution network failure judgment method and device | |
CN115860694A (en) | Business expansion process management and control method and system based on instant message technology | |
CN115660602A (en) | Software supervision system based on smart building site management cloud platform | |
CN114896652A (en) | BIM-based industrial building informatization control terminal | |
CN104484734A (en) | Low-carbon city energy optimized configuration data center architecture | |
CN109801364A (en) | A kind of 3-dimensional digital modeling method and digitlization workshop management 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: 20190412 |
|
RJ01 | Rejection of invention patent application after publication |