Civil aviation bid invitation file processing method based on natural language text

Abstract

The invention discloses a civil aviation bidding document processing method based on a natural language text. The method comprises the following steps: selecting a complete civil aviation industry bidding document; the civil aviation industry bid inviting file is backed up into two parts, one part is a file A, and the other part is a file B; after the file A is uploaded, the file A is divided by taking chapters as slice points, the file A is divided into a business part A1 and a technical part A2, and high-frequency key phrases of the two parts are searched; after the search is completed, the codes are retrieved again; the content in a picture form exists in the bid invitation file of the file A, and the file A globally searches the picture format; storing the whole-process file of the file A in an original file path and then processing the file B; and transmitting the file B to a machine learning code, and decomposing and learning the file B according to business and technology parts by the machine learning code. According to the method, key information points in civil aviation bid invitation files can be mined and classified, meanwhile, non-text files such as pictures and the like are independently arranged and stored, and the classification and arrangement efficiency of early-stage work is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tender document classification, and in particular to a civil aviation tender document processing method based on natural language text. Background Art

[0002] Due to its special nature, bidding documents contain a large amount of text and picture information, which can be divided into three types according to their functions: description, requirements, and results. Since the time for bidding projects is generally tight, bidders need to quickly organize and filter out relevant useful information after obtaining relevant documents, and classify the information in a short period of time to start organizing the bidding documents. In traditional processing methods, the understanding, organization, classification, and preservation of key contents of bidding documents need to be done manually, which is prone to omissions and information gaps in team communication in a short period of time, making it impossible to accurately and efficiently complete related work, making it easy to find problems in the later stage of bidding projects and difficult to deal with them in a timely manner. The existing technology has a mediocre processing effect on civil aviation bidding documents, and is unable to accurately identify important terms related to the business and technical parts, lacking special pertinence. A large amount of manual screening makes the efficiency of early work processing low.

[0003] Therefore, it is necessary to invent a civil aviation bidding document processing method based on natural language text to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide a method for processing civil aviation bidding documents based on natural language text, which can improve the efficiency of preliminary work.

[0005] In order to achieve the above object, the present invention provides the following technical solutions: A method for processing civil aviation bidding documents based on natural language text, the method comprising the following steps: Step 1. Select the complete civil aviation industry bidding documents and upload them for reading; Step 2: Back up the read civil aviation industry bidding documents into two copies, one is file A used for natural language text processing later, and the other is file B input into the background through the interface to provide a new model for subsequent deep learning training; Step 3: After the file A is uploaded and loaded, the text slicing code intervenes to divide the file A into chapters. After dividing the file A into chapters, the text slicing code divides the file A into the business part A1 and the technical part A2, and searches for high-frequency keyword groups in the business part A1 and the technical part A2; Step 4: After searching the high-frequency keyword groups of the business part A1 and the technical part A2, the keyword text content code is searched again; Step 5: Some of the bidding documents in file A contain content in the form of pictures. File A calls the picture format content search code function to start a global search for the picture format. Step 6: Save the process file generated by the text slicing segmentation and image format content search of file A in the file path where file A is stored, and process file B at this time; Step 7: File B is transmitted as a new data set to the natural language text processing code running in the background through an interface, and the machine learning code decomposes and learns file B according to the business and technical parts; Step 8: File B is used as a learning file training model for the technical equipment classification model method based on civil aviation bidding documents, and is placed in the temporary space of the server until the storage space is occupied to 95%, and then a reminder is issued.

[0006] Specifically, the method for searching the high-frequency keyword groups of the business part A1 and the technical part A2 in step 3 is as follows: According to the existing natural text training set results, search for the high-frequency keyword groups for the business and technical parts of civil aviation bidding documents. If there are none, search for the high-frequency keyword groups for the business part A1 and the technical part A2 of civil aviation bidding documents according to the default initial training set.

[0007] Specifically, in step 4, the code searches again for the following content and processing methods: The key symbols of the key clauses and bid cancellation clauses mentioned in the bidding documents are used as search points, and the full text is searched again. The paragraphs marked with key symbols are sorted out separately to form an EXCEL file, named "asterisk clauses" for easy viewing and processing later.

[0008] Specifically, in step 5, the image formats include: JPG, PNG, BMP, and SVG.

[0009] The beneficial effects of the present invention are: This patent is based on the writing process and characteristics of civil aviation bidding documents. It uses natural language text to perform machine learning analysis on each newly read bidding document and past bidding documents. It can accurately discover key information points in the text language part of civil aviation bidding documents and classify related content. At the same time, non-text files such as pictures are sorted out and saved separately, improving the efficiency of classification and sorting in the preliminary work.

[0010] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and implement it according to the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 The present invention is a flowchart of a method for processing civil aviation bidding documents based on natural language text. DETAILED DESCRIPTION

[0012] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0013] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0014] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0015] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0016] According to an embodiment of the present invention, a method for processing civil aviation bidding documents based on natural language text is proposed. Figure 1 , the method comprises the following steps: Step 1. Select the complete civil aviation industry bidding documents and upload them for reading; Step 2: Back up the read civil aviation industry bidding documents into two copies, one is file A used for natural language text processing later, and the other is file B input into the background through the interface to provide a new model for subsequent deep learning training; Step 3: After the file A is uploaded and loaded, the text slicing code intervenes to divide the file A into chapters. After dividing the file A into chapters, the text slicing code divides the file A into the business part A1 and the technical part A2, and searches for high-frequency keyword groups in the business part A1 and the technical part A2; Step 4: After searching the high-frequency keyword groups of the business part A1 and the technical part A2, the keyword text content code is searched again; Step 5: Some of the bidding documents in file A contain content in the form of pictures. File A calls the picture format content search code function to start a global search for the picture format. Step 6: Save the process file generated by the text slicing segmentation and image format content search of file A in the file path where file A is stored, and process file B at this time; Step 7: File B is transmitted as a new data set to the natural language text processing code running in the background through an interface, and the machine learning code decomposes and learns file B according to the business and technical parts; Step 8: File B is used as a learning file training model for the technical equipment classification model method based on civil aviation bidding documents, and is placed in the temporary space of the server until the storage space is occupied to 95%, and then a reminder is issued.

[0017] Specifically, the method for searching the high-frequency keyword groups of the business part A1 and the technical part A2 in step 3 is as follows: According to the existing natural text training set results, search for the high-frequency keyword groups for the business and technical parts of civil aviation bidding documents. If there are none, search for the high-frequency keyword groups for the business part A1 and the technical part A2 of civil aviation bidding documents according to the default initial training set.

[0018] Specifically, in step 4, the code searches again for the following content and processing methods: The key symbols of the key clauses and bid cancellation clauses mentioned in the bidding documents are used as search points, and the full text is searched again. The paragraphs marked with key symbols are sorted out separately to form an EXCEL file, named "asterisk clauses" for easy viewing and processing later.

[0019] Specifically, in step 5, the image formats include: JPG, PNG, BMP, and SVG.

[0020] In summary, this patent is based on the writing process and characteristics of civil aviation bidding documents. It uses natural language text to perform machine learning analysis on each newly read bidding document and past bidding documents. It can accurately discover key information points in the text language part of civil aviation bidding documents and classify related content. At the same time, non-text files such as pictures can be sorted out and saved separately, thereby improving the efficiency of classification and sorting in the preliminary work.

[0021] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0022] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for processing civil aviation bidding documents based on natural language text, characterized in that: The method comprises the following steps: Step 1. Select the complete civil aviation industry bidding documents and upload them for reading; Step 2: Back up the read civil aviation industry bidding documents into two copies, one is file A used for natural language text processing later, and the other is file B input into the background through the interface to provide a new model for subsequent deep learning training; Step 3: After the file A is uploaded and loaded, the text slicing code intervenes to divide the file A into chapters. After dividing the file A into chapters, the text slicing code divides the file A into the business part A1 and the technical part A2, and searches for high-frequency keyword groups in the business part A1 and the technical part A2; Step 4: After searching the high-frequency keyword groups of the business part A1 and the technical part A2, the keyword text content code is searched again; Step 5: Some of the bidding documents in file A contain content in the form of pictures. File A calls the picture format content search code function to start a global search for the picture format. Step 6: Save the process file generated by the text slicing segmentation and image format content search of file A in the file path where file A is stored, and process file B at this time; Step 7: File B is transmitted as a new data set to the natural language text processing code running in the background through an interface, and the machine learning code decomposes and learns file B according to the business and technical parts; Step 8: File B is used as a learning file training model for the technical equipment classification model method based on civil aviation bidding documents, and is placed in the temporary space of the server until the storage space is occupied to 95%, and then a reminder is issued.

2. A method for processing civil aviation bidding documents based on natural language text as claimed in claim 1, characterized in that: Step 3: The method for searching the high-frequency keyword groups of the business part A1 and the technical part A2 is as follows: According to the existing natural text training set results, search for the high-frequency keyword groups for the business and technical parts of civil aviation bidding documents. If there are none, search for the high-frequency keyword groups for the business part A1 and the technical part A2 of civil aviation bidding documents according to the default initial training set.

3. The method for processing civil aviation bidding documents based on natural language text as claimed in claim 1, characterized in that: In step 4, the code retrieves the content and processing method again: The key symbols of the key clauses and bid cancellation clauses mentioned in the bidding documents are used as search points, and the full text is searched again. The paragraphs marked with key symbols are sorted out separately to form an EXCEL file, named "asterisk clauses" for easy viewing and processing later.

4. A method for processing civil aviation bidding documents based on natural language text as claimed in claim 1, characterized in that: In step 5, the image formats include: JPG, PNG, BMP, and SVG.

Images