CN109800420A - A kind of feasibility study review report automatic generation method and storage medium - Google Patents
A kind of feasibility study review report automatic generation method and storage medium Download PDFInfo
- Publication number
- CN109800420A CN109800420A CN201811558946.4A CN201811558946A CN109800420A CN 109800420 A CN109800420 A CN 109800420A CN 201811558946 A CN201811558946 A CN 201811558946A CN 109800420 A CN109800420 A CN 109800420A
- Authority
- CN
- China
- Prior art keywords
- information
- project
- data
- index
- effect
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of feasibility study review report automatic generation method and storage medium, wherein method includes the following steps, the project data of acquisition is parsed, the investment information in project data is extracted by machine learning algorithm, procedural information, output information and effect information are identified, extract separation from project data, wherein, investment information includes the title of project, target fund or funds source associated description;Procedural information includes project duration, and budget enforcement associated description, output information includes physical assets, the title of such as output object, specification, quantity or the value for forming efficient portfolio;Effect information includes technical effect, economic benefit, managerial experiences, the associated description of social influence, and the investment information, procedural information, output information and effect information are classified and presented, and generates project application for developing.Solve the problems, such as that the related application for developing of project data cannot be automatically generated in the prior art.
Description
Technical field
The present invention relates to a kind of generation method of specialized dictionary in natural language processing field more particularly to power industry and
Storage medium.
Background technique
The evaluation major part application for developing of feasibility study content uploads to system at present, manually comments by being manually downloaded under line
It examines, grass-roots unit, the provinces and cities number of entry is more, and feasibility study document content is complicated, and basic staff business specialized capability is irregular, evaluation
Expert Resources are limited, and therefore, feasibility study content evaluation link is all the time weaker, and feasibility study is caused to evaluate low efficiency, as received basis
Amount is not high, and feasibility study depth is difficult to control.In order to solve the difficult landing of feasibility study economy audit, input and output lack practice demonstration, close
The problems such as rule property audit matter effect is bad, using technologies such as text analyzing and natural language processings, in conjunction with the rule of business experts' evaluation
Then deep examination and understand correlation report file, precisely points out disadvantage and potential problem in report, it is automatic by providing
The audit of change helps user to solve the problems, such as the audit of time and effort consuming, automates in conjunction with review report template and generates feasibility study evaluation report
It accuses, to improve the Compilation Quality of application for developing and the efficiency of evaluation.
Summary of the invention
For this reason, it may be necessary to provide a kind of feasibility study review report automatic generation method, solve in the prior art for project appraisal
Auxiliary information analytic technique it is certain, application for developing is required to the problem of manually generating;
To achieve the above object, a kind of feasibility study review report automatic generation method is inventor provided, is included the following steps,
The project data of acquisition is parsed, the investment information in project data, procedural information, production are extracted by machine learning algorithm
Information and effect information are identified, extract separation from project data out, wherein investment information includes the title of project, mesh
Mark fund or funds source associated description;Procedural information includes project duration, and budget enforcement associated description, output information includes real
Goods and materials production, the title of such as output object, specification, quantity or the value for forming efficient portfolio;Effect information includes technical effect, economy
Benefit, managerial experiences, the associated description of social influence,
The investment information, procedural information, output information and effect information are classified and presented, project application for developing is generated.
It specifically, further include step, integration project knowledge meta-model realizes data and index sentence group's contextual information, takes out
Time, main body, index, predicate, numerical value, unit are taken, then in conjunction with region library, industry vocabulary or mechanism characteristics vocabulary, while structure
It makes index storehouse and the extraction and identification that strategy carries out indication information is extracted using the machine learning method co-host of manual oversight, together
When integration project structuring essential information, realize the extraction of structural data index.
A kind of feasibility study review report automatically generates storage medium, is stored with computer program, the computer program is in quilt
It is followed the steps below when execution, the project data of acquisition is parsed, extracted in project data by machine learning algorithm
Information is put into, procedural information, output information and effect information are identified, extract separation from project data, wherein investment letter
Breath includes title, target fund or the funds source associated description of project;Procedural information includes project duration, and budget enforcement is related
Description, output information include physical assets, the title of such as output object, specification, quantity or the value for forming efficient portfolio;Effect letter
Breath includes technical effect, economic benefit, managerial experiences, the associated description of social influence,
The investment information, procedural information, output information and effect information are classified and presented, project application for developing is generated.
Preferably, the computer program also carries out including step when executed, and integration project knowledge meta-model is realized
Data and index sentence group's contextual information extract time, main body, index, predicate, numerical value, unit, then in conjunction with region library, row
Industry vocabulary or mechanism characteristics vocabulary, while constructing index storehouse and strategy is extracted using the machine learning method co-host of manual oversight
The extraction and identification for carrying out indication information realize structural data index in combination with the essential information of the structuring of project
It extracts.
It is different from the prior art, project data by being divided into " investment, process, output, benefit " four aspect by the present invention
Description solves the problems, such as that Pre-reading is connected defective tightness with monitoring, post-project evaluating in thing.Facilitate the automatic life of application for developing
At, improve project data examination efficiency.
Detailed description of the invention
Fig. 1 is the feasibility study review report automatic generation method flow chart that an embodiment of the present invention is related to.
Specific embodiment
Technology contents, construction feature, the objects and the effects for detailed description technical solution, below in conjunction with specific reality
It applies example and attached drawing is cooperated to be explained in detail.
Around company budgets informationization promotion and full-service data center operations content, with project feasibility study economy, finance
The problem of compliance is audited is point of penetration, introduces budget performance management philosophy, innovates intelligence evaluation tool, and realization project is examined online
Core " four can with ", i.e. " input and output are evaluable, investment field can collect, intelligence evaluation can apply, monomer benefit can be calculated ".
1, performance appraisal mechanism is established, appraisement modele is generated
The mechanism for relying on data-integrity, feasibility study economy and financial compliance evaluation work, carries out performance objective establishment
And evaluation.Wherein performance objective is mainly evaluated in terms of investment, process, output, effect four, and investment is primarily upon investment
Whether the direction of target is reasonable, whether fund utilization efficiency, financing package are feasible;Process is primarily upon project duration, and budget is held
Row harmony etc. embodies the timeliness that assets are formed;Output is primarily upon physical assets, title, specification, the quantity of output object,
Form the value of efficient portfolio;Effect is primarily upon benefit effect, and the effect in terms of technology, economy, management, society four carries out
Comprehensive consideration.
2, analysis model, template engine combination appraised index result are generated in conjunction with machine learning and natural language processing technique
Generate review report.
It is a kind of feasibility study review report automatic generation method of the present invention program, packet in embodiment once shown in Fig. 1
Following steps are included, S100 parses the project data of acquisition, extracts the investment in project data by machine learning algorithm
Information, procedural information, output information and effect information are identified, extract separation from project data, wherein investment packet
Include the title, target fund or funds source associated description of project;Procedural information includes project duration, and budget enforcement correlation is retouched
It states, output information includes physical assets, the title of such as output object, specification, quantity or the value for forming efficient portfolio;Effect information
Including technical effect, economic benefit, managerial experiences, the associated description of social influence,
S102, which classifies the investment information, procedural information, output information and effect information, to be presented, and project feasibility study report is generated
It accuses.
It can also specifically be achieved by the steps of:
1) Knowledge Element and knowledge hierarchy, are established according to the Whole Course Management of deposit project and appraisement modele.
2), in conjunction with knowledge base, the extraction and identification of project relevant knowledge member, secondary operation are realized.
Steps are as follows:
(1), non-structured document analytics engine is constructed, the non-structured documents such as WORD, EXCEL, PDF, WPS are read in support
Content, and picture and text analysis is carried out, realize the identification of content of text and table, image content.
(2), middle extract forms numerical value sentence group library containing the relevant sentence group of index in non-structured text content, including
Index sentence group identification and extraction, filtering, re-scheduling etc..
(3), integration project knowledge meta-model realizes data and index sentence group's contextual information, extracts the time, main body, refers to
Mark, predicate, numerical value, unit then in conjunction with region library, industry vocabulary, mechanism characteristics vocabulary, while constructing index storehouse co-host
The extraction and identification for extracting strategy progress indication information (use rule-based machine learning algorithm, constantly study and adjustment is each
Class scene, while manual oversight pattern learning is used, so that decimation rule is reached more excellent), in combination with the base of the structuring of project
This information realizes the extraction of structural data index, realizes the foundation of entire project knowledge system.
(4), the evaluation and analysis that every appraised index is realized according to appraisement modele realize appraised index according to score value weight
Marking.
(5), template engine combination review report template and indices review result generate review report, provide simultaneously
It checks and manually revises online.
A kind of feasibility study review report automatically generates storage medium, is stored with computer program, the computer program is in quilt
It is followed the steps below when execution, the project data of acquisition is parsed, extracted in project data by machine learning algorithm
Information is put into, procedural information, output information and effect information are identified, extract separation from project data, wherein investment letter
Breath includes title, target fund or the funds source associated description of project;Procedural information includes project duration, and budget enforcement is related
Description, output information include physical assets, the title of such as output object, specification, quantity or the value for forming efficient portfolio;Effect letter
Breath includes technical effect, economic benefit, managerial experiences, the associated description of social influence,
The investment information, procedural information, output information and effect information are classified and presented, project application for developing is generated.
Preferably, the computer program also carries out including step when executed, and integration project knowledge meta-model is realized
Data and index sentence group's contextual information extract time, main body, index, predicate, numerical value, unit, then in conjunction with region library, row
Industry vocabulary or mechanism characteristics vocabulary, while constructing index storehouse and strategy is extracted using the machine learning method co-host of manual oversight
The extraction and identification for carrying out indication information realize structural data index in combination with the essential information of the structuring of project
It extracts.
It should be noted that being not intended to limit although the various embodiments described above have been described herein
Scope of patent protection of the invention.Therefore, it based on innovative idea of the invention, change that embodiment described herein is carried out and is repaired
Change, or using equivalent structure or equivalent flow shift made by description of the invention and accompanying drawing content, it directly or indirectly will be with
Upper technical solution is used in other related technical areas, is included within scope of patent protection of the invention.
Claims (4)
1. a kind of feasibility study review report automatic generation method, which is characterized in that include the following steps, to the project data of acquisition into
Row parsing, by machine learning algorithm extract project data in investment information, procedural information, output information and effect information into
Separation is extracted in row identification from project data, wherein investment information includes the title of project, target fund or funds source phase
Close description;Procedural information includes project duration, and budget enforcement associated description, output information includes physical assets, such as output object
Title, specification, quantity or the value for forming efficient portfolio;Effect information includes technical effect, economic benefit, managerial experiences, society
The associated description that will affect,
The investment information, procedural information, output information and effect information are classified and presented, project application for developing is generated.
2. feasibility study review report automatic generation method according to claim 1, which is characterized in that it further include step, in conjunction with
Project knowledge meta-model realizes data and index sentence group's contextual information, extracts time, main body, index, predicate, numerical value, list
Position then in conjunction with region library, industry vocabulary or mechanism characteristics vocabulary, while constructing the machine learning that index storehouse uses manual oversight
Method co-host extracts the extraction and identification that strategy carries out indication information, in combination with the essential information of the structuring of project,
Realize the extraction of structural data index.
3. a kind of feasibility study review report automatically generates storage medium, which is characterized in that be stored with computer program, the computer
Program follows the steps below when executed, parses to the project data of acquisition, extracts project by machine learning algorithm
Investment information in data, procedural information, output information and effect information are identified, extract separation from project data,
In, investment information includes the title of project, target fund or funds source associated description;Procedural information includes project duration, in advance
It calculates and executes associated description, output information includes physical assets, such as the title of output object, specification, quantity or formation efficient portfolio
Value;Effect information includes technical effect, economic benefit, managerial experiences, the associated description of social influence,
The investment information, procedural information, output information and effect information are classified and presented, project application for developing is generated.
4. feasibility study review report according to claim 3 automatically generates storage medium, which is characterized in that the computer journey
Sequence also carries out including step when executed, and integration project knowledge meta-model realizes data and index sentence group's contextual information, takes out
Time, main body, index, predicate, numerical value, unit are taken, then in conjunction with region library, industry vocabulary or mechanism characteristics vocabulary, while structure
It makes index storehouse and the extraction and identification that strategy carries out indication information is extracted using the machine learning method co-host of manual oversight, together
When integration project structuring essential information, realize the extraction of structural data index.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811558946.4A CN109800420A (en) | 2018-12-19 | 2018-12-19 | A kind of feasibility study review report automatic generation method and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811558946.4A CN109800420A (en) | 2018-12-19 | 2018-12-19 | A kind of feasibility study review report automatic generation method and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109800420A true CN109800420A (en) | 2019-05-24 |
Family
ID=66557278
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811558946.4A Pending CN109800420A (en) | 2018-12-19 | 2018-12-19 | A kind of feasibility study review report automatic generation method and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109800420A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110766037A (en) * | 2019-08-30 | 2020-02-07 | 国网浙江省电力有限公司 | Processing method for storing item relevance cluster |
CN110968622A (en) * | 2019-12-20 | 2020-04-07 | 上海鲲贝管理咨询有限公司 | Accounting report customization method, platform and terminal |
CN112800739A (en) * | 2021-01-18 | 2021-05-14 | 国网青海省电力公司 | Excel-based standing book generation method and device and electronic equipment |
CN113408890A (en) * | 2021-06-16 | 2021-09-17 | 瑞格人工智能科技有限公司 | Artificial intelligence-based method and system for generating evaluation report after industrial investment project |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007241347A (en) * | 2006-03-06 | 2007-09-20 | Nomura Research Institute Ltd | Program quality management device, and method for creating quality management report of program |
CN105184513A (en) * | 2015-10-16 | 2015-12-23 | 北京恒华伟业科技股份有限公司 | Evaluation result output method and system |
CN106649223A (en) * | 2016-12-23 | 2017-05-10 | 北京文因互联科技有限公司 | Financial report automatic generation method based on natural language processing |
CN107730158A (en) * | 2017-11-29 | 2018-02-23 | 福建亿榕信息技术有限公司 | Power network project intelligent evaluation method and system |
-
2018
- 2018-12-19 CN CN201811558946.4A patent/CN109800420A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007241347A (en) * | 2006-03-06 | 2007-09-20 | Nomura Research Institute Ltd | Program quality management device, and method for creating quality management report of program |
CN105184513A (en) * | 2015-10-16 | 2015-12-23 | 北京恒华伟业科技股份有限公司 | Evaluation result output method and system |
CN106649223A (en) * | 2016-12-23 | 2017-05-10 | 北京文因互联科技有限公司 | Financial report automatic generation method based on natural language processing |
CN107730158A (en) * | 2017-11-29 | 2018-02-23 | 福建亿榕信息技术有限公司 | Power network project intelligent evaluation method and system |
Non-Patent Citations (1)
Title |
---|
周灿芳: "农业投资项目智能决策支持系统的研究与开发", 《农业图书情报学刊》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110766037A (en) * | 2019-08-30 | 2020-02-07 | 国网浙江省电力有限公司 | Processing method for storing item relevance cluster |
CN110766037B (en) * | 2019-08-30 | 2023-09-15 | 国网浙江省电力有限公司 | Processing method for reserve project relevance cluster |
CN110968622A (en) * | 2019-12-20 | 2020-04-07 | 上海鲲贝管理咨询有限公司 | Accounting report customization method, platform and terminal |
CN110968622B (en) * | 2019-12-20 | 2024-04-02 | 同济大学 | Accounting report customization method, platform and terminal |
CN112800739A (en) * | 2021-01-18 | 2021-05-14 | 国网青海省电力公司 | Excel-based standing book generation method and device and electronic equipment |
CN113408890A (en) * | 2021-06-16 | 2021-09-17 | 瑞格人工智能科技有限公司 | Artificial intelligence-based method and system for generating evaluation report after industrial investment project |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109800420A (en) | A kind of feasibility study review report automatic generation method and storage medium | |
CN115310425B (en) | Policy text analysis method based on policy text classification and key information identification | |
CN108153729B (en) | Knowledge extraction method for financial field | |
CN109992668A (en) | A kind of enterprise's the analysis of public opinion method and apparatus based on from attention | |
CN114168716A (en) | Deep learning-based automatic engineering cost extraction and analysis method and device | |
CN112100401B (en) | Knowledge graph construction method, device, equipment and storage medium for science and technology services | |
CN108563783A (en) | A kind of financial analysis management system and method based on big data | |
O’Leary | Big Data and knowledge management with applications in accounting and auditing: The case of Watson | |
CN109933783A (en) | A kind of essence of a contract method of non-performing asset operation field | |
CN115357719A (en) | Power audit text classification method and device based on improved BERT model | |
CN110046345A (en) | A kind of data extraction method and device | |
CN113138920A (en) | Software defect report allocation method and device based on knowledge graph and semantic role labeling | |
CN115455189A (en) | Policy text classification method based on prompt learning | |
Raza et al. | Applying artificial intelligence techniques for predicting the environment, social, and governance (ESG) pillar score based on balance sheet and income statement data: A case of non-financial companies of USA, UK, and Germany | |
Jackson et al. | From natural language to simulations: Applying gpt-3 codex to automate simulation modeling of logistics systems | |
CN113220885B (en) | Text processing method and system | |
CN103019924B (en) | The intelligent evaluating system of input method and method | |
Shweta et al. | Comparative study of feature engineering for automated short answer grading | |
Schmidt et al. | Leveraging textual information for improving decision-making in the business process lifecycle | |
Visalli et al. | ESG Data Collection with Adaptive AI. | |
US20230342693A1 (en) | Methods and apparatus for natural language processing and governance | |
Chen | Designing an Investment Research System for Asset Management Based on Natural Language Processing | |
CN117151117B (en) | Automatic identification method, device and medium for power grid lightweight unstructured document content | |
Zhang et al. | A semantic search framework for similar audit issue recommendation in financial industry | |
Zubair et al. | Natural Language Generation: Recent Advances and Applications |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190524 |