Project information base construction method and system for feasibility research stage of power grid infrastructure project

Abstract

The invention relates to a project information base construction method and system for the feasibility research stage of a power grid infrastructure project, and the method comprises the following steps: obtaining the related business data of the feasibility research stage of the power grid infrastructure project, and carrying out the preprocessing; the method comprises the following steps: acquiring a data file of a feasibility research stage of a multi-modal power grid infrastructure project, performing multi-modal file analysis, and respectively identifying characters and keywords; defining project fields, and constructing an empty project information base; and based on the preprocessed related business data and the identified characters and keywords, matching according to project fields and mapping to the empty project information base to form a final project information base of the feasibility research stage. Compared with the prior art, the method has the advantages of accuracy, rapidness and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of data statistics, and in particular to a method and system for constructing a project information database in the feasibility study stage of a power grid infrastructure project. Background Art

[0002] With the rapid development of power systems and the continuous advancement of grid construction, the complexity and scale of grid infrastructure projects are increasing. During the feasibility study phase of a project, a large amount of information involving technical, economic, environmental and social impacts needs to be comprehensively evaluated and analyzed.

[0003] Traditional methods rely on manual collection and organization of this information, which is not only inefficient but also prone to inaccurate, incomplete, or untimely updates, impacting project decision-making and implementation. During the feasibility study phase of power grid infrastructure projects, the accuracy and completeness of information are crucial. Incorrect or outdated information can lead to biased project evaluations, impacting the project's economic and technical feasibility. Therefore, there is an urgent need for a method that can efficiently and accurately construct and manage a power grid infrastructure project information database to support scientific decision-making and smooth project implementation. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for constructing a project information database in the feasibility study stage of a power grid infrastructure project, which realizes automatic organization of information in the feasibility study stage.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] A method for constructing a project information database in the feasibility study phase of a power grid infrastructure project comprises the following steps:

[0007] Obtain relevant business data during the feasibility study phase of power grid infrastructure projects and perform pre-processing;

[0008] Obtain data files from the feasibility study phase of multimodal power grid infrastructure projects, perform multimodal file parsing, and identify characters and keywords;

[0009] Define project fields and build an empty project information base;

[0010] Based on the pre-processed relevant business data and the identified characters and keywords, matching is performed according to the project fields and mapped into the empty project information database to form the final project information database for the feasibility study stage.

[0011] Furthermore, the pre-processing step includes:

[0012] Deduplication processing is performed on the relevant business data;

[0013] Based on the deduplicated relevant business data, the missing values are filled using the filling method or prediction method to complete the preprocessing process.

[0014] Furthermore, the filling method uses the mean or median to fill the missing values, and the prediction method uses Lagrange polynomial interpolation to predict the missing values.

[0015] Furthermore, the step of predicting missing values using the Lagrange polynomial interpolation method includes:

[0016] Construct a set of Lagrangian basis functions L i (x)(i=0,...,n):

[0017]

[0018] In the formula, K is the unknown coefficient, x i 、x j are data points and corresponding known values, respectively. The Lagrange basis function is a polynomial of degree not exceeding n, with the following properties:

[0019]

[0020] Where x j is a data node, so the Lagrangian basis function is expressed as:

[0021]

[0022] Where ∏ is the continuous product;

[0023] The Lagrange basis functions are linearly combined to obtain the Lagrange interpolation polynomial:

[0024]

[0025] Where L(x) is the Lagrange interpolation polynomial;

[0026] Verify whether the Lagrange interpolation polynomial meets the interpolation condition, where the interpolation condition is:

[0027] y i =P(x i )(i=0,1,...,n)

[0028] The missing value at the missing point is predicted based on the verified Lagrange interpolation polynomial.

[0029] Furthermore, the modalities of the data file include picture modality and document modality, wherein the document modality includes PDF, Word, and Excel.

[0030] Furthermore, the steps of respectively identifying characters and keywords include:

[0031] For image modal:

[0032] Recognize characters from an image using OCR technology and correct them using post-processing technology to obtain a final character recognition result of the image, wherein the post-processing technology includes spelling correction, language model error correction, and rule verification. A method for constructing a project information database in the feasibility study stage of a power grid infrastructure project.

[0033] For document modal:

[0034] Natural language processing technology is used to process the document, including word segmentation and keyword extraction, to obtain the final keyword recognition result of the document.

[0035] Furthermore, the step of using OCR technology to recognize characters from the image includes:

[0036] Perform pre-processing operations on the image, including binarization, image denoising, grayscale conversion, and image enhancement;

[0037] Based on the pre-processed image, character segmentation is performed using image processing technology to obtain character images;

[0038] Extracting features based on the character image to obtain key features of the character;

[0039] The key features of the characters are classified and identified to complete the character recognition process, wherein the classification and recognition process adopts a project information database construction method or multiple implementations of a feasibility study stage of a power grid infrastructure project among template matching, statistical models, machine learning algorithms and deep learning models.

[0040] Furthermore, the step of obtaining the final keyword recognition result of the document includes:

[0041] Use word segmentation to split the document into individual words or tokens, and mark the parts of speech to obtain the segmented documents;

[0042] Based on the segmented documents, named entity recognition is performed to obtain named entities;

[0043] Based on the segmented documents, performing grammatical analysis to determine semantic and logical relationships at the sentence level;

[0044] Keywords are extracted from the document based on the named entities and grammatical analysis results.

[0045] Furthermore, the project fields include project name, project type, construction location, investment amount, construction scale, and key technical parameters.

[0046] The present invention also provides a system for constructing a project information database in the feasibility study phase of a power grid infrastructure project, comprising:

[0047] Data acquisition and preprocessing module: used to acquire relevant business data in the feasibility study phase of power grid infrastructure projects and perform preprocessing;

[0048] File acquisition and parsing module: used to obtain data files of the feasibility study stage of multi-modal power grid infrastructure projects, perform multi-modal file parsing, and identify characters and keywords respectively;

[0049] Empty project information base construction module: used to define project fields and build an empty project information base;

[0050] Project information database forming module: used to match and map pre-processed relevant business data and recognized characters and keywords according to project fields into the empty project information database to form the final project information database for the feasibility study stage.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] (1) The present invention preprocesses and parses the relevant business data and information files in the feasibility study stage of the power grid infrastructure project, and matches the preprocessing results and the parsing results with the set project fields to map them to the project information library, thereby realizing the automatic organization of the feasibility study stage information.

[0053] (2) The present invention pre-processes the relevant business data by removing duplicates and filling missing values with Lagrange polynomial interpolation, which can improve the integrity and accuracy of the information.

[0054] (3) The present invention adopts OCR technology and natural language processing technology, which can perform multimodal file parsing without the need for format conversion and other operations. By identifying characters and keywords and matching them, it helps to integrate information efficiently and accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 Schematic diagram of the method of the present invention. DETAILED DESCRIPTION

[0056] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0057] Example 1

[0058] This embodiment provides a method for constructing a project information database in the feasibility study stage of a power grid infrastructure project. Figure 1 As shown, the method includes the following steps:

[0059] Step 1. Acquisition and preprocessing of relevant business data during the feasibility study phase of power grid infrastructure projects.

[0060] Remove duplicate data, process missing values, and correct errors from the original data to ensure improved accuracy of data matching.

[0061] (1) For the evaluation project center, the statistical calculation of relevant data is required. Missing value processing can be done by filling in, predicting, and other methods. Filling in mainly combines the missing data types and uses the mean and median statistical values to fill in; predicting mainly uses interpolation to make predictions to supplement the missing values and ensure data integrity.

[0062] The interpolation method mainly uses Lagrange polynomial interpolation. First, a set of Lagrange basis functions L are constructed. i (x)(i=0,...,n), these basis functions are polynomials of degree not exceeding n and have the following properties:

[0063]

[0064] Then make a linear combination of these basis functions to obtain the Lagrange interpolation polynomial:

[0065]

[0066] It is easy to verify that the polynomial L(x) satisfies the interpolation condition y i =P(x i )(i=0,1,...,n);

[0067] Lagrangian basis function L i The construction of (x) is as follows:

[0068] According to the properties of the basis function, when j∈{0,1,...,n}\{i}, L i (x j )=0, that is, x j For L i The zero point of (x) can be assumed to be:

[0069]

[0070] Among them, K is the unknown coefficient. Then L i (x i )=1, we get

[0071] Thus we get:

[0072]

[0073] Therefore, the basis functions:

[0074]

[0075] Let w(x)=(x-x0)(x-x1)…(x n ), then L i (x) can also be expressed as

[0076]

[0077] Step 2. Multimodal file acquisition and parsing.

[0078] In this example, both the relevant business data and project documentation are related to power grid infrastructure projects. Power grid infrastructure project documentation is often in various formats, including PDF, Word, Excel, and images. Content identification is required to obtain data information for different projects, necessitating content parsing. Research has revealed that the following technologies are primarily used for content identification in this project.

[0079] (1) Optical Character Recognition (OCR)

[0080] Image preprocessing: The first step in OCR is to preprocess the input image to improve the accuracy of character recognition. This includes operations such as image denoising, grayscale conversion, binarization, and image enhancement to remove noise from the image and improve the readability of characters.

[0081] Character segmentation: In OCR, character segmentation is the process of separating characters in a text image. This is a critical step, especially for printed text, where characters are often separated from each other. Character segmentation can be achieved using image processing techniques, edge detection, connected component analysis, and other methods.

[0082] Feature extraction: In OCR, feature extraction is the process of converting character images into discriminative feature vectors. Common feature extraction methods include those based on shape, texture, projection, and statistical features. These features are used to represent key information about the characters for subsequent classification and recognition.

[0083] Character classification and recognition: In the final stage of OCR, a classifier or recognition model is used to classify and recognize the feature vectors. Common classification and recognition methods include those based on template matching, statistical models (such as hidden Markov models), machine learning algorithms (such as support vector machines and random forests), and deep learning models (such as convolutional neural networks).

[0084] Text post-processing: OCR recognized text may contain errors and require post-processing to improve accuracy. Post-processing techniques can include spelling correction, language model error correction, rule verification, etc. to improve the quality of the final recognition results.

[0085] (2) Natural Language Processing (NLP)

[0086] Word segmentation: Split PDF text into individual words or tokens for subsequent processing and analysis. Word segmentation is a fundamental step in NLP tasks and can be performed based on spaces, punctuation, word boundaries, etc.

[0087] Named Entity Recognition (NER): Identifies named entities in PDF text, such as names of people, places, organizations, dates, and more. NER (Named Entity Recognition) technology can help identify and extract important entity information from PDFs for further information extraction and analysis.

[0088] Part-of-speech tagging: Assign a part-of-speech tag to each word or token in the PDF text, such as noun, verb, adjective, etc. Part-of-speech tagging can help understand and analyze the grammatical structure, syntactic relations, and word meaning of the PDF text.

[0089] Syntax analysis: Perform grammatical analysis on PDF text to determine the structure of sentences and the relationship between components. Syntax analysis can help understand the semantics and logical relationships of PDF text at the sentence level.

[0090] Keyword Extraction: Automatically extract keywords or phrases from PDF text to represent the text's theme or content summary. Keyword extraction can be based on methods such as word frequency, part of speech, and TF-IDF.

[0091] Step 3. Data matching and project information database construction.

[0092] After review, power grid infrastructure projects must be matched to several core values, including grid improvement indicators, issues, and total investment. These values must be tied to data such as project name, region, inventory attributes, key areas, issue types, indicator rates, and previous indicators. When building a project information database, project fields must first be defined and an empty project information database constructed. Preprocessed business data, along with identified characters and keywords, are then matched and mapped to the empty project information database based on the project fields. This creates the final feasibility study-stage project information database for data display, necessitating research into data matching technology.

[0093] The recognized characters are matched using string matching, which includes exact matching, pattern matching, regular expressions, etc.

[0094] For the identified keywords, text matching is used for matching. Text matching can be based on technologies such as keyword matching, word vector model, and text similarity calculation.

[0095] For pre-processed related business data, matching is performed based on field values or data attributes.

[0096] Example 2

[0097] This embodiment provides a system for constructing a project information database in the feasibility study phase of a power grid infrastructure project, including:

[0098] Data acquisition and preprocessing module: used to acquire relevant business data in the feasibility study phase of power grid infrastructure projects and perform preprocessing;

[0099] File acquisition and parsing module: used to obtain data files of the feasibility study stage of multi-modal power grid infrastructure projects, perform multi-modal file parsing, and identify characters and keywords respectively;

[0100] Empty project information base construction module: used to define project fields and build an empty project information base;

[0101] Project information database forming module: used to match and map pre-processed relevant business data and recognized characters and keywords according to project fields into the empty project information database to form the final project information database for the feasibility study stage.

[0102] The rest is the same as Example 1.

[0103] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0104] It will be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention may be implemented in various computer languages, for example, the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0105] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0106] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0107] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0108] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0109] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

[0110] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0111] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for constructing a project information database in the feasibility study stage of a power grid infrastructure project, characterized in that: The following steps are involved: Obtain relevant business data during the feasibility study phase of power grid infrastructure projects and perform pre-processing; Obtain data files from the feasibility study phase of multimodal power grid infrastructure projects, perform multimodal file parsing, and identify characters and keywords; Define project fields and build an empty project information base; Based on the pre-processed relevant business data and the identified characters and keywords, matching is performed according to the project fields and mapped into the empty project information database to form the final project information database for the feasibility study stage.

2. The method for constructing a project information database in the feasibility study stage of a power grid infrastructure project according to claim 1, characterized in that: The pre-processing steps include: Deduplication processing is performed on the relevant business data; Based on the deduplicated relevant business data, the missing values are filled using the filling method or prediction method to complete the preprocessing process.

3. The method for constructing a project information database in the feasibility study stage of a power grid infrastructure project according to claim 2, characterized in that: The filling method uses the mean or median to fill the missing values, and the prediction method uses the Lagrange polynomial interpolation method to predict the missing values.

4. The method for constructing a project information database in the feasibility study stage of a power grid infrastructure project according to claim 3, characterized in that: The step of using the Lagrange polynomial interpolation method to predict missing values includes: Construct a set of Lagrangian basis functions L i (x)(i=0,...,n): In the formula, K is the unknown coefficient, x i 、x j are data points and corresponding known values, respectively. The Lagrange basis function is a polynomial of degree not exceeding n, with the following properties: Where x j is a data node, so the Lagrangian basis function is expressed as: Where ∏ is the continuous product; The Lagrange basis functions are linearly combined to obtain the Lagrange interpolation polynomial: Where L(x) is the Lagrange interpolation polynomial; Verify whether the Lagrange interpolation polynomial meets the interpolation condition, where the interpolation condition is: y i =P(x i )(i=0,...,n) The missing value at the missing point is predicted based on the verified Lagrange interpolation polynomial.

5. The method for constructing a project information database in the feasibility study stage of a power grid infrastructure project according to claim 1, characterized in that: The modalities of the data file include picture modality and document modality, wherein the document modality includes PDF, Word, and Excel.

6. A method for constructing a project information database in the feasibility study phase of a power grid infrastructure project according to claim 5, characterized in that: The steps of respectively identifying characters and keywords include: For image modal: Recognize characters from an image using OCR technology and correct them using post-processing technology to obtain a final character recognition result of the image, wherein the post-processing technology includes spelling correction, language model error correction, and rule verification. A method for constructing a project information database in the feasibility study stage of a power grid infrastructure project. For document modal: Natural language processing technology is used to process the document, including word segmentation and keyword extraction, to obtain the final keyword recognition result of the document.

7. A method for constructing a project information database in the feasibility study phase of a power grid infrastructure project according to claim 6, characterized in that: The step of using OCR technology to recognize characters from the image includes: Perform pre-processing operations on the image, including binarization, image denoising, grayscale conversion, and image enhancement; Based on the pre-processed image, character segmentation is performed using image processing technology to obtain character images; Extracting features based on the character image to obtain key features of the character; The key features of the characters are classified and identified to complete the character recognition process, wherein the classification and recognition process adopts a project information database construction method or multiple implementations of a feasibility study stage of a power grid infrastructure project among template matching, statistical models, machine learning algorithms and deep learning models.

8. The method for constructing a project information database in the feasibility study phase of a power grid infrastructure project according to claim 6, characterized in that: The step of obtaining the final keyword recognition result of the document includes: Use word segmentation to split the document into individual words or tokens, and mark the parts of speech to obtain the segmented documents; Performing named entity recognition based on the segmented documents to obtain named entities; Based on the segmented documents, performing grammatical analysis to determine semantic and logical relationships at the sentence level; Keywords are extracted from the document based on the named entities and grammatical analysis results.

9. The method for constructing a project information database in the feasibility study phase of a power grid infrastructure project according to claim 1, characterized in that: The project fields include project name, project type, construction location, investment amount, construction scale, and key technical parameters.

10. A system for constructing a project information database in the feasibility study phase of a power grid infrastructure project, characterized in that: include: Data acquisition and preprocessing module: used to acquire relevant business data in the feasibility study phase of power grid infrastructure projects and perform preprocessing; File acquisition and parsing module: used to obtain data files of the feasibility study stage of multi-modal power grid infrastructure projects, perform multi-modal file parsing, and identify characters and keywords respectively; Empty project information base construction module: used to define project fields and build an empty project information base; Project information database forming module: used to match and map pre-processed relevant business data and recognized characters and keywords according to project fields into the empty project information database to form the final project information database for the feasibility study stage.

Images