Main material and equipment price selection method and system for maintenance project

Abstract

The invention discloses a main material and equipment price selection method and system for a maintenance project, and relates to the technical field of power maintenance project price selection, and the method comprises the steps: extracting field information from a material price library, and recognizing a core word through a semantic analysis model; constructing a core word index file, and performing word segmentation and matching processing on retrieval keywords; and sorting the matched data based on a weight rule, and generating a recommendation result for a user to refer to. According to the method, a dynamic and real-time data basis is provided for subsequent analysis, so that the system can better adapt to continuously changing market requirements, the reading speed of the index file is increased, the search sensitivity and accuracy are improved, the requirement of a user for instant information is met, and the user experience is improved. According to the method, the recommendation transparency and credibility are improved, and the user experience and participation sense are improved, so that the pertinence and rationality of decision making are improved, and efficient market response and material selection strategy optimization are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of power maintenance project price selection, and specifically to a method and system for selecting the main materials and equipment prices of a maintenance project. Background Art

[0002] In modern power maintenance projects, the selection of main material and equipment prices is crucial for the precise control of project costs; in power maintenance projects, materials and equipment are usually already determined, but how to select reasonable prices in the market and form a scientific cost plan is still a complex process; with the rapid development of information technology, data-driven price management methods have gradually replaced traditional empirical methods; in recent years, the application of Building Information Modeling (BIM), big data analysis, and intelligent evaluation technologies has promoted the refined management of price selection, especially the introduction of semantic analysis and natural language processing technologies, which has made the analysis and processing of price information more efficient; these technologies provide scientific basis for decision-makers by monitoring market price fluctuations and supplier data in real time, thereby effectively reducing project costs and ensuring the rationality and transparency of project costs.

[0003] Despite certain progress in price selection technologies, existing solutions still face significant limitations; currently, price management usually relies on static price databases and lacks a dynamic update mechanism, resulting in the inability to accurately reflect the real-time state of the market; this information island phenomenon weakens the decision-making flexibility in the price selection process and often fails to meet the high requirements of power maintenance projects for timeliness and accuracy; in addition, existing semantic analysis models have limited ability to capture price-related professional terms and context semantics, resulting in insufficient accuracy in price matching and analysis; moreover, traditional information retrieval and recommendation systems usually adopt simple word segmentation algorithms when dealing with price matching and lack comprehensive consideration of keyword relevance and weight rules; this single method cannot provide users with price decision-making suggestions based on multi-dimensional data analysis and ignores important factors such as market dynamics, supplier reputation, and price stability, making it difficult to adapt to complex power maintenance project scenarios and thus affecting the scientificity and rationality of cost control. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: the existing power maintenance project price selection methods rely on static price databases, cannot dynamically update price information, have insufficient semantic analysis capabilities, are difficult to accurately match industry-specific terms and context semantics, lack comprehensive consideration of multi-dimensional factors such as supplier reputation, price fluctuations, and market trends, and how to achieve real-time, accurate, and dynamic price selection and rationalize project cost evaluation.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: A method for selecting the main materials and equipment prices in a maintenance project, including extracting field information from a material price database and identifying core words through a semantic analysis model; constructing a core word index file and performing word segmentation and matching processing on the retrieval keywords; sorting the matching data based on weight rules and generating a recommended result for the user to refer to.

[0007] As a preferred embodiment of the method for selecting the main materials and equipment prices in the maintenance project described in the present invention, wherein: the extracting field information from the material price database includes extracting field information including name, specification, unit, and price from the material price database through a preset field extraction rule.

[0008] Clean the field data to eliminate invalid or redundant data.

[0009] Use the cleaned field data as a preliminary data set.

[0010] As a preferred embodiment of the method for selecting the main materials and equipment prices in the maintenance project described in the present invention, wherein: the identifying core words through the semantic analysis model includes using the BERT model to perform semantic analysis on the field information and extract the semantic features of each field.

[0011] Generate a core word list corresponding to the field through synonym normalization processing and context correlation analysis.

[0012] Build a dynamic association relationship between the field and the core word based on the semantic features and generate a core word library.

[0013] As a preferred embodiment of the method for selecting the main materials and equipment prices in the maintenance project described in the present invention, wherein: the constructing the core word index file includes grouping the core words according to their categories and constructing a categorized index file, and the categories include building materials and electrical equipment.

[0014] Generate a mapping table for each category of index file to record the core word, field value, and field priority.

[0015] Use the hash mapping technology to accelerate the reading of the index file for data positioning.

[0016] As a preferred embodiment of the method for selecting the main materials and equipment prices in the maintenance project described in the present invention, wherein: the performing word segmentation and matching processing on the retrieval keywords includes performing word segmentation on the retrieval keywords input by the user, and the word segmentation rules are dynamically adjusted according to the synonym library and specific domain rules.

[0017] Compare each word segmentation result with the core words in the index file one by one to calculate the semantic similarity.

[0018] Filter out the most matching index file according to the calculation results and determine the retrieval data range.

[0019] As a preferred solution of the method for selecting the main materials and equipment prices in the maintenance project described in the present invention, wherein: the sorting of the matching data based on the weight rule includes assigning weights to the fields in the matching data, and the field priority rule is that the material name is greater than the specification is greater than the price is greater than the unit.

[0020] Dynamically adjust the weight assignment rule according to the characteristics of the keywords input by the user.

[0021] Calculate the total score of each piece of matching data according to the field weights, and give priority to recommending those with high scores.

[0022] As a preferred solution of the method for selecting the main materials and equipment prices in the maintenance project described in the present invention, wherein: generating the recommended results for the user to refer to includes performing logical verification on the initially recommended results to confirm that the recommended results meet the retrieval conditions input by the user.

[0023] Generate a report of the recommended results, and the report includes the material name, price, recommended score and recommended reasons.

[0024] The user adjusts the recommended results through the interaction interface.

[0025] Another object of the present invention is to provide a system for selecting the main materials and equipment prices in a maintenance project, which can solve the problems of slow data retrieval speed and inaccurate semantic matching in the current material and equipment indexing technology by constructing a core word index file and performing word segmentation and matching processing on the retrieval keywords.

[0026] As a preferred solution of the system for selecting the main materials and equipment prices in the maintenance project described in the present invention, wherein: it includes a core word recognition module, a word segmentation and matching processing module, and a result generation module.

[0027] The core word recognition module is used to extract field information from the material price database and identify the core words through a semantic analysis model; the word segmentation and matching processing module is used to construct a core word index file and perform word segmentation and matching processing on the retrieval keywords; the result generation module is used to sort the matching data based on the weight rule and generate recommended results for the user to refer to.

[0028] A computer device includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps of the method for selecting the main materials and equipment prices in a maintenance project.

[0029] A computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the steps of the method for selecting the main materials and equipment prices in a maintenance project are implemented.

[0030] Advantages of the present invention: The method for selecting the main materials and equipment prices in the overhaul project provided by the present invention extracts the field information including name, specification, unit and price from the material price library, and cleans the invalid or redundant data to form a clean preliminary data set; effectively reduces the interference of data redundancy and error information, improves the data processing efficiency and reliability of the system. Through the context understanding ability of the BERT model, it can identify industry-specific terms, solves the problem of insufficient semantic understanding in traditional methods, constructs a dynamic core vocabulary, ensures that the retrieval content input by users in different contexts can be accurately understood, and improves the relevance of the recommendation results. The core words are grouped by categories such as building materials and electrical equipment, and a mapping table is generated for each category to record the field values and priorities; this classification method is convenient for quickly locating the core words of specific categories and meets the user's needs for information in different fields. The core words are quickly located through the hash function and hash table technology, reducing the possibility of data conflicts; greatly improving the retrieval speed of the index file, especially excellent in processing large-scale data; dynamic word segmentation ensures the flexibility of keyword parsing, and semantic similarity calculation captures the deep meaning of the user's real needs; logically verifies the recommendation results to ensure compliance with the user's retrieval conditions, and generates a report including name, price, score and recommendation reasons; the transparency of the report enhances the user's trust in the recommendation results and provides detailed basis for decision-making; allows users to adjust the recommendation weight through the interface and dynamically optimize the recommendation results; realizes the personalization and flexibility of the recommendation process, further improving the decision-making efficiency and the practicality of the system. The present invention achieves better results in terms of material selection accuracy, data processing efficiency and user interaction experience. Description of the Drawings

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0032] Figure 1 It is the overall flowchart of a method for selecting the main materials and equipment prices in the overhaul project provided by the first embodiment of the present invention.

[0033] Figure 2 It is the overall flowchart of a system for selecting the main materials and equipment prices in the overhaul project provided by the third embodiment of the present invention. Detailed Embodiments

[0034] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0035] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides a method for selecting the prices of main materials and equipment for a maintenance project, comprising:

[0036] S1: Extract field information from the material price database and identify core words through the semantic analysis model.

[0037] Furthermore, extracting field information from the material price library includes extracting field information including name, specification, unit, and price from the material price library through a preset field extraction rule.

[0038] Clean the field data and remove invalid or redundant data.

[0039] The cleaned field data is used as the preliminary dataset.

[0040] It should be noted that identifying core words through a semantic analysis model includes using a BERT model to perform semantic analysis on field information and extract semantic features of each field.

[0041] Through synonym normalization and context association analysis, a core word list corresponding to the field is generated.

[0042] Build dynamic associations between fields and core words based on semantic features, and generate a core vocabulary.

[0043] It should also be noted that a preferred solution for semantic analysis of field information using the BERT model includes, during the process of semantic analysis of field information using the BERT model, first extracting relevant field information from the material price database, including name, specification, unit, and price, and cleaning it to remove invalid or redundant data to form a clean preliminary dataset. Next, use the BERT tokenizer to encode the cleaned material names and convert them into an input format acceptable to the model. The specific steps are as follows: Select a suitable BERT model, such as "bert-base-uncased", then import the corresponding tokenizer, encode each material name, and produce the corresponding input tensor. The input tensor is then fed into the BERT model for inference to obtain the context representation of each name. Among the extracted context vectors, use the mean or other aggregation methods to obtain the semantic features of each field. Next, by calculating the cosine similarity between vectors, identify the synonymous relationships of different material names, generate a thesaurus, and generalize the core words for each material name. Thus, perform synonym normalization and context association analysis, and form a dynamic association relationship between the field and the core word by comparing the similarity of semantic features. Finally, construct a core word library covering multiple material names. After establishing the relationship between all core words and the corresponding field information, output it as a structured core word index file for subsequent retrieval and matching operations. In addition, use the hash mapping technology to accelerate the reading of the index file, ensure rapid data positioning, and thus improve the matching efficiency of subsequent user retrieval keywords, forming a complete semantic analysis chain to help the system provide efficient support in subsequent matching and sorting.

[0044] It should also be noted that after extracting the field information, applying the BERT model for semantic analysis enables the system to deeply understand the semantic features of each field. Based on the recognition of specific information, through synonym normalization and context association analysis, a comprehensive core word library is generated, ensuring that the retrieval content input by the user in different contexts can be reliably recognized and understood. Through accurate core word recognition, the system can more comprehensively and deeply understand and classify various material information, laying a foundation for providing more accurate and relevant material recommendations to the user. During the material selection process, the user can quickly obtain high-quality information, thereby improving the efficiency and accuracy of decision-making. The core word library constructed based on semantic analysis helps reduce the chance of information misreading, improves the system's response ability under diverse requirements, enhances the aggregation and clarity of information, and provides new possibilities for realizing the scientific and intelligent material selection.

[0045] S2: Construct a core word index file, and perform word segmentation and matching processing on the retrieval keywords.

[0046] Further, constructing the core word index file includes grouping the core words according to their respective categories to construct a categorized index file, where the categories include building materials and electrical equipment.

[0047] Generate a mapping table for the index file of each category, recording the core words, field values, and field priorities.

[0048] Utilize the hash mapping technique to accelerate the reading of the index file for data positioning.

[0049] It should be noted that the tokenization and matching process of the retrieval keywords includes tokenizing the retrieval keywords input by the user, and the tokenization rules are dynamically adjusted according to the thesaurus and specific domain rules.

[0050] Calculate the semantic similarity by comparing each tokenization result with the core words in the index file one by one.

[0051] Filter out the most matching index file based on the calculation results and determine the retrieval data range.

[0052] It should also be noted that a preferred solution for utilizing the hash mapping technique to accelerate the reading of the index file includes, when constructing the core word index file, creating a hash table for each core word, using the core word as the key and the corresponding field value and priority as the value; quickly locating the position of any given core word in the index file; specifically, when implementing, using a hash function to convert the core word into a hash value, ensuring that the hash values of different core words are as evenly distributed as possible to reduce the probability of conflicts. Next, when the user inputs a retrieval keyword, the system first converts the keyword into a hash value through the same hash function, and then quickly searches for it in the hash table; if a matching core word is found, the system immediately locates the corresponding field value and priority; based on hash conflicts, use the chaining method or open addressing method to effectively manage multiple core words corresponding to the same hash value; the hash mapping technique not only improves the reading speed of the core word index file, but also ensures the response efficiency of the system when dealing with a large number of requests, ensuring that users can quickly obtain formatted recommended results, making the material selection and procurement process more efficient and accurate.

[0053] It should also be noted that by constructing a core word index file and performing word segmentation and matching processing on the user's retrieved keywords, the system has achieved efficient information retrieval and precise matching. The core words are grouped according to their respective categories, and the hash mapping technology is used to optimize the reading speed of the index file, enabling fast data positioning, which lays the foundation for the efficiency of subsequent retrieval operations. The retrieved keywords input by the user undergo dynamic word segmentation processing and are adjusted in real time relying on the thesaurus and rules in specific fields. This dynamic word segmentation not only improves the flexibility of keyword parsing but also adapts to different input methods of users, ensuring the maximum coverage of the required information. By comparing the word segmentation results with the core word index file one by one, the system calculates the semantic similarity between each retrieved keyword and the core word. Based on the matching processing of semantic similarity, it can more accurately capture the true needs of users, thereby screening out the index file that best matches the user's needs, determining the relevant retrieval data range, effectively reducing the risks of information redundancy and improper matching, and improving the scientificity and effectiveness of decision-making.

[0054] S3: Sort the matching data based on the weight rules and generate a recommended result for the user's reference.

[0055] Furthermore, sorting the matching data based on the weight rules includes assigning weights to the fields in the matching data. The field priority rules are that the material name is greater than the specification, which is greater than the price, which is greater than the unit.

[0056] Dynamically adjust the weight assignment rules according to the characteristics of the keywords input by the user.

[0057] Calculate the total score of each piece of matching data according to the field weights, and give priority to recommending those with higher scores.

[0058] It should be noted that generating a recommended result for the user's reference includes performing logical verification on the initially recommended result to confirm that the recommended result meets the retrieval conditions input by the user.

[0059] Generate a report on the recommended result. The report includes the material name, price, recommended score, and reasons for recommendation.

[0060] The user adjusts the recommended result through the interaction interface.

[0061] It should also be noted that, based on the principle of assigning weights to matching data, the system has implemented a sorting mechanism based on field priorities. This mechanism sorts the key fields of material name, specification, and price according to importance, ensuring that the system first highlights the material information that best meets the user's needs in the recommended results. Through the dynamically adjusted weight assignment rules, the system can accurately adapt to the actual needs of the user for specific keywords entered by the user, thereby improving the accuracy of the recommendation. During the generation of the recommended results, the system conducts strict logical verification on the preliminarily recommended data to ensure compliance with the retrieval conditions entered by the user. The generated recommended result report includes the material name, price, recommendation score, and recommendation reasons, which not only improves the transparency and trust of the recommendation but also provides a basis for the user's decision-making reference. At the same time, the user is allowed to adjust the recommended results through the interface, making the recommendation process more flexible and personalized. Through the scientific and dynamic weight sorting and logical verification mechanism, the recommended results not only have accuracy but also enhance the user's sense of participation and decision-making autonomy, effectively improving the intelligent level of material selection and ensuring that the user can quickly and accurately find the materials that meet their needs in a complex market environment, ultimately achieving the optimization of the material procurement decision-making.

[0062] Example 2, an embodiment of the present invention, provides a method for selecting the main materials and equipment prices for an overhaul project. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0063] First, a material selection system based on semantic analysis and data processing is constructed to optimize the efficiency and accuracy of the material procurement process. The experimental preparation work includes collecting price information of common building materials and equipment on the market to form a price library containing various materials. In the data set, preset extraction of field information is carried out, mainly including material name, specification, unit, and price. After extraction, data cleaning is performed to eliminate invalid and redundant information to ensure the quality of the preliminary data set. For example, if the prices of a certain material are inconsistent among multiple suppliers, the most representative price needs to be selected. At the same time, the BERT semantic analysis model is applied to deeply analyze the remaining field information, extract the semantic features of each field, generate a core word list corresponding to the field through synonym normalization processing and context correlation analysis, so that different material names are semantically consistent. Through context correlation analysis, a dynamic core word library is constructed to accurately match the user's retrieval request in subsequent steps. For example, for the material "concrete", the core words may include "cement", "sand and gravel", "water", etc. Based on the semantic features, a dynamic association relationship between the field and the core word is constructed, and a core word library is generated. Next, a core word index file is constructed, and the core words are grouped according to categories such as building materials and electrical equipment. For each category, a mapping table is generated to record the core word, field value, and priority. The hash mapping technology is used to accelerate the reading of the index file and improve the efficiency of data location. During the implementation process, various retrieval keywords are simulated for user input, and the input content is segmented using the dynamic word segmentation algorithm. In the matching processing module, the segmented results are compared with the core word index one by one, and the semantic similarity is calculated to screen out the index file with the highest matching degree. Through a sorting mechanism based on weight rules, different weights are assigned to each field to ensure that the material name has the highest priority in the matching data, followed by specification, price, and unit in turn. On the user interaction interface, when generating the recommendation result, the user can also adjust the recommendation weight according to the feedback, and finally a report containing the material name, price, recommendation score, and its reasons is generated for the reference of the procurement personnel. According to the experimental results, the present invention provides a more efficient, accurate, and convenient solution for the material management of large-scale engineering projects.

[0064] Example 3, referring to Figure 2 , which is an embodiment of the present invention, provides a system for selecting the main materials and equipment prices for maintenance projects, including a core word recognition module, a segmentation matching processing module, and a result generation module.

[0065] Among them, the core word recognition module is used to extract field information from the material price library and identify the core word through the semantic analysis model; the segmentation matching processing module is used to construct a core word index file and perform segmentation and matching processing on the retrieval keywords; the result generation module is used to sort the matching data based on the weight rules and generate a recommendation result for the user's reference.

[0066] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs, Read-Only Memories), random access memories (RAMs, Random Access Memories), magnetic disks, or optical discs that can store program codes.

[0067] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in combination with an instruction execution system, apparatus, or device.

[0068] More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (electronic devices), portable computer disk cartridges (magnetic devices), random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), fiber optic devices, and portable compact disc read-only memories (CDROMs). Additionally, a computer-readable medium can even be paper or other suitable media on which a program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or, if necessary, other suitable processing, and then storing it in a computer memory.

[0069] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

[0070] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A method for selecting the prices of main materials and equipment in a maintenance project, characterized in that, It includes: Extract field information from the material price library and identify core words through a semantic analysis model; Construct a core word index file and perform word segmentation and matching processing on the retrieval keywords; Sort the matching data based on weight rules and generate recommended results for users' reference.

2. The method for selecting the prices of main materials and equipment for the maintenance project according to claim 1, characterized in that: The extraction of field information from the material price library includes extracting field information including name, specification, unit, and price from the material price library through preset field extraction rules; Clean the field data to eliminate invalid or redundant data; Use the cleaned field data as the preliminary data set.

3. The method for selecting the main materials and equipment prices of the maintenance project according to claim 2, characterized in that: The identification of core words through the semantic analysis model includes using the BERT model to perform semantic analysis on the field information and extract the semantic features of each field; Generate a list of core words corresponding to the fields through synonym normalization processing and context correlation analysis; Construct a dynamic association relationship between fields and core words based on semantic features and generate a core word library.

4. The method for selecting the prices of main materials and equipment for the overhaul project according to claim 3, characterized in that: The construction of the core word index file includes grouping the core words according to their categories and constructing a categorized index file, where the categories include building materials and electrical equipment; Generate a mapping table for each category of index file to record core words, field values, and field priorities; Use hash mapping technology to accelerate the reading of the index file for data positioning.

5. The method for selecting the prices of main materials and equipment for the overhaul project according to claim 4, characterized in that: The word segmentation and matching processing of the retrieval keywords includes performing word segmentation on the retrieval keywords input by the user, and the word segmentation rules are dynamically adjusted according to the synonym library and specific domain rules; Calculate the semantic similarity by comparing each word segmentation result with the core words in the index file one by one; Filter out the most matching index file according to the calculation results and determine the retrieval data range.

6. The method for selecting the main material and equipment prices of the maintenance project as described in claim 5, characterized in that: The sorting of the matching data based on weight rules includes assigning weights to the fields in the matching data, and the field priority rules are that the material name is greater than the specification, which is greater than the price, which is greater than the unit; Dynamically adjust the weight assignment rules according to the characteristics of the keywords input by the user; Calculate the total score of each matching data according to the field weights, and those with higher scores are recommended first.

7. The method for selecting the prices of main materials and equipment for the maintenance project as described in claim 6, characterized in that: The generation of recommended results for users' reference includes performing logical verification on the preliminarily recommended results to confirm that the recommended results meet the retrieval conditions input by the user; Generate a report of the recommended results, and the report includes the material name, price, recommended score, and recommended reasons; The user adjusts the recommended results through the interaction interface.

8. A system adopting the method for selecting the main material and equipment prices of the overhaul project as described in any one of claims 1 to 7, characterized in that: It includes a core word recognition module, a word segmentation and matching processing module, and a result generation module; The core word recognition module is used to extract field information from the material price library and identify core words through a semantic analysis model; The word segmentation and matching processing module is used to construct a core word index file and perform word segmentation and matching processing on the retrieval keywords; The result generation module is used to sort the matching data based on weight rules and generate recommended results for users' reference.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for selecting the main materials and equipment prices of the overhaul project described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for selecting the main materials and equipment prices of the overhaul project described in any one of claims 1 to 7.

Images