Engineering survey design file management method and system based on NLP

Abstract

The invention provides an NLP-based engineering survey design archive management method and system, relates to the technical field of engineering archive management, and aims to solve the technical problems that the quantity and content of engineering survey design archives are greatly different along with the engineering scale, and a unified large language model is adopted to possibly cause resource waste or poor recognition effect. According to the method, the to-be-archived engineering survey design data is acquired, the scale index of the engineering is calculated according to the to-be-archived engineering survey design data, and then the model for engineering survey design data management is selected according to the scale index, so that flexible selection of the NLP model and reasonable allocation of calculation resources according to the engineering scale are realized; and the file management efficiency and the identification accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering archive management, and in particular to an engineering survey and design archive management method and system based on NLP. Background Art

[0002] In recent years, electronic archive management has been widely used in the survey and design industry, but it faces the problem of efficient management of diversified archives. NLP (natural language processing) technology, with its ability to understand and process human language, provides the possibility for intelligent archive management. Through functions such as automatic classification and intelligent compilation and research, NLP technology improves the efficiency of archive management and reduces costs.

[0003] However, the number and content of engineering survey and design archives often vary greatly with the scale of the project. For some small projects, the number of survey and design archives is small and the information is relatively simple; for large projects, the survey and design archives may contain millions of files, covering complex geological, environmental, design and other information.

[0004] In this context, if a unified large language model is used for recognition and processing, two situations may occur: one is the waste of computing resources, because for small projects, the processing power of the large language model far exceeds the requirements, resulting in idle computing resources; the other is insufficient volume. For large projects, the large language model may not be able to fully capture and process all the important information in the archives, resulting in the accuracy and completeness of the recognition results being affected.

[0005] Therefore, how to select a suitable NLP model according to the scale of engineering survey and design archives to achieve rational allocation and efficient utilization of resources has become an important technical issue facing the current engineering survey and design archive management. Summary of the invention

[0006] The present invention provides an engineering survey and design archive management method and system based on NLP, so as to realize flexible selection of NLP models according to the scale of the project, reasonably allocate computing resources, and improve archive management efficiency and recognition accuracy.

[0007] A method for managing engineering survey and design archives based on NLP specifically includes the following steps: Step S1, data collection: obtaining engineering survey and design data to be archived; Step S2, scale calculation: obtaining document parameters, picture drawing parameters and video parameters according to the engineering survey and design data to be archived, and calculating the scale index of the project according to the parameters; Step S3, model selection: selecting a model for engineering survey and design data management according to the scale index, specifically, when the scale index is less than or equal to a preset threshold, selecting a first management model, and when the scale index is greater than the preset threshold, selecting a second management model; Step S4, file identification: inputting the engineering survey and design data into the selected management model, identifying the engineering survey and design data through the management model, and obtaining archive information; Step S5, data preservation: the archived information is saved in a database.

[0008] Furthermore, the method for obtaining the scale indicator is: Step S21, dividing the engineering survey and design data to be archived into documents, pictures, drawings and videos; Step S22, obtaining the total word count W and the document conversion coefficient α1 of the document; obtaining the file size S, the picture-drawing conversion coefficient α2 and the picture-drawing resolution adjustment factor β of the picture-drawing; obtaining the file size V, the video conversion coefficient α3 and the video resolution adjustment factor γ of the video; Step S23, calculating the scale index according to the parameters obtained in step S22.

[0009] Furthermore, the calculation formula of the scale indicator TRS is: TRS=W / α1+S×β / α2+V×γ / α3.

[0010] Furthermore, the image resolution adjustment factor β is taken as: ; Among them, ω TP is the weight of the image, N TP is the number of pictures, S TPi is the size of the i-th picture, β TPi is the resolution of the i-th image, ω TZ is the weight of the drawing, N TZ is the number of drawings, S TZj is the size of the jth drawing, β TZj is the resolution of the jth drawing.

[0011] Furthermore, the video resolution adjustment factor γ is taken as: ; Among them, ω Vk is the weight of the kth video, V k is the size of the kth video, γ Vk is the resolution of the kth video, N V is the number of videos.

[0012] Furthermore, the first management model is an LSTM model, and the second management model is a Transformer model; Furthermore, the specific parameters of the first management model are set as: The number of hidden layers is 2, the number of neurons in each layer is 256, the activation function is sigmoid function, the optimizer is Adam, the learning rate is 0.001, the loss function is the cross entropy loss function, and the batch size is 32.

[0013] Furthermore, the specific parameters of the second management model are set as: The number of hidden layers is 3, the number of neurons in each layer is 512, the optimizer is Adam, the learning rate is 0.0001, the loss function is the cross entropy loss function, the activation function is GELU function, and the batch size is 64.

[0014] An engineering survey and design archive management system based on NLP, using the engineering survey and design archive management method based on NLP as described in any of the above items, specifically includes the following modules: Data collection module: obtain engineering survey and design data to be archived; Scale calculation module: connected to the data collection module, used to obtain document parameters, picture drawing parameters and video parameters according to the engineering survey and design data to be archived, and calculate the scale index of the project according to the parameters; Model selection module: connected to the scale calculation module, used to select a model for engineering survey and design data management according to the scale index, specifically, when the scale index is less than or equal to a preset threshold, select the first management model, when the scale index is greater than the preset threshold, select the second management model; File recognition module: connected to the model selection module, used to input the engineering survey and design data into the selected management model and recognize the engineering survey and design data into computer language; Data saving module: connected to the file identification module, used to save the identification results output by the management model into the database.

[0015] An electronic device comprises: a processor and a memory, wherein the processor is used to execute the steps of the NLP-based engineering survey and design archive management method as described in any one of the above items by calling a program or instruction stored in the memory.

[0016] Compared with the prior art, the beneficial effects of the present invention are: First, the present invention achieves accurate matching of computing resources by intelligently identifying the scale of engineering survey and design archives and automatically selecting the most suitable NLP model for processing, thus avoiding the waste of resources when large models are used to process small projects, and ensuring that the accuracy and completeness of the recognition results will not be affected by the lack of capacity of small models when processing large projects. The present invention not only improves the efficiency of archive management, but also significantly reduces operating costs; Secondly, the scale index calculation method proposed in the present invention comprehensively considers various data types such as documents, pictures, drawings and videos in engineering survey and design archives, and uniformly converts different types of data into comparable identification scale values ​​by setting conversion coefficients and resolution adjustment factors. This method provides managers with an intuitive and accurate evaluation tool, enabling them to quickly understand the overall scale and complexity of engineering survey and design archives, so as to make more reasonable archive management decisions. In addition, the calculation of scale indicators also provides an important basis for the subsequent selection of appropriate NLP models, ensuring the scientificity and efficiency of the archive management process; Thirdly, the present invention has carried out careful design and optimization in the setting of model parameters. Different NLP models are selected for engineering survey and design data of different scales, and reasonable parameters are set for them. The scale and complexity of the engineering survey and design data are fully considered. Through reasonable selection and configuration, reasonable allocation of resources is achieved, processing efficiency is improved, model adaptability is enhanced, and operating costs are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flowchart of the engineering survey and design archive management method based on NLP in an embodiment of the present invention; Figure 2 This is a structural diagram of the engineering survey and design archive management system based on NLP in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. 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 belong to the scope of protection of the present invention.

[0020] The specific implementation of the present invention is described below with reference to the accompanying drawings (tables).

[0021] Natural Language Processing (NLP) is an important branch of artificial intelligence, which aims to enable computers to understand and process human language. With the rapid development of deep learning technology, neural network models have made significant progress in the field of NLP and have become the main tool for processing natural language tasks. Commonly used NLP models include: recursive neural network (RNN), long short-term memory network (LSTM), convolutional neural network (CNN), transformer (Transformer) and pre-trained models such as BERT.

[0022] Based on the above model, the present invention studies the method of engineering survey and design archive management, obtains the engineering survey and design data to be archived, calculates the scale index of the project according to the engineering survey and design data to be archived, and then selects the model for engineering survey and design data management according to the scale index, thereby realizing flexible selection of NLP models according to the project scale, reasonable allocation of computing resources, and improving archive management efficiency and recognition accuracy.

[0023] Example 1 like Figure 1 As shown, the present invention proposes an engineering survey and design archive management method based on NLP, which specifically includes steps S1-S5: Step S1, data collection: obtaining engineering survey and design data to be archived; The engineering survey and design data to be archived are not of a single type, but include many different types of data. Specifically, these data can be divided into three categories: documents, pictures and drawings, and videos.

[0024] Document materials usually contain a large amount of text information, such as engineering reports, design drawings, contract documents, etc.

[0025] Picture and drawing materials are mainly presented in the form of images, such as photos of the construction site, electronic drawings, etc., which intuitively show the actual situation and design results of the project and are important auxiliary tools for understanding the status of the project.

[0026] Video materials record some key links or on-site conditions in the engineering survey and design process through dynamic images. Compared with pictures and drawings, video materials provide richer temporal and spatial information, which helps to understand the engineering situation more comprehensively.

[0027] Step S2, scale calculation: obtaining document parameters, picture drawing parameters and video parameters according to the engineering survey and design data to be archived, and calculating the scale index of the project according to the parameters; The existing technology uses a unified large language model to identify and process engineering survey and design data, which may lead to two situations: one is the waste of computing resources, because for small projects, the processing capacity of the large language model far exceeds the required, resulting in idle computing resources; the other is insufficient volume. For large projects, the large language model may not be able to fully capture and process all the important information in the archives, resulting in the accuracy and completeness of the recognition results being affected. Therefore, it is crucial to choose a suitable model based on the scale of the engineering survey and design archives.

[0028] By calculating the scale index of the project, we can accurately understand the overall scale and complexity of the engineering survey and design data to be archived, which will help to select the appropriate management model according to the scale of the data, thereby achieving a reasonable allocation of computing resources, avoiding resource waste, and ensuring the accuracy and completeness of the identification results.

[0029] Furthermore, the method for obtaining the scale indicator is: Step S21, dividing the engineering survey and design data to be archived into documents, pictures, drawings and videos; Step S22, obtaining the total word count W and the document conversion coefficient α1 of the document; obtaining the file size S, the picture-drawing conversion coefficient α2 and the picture-drawing resolution adjustment factor β of the picture-drawing; obtaining the file size V, the video conversion coefficient α3 and the video resolution adjustment factor γ of the video; Step S23, calculating the scale index according to the parameters obtained in step S22.

[0030] When considering the size calculation of a document, the total number of words is used as a statistical indicator to calculate the size of the document; When considering the recognition scale of pictures, drawings and videos, the present invention not only considers the file size, but also the file resolution. The resolution reflects the clarity and detail of the image or video, which is of great significance for evaluating the recognition scale of the material.

[0031] The following is a specific example of how to obtain the scale indicator: 1. Set the conversion coefficient and resolution adjustment factor document: Original statistical indicators: word count W (10,000 words); Conversion factor: α1 (assuming that the equivalent number of words of 1MB is α ten thousand words); Converted indicator: W'=W / α1 (convert the number of words to an equivalent value in MB); Picture drawings: Original statistical indicators: file size (S, unit: MB) and resolution (R, unit: number of pixels or DPI / PPI); Conversion factor: α2 (i.e. converting file size to MB); Resolution adjustment factor: β (set an adjustment factor according to the resolution. The higher the resolution, the larger the β value); Index after conversion: S'=S / α2×β (adjust the file size according to the resolution); video: Original statistical indicators: file size (V, unit: MB) and resolution (Res, usually expressed as horizontal pixels × vertical pixels); Conversion factor: α3 (i.e. converting file size to MB); Resolution adjustment factor: γ (set an adjustment factor according to the video resolution. The higher the resolution, the larger the γ value); Index after conversion: V'=V / α3×γ (adjust the file size according to the resolution); 2. Calculate the resolution adjustment factor The settings of resolution adjustment factors β and γ can be determined based on actual conditions and experience. For example, a series of resolution intervals can be set and an adjustment factor value can be assigned to each interval. The higher the resolution, the larger the adjustment factor value to reflect the complexity of high-resolution data in identification and processing.

[0032] In this embodiment, the image drawing resolution adjustment factor β is taken as: ; Among them, ω TP is the weight of the image, N TP is the number of pictures, S TPi is the size of the i-th picture, β TPi is the resolution of the i-th image, ω TZ is the weight of the drawing, N TZ is the number of drawings, S TZj is the size of the jth drawing, β TZj is the resolution of the jth drawing; the drawings contain more and more important details and information, so ω TZ >ω TP .

[0033] The value of the image and drawing resolution adjustment factor β is set according to the resolution of the image and drawing. The higher the resolution, the richer the information contained in the image and drawing, and the clearer the details, so more computing resources and processing time are required for recognition and processing. In order to reflect the complexity of such high-resolution data in recognition and processing, the β value will be set accordingly higher.

[0034] The above formula can ensure that high-resolution images and drawings are fully processed during the recognition process by setting a reasonable β value, thereby improving the accuracy and completeness of recognition. At the same time, it also provides managers with an intuitive and accurate evaluation tool to quickly understand the complexity of images and drawings and the required computing resources.

[0035] In this embodiment, the video resolution adjustment factor γ is taken as: ; Among them, ω Vk is the weight of the kth video, V k is the size of the kth video, γ Vk is the resolution of the kth video, N V is the number of videos; The value of the video resolution adjustment factor γ is closely related to the resolution of the video. Similar to pictures and drawings, high-resolution videos require more computing resources and processing time when they are recognized and processed. Therefore, the γ value will also be adjusted accordingly according to the resolution of the video to reflect this complexity.

[0036] By setting a reasonable γ value, we can ensure that high-resolution videos are fully processed during the recognition process, thereby improving the accuracy and completeness of recognition. At the same time, this also provides managers with intuitive information about the complexity of video materials and the required computing resources, which helps to make more reasonable archive management decisions.

[0037] 3. Calculate the total value of identification scale After setting the conversion coefficient and resolution adjustment factor, the statistical indicators of all data can be converted into a unified unit (MB) and the total value of the identification scale can be calculated. The calculation formula is as follows: Total Recognition Scale (TRS) = Σ(W'+S'+V') = W / α1+S×β / α2+V×γ / α3.

[0038] Among them, Σ represents the sum operation, and W', S', and V' represent the statistical indicators after the conversion of documents, pictures and drawings, and video materials, respectively.

[0039] 4. Example Calculation Assume that the following engineering survey and design data are available: Document data: The total word count is 100,000 words, and the conversion coefficient α1 is set to 0.001 (i.e., the equivalent word count of 1MB is 100,000 words); Image and drawing materials: total file size 5MB, resolution 300DPI (set the adjustment factor β below 300DPI to 1, 300-600DPI to 1.5, and above 600DPI to 2); Video data: The total file size is 3MB, and the resolution is 1920×1080 (the adjustment factor γ is set to 1 for 1080P and below, 1.5 for 4K, and 2 for 8K and above); The converted statistical indicators are: Document data: W'=10 / 0.001=10MB; Image and drawing data: S'=5 / 1×2=10MB (because the resolution is 300DPI, which is in the range of 300-600DPI, the adjustment factor β is 1.5, but to simplify the calculation, the upper limit 2 is directly taken here. The file unit is already MB, so the conversion coefficient α2=1); Video data: V'=3 / 1×1=3MB (because the resolution is 1920×1080, which is 1080P or lower, the adjustment factor γ is 1, and the file unit is already MB, so the conversion coefficient α3=1); Therefore, the total value of the scale indicator is: TRS=10+10+3=23MB; This value can be used as a reference indicator to measure the scale and complexity of engineering survey and design data, and takes into account the impact of resolution on the scale indicator.

[0040] Step S3, model selection: selecting a model for engineering survey and design data management according to the scale index, specifically, when the scale index is less than or equal to a preset threshold, selecting a first management model, and when the scale index is greater than the preset threshold, selecting a second management model; The selection of preset thresholds is intended to effectively distinguish engineering survey and design data into categories of different sizes or complexities. By setting a specific value (such as 5000), the data can be clearly divided into "small" or "simple" categories (size index ≤ 5000) and "large" or "complex" categories (size index > 5000).

[0041] The first management model may be more inclined to choose LSTM or simpler RNN variants, because these models perform well when processing smaller and less complex sequence data, and the parameter settings are relatively simple, which is conducive to reducing computing resource consumption.

[0042] In this embodiment, the first management model is an LSTM model, and the specific parameters are set as: The number of hidden layers is 2, the number of neurons in each layer is 256, the activation function is sigmoid function, the optimizer is Adam, the learning rate is 0.001, the loss function is the cross entropy loss function, and the batch size is 32.

[0043] Specifically, Number of hidden layers: 1 or 2. When the data set is small and the task is relatively simple, fewer hidden layers can reduce the complexity of the model and prevent overfitting. Number of neurons per layer: 128 or 256. On a small-scale data set, too many neurons may cause the model to overfit. Therefore, choosing an appropriate number of neurons can reduce computational complexity while maintaining model performance. Optimizer: Adam or SGD (with momentum). The Adam optimizer performs well in most cases, while SGD (with momentum) may also perform well on simple tasks. In practical applications, the appropriate optimizer can be selected based on the convergence speed and stability of the model.

[0044] Learning rate: 0.001 or 0.002. In the small-scale engineering survey and design archive management, a larger learning rate can accelerate the convergence process of the model, but it is also necessary to pay close attention to the training process of the model to prevent overfitting; Loss function: Cross entropy loss function. For simple tasks and small datasets, the cross entropy loss function is usually sufficient to measure the performance of the model. Activation function: ReLU function. ReLU function usually performs well on simple tasks and has high computational efficiency. Batch size: 16 or 32. In small-scale engineering survey and design archive management, a smaller batch size helps the model better capture the detailed features in the data, but it also increases the training time. Therefore, it is necessary to select an appropriate batch size based on hardware resources and training time.

[0045] The second management model may be more inclined to choose pre-trained models such as Transformer or BERT, because these models perform well when processing large-scale and complex data, and can capture more language features through complex parameter settings to improve recognition accuracy.

[0046] In this embodiment, the second management model is a Transformer model, and the specific parameters are set as follows: The number of hidden layers is 3, the number of neurons in each layer is 512, the optimizer is Adam, the learning rate is 0.0001, the loss function is the cross entropy loss function, the activation function is GELU function, and the batch size is 64.

[0047] Specifically, Number of hidden layers: 3 or 4. When the data set is large and the task is complex, increasing the number of hidden layers can help the model better capture the deep features in the data and improve the performance of the model. Number of neurons per layer: 512 or 1024. Increasing the number of neurons can enhance the representation ability of the model, but it will also increase the computational complexity and memory consumption of the model. On large-scale datasets, more neurons usually lead to better performance. Optimizer: AdamW or RAdam. AdamW is a variant of the Adam optimizer that improves on weight decay and helps prevent model overfitting. RAdam is another improved Adam optimizer that excels in dealing with non-convex optimization problems. Learning rate: 0.0005 or 0.0001. On large-scale datasets, a smaller learning rate is usually more stable and helps the model find a better global optimal solution. Loss function: Cross entropy loss function (with weights) or Focal Loss; when there is a class imbalance problem in the data set, you can use the weighted cross entropy loss function or Focal Loss to focus on minority class samples and improve the generalization ability of the model; Activation function: GELU function or Leaky ReLU function. The GELU function performs well in most cases, but the Leaky ReLU function can maintain a certain gradient when processing negative inputs, which helps prevent the model from falling into a dead zone during training; Batch size: 64 or 128. A larger batch size can speed up the training process, but it may also cause the model to fall into a local optimal solution during training. In practical applications, it is necessary to select an appropriate batch size based on hardware resources and data set size.

[0048] The above parameter setting scheme is a preferred scheme for the present invention. In practical applications, these parameters can be flexibly adjusted according to specific task requirements, data set size, hardware resources, and experimental feedback. At the same time, the model needs to be fully trained and verified to ensure its accuracy and stability in practical applications.

[0049] The selection of the two model parameters is a study of engineering archives of different sizes, aiming to achieve accurate matching of computing resources. For small engineering archives, the first management model achieves effective utilization of resources with its smaller scale and faster processing speed; while for large engineering archives, the second management model ensures the integrity and reliability of the recognition results with its stronger processing power and higher accuracy.

[0050] Step S4, file identification: inputting the engineering survey and design data into the selected management model, identifying the engineering survey and design data through the management model, and obtaining archive information; Through the natural language processing (NLP) technology in the management model, the engineering survey and design data are deeply analyzed and identified, and key information in the engineering survey and design data is extracted and sorted, including but not limited to: project name, project location, design unit, design date, project type, scale parameters (such as area, length, height, capacity, etc.), main materials, construction requirements, safety specifications, environmental protection standards, etc. According to the preset archiving information template or data structure, the extracted key information is formatted and structured to form clear and complete archiving information.

[0051] Ensure that the archived information contains both necessary metadata (such as file type, format, size, creation time, etc.) and the core content and characteristics of the engineering survey and design data to facilitate subsequent search, retrieval and data analysis.

[0052] Such archived information not only facilitates managers to quickly understand the main contents of engineering survey and design data, but also provides strong data support for subsequent project management, quality control, cost control, etc. At the same time, structured archived information is also easier to store, retrieve and analyze efficiently through the database system.

[0053] Step S5, data preservation: the archived information is saved in a database.

[0054] In the present invention, the engineering survey and design data are identified and converted into computer language by using natural language processing (NLP) technology according to the type and scale indicators of the data. This process realizes the intelligent processing of engineering survey and design data, so that the originally complex and diverse data can be understood and processed by computers, which provides convenience for subsequent data storage, retrieval and analysis steps.

[0055] The present invention can flexibly select appropriate NLP models for processing according to the scale and complexity of engineering survey and design data, thus achieving reasonable allocation and efficient utilization of computing resources. This not only improves the efficiency of file management, but also significantly reduces operating costs, providing a new solution for intelligent management in the field of engineering survey and design.

[0056] Example 2 like Figure 2 As shown, the present invention also proposes an engineering survey and design archive management system based on NLP, using the engineering survey and design archive management method based on NLP as described in any one of Embodiment 1, including the following modules: Data collection module: obtain engineering survey and design data to be archived; Scale calculation module: connected to the data collection module, used to obtain document parameters, picture drawing parameters and video parameters according to the engineering survey and design data to be archived, and calculate the scale index of the project according to the parameters; Model selection module: connected to the scale calculation module, used to select a model for engineering survey and design data management according to the scale index, specifically, when the scale index is less than or equal to a preset threshold, select the first management model, when the scale index is greater than the preset threshold, select the second management model; File recognition module: connected to the model selection module, used to input the engineering survey and design data into the selected management model and recognize the engineering survey and design data into computer language; Data saving module: connected to the file recognition module, used to save the recognition results output by the management model into the database.

[0057] Example 3 An electronic device, comprising: Processor and memory; The processor is used to execute the steps of the engineering survey and design archive management method based on NLP as described in any one of Example 1 by calling the program or instruction stored in the memory.

[0058] Example 4 A computer-readable storage medium, comprising computer program instructions, wherein the computer program instructions enable a computer to execute the steps of the NLP-based engineering survey and design archive management method as described in any one of Example 1.

[0059] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0060] It should be noted that the terms used in the present invention are only for describing specific embodiments, rather than limiting the scope of the present invention. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of more restrictions, the elements defined by the statement "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0061] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", 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 a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. 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 an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A method for managing engineering survey and design archives based on NLP, characterized in that: The specific steps include: Step S1, data collection: obtaining engineering survey and design data to be archived; Step S2, scale calculation: obtaining document parameters, picture drawing parameters and video parameters according to the engineering survey and design data to be archived, and calculating the scale index of the project according to the parameters; Step S3, model selection: selecting a model for engineering survey and design data management according to the scale index, specifically, when the scale index is less than or equal to a preset threshold, selecting a first management model, and when the scale index is greater than the preset threshold, selecting a second management model; Step S4, file identification: inputting the engineering survey and design data into the selected management model, identifying the engineering survey and design data through the management model, and obtaining archive information; Step S5, data preservation: the archived information is saved in a database.

2. The NLP-based engineering survey and design archive management method according to claim 1, characterized in that: The method for obtaining the scale indicator is: Step S21, dividing the engineering survey and design data to be archived into documents, pictures, drawings and videos; Step S22, obtaining the total word count W of the document and the document conversion coefficient α1; Obtain the file size S of the picture drawing, the picture drawing conversion coefficient α2 and the picture drawing resolution adjustment factor β; obtain the file size V of the video, the video conversion coefficient α3 and the video resolution adjustment factor γ; Step S23, calculating the scale index according to the parameters obtained in step S22.

3. The engineering survey and design archive management method based on NLP according to claim 2 is characterized in that: The calculation formula of the scale indicator TRS is: TRS=W / α1+S×β / α2+V×γ / α3.

4. The NLP-based engineering survey and design archive management method according to claim 2 is characterized in that: The image resolution adjustment factor β is: ； Among them, ω TP is the weight of the image, N TP is the number of pictures, S TPi is the size of the i-th picture, β TPi is the resolution of the i-th image, ω TZ is the weight of the drawing, N TZ is the number of drawings, S TZj is the size of the jth drawing, β TZj is the resolution of the jth drawing.

5. The NLP-based engineering survey and design archive management method according to claim 2, characterized in that: The video resolution adjustment factor γ is taken as: ； Among them, ω Vk is the weight of the kth video, V k is the size of the kth video, γ Vk is the resolution of the kth video, N V is the number of videos.

6. The NLP-based engineering survey and design archive management method according to claim 1, characterized in that: The first management model is an LSTM model, and the second management model is a Transformer model.

7. The NLP-based engineering survey and design archive management method according to claim 1, characterized in that: The specific parameters of the first management model are set as: The number of hidden layers is 2, the number of neurons in each layer is 256, the activation function is sigmoid function, the optimizer is Adam, the learning rate is 0.001, the loss function is the cross entropy loss function, and the batch size is 32.

8. The NLP-based engineering survey and design archive management method according to claim 1, characterized in that: The specific parameters of the second management model are set as: The number of hidden layers is 3, the number of neurons in each layer is 512, the optimizer is Adam, the learning rate is 0.0001, the loss function is the cross entropy loss function, the activation function is GELU function, and the batch size is 64.

9. An NLP-based engineering survey and design archive management system, using the NLP-based engineering survey and design archive management method according to any one of claims 1 to 8, characterized in that: The modules include: Data collection module: obtain engineering survey and design data to be archived; Scale calculation module: connected to the data collection module, used to obtain document parameters, picture drawing parameters and video parameters according to the engineering survey and design data to be archived, and calculate the scale index of the project according to the parameters; Model selection module: connected to the scale calculation module, used to select a model for engineering survey and design data management according to the scale index, specifically, when the scale index is less than or equal to a preset threshold, select the first management model, when the scale index is greater than the preset threshold, select the second management model; File recognition module: connected to the model selection module, used to input the engineering survey and design data into the selected management model and recognize the engineering survey and design data into computer language; Data saving module: connected to the file recognition module, used to save the recognition results output by the management model into the database.

10. An electronic device, comprising: A processor and a memory, characterized in that the processor is used to execute the steps of the engineering survey and design archive management method based on NLP as described in any one of claims 1 to 8 by calling the program or instructions stored in the memory.

Images