1. A method for generating a post-evaluation report of an industrial investment project is characterized by comprising the following steps of establishing a post-evaluation database aiming at the industrial investment project;

selecting an evaluation report template;

collecting project information;

extracting an evaluation index;

evaluating economic benefits;

and generating an evaluation report.

2. The post-evaluation report generating method according to claim 1, wherein the post-evaluation database includes an evaluation report template, an evaluation index, an economic benefit evaluation model, laws and regulations, standard data, and policy documents.

3. The post-evaluation report generation method according to claim 1, wherein the collection of project information is to collect important information of an industrial investment project at an early stage, a construction period and an operation period, the collection mode includes manual input and file uploading, the manually input content is project basic information and content obtained by site interview investigation, and the file uploading is to upload a data list to be consulted according to post-evaluation of different project types.

4. The post-evaluation report generation method according to claim 1, wherein the extracting of the evaluation index is extracting the collected project information according to the evaluation index corresponding to the selected report template, and the extracting manner includes direct extraction and indirect extraction, wherein,

the direct extraction is to adopt OCR character recognition technology and NLP natural language processing technology to process unstructured data in the project information, extract corresponding structured data of post-evaluation index,

the indirect extraction is to process the directly extracted index data according to an agreed rule to obtain other evaluation index data in the selected post-evaluation report template.

5. The method of claim 1, wherein the step of evaluating economic benefits comprises determining economic benefit evaluation input metrics and calculating based on the selected economic benefit evaluation model.

6. The method for generating a post-evaluation report according to claim 1, wherein in the generation of the evaluation report, a deep learning algorithm is adopted, and evaluation conclusion and suggestion of industrial investment projects are automatically generated based on the extracted evaluation index data and information including laws, regulations, national and industrial standard data and policy documents in the post-evaluation database.

7. A system for generating an evaluation report after an industrial investment project is characterized by comprising a server, a storage and a display, wherein the server is provided with the storage; and

a processor coupled to the memory, the processor configured to execute a plurality of program modules stored in the memory, the program modules including a project information collection module, an evaluation index extraction module, an economic benefit assessment module, a report generation module, a post-evaluation database module,

the project information acquisition module is used for acquiring important information of project earlier stage, construction period and operation period, and specifically comprises a manual input module and a file uploading module, wherein,

the manual input module is used for directly inputting basic information of a project and contents acquired by field interview research by a user,

the file uploading module is used for uploading files respectively according to data lists needing to be consulted for post-evaluation of different project types by a user;

the evaluation index extraction template is used for extracting the data of the evaluation index after extraction and comprises a direct extraction module and an indirect extraction module, wherein,

the direct extraction module is used for processing unstructured data in the project information based on an OCR character recognition technology and an NLP natural language processing technology,

the indirect extraction module is used for processing the directly extracted index data according to an agreed rule to obtain other evaluation index data in the selected post-evaluation report template;

the economic benefit evaluation template is used for evaluating the economic benefit of a project and comprises an index confirmation module and a calculation evaluation module, wherein,

the index confirmation module is used for confirming the input index data of the economic benefit evaluation,

the calculation evaluation module is used for calculating the confirmed input index according to the selected economic benefit evaluation model;

the report generation template is used for generating a post-evaluation report and comprises an automatic generation module and a manual review module, wherein,

the automatic generation module is used for calling the extracted indexes and the economic benefit evaluation data to fill in the report template, intelligently compiling evaluation conclusions and suggestions based on a deep learning algorithm, generating an initial version of the evaluation report,

and the manual auditing module is used for auditing and modifying the evaluation report after the initial edition by a user to generate an evaluation report after the final edition.

And the post-evaluation database module is used for storing various data related to post-evaluation work, and comprises a report template, evaluation indexes, an economic benefit evaluation model, laws and regulations, national and industrial standard data and policy documents.

8. A post-industrial investment project evaluation report generation terminal, characterized in that the terminal issues a request to a server in the post-evaluation report generation system according to claim 7, said server providing a post-industrial investment project evaluation report in response to the request.

9. A storage medium on which a computer program is stored which, when executed by a processor, carries out the method of any one of claims 1 to 6.

Background

The post-industrial investment project evaluation is the activities of managing, developing and analyzing benefits, evaluating, proposing improvement suggestions, providing experience for subsequent projects and the like of the industrial investment project of which the investor completes the completion settlement or completes and purchases and operates for a certain time. The post-evaluation of the industrial investment project is taken as an important link in the investment management process of industrial enterprises, and the investment decision management level is favorably improved and the enterprise investment target is realized by summarizing experience and searching deficiency.

And at the present stage, evaluating work is carried out after industrial investment projects, and after-evaluation personnel manually collect a large amount of data including research reports, review and approval documents, construction acceptance documents, production data, financial statements and the like in the early stage of the projects, browse and look up all project data one by one, manually sort key data, carry out contrastive analysis and write research reports. The traditional mode not only causes large workload of post-evaluation personnel, higher labor and time costs and lower working efficiency, but also has a series of problems of non-uniform evaluation model standards, subjective factor influence on data analysis, non-standard report formats, uneven report quality and the like.

Disclosure of Invention

The embodiment of the invention provides a method for generating a post-evaluation report of an industrial investment project, which comprises the steps of establishing a post-evaluation database aiming at the industrial investment project; selecting an evaluation report template; collecting project information; extracting an evaluation index; evaluating economic benefits; and generating an evaluation report. And in the evaluation report generation process, a deep learning algorithm is adopted, the evaluation conclusion and the suggestion of the project are automatically generated based on the extracted evaluation index data and the information in the post-evaluation database, the evaluation conclusion and the suggestion are intelligently compiled, an initial post-evaluation report is generated, manual examination and modification are carried out, and a final post-evaluation report is generated. The invention overcomes the defects in the generation process of the existing evaluation report after investment projects and provides a standard and accurate evaluation report approved by an investor.

Drawings

The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:

fig. 1 is a flowchart of a method for automatically generating an evaluation report after an industrial investment project based on artificial intelligence according to one embodiment of the present invention.

Fig. 2 is a block diagram of an automatic post-industrial investment project evaluation report generation system based on artificial intelligence according to an embodiment of the present invention.

Detailed Description

The problems of low efficiency, non-standardization and the like existing in the existing artificially written evaluation report realize the intelligent compilation of the post-evaluation report, reduce the time and labor cost of post-evaluation work input, and greatly improve the efficiency and quality of the post-evaluation work.

According to one or more embodiments, as shown in fig. 1, a method for automatically generating an evaluation report after an industrial investment project based on artificial intelligence technology comprises the following steps:

selecting a report template; collecting project information; extracting an evaluation index; evaluating economic benefits; and calling the extracted indexes and the economic benefit evaluation data to fill in a report template, intelligently compiling evaluation conclusions and suggestions, generating an initial edition of a post-evaluation report, manually auditing and modifying, and generating a final edition of the post-evaluation report. In particular, the method also comprises the following steps,

1) selecting a reporting template is selecting a reporting template in the post-evaluation database based on the item type.

2) The project information acquisition is to acquire important information of project earlier stage, construction period and operation period, the acquisition mode comprises manual input and file uploading, the manual input content is project basic information and on-site interview investigation acquisition content, and the file uploading is to respectively upload data lists which need to be consulted according to post-evaluation of different project types.

3) And extracting the evaluation indexes, namely extracting the acquired project information according to the evaluation indexes corresponding to the selected report template, wherein the extraction mode comprises direct extraction and indirect extraction, wherein the direct extraction is to process unstructured data in the project information by adopting an OCR character recognition technology and an NLP natural language processing technology and extract the corresponding structured data of the post-evaluation indexes. The indirect extraction is to process the directly extracted index data according to an agreed rule to obtain other evaluation index data in the selected post-evaluation report template. And the related keyword matching method is realized by keyword grabbing based on understanding of investment evaluation and keyword grabbing based on natural semantic analysis. Keyword grabbing realized based on understanding of investment evaluation provides a configuration label based on investment evaluation understanding aiming at the keywords, and the extraction accuracy is effectively improved. The keyword grabbing based on natural semantic analysis is realized by building an NLP model, carrying out accurate semantic analysis on text/table contents and extracting keyword information.

4) The intelligent compilation evaluation conclusion and suggestion adopts a deep learning algorithm, and automatically generates evaluation conclusion and suggestion of a project based on extracted post-evaluation index data and information in a post-evaluation database, including laws and regulations, national and industrial standard data, policy documents and the like.

In accordance with one or more embodiments, as shown in fig. 2, a post-industrial investment project evaluation report automatic generation system based on artificial intelligence technology, the system comprising: the system comprises a project information acquisition module, an evaluation index extraction module, an economic benefit evaluation module, a report generation module and a post-evaluation database module. In particular, the method comprises the following steps of,

1) the project information acquisition module is used for acquiring important information of project earlier stage, construction period and operation period, and specifically comprises a manual input module and a file uploading module. The file uploading module is used for uploading files respectively according to data lists needing to be consulted for post evaluation of different project types.

2) The evaluation index extraction template is used for extracting data of the evaluation index after extraction, and specifically comprises a direct extraction module and an indirect extraction module. The direct extraction module is used for processing unstructured data in the project information based on an OCR character recognition technology and an NLP natural language processing technology, and the indirect extraction module is used for processing the directly extracted index data according to an agreed rule to obtain other evaluation index data in the selected post-evaluation report template.

3) The economic benefit evaluation template is used for evaluating the economic benefit of a project and specifically comprises an index confirmation module and a calculation evaluation module. The index confirmation module is used for confirming input index data of economic benefit evaluation, and the calculation evaluation module is used for calculating the confirmed input index according to the selected economic benefit evaluation model.

4) The report generation template is used for generating a post-evaluation report and specifically comprises an automatic generation module and a manual review module. The automatic generation module is used for calling the extracted indexes and the economic benefit evaluation data to fill in the report template, intelligently compiling evaluation conclusions and suggestions based on a deep learning algorithm and generating an initial version of the post-evaluation report, and the manual review module is used for a user to review and modify the initial version of the post-evaluation report and generate a final version of the post-evaluation report.

5) And the post-evaluation database module is used for storing various data related to post-evaluation work, and comprises a report template, evaluation indexes, an economic benefit evaluation model, laws and regulations, national and industrial standard data, policy files and the like.

The beneficial effects of the invention include:

1. the invention can realize the online acquisition and classified lookup of industrial investment project information, and avoid the complexity of manually collecting project data and the inconvenience of looking up the data.

2. The invention can realize the automatic grabbing of the evaluation indexes after the industrial investment project, simplifies the work of manually looking up a large amount of project data and combing the indexes, and greatly saves the labor and time cost.

3. The invention can provide different post-evaluation report fixing templates according to different project types, and can effectively reduce the problems of non-standardization in the post-evaluation report and easy error occurrence in manual editing.

4. The invention takes a huge database as a support and adopts artificial intelligence technologies such as a deep learning algorithm and the like, so that the report content is more comprehensive and deeper.

5. The invention can realize the more rapid and accurate generation of the post-evaluation report of the industrial investment project and effectively improve the efficiency and quality of the post-evaluation work.

The method adopts a deep learning algorithm, automatically generates the evaluation conclusion and suggestion of the project based on the extracted post-evaluation index data and the information in the post-evaluation database, supports definite evaluation index data replacement, can automatically generate non-standardized data content, and has wide application range. The method can be applied to post-evaluation work of industrial investment projects, greatly improves the efficiency of the post-evaluation work, reduces the input cost, and realizes the intellectualization of the post-evaluation work. In addition, the invention can also be applied to other business fields for generating reports in any form and content based on file data, and users can adjust the report template and index information according to business requirements to quickly obtain report content.

The invention, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.