CN107730158A - Power network project intelligent evaluation method and system - Google Patents
Power network project intelligent evaluation method and system Download PDFInfo
- Publication number
- CN107730158A CN107730158A CN201711224844.4A CN201711224844A CN107730158A CN 107730158 A CN107730158 A CN 107730158A CN 201711224844 A CN201711224844 A CN 201711224844A CN 107730158 A CN107730158 A CN 107730158A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- user
- business element
- evaluation model
- score
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 59
- 238000013210 evaluation model Methods 0.000 claims abstract description 46
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 13
- 230000008901 benefit Effects 0.000 claims abstract description 8
- 230000009466 transformation Effects 0.000 claims abstract description 7
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 6
- 238000013135 deep learning Methods 0.000 claims abstract description 5
- 230000000694 effects Effects 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 5
- 235000013399 edible fruits Nutrition 0.000 claims description 5
- 238000013136 deep learning model Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007618 network scheduling algorithm Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Power network project budget intelligent evaluation method and system, wherein method comprises the following steps, business element is received, the business element includes scale of input, fund configuration, budget completion rate, investment plan completion rate, planned budget adjustment number, power transformation capacity, line length, cable length, economic benefit, safe mass or satisfaction;User's evaluation model information is received, user's evaluation model includes Rationality Assessment result, the target property reached result, and Automatic Evaluation Model is obtained as output training deep learning algorithm using business element as input, user's evaluation model;Project score is calculated according to business element and user's evaluation model, project appraisal result is obtained, improves the operating efficiency and mass content of evaluation, improve automation and the intelligent Application of evaluation.
Description
Technical field
The present invention relates to the office automatic field of power network project appraisal, more particularly to a kind of new power network project intelligence
Change reviewing method and system.
Background technology
Project budget performance review substantially uses manual examination and verification mode at present, extracts the key index of feasibility study content, people
Work carries out economic feasibility study, the examination & verification of financial compliance, lacks automation examination & verification processing, and examination amount is very big, the cycle is longer,
It is inefficient.Some projects use the method for fixed model+manual intervention under line to carry out, and evaluation model is relatively fixed, not clever enough
Living, autgmentability is not strong, and history evaluation data are failed to make full use of, the work such as lack of wisdomization application.
This invention mainly solve examination amount is big, inefficient, evaluation model is single, evaluation lack automation and intelligence
The problems such as changing.Electronic document is converted to by text-only file by OCR technique, using natural language and machine learning techniques,
Text feature information is extracted from various dimensions, natural text is converted to the data that can be analyzed, easily analyze.Combining assessment knowledge base,
Automatic Evaluation, output result and classification storage are carried out according to project performance evaluation model, using association study, cluster calculation, god
Depth self study is carried out through network scheduling algorithm, constantly corrects evaluating, improves evaluation knowledge base.Introduce regulation engine simultaneously
And artificial intelligence technology, the operating efficiency and mass content of evaluation are substantially increased, improves the automation and intellectuality of evaluation
Using.
The content of the invention
For this reason, it may be necessary to provide a kind of new power network project intelligent evaluation method, solves existing power network project scoring examination & verification
There is no the problem of Automated check function.
To achieve the above object, a kind of power network project budget intelligent evaluation method, including following step are inventor provided
Suddenly, receive business element, the business element include scale of input, fund configuration, budget completion rate, investment plan completion rate,
Planned budget adjustment number, power transformation capacity, line length, cable length, economic benefit, safe mass or satisfaction;
User's evaluation model information is received, user's evaluation model includes Rationality Assessment result, the target property reached knot
Fruit, Automatic Evaluation Model is obtained as output training deep learning algorithm using business element as input, user's evaluation model;
Project score is calculated according to business element and user's evaluation model, obtains project appraisal result.
Specifically, the Rationality Assessment result includes input score, process score, output score and effect score;Institute
Stating the target property reached result includes target weight, deviation ratio, target grading.
Further, in addition to step, Integrity Assessment is carried out according to the index of business element, and evaluation result is classified
Collect.
A kind of power network project budget intelligent evaluation system, including following module, business element module, user evaluate mould
Block, training module, computing module;
The business element module is used to receive business element, and the business element includes scale of input, fund configures, pre-
Calculate completion rate, investment plan completion rate, planned budget adjustment number, power transformation capacity, line length, cable length, economic benefit,
Safe mass or satisfaction;
User's evaluation module is used to receive user's evaluation model information, and user's evaluation model is commented including reasonability
Valency result, the target property reached result,
The training module trains deep learning model using business element as input, user's evaluation model as output,
Obtain Automatic Evaluation Model;
The computing module is used to calculate project score according to business element and user's evaluation model, obtains project appraisal knot
Fruit.
Specifically, the Rationality Assessment result includes input score, process score, output score and effect score;Institute
Stating the target property reached result includes target weight, deviation ratio, target grading.
Further, in addition to integrity module, the integrity module are used to carried out according to the index of business element
The evaluation of whole property, and by evaluation result Classifying Sum.
By above-mentioned design, this programme can be on the premise of incoming traffic element be limited, and business element is converted to can
Calculate, the parameter easily analyzed, improve project appraisal intelligence degree.
Brief description of the drawings
Fig. 1 is the power network project intelligent evaluation method flow diagram described in the specific embodiment of the invention;
Fig. 2 is the power network project intelligent evaluation system module figure described in the specific embodiment of the invention.
Description of reference numerals
200th, business element module
202nd, user's evaluation module
204th, training module
206th, computing module;
208th, integrity module.
Embodiment
To describe the technology contents of technical scheme, construction feature, the objects and the effects in detail, below in conjunction with specific reality
Apply example and coordinate accompanying drawing to be explained in detail.
Referring to Fig. 1, a kind of power network project budget intelligent evaluation method, comprises the following steps, S100 receives business member
Element, the business element include scale of input, fund configuration, the adjustment time of budget completion rate, investment plan completion rate, planned budget
Number, power transformation capacity, line length, cable length, economic benefit, safe mass or satisfaction;Above-mentioned parameter is generally numeral,
Receive one kind in above-mentioned business element or it is several after store, wait subsequent treatment.
S102 receives user's evaluation model information, and user's evaluation model includes Rationality Assessment result, target is reached
Property result, specifically, the Rationality Assessment result includes input score, process score, output score and effect score;It is described
The target property reached result includes target weight, deviation ratio, target grading.Also carry out step S104 using business element as input,
User's evaluation model obtains Automatic Evaluation Model as output training deep learning algorithm;Automatic Evaluation Model after training exists
When inputting new business element item collection, evaluation model, newly-generated automatic Evaluation can be generated automatically according to business element
Model can automatically generate Rationality Assessment result, the target property reached result by the input of business element, reach automatically to industry
Business element input carries out the effect of preliminary treatment.
Also carry out step S106 and project score is calculated according to business element and user's evaluation model or Automatic Evaluation Model, obtain
To project appraisal result.The calculating of review result can be according to business element item input value, input score, process score, output
Score, effect score, target weight, deviation ratio and the numerical computations of target grading draw, by the above method, solve power network
It can not be inputted in project intellectuality according to business element and automatically generate evaluation model, evaluation knot is automatically generated further according to evaluation model
The problem of fruit.
In some further embodiments, in addition to step, Integrity Assessment is carried out according to the index of business element, and
By evaluation result Classifying Sum.In the particular embodiment, score can also be calculated automatically according to according to indices coefficient, and
Evaluation result is conversed automatically according to metrics evaluation collection (V1 is complete, V2 is substantially complete, V3 is imperfect, V4 is very imperfect), and
Classifying Sum.The intelligentized effect of raising power network project is preferably reached by such scheme.
In the embodiment shown in Figure 2, a kind of power network project intelligent evaluation system, including following module, business are introduced
Element module 200, user's evaluation module 202, training module 204, computing module 206;
The business element module is used to receive business element, and the business element includes scale of input, fund configures, pre-
Calculate completion rate, investment plan completion rate, planned budget adjustment number, power transformation capacity, line length, cable length, economic benefit,
Safe mass or satisfaction;
User's evaluation module is used to receive user's evaluation model information, and user's evaluation model is commented including reasonability
Valency result, the target property reached result,
The training module trains deep learning model using business element as input, user's evaluation model as output,
Obtain Automatic Evaluation Model;
The computing module is used to calculate project score according to business element and user's evaluation model, obtains project appraisal knot
Fruit.
In specific embodiment, the Rationality Assessment result includes input score, process score, output score and effect
Score;The target property the reached result includes target weight, deviation ratio, target grading.Set by said system, solve electricity
It can not be inputted in net project intellectuality according to business element and automatically generate evaluation model, evaluation is automatically generated further according to evaluation model
As a result the problem of.
In the further embodiment shown in Fig. 2, in addition to integrity module 208, the integrity module are used for root
Integrity Assessment is carried out according to the index of business element, and by evaluation result Classifying Sum.Set by above-mentioned module, preferably reached
The intelligentized effect of raising power network project is arrived.
The intellectualizing system of the present invention program also includes following functions:
(1) material electronicsizationes processing is evaluated, according to<Input, process, output, effect>Etc. the electricity that dimension carries out evaluation material
Sonization file process, electronic disposal is carried out to evaluation material using high photographing instrument, scanner etc., according to business rule template definition
It is automatic to extract business element.
(2) evaluation model management function, the principle evaluated according to target Rationality Assessment and the target property reached are evaluated
The Template Manager of model.Target reasonability is carried out according to SMART principles, and target examining content is using standard x ML configurations, using commenting
Point system is examined.The target property reached is set according to weight and single target is reached marking mode and carried out, and weight and reaches scoring
Standard is configured using standard x ML, is examined using graduation.
(3) automatic Evaluation is handled, according to evaluation element (scale of input, fund configuration, the budget completion of standard x ML configurations
Rate, investment plan completion rate, planned budget adjustment number, power transformation capacity, line length, cable length, economic benefit, safe matter
Amount, satisfaction etc.), according to target Rationality Assessment (input, process, output and effect) and the target property reached (target weight, partially
Rate, score grading) dimension evaluated.Using multithreading and rule engine technique, evaluation element is automatically processed, from
Whether dynamic generation project objective examination result (finds to include other list-items, whether finds partition project verification, whether finds project
Capital expenditures and cost-effectivenes pay that division is inaccurate, whether finds to tear open that past heritage money quantity and processing scheme are unreasonable, whether send out
Existing engineering other fees expenditure is unreasonable), score is calculated automatically according to indices coefficient, and (V1 is complete according to metrics evaluation collection
Whole, V2 is substantially complete, V3 is imperfect, V4 is very imperfect) evaluation result, and Classifying Sum are conversed automatically.
(4) knowledge base management is evaluated, classification storage is carried out to evaluation result, classification pipe is carried out according to 16 class special project types
Reason, it is managed according to dimensions such as item types, item attribute, evaluation element, evaluation index, evaluation coefficient, evaluation results.Comment
Valency knowledge base is that the power network project budget evaluates a kind of new method, by constantly learning, accumulates project appraisal empirical value.Using
Deeplearning4j frameworks, the evaluation attributes of same project type are compared using clustering algorithm, constantly excavated
New evaluation element and index.Learnt by correlation rule, the associated data of assay element and index, improve evaluation rule
Then.Decision tree is generated using neural network algorithm, deep learning, constantly improve evaluation element and evaluation are carried out to evaluation knowledge base
Index, complete evaluation knowledge base self-teaching process.
It should be noted that although the various embodiments described above have been described herein, but not thereby limit
The scope of patent protection of the present invention.Therefore, based on the present invention innovative idea, to embodiment described herein carry out change and repair
Change, or the equivalent structure or equivalent flow conversion made using description of the invention and accompanying drawing content, directly or indirectly will be with
Upper technical scheme is used in other related technical areas, is included within the scope of patent protection of the present invention.
Claims (6)
- A kind of 1. power network project intelligent evaluation method, it is characterised in that comprise the following steps, receive business element, the industry Business element includes scale of input, fund configuration, budget completion rate, investment plan completion rate, planned budget adjustment number, change electric capacity Amount, line length, cable length, economic benefit, safe mass or satisfaction;User's evaluation model information is received, user's evaluation model includes Rationality Assessment result, the target property reached result, will Business element obtains Automatic Evaluation Model as input, user's evaluation model as output training deep learning algorithm;Project score is calculated according to business element and user's evaluation model, obtains project appraisal result.
- 2. power network project according to claim 1 can change reviewing method, it is characterised in that the Rationality Assessment result bag Include input score, process score, output score and effect score;The target property the reached result include target weight, deviation ratio, Target is graded.
- 3. power network project intelligent evaluation method according to claim 1, it is characterised in that also including step, according to industry The index of element of being engaged in carries out Integrity Assessment, and by evaluation result Classifying Sum.
- 4. a kind of power network project intelligent evaluation system, it is characterised in that including following module, business element module, Yong Huping Valency module, training module, computing module;The business element module is used to receive business element, and the business element includes scale of input, fund configures, budget is complete Into rate, investment plan completion rate, planned budget adjustment number, power transformation capacity, line length, cable length, economic benefit, safety Quality or satisfaction;User's evaluation module is used to receive user's evaluation model information, and user's evaluation model includes Rationality Assessment knot Fruit, the target property reached result,The training module obtains business element as input, user's evaluation model as output training deep learning model Automatic Evaluation Model;The computing module is used to calculate project score according to business element and user's evaluation model, obtains project appraisal result.
- 5. power network project intelligent evaluation system according to claim 4, it is characterised in that the Rationality Assessment result Including input score, process score, output score and effect score;The target property the reached result includes target weight, deviation Rate, target grading.
- 6. power network project intelligent evaluation system according to claim 4, it is characterised in that also including integrity module, The integrity module is used to carry out Integrity Assessment according to the index of business element, and by evaluation result Classifying Sum.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711224844.4A CN107730158A (en) | 2017-11-29 | 2017-11-29 | Power network project intelligent evaluation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711224844.4A CN107730158A (en) | 2017-11-29 | 2017-11-29 | Power network project intelligent evaluation method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107730158A true CN107730158A (en) | 2018-02-23 |
Family
ID=61218792
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711224844.4A Pending CN107730158A (en) | 2017-11-29 | 2017-11-29 | Power network project intelligent evaluation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107730158A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108171487A (en) * | 2018-03-27 | 2018-06-15 | 国家电网公司 | A kind of project of transmitting and converting electricity design review system |
CN109345133A (en) * | 2018-10-17 | 2019-02-15 | 大国创新智能科技(东莞)有限公司 | Reviewing method and robot system based on big data and deep learning |
CN109800420A (en) * | 2018-12-19 | 2019-05-24 | 福建亿榕信息技术有限公司 | A kind of feasibility study review report automatic generation method and storage medium |
CN110427675A (en) * | 2019-07-23 | 2019-11-08 | 江西博微新技术有限公司 | A kind of data detection method for three dimensional design evaluation |
CN114926012A (en) * | 2022-05-16 | 2022-08-19 | 广东省技术经济研究发展中心 | Intelligent acceptance and review method and system for research and development project and readable storage medium |
-
2017
- 2017-11-29 CN CN201711224844.4A patent/CN107730158A/en active Pending
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108171487A (en) * | 2018-03-27 | 2018-06-15 | 国家电网公司 | A kind of project of transmitting and converting electricity design review system |
CN109345133A (en) * | 2018-10-17 | 2019-02-15 | 大国创新智能科技(东莞)有限公司 | Reviewing method and robot system based on big data and deep learning |
CN109800420A (en) * | 2018-12-19 | 2019-05-24 | 福建亿榕信息技术有限公司 | A kind of feasibility study review report automatic generation method and storage medium |
CN110427675A (en) * | 2019-07-23 | 2019-11-08 | 江西博微新技术有限公司 | A kind of data detection method for three dimensional design evaluation |
CN110427675B (en) * | 2019-07-23 | 2023-01-03 | 江西博微新技术有限公司 | Data detection method for three-dimensional design review |
CN114926012A (en) * | 2022-05-16 | 2022-08-19 | 广东省技术经济研究发展中心 | Intelligent acceptance and review method and system for research and development project and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107730158A (en) | Power network project intelligent evaluation method and system | |
CN113642088B (en) | Method for feeding back construction progress information and displaying deviation of BIM (building information modeling) model in real time | |
CN112383052B (en) | Power grid fault repairing method and device based on power internet of things | |
CN109033497B (en) | High-concurrency-oriented multi-stage data mining algorithm intelligent selection method | |
CN107861942A (en) | A kind of electric power based on deep learning is doubtful to complain work order recognition methods | |
CN108154430A (en) | A kind of credit scoring construction method based on machine learning and big data technology | |
CN106483947A (en) | Distribution Running State assessment based on big data and method for early warning | |
CN108229828A (en) | A kind of analysis system based on industrial data | |
CN107368918A (en) | Data processing method and device | |
CN105931116A (en) | Automated credit scoring system and method based on depth learning mechanism | |
CN101826090A (en) | WEB public opinion trend forecasting method based on optimal model | |
CN103092975A (en) | Detection and filter method of network community garbage information based on topic consensus coverage rate | |
CN108985542A (en) | A kind of evaluation on S&T projects method and system | |
CN105574544A (en) | Data processing method and device | |
CN110147389A (en) | Account number treating method and apparatus, storage medium and electronic device | |
CN108446885A (en) | A kind of automatic collecting method of review comment | |
CN112785427B (en) | Enterprise credit analysis system based on power data | |
CN108228788A (en) | Guide of action automatically extracts and associated method and electronic equipment | |
CN114202243A (en) | Engineering project management risk early warning method and system based on random forest | |
CN109299753A (en) | A kind of integrated learning approach and system for Law Text information excavating | |
CN112347254A (en) | News text classification method and device, computer equipment and storage medium | |
CN116775879A (en) | Fine tuning training method of large language model, contract risk review method and system | |
CN115794803A (en) | Engineering audit problem monitoring method and system based on big data AI technology | |
CN107798137B (en) | A kind of multi-source heterogeneous data fusion architecture system based on additive models | |
CN115438190B (en) | Power distribution network fault auxiliary decision knowledge extraction method and 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180223 |