Railway design key point generation method, equipment and device based on large model and medium

Abstract

The invention relates to the technical field of computers, in particular to a railway design key point generation method, equipment and device based on a large model and a medium. According to the method, a computer programming technology is adopted, a multi-source data set is systematically collected, and training of a deep learning model is carried out on the basis of the multi-source data set; further, a specialized large model capable of screening review opinions and preliminarily extracting keywords from the review opinions is constructed, and compared with the prior art, the complexity of data management is remarkably simplified; according to the method, the weight of the keyword is calculated according to the preliminarily extracted keyword, the design key and difficult points needing to be concerned are obtained, valuable verification data can be intelligently extracted, and the method not only facilitates deep summarization of the current railway engineering project, but also provides accurate data support and experience reference for smooth development and design of future projects.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, equipment, device and medium for generating railway design key points based on a large model. Background Art

[0002] In the current collaborative design process of railway projects, design units use various advanced digital systems and platforms to conduct detailed review of design outputs, and this process generates a large number of opinions. The number of opinions generated in all professional fields of a single railway project ranges from thousands to tens of thousands. These opinion data obtained after strict review are valuable knowledge and experience accumulation for subsequent projects. They can effectively assist future review work and significantly improve the quality of design results. However, the governance of these review opinions is extremely challenging, especially the difficulty of accurately classifying and utilizing them. Therefore, how to efficiently use the experience of previous projects to provide guidance for subsequent projects has become an urgent problem to be solved. Summary of the invention

[0003] The purpose of the present invention is to provide a method, equipment, device and medium for generating railway design key points based on a large model to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0004] In a first aspect, the present application provides a method for generating railway design key points based on a large model, comprising:

[0005] Obtain review opinions, and screen the review opinions for validity based on the big model to obtain valid opinions;

[0006] Extract keywords from the valid opinions based on the big model to obtain a keyword data set;

[0007] Count the number of times each keyword appears in the valid opinions, and calculate the weight of each keyword based on the data attributes of each valid opinion and the number of times the keyword appears;

[0008] Sorting the keywords according to the weight of each keyword;

[0009] Obtaining a target number of opinions, and extracting keywords in a keyword data set in a sorted order according to the target number of opinions to obtain target keywords;

[0010] According to the target keywords, the valid opinions are searched to obtain the design focus.

[0011] In a second aspect, the present application also provides a railway design key point generation device based on a large model, which includes:

[0012] A screening module is used to obtain review opinions and screen the review opinions for validity based on the big model to obtain valid opinions;

[0013] A keyword extraction module, used to extract keywords from the valid opinions based on the large model to obtain a keyword data set;

[0014] A weight calculation module, used to count the number of occurrences of each keyword in the valid opinions, and calculate the weight of each keyword according to the data attributes of each valid opinion and the number of occurrences of the keyword;

[0015] A sorting module, used for sorting the keywords according to the weight of each keyword;

[0016] A target keyword determination module is used to obtain a target number of opinions, and extract keywords in a keyword data set in a sorted order according to the target number of opinions to obtain target keywords;

[0017] The design focus generation module is used to search the valid opinions according to the target keywords to obtain the design focus.

[0018] In the third aspect, the present application also provides a device for generating key points of railway design based on a large model, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for generating key points of railway design based on a large model described in the present application when executing the computer program.

[0019] In a fourth aspect, the present application further provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method for generating key points of railway design based on a large model described in the present application are implemented.

[0020] The beneficial effects of the present invention are:

[0021] The present invention adopts computer programming technology to systematically collect multi-source data sets, and trains deep learning models based on this, thereby constructing a large professional model that can screen review opinions and preliminarily extract keywords therefrom, which significantly simplifies the complexity of data management compared to the prior art; the weights of the keywords preliminarily extracted are calculated to obtain the key design difficulties that need attention, thereby enabling intelligent extraction of valuable review data. The method of the present application not only helps to make an in-depth summary of current railway engineering projects, but also provides accurate data support and experience reference for the smooth development and design of future projects.

[0022] Other features and advantages of the present invention will be set forth in the following description, and in part will become apparent from the description, or may be understood by practicing embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 This is a flow chart of a method for generating key points of railway design based on a large model in an embodiment of the present application;

[0025] Figure 2 It is a structural schematic diagram of a railway design key point generation device based on a large model in an embodiment of the present application;

[0026] Figure 3 This is a structural schematic diagram of the key generation equipment for railway design based on a large model in an embodiment of the present application.

[0027] Figure numerals: 100, railway design key point generation device based on large model; 200, screening module; 300, keyword extraction module; 400, weight calculation module; 410, first calculation unit; 420, second calculation unit; 430, third calculation unit; 440, fourth calculation unit; 450, fifth calculation unit; 460, sixth calculation unit; 431, H calculation subunit; 432, N1 calculation subunit; 433, N2 calculation subunit; 434, N3 calculation subunit Operator unit; 435, weighted calculation subunit; 500, sorting module; 600, target keyword determination module; 610, target word quantity calculation module; 620, association table construction unit; 630, priority association table acquisition unit; 640, extraction unit; 700, design focus generation module; 800, railway design focus generation equipment based on large model; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0029] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0030] Example 1

[0031] like Figure 1 As shown, the present application provides a method for generating railway design key points based on a large model, including steps S100, S200, S300, S400, S500 and S600.

[0032] Step S100: Obtain review opinions, and screen the review opinions for validity based on the big model to obtain valid opinions;

[0033] The review opinions are a large number of modification suggestions generated during the collaborative design of railway projects, and have been reviewed by experts. Each review opinion has its corresponding data attributes. When the review opinions are obtained from the collaborative design platform of railway projects, their data attributes are obtained at the same time. In this embodiment, the data attributes include project (ProjectType) attributes, area (Area) attributes, railway level (Standard) attributes, length (Length) attributes, stage level (Stage) attributes, majors attributes, and importance level (Rank) attributes.

[0034] Among these review opinion data, some data are invalid data, for example, "Please see the review form for details of the review opinion", "Agree", "No review opinion", etc. These are meaningless opinion data that need to be eliminated. Due to the large number of review opinions, it is impossible to screen them manually one by one. Therefore, this application uses a large model for screening.

[0035] Specifically, based on the existing open source large models, such as Qwen2-72B, large model training data is written to conduct validity screening training. The data writing content adopts the form of Prompt+Completion, and the data format uses JSON format.

[0036] Here is an example:

[0037] ①Prompt: Please judge whether the following opinions are valid opinions, answer yes or no: In the case of current uncertain geological conditions, combined with the review experience and internal control principles of the appraisal center, the control values ​​of the clear distances of various types of adjacent, parallel, underpass and overpass risk source structures are temporarily determined by the corresponding multiples of the maximum span D of tunnel excavation.

[0038] Completion: Yes.

[0039] ②Prompt: Please judge whether the following opinions are valid opinions. Answer yes or no: Agree to send it to the hospital for review.

[0040] Completion: No.

[0041] ③Prompt: Please judge whether the following opinions are valid opinions, and answer yes or no: "Control elevation" should be clearly defined as "Track surface control elevation".

[0042] Completion: Yes.

[0043] ④Prompt: Please judge whether the following opinions are valid opinions, answer yes or no: Please refer to the audit form for details of the audit opinions.

[0044] Completion: No.

[0045] After effectiveness screening training, the resulting large screening model can judge and screen the effectiveness of all review opinions to obtain effective opinions.

[0046] Step S200: extract keywords from the valid opinions based on the large model to obtain a keyword data set;

[0047] In order to make a refined statistics of the effective opinions and further refine the high-frequency design difficulties that need to be paid attention to in the effective opinions to assist in design review and output results report, it is first necessary to extract keywords for each effective opinion.

[0048] This application is based on the existing open source big model to perform keyword extraction training, so that the trained big model can accurately give the key contents of railway engineering collaborative design. The training data writing type adopts the form of Prompt+Completion, and the data format uses JSON format. The example is as follows:

[0049] ①Prompt: Please list the key words in the following opinions: supplementary water level, overpass and other control elevations.

[0050] Completion: water level, interchange, control elevation.

[0051] ②Prompt: Please list the key words in the following opinions: The contact network span of the roadbed section is generally 55m, and the maximum is more than 60m. This is wrong. It is recommended to change it to: The contact network span of the roadbed section is generally 55m, and the maximum is not more than 60m.

[0052] Completion: roadbed section and contact network span.

[0053] ③Prompt: Please list the keywords in the following comments: Verify whether the mileage position of C1K97+629 culvert conflicts with the bridge table

[0054] Completion: culvert, mileage, bridge table.

[0055] After training, the obtained analysis model can extract keywords from all valid opinions and obtain a keyword data set.

[0056] The training process of the large model in step S200 also includes steps S210, S220 and S230.

[0057] Step S210, eliminating Tokenization misunderstandings;

[0058] In the railway engineering design review data, there are cases where chapter numbers such as 1.11 and design values ​​such as 1.11 appear. After tokenization, the big model will form a result of 1 / . / 11, which cannot correctly understand the actual size of the design value. Through the big model's tuning module, the position of different types of numbers in the opinions and their matching with different words are provided, so that the big model can determine in what context the value is a floating point number and eliminate misunderstandings.

[0059] Step S220, eliminating confusion errors in professional terms and concepts;

[0060] During the railway engineering design review process, each review expert cannot unify the way of expressing the same thing, and the big model cannot judge. For example, "slope difference" and "slope algebraic difference" are two ways of saying the same word. The untrained big model will extract the "algebraic difference" in the latter as the design focus. At this time, the output result will analyze "slope difference" and "algebraic difference" as two results. Therefore, it is necessary to provide more data training data tuning containing these two terms and their contexts, so that the exclusive big model can fully learn the relationship between them and perform combined statistics.

[0061] Step S230: Eliminate the ambiguity of railway engineering project-specific terms

[0062] In the railway engineering design review data, there are a lot of abbreviations replacing items. For example, "Wenfu" represents Wenzhou to Fuzhou in railway engineering. The big model cannot determine the meaning of the word, and it will cause ambiguity when combined with other words. Therefore, it is necessary to correct the errors of such words in the model through tuning, and through word combination, let the big model understand the meaning of the exclusive noun in the sentence.

[0063] Step S300: Count the number of occurrences of each keyword in the valid opinions, and calculate the weight of each keyword according to the data attributes of each valid opinion and the number of occurrences of the keyword;

[0064] After extracting keywords from each valid opinion through the big analysis model, it is necessary to analyze the value (importance) of each keyword. The specific methods include:

[0065] Step S310: Calculate the importance weight coefficient W according to the importance level (Rank) attribute of the valid opinion and the number of occurrences of the keyword. i ;

[0066] The Rank attribute is divided into three categories: MI (Group Chief Engineer Approval Level), I (Professional Chief Engineer Approval Level), and N (Special Volume, Qualified Approval Level);

[0067] Count the number of times a keyword appears in the valid opinions of these three types of Rank attributes. For example, if the total number of times a keyword appears in all valid opinions is x, then x of them appear in the valid opinions with Rank attribute MI. MI times, x appears in the valid opinions with Rank attribute I I times, x appears in the valid opinions with Rank attribute N N times, x=x MI +x I +x N .

[0068] Under MI attributes, W i (MI) = 3x MI 2 ;

[0069] Under I attribute, W i (I) = 2x I +1;

[0070] Under the N attribute, W i (N) = x N +0.5;

[0071] but

[0072] Step S320: Obtain the occurrence weight coefficient W according to the occurrence number of the keyword. t ;

[0073] Occurrence weight coefficient W t =α×log2(1+x), where x is the total number of times the keyword appears; α is the adjustment parameter. The value of the adjustment parameter α can be set according to the total number of valid opinions to ensure that W t Not too big or too small.

[0074] Step S330: Obtain the railway level weight coefficient W according to the railway level (Standard) attribute of the valid opinion and the number of occurrences of the keyword sd ;

[0075] Standard attributes are divided into H, N1, N2, and N3 (representing the level of railways). The number of times keywords appear in the valid opinions of these four types of Standard attributes is x. H 、x N1 、x N2 、x N3 ; x is the total number of times the keyword appears, x=x H +x N1 +x N2 +x N3 ;

[0076] According to the number of occurrences of the keyword in the valid opinions of railway-level attribute type H, x H , calculate the first weight coefficient W sd (H):

[0077]

[0078] According to the number of occurrences of the keyword in the valid opinions of railway-level attribute type N1 x N1 , calculate the second weight coefficient W sd (N1):

[0079] W sd (N1) = 1.3x N1 ·(1+0.08ln(1+0.5x N1 ));

[0080] According to the number of occurrences of the keyword in the valid opinions of railway-level attribute type N2 x N2 , calculate the third weight coefficient W sd (N2):

[0081] W sd (N2) = 1.1x N2 (1+0.06x N2+0.003x N2 2 );

[0082] According to the number of occurrences of the keyword in the valid opinions of railway-level attribute type N3 x N3 , calculate the fourth weight coefficient W sd (N3):

[0083]

[0084] According to the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient, the railway level weight coefficient W is obtained by weighted calculation. sd :

[0085]

[0086] Step S340: Obtain a data density weight coefficient W according to the number of occurrences of the keyword and the total number of valid opinions. ρ ;

[0087] Data density weight coefficient Where x is the total number of times the keyword appears, n is the total number of valid opinions, and β is the adjustment parameter. The value of the adjustment parameter β can be set according to the total number of valid opinions to ensure that W ρ Not too big or too small.

[0088] Step S350: Obtain the stage-level weight coefficient W according to the stage-level attribute of the valid opinion and the number of occurrences of the keyword. sg ;

[0089] The Stage attribute is divided into Pre (pre-feasibility study), FS (feasibility study), PD (preliminary design), and CD (construction drawing design); the number of times the keywords appear in the valid opinions of these four Stage attributes is x Pre 、x FS 、x PD 、x CD , x is the total number of times the keyword appears, x=x Pre +x FS +x PD +x CD ;

[0090] W under each attribute sg Calculation formula:

[0091] Under the Pre attribute W sg (Pre) = 1.1x Pre ×e 0.06xPre ;

[0092] Under FS properties,sg (FS)=1.4x FS ×e 0.09xFS ;

[0093] Under PD properties, W sg (PD) = 1.7x PD ×e 0.12xPD ;

[0094] Under CD properties, sg (CD) = 2x CD ×e 0.15xCD ;

[0095] but

[0096] Step S360: According to W i , W t , W sd , W ρ and W sg Get the keyword weight W; the calculation formula of weight W is:

[0097] W=W i ×W t ×W sd ×W ρ ×(1+W sg ).

[0098] Step S400: sorting the keywords according to the weight of each keyword;

[0099] After calculation in step S300 , each keyword can obtain a weight W, and all keywords are sorted in descending order according to the weight W.

[0100] Step S500: obtaining a target number of opinions, and extracting keywords in a keyword data set in a sorted order according to the target number of opinions to obtain target keywords;

[0101] The target number of opinions refers to the number of opinions that need to be output for display. In this embodiment, the target number of opinions is determined by the number of engineering projects y, and the target number of opinions R = 10 + 40 × {1-math.exp(-0.1y)} × {math.log(1+0.1y) / math.log(2)}.

[0102] The number of engineering projects y can be obtained through the engineering project (ProjectType) attribute of valid opinions. The value of y can be obtained by counting the number of ProjectType attributes corresponding to valid opinions.

[0103] According to the calculated target number of opinions R, the target number of keywords K is calculated, K = R / J, where J is the preset number of opinions to be displayed for each target keyword;

[0104] After obtaining K, the first K keywords can be directly extracted from the keyword dataset in sorted order and used as target keywords.

[0105] In the field of railway engineering design, different professions may focus on different points, that is, different professions may require different keywords. In order to improve the relevance of target keywords and professions, this embodiment preferably uses the following method to extract target keywords:

[0106] The data attributes of the effective opinions include major attributes, and the effective opinions are classified according to the major attributes; for each type of professional effective opinions, it is determined whether the number of times any two keywords appear in the same effective opinion exceeds a preset threshold, and if so, the two keywords are related words to each other; a keyword may have one or more related words, or may not have any; a related table is constructed according to the related words under each type of professional attributes;

[0107] For example, based on the effective opinions of M1 major, association table 1 was constructed, in which keyword A and keyword B were associated words;

[0108] Based on the effective opinions of M2 professionals, association table 2 was constructed, in which keyword A and keyword C were associated words;

[0109] Before extracting keywords, obtain the priority professional type, and obtain the corresponding priority association table according to the priority professional type;

[0110] The priority major type may be a query condition input by a user. For example, if the priority major type is M2 major, association table 2 is obtained as the priority association table.

[0111] Keywords are extracted from the keyword data set in sorted order, and their associated words are extracted one by one in the priority association table according to the extracted keywords. When the sum of the extracted keywords and the associated words reaches the target keyword quantity, the extraction is stopped to obtain the target keyword.

[0112] For example, in the keyword data set, the first keyword is keyword A, keyword A is extracted, and the associated word of keyword A is retrieved according to association table 2 as keyword C, and keyword C is extracted; then the same operation is performed on subsequent keywords in the keyword data set until the sum of the extracted keywords and associated words reaches the target number of keywords K, and these extracted keywords are used as target keywords.

[0113] It should be noted that the target keywords are not extracted repeatedly. For example, after extracting keyword A and keyword C according to the above example, it is later found that the tenth keyword in the keyword data set is keyword C, that is, the tenth keyword is skipped and the next one is extracted.

[0114] S600: Search the valid opinions according to the target keywords to obtain design highlights.

[0115] According to the K target keywords, a reverse search is performed in the analysis model to retrieve valid opinions containing the target keywords. The same valid opinion may appear multiple times. The valid opinions are arranged from the most to the least according to the number of appearances. The first J valid opinions are selected and displayed as the design focus.

[0116] For example, the number of opinions to be displayed for each target keyword is preset to be J=3, and the target keyword "safety line" is obtained. Among the valid opinions containing "safety line", "verify whether the safety line is in the form of setting a curve away from the main line and to the departure line", "whether a safety line is added to the maintenance area", and "the safety line should not enter the bridge range" appear the most times. These three valid opinions are displayed as design focuses.

[0117] As an optional implementation of the present application, the railway engineering design focus generation method further includes step S700:

[0118] Classifying the design priorities according to the obtained professional attributes corresponding to the design priorities;

[0119] Fill the design focus into the preset template according to the classification to obtain an analysis report.

[0120] Example 2

[0121] like Figure 2 As shown, this embodiment provides a railway design key point generation device based on a large model, including:

[0122] A screening module is used to obtain review opinions and screen the review opinions for validity based on the big model to obtain valid opinions;

[0123] A keyword extraction module, used to extract keywords from the valid opinions based on the large model to obtain a keyword data set;

[0124] A weight calculation module, used to count the number of occurrences of each keyword in the valid opinions, and calculate the weight of each keyword according to the data attributes of each valid opinion and the number of occurrences of the keyword;

[0125] A sorting module, used for sorting the keywords according to the weight of each keyword;

[0126] A target keyword determination module is used to obtain a target number of opinions, and extract keywords in a keyword data set in a sorted order according to the target number of opinions to obtain target keywords;

[0127] The design focus generation module is used to search the valid opinions according to the target keywords to obtain the design focus.

[0128] In a specific implementation manner disclosed in the present application, the data attributes of the effective opinions include importance level attributes, railway level attributes and stage level attributes; the weight calculation module includes:

[0129] A first calculation unit, configured to obtain an importance weight coefficient according to the importance level attribute of the valid opinion and the number of occurrences of the keyword;

[0130] A second calculation unit is used to obtain an appearance frequency weight coefficient according to the appearance frequency of the keyword;

[0131] A third calculation unit is used to obtain a railway level weight coefficient according to the railway level attribute of the valid opinion and the number of occurrences of the keyword;

[0132] a fourth calculation unit, configured to obtain a data density weight coefficient according to the number of occurrences of the keyword and the total number of valid opinions;

[0133] a fifth calculation unit, configured to obtain a stage-level weight coefficient according to the stage-level attribute of the valid opinion and the number of occurrences of the keyword;

[0134] The sixth calculation unit is used to obtain the weight of the keyword according to the importance weight coefficient, the occurrence weight coefficient, the railway level weight coefficient, the data density weight coefficient and the stage level weight coefficient.

[0135] In a specific implementation manner disclosed in the present application, the types of the railway-level attributes include H, N1, N2 and N3; the third calculation unit includes:

[0136] The H calculation subunit is used to calculate a first weight coefficient according to the number of occurrences of the keyword in the valid opinions with the railway level attribute type H;

[0137] The N1 calculation subunit is used to calculate a second weight coefficient according to the number of occurrences of the keyword in the valid opinions with the railway level attribute type N1;

[0138] The N2 calculation subunit is used to calculate a third weight coefficient according to the number of occurrences of the keyword in the valid opinions with the railway level attribute type N2;

[0139] N3 calculation subunit, used for calculating a fourth weight coefficient according to the number of occurrences of the keyword in the valid opinions with the railway level attribute type N3;

[0140] The weighted calculation subunit is used to obtain a road level weight coefficient by weighted calculation according to the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient.

[0141] In a specific implementation manner disclosed in the present application, the data attributes of the effective opinions include professional attributes, and the target keyword determination module includes:

[0142] A target word quantity calculation unit, used to calculate the target keyword quantity according to the target number of opinions;

[0143] The association table construction unit is used to classify the valid opinions according to the professional attributes; for each category of the valid opinions, determine whether the number of times any two of the keywords appear in the same valid opinion exceeds a preset threshold, and if so, the two keywords are related words to each other; and construct an association table according to the related words under each category of professional attributes;

[0144] A priority association table acquisition unit is used to acquire a priority professional type, and acquire a corresponding priority association table according to the priority professional type;

[0145] The extraction unit is used to extract keywords in the keyword data set in sorted order, and extract the associated keywords in the priority association table one by one according to the extracted keywords. When the sum of the extracted keywords and the associated keywords reaches the target keyword quantity, the extraction is stopped to obtain the target keyword.

[0146] Example 3

[0147] Corresponding to the above method embodiment, this embodiment also provides a railway design focus generation device based on a large model. The railway design focus generation device based on a large model described below and the railway design focus generation method based on a large model described above can refer to each other.

[0148] Figure 3 8 is a block diagram of a railway design key point generation device 800 based on a large model according to an exemplary embodiment. Figure 3As shown, the railway design key point generation device 800 based on the large model includes a processor 801 and a memory 802. The railway design key point generation device 800 based on the large model may also include one or more of a multimedia component 803, an input / output (I / O) interface 804, and a communication component 805. Among them, the processor 801 is used to control the overall operation of the railway design key point generation device 800 based on the large model to complete all or part of the steps in the railway design key point generation method based on the large model. The memory 802 is used to store various types of data to support the operation of the railway design key point generation device 800 based on the large model, and these data may include, for example, commands for any application or method operating on the railway design key point generation device 800 based on the large model, and application-related data, such as contact data, messages sent and received, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, disk or optical disk.

[0149] The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone, and the microphone is used to receive external audio signals.

[0150] The received audio signal can be further stored in the memory 802 or sent through the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the railway design key generation device 800 based on the large model and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0151] In an exemplary embodiment, the device 800 for mutual signing and verification of digital files can be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), digital signal processors (Digital Signal Processor, referred to as DSP), digital signal processing devices (Digital Signal Processing Device, referred to as DSPD), programmable logic devices (Programmable Logic Device, referred to as PLD), field programmable gate arrays (Field Programmable Gate Array, referred to as FPGA), controllers, microcontrollers, microprocessors or other electronic components, and is used to execute the above-mentioned large model-based railway design key point generation method.

[0152] In another exemplary embodiment, a computer-readable storage medium including program commands is also provided, and when the program commands are executed by a processor, the steps of the above-mentioned method for generating railway design highlights based on a large model are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program commands, and the above-mentioned program commands can be executed by the processor 801 of the device 800 for generating railway design highlights based on a large model to complete the above-mentioned method for generating railway design highlights based on a large model.

[0153] Example 4

[0154] Corresponding to the above embodiment of the railway design focus generation method based on a large model, this embodiment also provides a readable storage medium, and the readable storage medium described below and the railway design focus generation method based on a large model described above can refer to each other.

[0155] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the embodiment of the railway design key generation method based on a large model.

[0156] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0157] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0158] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for generating key points of railway design based on a large model, characterized in that: include: Obtain review opinions, and screen the review opinions for validity based on the big model to obtain valid opinions; Extract keywords from the valid opinions based on the big model to obtain a keyword data set; Count the number of times each keyword appears in the valid opinions, and calculate the weight of each keyword based on the data attributes of each valid opinion and the number of times the keyword appears; Sorting the keywords according to the weight of each keyword; Obtaining a target number of opinions, and extracting keywords in a keyword data set in a sorted order according to the target number of opinions to obtain target keywords; According to the target keywords, the valid opinions are searched to obtain the design focus.

2. The method for generating key points of railway design based on a large model according to claim 1, characterized in that: The data attributes of the valid opinions include importance level attributes, railway level attributes and stage level attributes; The counting of the number of occurrences of each keyword and the calculation of the keyword weight according to the data attributes of each valid opinion and the number of occurrences of the keyword include: Obtaining importance weight coefficients according to the importance level attributes of the valid opinions and the number of occurrences of the keywords; According to the number of occurrences of the keyword, obtaining the number of occurrence weight coefficient; According to the railway-level attributes of the valid opinions and the number of occurrences of the keywords, a railway-level weight coefficient is obtained; Obtaining a data density weight coefficient according to the number of occurrences of the keyword and the total number of valid opinions; According to the stage-level attributes of the valid opinions and the number of occurrences of the keywords, a stage-level weight coefficient is obtained; The weight of the keyword is obtained according to the importance weight coefficient, the occurrence weight coefficient, the railway level weight coefficient, the data density weight coefficient and the stage level weight coefficient.

3. The method for generating key points of railway design based on a large model according to claim 2, characterized in that: The types of the railway-level attributes include H, N1, N2 and N3; The railway level weight coefficient is obtained according to the railway level attribute of the valid opinion and the number of occurrences of the keyword, including: Calculate a first weight coefficient according to the number of occurrences of the keyword in valid opinions with railway-level attribute type H; Calculating a second weight coefficient according to the number of occurrences of the keyword in valid opinions with railway-level attribute type N1; Calculating a third weight coefficient according to the number of occurrences of the keyword in valid opinions with railway-level attribute type N2; Calculating a fourth weight coefficient according to the number of occurrences of the keyword in valid opinions with railway-level attribute type N3; The railway level weight coefficient is obtained by weighted calculation based on the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient.

4. The method for generating key points of railway design based on a large model according to claim 1, characterized in that: The step of extracting keywords in the keyword data set in a sorted order according to the target number of opinions to obtain target keywords includes: Calculate the number of target keywords based on the target number of opinions; The data attributes of the effective opinions include professional attributes, and the effective opinions are classified according to the professional attributes; for each type of the effective opinions, it is determined whether the number of times any two of the keywords appear in the same effective opinion exceeds a preset threshold, and if so, the two keywords are related words to each other; a related table is constructed according to the related words under each type of professional attributes; Obtain a priority major type, and obtain a corresponding priority association table according to the priority major type; Keywords are extracted from the keyword data set in sorted order, and their associated words are extracted one by one in the priority association table according to the extracted keywords. When the sum of the extracted keywords and the associated words reaches the target keyword quantity, the extraction is stopped to obtain the target keyword.

5. A railway design key point generation device based on a large model, characterized in that: include: A screening module is used to obtain review opinions and screen the review opinions for validity based on the big model to obtain valid opinions; A keyword extraction module, used to extract keywords from the valid opinions based on the large model to obtain a keyword data set; A weight calculation module, used to count the number of occurrences of each keyword in the valid opinions, and calculate the weight of each keyword according to the data attributes of each valid opinion and the number of occurrences of the keyword; A sorting module, used for sorting the keywords according to the weight of each keyword; A target keyword determination module is used to obtain a target number of opinions, and extract keywords in a keyword data set in a sorted order according to the target number of opinions to obtain target keywords; The design focus generation module is used to search the valid opinions according to the target keywords to obtain the design focus.

6. The railway design key point generation device based on a large model according to claim 5 is characterized in that: The data attributes of the valid opinions include importance level attributes, railway level attributes and stage level attributes; The weight calculation module comprises: A first calculation unit, configured to obtain an importance weight coefficient according to the importance level attribute of the valid opinion and the number of occurrences of the keyword; A second calculation unit is used to obtain an appearance frequency weight coefficient according to the appearance frequency of the keyword; A third calculation unit is used to obtain a railway level weight coefficient according to the railway level attribute of the valid opinion and the number of occurrences of the keyword; a fourth calculation unit, configured to obtain a data density weight coefficient according to the number of occurrences of the keyword and the total number of valid opinions; a fifth calculation unit, configured to obtain a stage-level weight coefficient according to the stage-level attribute of the valid opinion and the number of occurrences of the keyword; The sixth calculation unit is used to obtain the weight of the keyword according to the importance weight coefficient, the occurrence weight coefficient, the railway level weight coefficient, the data density weight coefficient and the stage level weight coefficient.

7. The railway design key point generation device based on a large model according to claim 6 is characterized in that: The types of the railway-level attributes include H, N1, N2 and N3; The third computing unit comprises: The H calculation subunit is used to calculate a first weight coefficient according to the number of occurrences of the keyword in the valid opinions with the railway level attribute type H; The N1 calculation subunit is used to calculate a second weight coefficient according to the number of occurrences of the keyword in the valid opinions with the railway level attribute type N1; The N2 calculation subunit is used to calculate a third weight coefficient according to the number of occurrences of the keyword in the valid opinions with the railway level attribute type N2; N3 calculation subunit, used for calculating a fourth weight coefficient according to the number of occurrences of the keyword in the valid opinions with the railway level attribute type N3; The weighted calculation subunit is used to obtain a road level weight coefficient by weighted calculation according to the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient.

8. The railway design key point generation device based on a large model according to claim 5 is characterized in that: The data attributes of the effective opinions include professional attributes, and the target keyword determination module includes: A target word quantity calculation unit, used to calculate the target keyword quantity according to the target number of opinions; The association table construction unit is used to classify the valid opinions according to the professional attributes; for each category of the valid opinions, determine whether the number of times any two of the keywords appear in the same valid opinion exceeds a preset threshold, and if so, the two keywords are related words to each other; and construct an association table according to the related words under each category of professional attributes; A priority association table acquisition unit is used to acquire a priority professional type, and acquire a corresponding priority association table according to the priority professional type; The extraction unit is used to extract keywords in the keyword data set in sorted order, and extract the associated keywords in the priority association table one by one according to the extracted keywords. When the sum of the extracted keywords and the associated keywords reaches the target keyword quantity, the extraction is stopped to obtain the target keyword.

9. A device for generating key points of railway design based on a large model, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for generating key points of railway design based on a large model as claimed in any one of claims 1 to 4 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the railway design focus generation method based on a large model as claimed in any one of claims 1 to 4 are implemented.

Images