Material supply chain intelligent recommendation method and system for construction industry

Abstract

The invention relates to the technical field of building industry material supply chains, in particular to a material supply chain intelligent recommendation method and system for the building industry, and the method comprises the following steps: a supplier uploads a report on a platform, and the platform generates an archive data packet and synchronizes the archive data packet to a purchase cloud platform; the purchase cloud platform generates industry labels after receiving the data, calculates index scores and builds a table to form a classification index system; a buyer submits a demand, the platform analyzes the demand and then executes a screening mechanism, and suppliers are screened and comprehensively scored to form a scheme list; the buyer evaluates, selects and generates an order, and the platform updates inventory and logistics information. Through a multi-dimensional data processing technology, supplier information is comprehensively recorded, classification indexes are constructed, and accurate screening is achieved; the screening standard is flexibly adjusted by applying a dynamic scoring and hierarchical screening technology; through the grouping and parallel computing technology, the global problem is disassembled, and the computing efficiency is improved; through a comprehensive scoring technology, suppliers are objectively evaluated, the purchasing efficiency is finally improved, and supply chain matching is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of material supply chain for the construction industry, and in particular to an intelligent recommendation method and system for a material supply chain for the construction industry. Background Art

[0002] In today's construction industry, material supply chain management is crucial for ensuring smooth project execution. However, existing construction material supply chain management methods and systems present numerous challenges that require urgent attention, leading to inefficient procurement, poor supply chain alignment, and difficulties ensuring project quality and progress.

[0003] First, in terms of supplier information management, traditional methods often lack detailed and accurate data uploaded by suppliers. Many systems only record basic supplier information, with vague descriptions of their business scope and inability to clearly cover building material categories and specifications. This makes it difficult for procurement cloud platforms to accurately locate suitable suppliers. For example, when searching for suppliers of a specific type of rebar, inaccurate information requires buyers to sift through a vast number of suppliers, resulting in significant inefficiency. Furthermore, inventory and logistics information is not recorded in sufficient detail, failing to record current inventory levels, average monthly shipments, and inventory status by SKU granularity. Furthermore, there is a lack of comprehensive information on logistics coverage areas, average shipping times, and carrier lists. This makes it difficult for buyers to accurately predict replenishment points, leading to work stoppages and inventory backlogs, increasing costs. Furthermore, it is difficult to assess transportation reliability, and project progress is easily delayed by logistics issues.

[0004] Secondly, in terms of supplier classification and screening mechanisms, the existing system lacks an effective classification indexing system. The construction of industry labels is simple and crude, unable to meet the needs of the construction industry, which has a wide variety of materials and widely varying characteristics. For example, classification is limited to the broad categories of building materials, failing to refine them to specific subcategories and models, making it difficult for buyers to conduct accurate searches and reducing the matching efficiency of the material supply chain. Moreover, the screening mechanism often uses fixed rules and standards and cannot be flexibly adjusted to changes in procurement needs. Targeted screening is impossible to address the different requirements of different projects for building materials inventory, logistics, quality, and price. As a result, the selected suppliers do not match actual needs, greatly reducing the effectiveness and practicality of the recommended solutions.

[0005] Furthermore, with the increasing number of suppliers, traditional processing methods face serious bottlenecks in computational efficiency. Directly processing all suppliers requires enormous computational effort, resulting in a time-consuming screening process and an inability to meet real-time requirements. Furthermore, existing systems lack clear distinctions and corresponding processing mechanisms for different types of procurement requirements, such as rigid, flexible, and combined requirements. This fails to fully account for the various scenarios that may arise in actual procurement, limiting buyers' choices and reducing procurement success rates.

[0006] Furthermore, existing supplier evaluation systems are not comprehensive or objective. They often focus on one or a few aspects, such as price or quality, while overlooking other crucial factors, such as inventory compatibility and logistics timeliness. This prevents buyers from conducting a comprehensive and accurate supplier evaluation, making it difficult to select the most suitable supplier. Furthermore, evaluation results cannot be effectively fed back to suppliers, hindering their ability to improve their management and service strategies.

[0007] In view of this, an intelligent recommendation method and system for material supply chain in the construction industry is proposed. Summary of the Invention

[0008] The purpose of the present invention is to provide a material supply chain intelligent recommendation method and system for the construction industry to improve procurement efficiency, optimize supply chain matching, ensure project quality and progress, and promote suppliers to improve service quality.

[0009] To solve the above technical problems, the present invention provides a material supply chain intelligent recommendation method for the construction industry, comprising the following steps: S1. Suppliers upload reports containing business scope, inventory, and logistics information on the supplier management platform. The supplier management platform generates a supplier profile data package using the business license number as the primary key and synchronizes it to the procurement cloud platform. S2. After receiving the supplier's archive data package, the procurement cloud platform generates industry tags based on the business scope keywords and calculates the inventory matching degree, logistics timeliness, and material quality index scores according to preset rules. It then creates an inventory matching degree table, a logistics timeliness table, and a material quality table in descending order of index scores. Furthermore, it creates a price table based on the selling price, establishing a classification index system by material type. S3. After the buyer submits the purchase request, the following screening is performed: the supplier list is split using a hash algorithm and processed in parallel through distributed nodes; the screening rules and weight coefficients are adjusted in real time based on the demand parameters to select suppliers that meet rigid, flexible, and combined requirements; the suppliers are comprehensively scored and a list of solutions is formed in descending order of the comprehensive scores; S4. The buyer evaluates and selects the options list, and generates a final purchase order after confirmation. The procurement cloud platform simultaneously updates inventory and logistics information.

[0010] As a further improvement of the present technical solution, in said S1, the business scope includes categories, specifications and models of building materials; the inventory records the current inventory, average monthly shipments and inventory status at the SKU granularity; the logistics information includes the coverage area, average transportation time and carrier list; the supplier management platform automatically verifies the data integrity of the report; when the missing rate of data in the report is greater than the preset value A, the manual review process is triggered.

[0011] As a further improvement of this technical solution, in S1, a hash value is generated with the business license number as the primary key; the data in the supplier file data package includes business scope, logistics information, inventory, upload timestamp and data version number. When the inventory change is greater than the preset value B or the logistics information is updated, the supplier file data package is automatically updated.

[0012] As a further improvement of the present technical solution, in S2, the industry classification label is generated based on the building material category entity in the business scope. At the same time, the label is constructed in three layers according to the building material category, building material subcategory, and building material model.

[0013] As a further improvement to this technical solution, in S2, the index score for inventory matching is = current inventory / average daily shipment volume of similar inventory on the procurement cloud platform × 100%, the index score for logistics timeliness is = ∑ (number of regional covered cities × timeliness coefficient) / total number of covered cities, and the index score for material quality is scored based on historical quality inspection data. The classification index system is based on building material models, and establishes inventory matching table, logistics timeliness table, material quality table and price table respectively.

[0014] As a further improvement of this technical solution, in S3, the screening is specifically as follows: Based on procurement demand parameters, dynamic scoring nodes are used to screen data in the inventory matching table, logistics timeliness table, material quality table, and price table. The parts of each table that meet the procurement demand parameters are extracted to obtain a list of multiple candidate suppliers, completing the initial screening. For each candidate supplier list, a hash value modulo N is taken as a grouping identifier. The candidate suppliers are assigned to corresponding grouping identifiers according to their corresponding hash values ​​and stored independently to obtain a group directory for each candidate supplier list. In the modulo N grouping algorithm, a hierarchical hashing strategy is automatically triggered when the number of suppliers exceeds a preset threshold. In multiple candidate supplier lists, computing nodes with corresponding computing power are allocated according to the number of suppliers in the same group directory. After filtering out irrelevant groups through filters, the intersection calculation is performed on the group directory of each candidate supplier list of the same type to obtain suppliers that exist in multiple similar groups as the supplier group.

[0015] As a further improvement to this technical solution, the supplier's exclusive data in each table is independently extracted from the inventory matching table, logistics timeliness table, material quality table, and price table, and corresponding information nodes are configured for the supplier's exclusive data in each table; The dynamic scoring node includes a demand receiving end, a parsing and mapping module, and a data docking end, wherein the demand receiving end is used to receive procurement demand parameters; the parsing and mapping module is provided with a screening rule library corresponding to the inventory matching table, logistics timeliness table, material quality table and price table respectively; the parsing and mapping module parses the procurement demand parameters through natural language technology, converts the parsed procurement demand parameters into specific data screening conditions, and stores the data screening conditions in the screening rule library of the corresponding table; the data docking end is used to interact with all information nodes in a single table for exclusive data information, and screens the exclusive data bound to the information node according to the data screening conditions in the corresponding table screening rule library in the parsing and mapping module to obtain information nodes that meet the data screening conditions.

[0016] As a further improvement of the present technical solution, in S3, the conditions for rigid demand are inventory ≥ demand, logistics ≤ deadline, quality ≥ standard, and price ≤ budget; the conditions for elastic demand are inventory < demand but adjustable, logistics ≤ deadline, quality ≥ standard, and price ≤ budget; the conditions for combined demand are a single supplier's inventory ≥ demand × preset value C, logistics ≤ deadline, quality ≥ standard, and price ≤ budget × preset value D. By changing the procurement demand parameters and adjusting the insertion position of the dynamic scoring node in each table, different lists of candidate suppliers can be obtained; comprehensive score = inventory matching index score × E + logistics timeliness index score × F + material quality index score × G + price index score × H, where E+F+G+H=1.

[0017] A material supply chain intelligent recommendation system for the construction industry, the material supply chain intelligent recommendation system for the construction industry is used to implement the material supply chain intelligent recommendation method for the construction industry, comprising: The supplier management platform receives supplier reports and extracts information, generates supplier profile data packets with hash values ​​based on business license numbers, and verifies data integrity; The procurement cloud platform is connected to the supplier management platform and includes a pre-processing module, a screening mechanism, and a ranking module. The pre-processing module is used to receive supplier archive data packets, generate industry classification tags based on the information in the supplier archive data packets, calculate the inventory matching degree, logistics timeliness, and material quality index scores according to preset rules, and form an inventory matching degree table, a logistics timeliness table, and a material quality table in descending order of the index scores. At the same time, a price table is formed according to the high and low selling prices, and a classification index system is established by material type; the screening mechanism matches the corresponding industry classification tags according to the material type, and sequentially selects suppliers that meet rigid demand, flexible demand, and combination demand according to the procurement demand; the ranking module comprehensively scores the suppliers and forms a list of solutions for rigid demand, flexible demand, and combination demand in descending order of the comprehensive scores; The determination module is connected to the procurement cloud platform and is used to show the buyer a list of solutions for rigid demand, flexible demand and combination demand. The buyer compares and selects the solutions and generates the final order. The procurement cloud platform simultaneously updates the inventory and logistics status.

[0018] Compared with the prior art, the present invention has the following beneficial effects: 1. This intelligent recommendation method and system for the material supply chain in the construction industry inserts dynamic scoring nodes into the four core business tables of inventory matching, logistics timeliness, material quality, and price. By adjusting the position of the dynamic scoring nodes, it supports multi-dimensional combination screening, covering the full range of scenario requirements from rigid to flexible, and significantly improving screening flexibility. At the same time, through a layered screening strategy, it covers the full range of scenarios from strict matching to flexible combinations. Combined with the weight adjustment of the dynamic scoring nodes, it provides buyers with a variety of recommendation solutions.

[0019] 2. This intelligent recommendation method and system for the material supply chain in the construction industry uses hash grouping to decompose the global problem into independent intra-group calculations, combined with distributed parallel processing, to compress computing efficiency and break through the efficiency bottleneck of traditional screening.

[0020] 3. This intelligent recommendation method and system for the material supply chain in the construction industry uses fine-grained classification indexing to achieve accurate matching from material type to specific model. Combined with dynamic scoring nodes, it ensures that the screening results are highly aligned with the model, specifications and other details of the procurement requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 Schematic diagram of the method flow of the present invention; Figure 2 Schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all secondary embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of the present invention.

[0023] Currently, existing construction material supply chain management methods and systems have significant deficiencies in supplier information management, classification and screening mechanisms, computational efficiency, and supplier evaluation, failing to meet the construction industry's growing demand for refined management and efficient operations. Therefore, a new, more intelligent, and efficient construction material supply chain intelligent recommendation method and system is urgently needed to improve procurement efficiency, optimize supply chain matching, ensure project quality and progress, and encourage suppliers to improve service quality. For this reason, see Figure 1 As shown, one of the purposes of the present invention is to provide a material supply chain intelligent recommendation method for the construction industry, the material supply chain intelligent recommendation method for the construction industry comprises the following steps: S1. Suppliers upload reports containing business scope, inventory, and logistics information on the supplier management platform. The supplier management platform generates a supplier profile data package using the business license number as the primary key and synchronizes it to the procurement cloud platform. S2. After receiving the supplier's archive data package, the procurement cloud platform generates industry tags based on the business scope keywords and calculates the inventory matching degree, logistics timeliness, and material quality index scores according to preset rules. It then creates an inventory matching degree table, a logistics timeliness table, and a material quality table in descending order of index scores. Furthermore, it creates a price table based on the selling price, establishing a classification index system by material type. S3. After the buyer submits the purchase request, the following screening is performed: the supplier list is split using a hash algorithm and processed in parallel through distributed nodes; the screening rules and weight coefficients are adjusted in real time based on the demand parameters to select suppliers that meet rigid, flexible, and combined requirements; the suppliers are comprehensively scored and a list of solutions is formed in descending order of the comprehensive scores; S4. The buyer evaluates and selects the options list, and generates a final purchase order after confirmation. The procurement cloud platform simultaneously updates inventory and logistics information.

[0024] In this intelligent recommendation method for the material supply chain in the construction industry, dynamic scoring nodes are inserted into the four core business tables of inventory matching, logistics timeliness, material quality, and price. By adjusting the position of the dynamic scoring nodes, multi-dimensional combination screening is supported, covering the full range of scenario requirements from rigid to flexible, significantly improving screening flexibility. At the same time, through a hierarchical screening strategy, the full range of scenarios from strict matching to flexible combinations is covered. Combined with the weight adjustment of dynamic scoring nodes, a variety of recommendation solutions are provided to buyers. In addition, hash grouping is used to decompose the global problem into independent intra-group calculations. Combined with distributed parallel processing, the computing efficiency is compressed, breaking through the efficiency bottleneck of traditional screening.

[0025] Considering the extremely precise requirements for building materials in construction projects, different building design and construction phases require specific building material categories and corresponding specifications. For example, the load-bearing structure of a high-rise building must use steel bars of a specific strength grade that meets national standards (such as HRB400E). Only by clearly defining the building material categories and specifications can the procurement cloud platform subsequently accurately locate suitable suppliers, achieving a "needle-in-a-haystack" screening process among a vast number of suppliers, improving procurement efficiency and matching project quality. Therefore, in step S1, the business scope includes building material categories, specifications, and models. Due to the large scale of construction projects and the long and volatile material consumption cycle, taking the construction of large commercial complexes as an example, the average monthly shipments of main materials such as cement and steel vary significantly at different construction stages. Understanding the real-time current inventory and average monthly shipments allows buyers to accurately predict replenishment nodes, avoid work stoppages or inventory backlogs, and reduce costs. Inventory status (such as normal, slow-moving, out-of-stock warnings, etc.) provides suppliers with intuitive basis for inventory management and buyers for adjusting procurement plans. Therefore, inventory records the current inventory, average monthly shipments, and inventory status at the SKU level. At the same time, because construction material transportation is limited by site and construction deadlines, stringent requirements are placed on logistics coverage and timeliness. For materials like concrete, which have a limited initial setting time, suppliers must ensure that their logistics can reach the construction site within a short timeframe. The carrier list correlates logistics stability with service quality, allowing buyers to assess transportation reliability, avoid the risk of project delays caused by shipping delays, and ensure project progress. Therefore, logistics information includes coverage area, average shipping time, and carrier list. Considering that supplier-uploaded data serves as the "raw material" for intelligent recommendations across the entire supply chain, data errors or omissions can trigger a chain reaction, leading to biased selection and ineffective recommendations. In the construction industry, erroneous data can lead to serious consequences such as purchasing the wrong building materials and delaying construction schedules. For example, entering incorrect steel inventory data can prevent buyers from receiving their orders on time, delaying critical construction milestones. Therefore, the supplier management platform automatically verifies the data integrity of reports. When the missing data rate within a report exceeds a preset value A, a manual review process is triggered. Leveraging the experience of professionals, this ensures highly accurate data, laying a solid foundation for subsequent, precise recommendations.

[0026] Considering that the business license number is the supplier's only legal identification and is unique and stable, in step S1, a hash value is generated using the business license number as the primary key. This embodiment may use a hash algorithm, such as MD5, SHA-256, etc. The hash algorithm can ensure that each supplier corresponds to a unique hash identifier, facilitating the system to quickly and accurately identify and manage suppliers, avoiding identification confusion caused by duplication or changes in supplier names, and improving the accuracy and efficiency of data management. In order to comprehensively record supplier-related information and facilitate subsequent analysis and screening by the procurement cloud platform, the data in the supplier archive data package includes business scope, logistics information, inventory, upload timestamp, and data version number. Considering that inventory and logistics information are dynamically changing and have a significant impact on procurement decisions, when the inventory change exceeds the preset value B or the logistics information is updated, the supplier archive data package is automatically updated to avoid procurement errors due to information lag. In this embodiment, database trigger technology is used to set triggers for inventory and logistics information-related tables in the database. When the inventory data change exceeds the preset value B or there is an update operation on the logistics information table, the trigger is automatically activated, and the supplier archive data package is updated. Due to the wide variety of materials in the construction industry, and the significant differences in characteristics, uses, and market demand for different materials, in step S2, industry classification labels are generated based on the building material category entities in the business scope. At the same time, the labels are constructed in three layers according to the building material category, building material subcategory, and building material model. This embodiment uses natural language processing (NLP) technology to parse the supplier's business scope text and extract the building material category entities therein. By generating labels based on the building material category entities in the business scope and performing a three-layer construction, the goal is to more accurately classify suppliers. This allows buyers to more easily find suitable suppliers based on material type, facilitates the platform's effective management and integration of supplier resources, and improves the matching efficiency of the material supply chain. At the same time, the three-layer labeling system can meet search and classification needs at different granularities. The broad categories of building materials can be used for macro-screening, the subcategories can further refine the scope, and the model numbers can achieve precise positioning, adapting to various scenarios where buyers need to search from fuzzy queries to precise searches. In this embodiment, database technology is used to establish an association between tags and supplier profiles, and a three-layer tag system is stored in a tree structure or hierarchical table to facilitate data query, update, and maintenance. Since the construction industry's material procurement needs are diverse and large in quantity, the procurement cloud platform needs to accurately assess the supplier's supply capacity. Therefore, in step S2, the inventory matching index score = current inventory / average daily shipment volume of similar inventory on the procurement cloud platform × 100%. By comparing the current inventory with the average daily shipment volume of similar inventory, the degree to which the supplier's inventory meets procurement needs can be measured, and it can be determined whether the supplier has sufficient inventory to cope with procurement, thus avoiding supply shortages. Given the tight construction schedule, timely material delivery is crucial. Therefore, the logistics timeliness index is calculated as ∑ (number of cities covered by the region × timeliness coefficient) / total number of cities covered. By combining the number of cities covered by the region with the timeliness coefficient to calculate logistics timeliness, we can comprehensively consider the supplier's logistics coverage and transportation speed, allowing buyers to select suppliers who can deliver materials to the construction site within the specified time, ensuring that the project progress is not affected by logistics. Considering that the quality of construction materials is directly related to the quality and safety of the project and is a key factor in procurement, the material quality index score is based on historical quality inspection data. The historical quality inspection data score can utilize past quality inspection results to objectively reflect the quality level of suppliers' materials, provide buyers with a quality reference, and ensure that the purchased materials meet the quality requirements of the construction project; Since building material models are important identifiers of building material products, different models often have different characteristics in terms of inventory, logistics, quality, and price. In terms of inventory, the market demand and inventory turnover speed of different building materials vary greatly; in terms of logistics, different models may have different transportation requirements and delivery timeliness; in terms of quality, each model has its own specific quality standards and inspection conditions; and prices vary depending on the model. Therefore, the classification index system is based on building material models, and inventory matching tables, logistics timeliness tables, material quality tables, and price tables are established respectively. By constructing an index system with building material models as the core, various types of data can be managed and queried more accurately, making it easier for business personnel to quickly locate relevant information on specific building materials models, meeting the needs of refined operations in supply chain management. Due to the complex and ever-changing procurement needs of the construction industry, different projects have very different requirements for building materials inventory, logistics, quality, and price. For example, urgent projects may place more emphasis on logistics timeliness and immediate inventory supply capabilities, while large-scale long-term projects may pay more attention to price and quality stability. Therefore, in step S3, the screening mechanism is specifically as follows: Based on procurement demand parameters, dynamic scoring nodes are used to screen data in the inventory matching table, logistics timeliness table, material quality table, and price table. The parts of each table that meet the procurement demand parameters are extracted to obtain multiple candidate supplier lists, completing the initial screening. By inserting dynamic scoring nodes in each table, the screening criteria can be flexibly adjusted according to specific procurement demand parameters, making the selected candidate supplier list more in line with actual needs and improving the accuracy and effectiveness of the screening. Considering that inventory matching, logistics timeliness, material quality, and price are the core independent dimensions of construction industry procurement decisions, and the data structures, evaluation criteria, and business logic of each dimension are significantly different (for example, inventory focus quantity and turnover efficiency, logistics focus area coverage and transportation timeliness), the supplier's exclusive data in each table is independently extracted from the inventory matching table, logistics timeliness table, material quality table, and price table, and corresponding information nodes are configured for the supplier's exclusive data in each table. In this embodiment, the information node can be a single cloud server or a single storage port. By independently extracting the corresponding supplier's exclusive data in each table and configuring the corresponding information node, cross-dimensional data mixing can be avoided, ensuring that the screening and scoring of each dimension are more focused and accurate, which meets the construction industry's needs for multi-dimensional refined management of the material supply chain. The exclusive data of each table means that the inventory matching table only extracts the supplier's corresponding inventory matching data, the logistics timeliness table only extracts the supplier's corresponding logistics timeliness data, the material quality table only extracts the supplier's corresponding material quality data, and the price table only extracts the supplier's corresponding price data. Since procurement requirements often contain fuzzy natural language descriptions (such as "high-quality steel" and "reasonable price"), they need to be converted into quantifiable screening conditions through dynamic scoring nodes. Therefore, the dynamic scoring node includes a demand receiving end, a parsing and mapping module, and a data docking end. Among them, the demand receiving end is used to receive procurement requirement parameters; the parsing and mapping module has a screening rule library corresponding to the inventory matching table, logistics timeliness table, material quality table, and price table respectively. Each screening rule library matches the corresponding table by table name and is switched in the parsing and mapping module; using natural language technology, the parsing and mapping module parses the procurement requirement parameters, converts the procurement requirement parameters into specific data screening conditions, and stores the data screening conditions in the screening rule library of the corresponding table. For example, the procurement requirement parameter is "a supplier who can supply at least 800 cubic meters of concrete within the next week". Through natural language technology, keywords in the procurement requirement parameters are extracted, such as "concrete" is the material type, "at least 800 cubic meters" is the quantity requirement, and "within the next week (the supply time must be within 7 days)" The time range is clarified and converted into specific data screening conditions: "the inventory quantity of concrete provided by the supplier is ≥ 800 cubic meters", and the inventory status is "available immediately" or "available for dispatch within the next week". The data docking terminal is used to interact with all information nodes in a single table for exclusive data. According to the data screening conditions in the corresponding table screening rule library in the parsing and mapping module, the exclusive data bound to the information node is filtered to obtain the information nodes that meet the data screening conditions. Then, the information nodes that meet the data screening conditions are reversely located, and the suppliers of the corresponding table are extracted. Finally, a list of multiple candidate suppliers is obtained to complete the preliminary screening. By setting the screening rule library corresponding to each table in the parsing and mapping module and supporting dynamic switching, exclusive screening rules can be matched according to the business logic of different tables (such as the quantity threshold of the inventory table and the inspection standard of the quality table) to achieve accurate mapping of "demand-rule-data", solving the problem that traditional fixed rule screening cannot adapt to complex needs.

[0027] As the number of suppliers continues to increase, directly processing all candidate suppliers will result in a huge amount of computation and low efficiency. Therefore, using hash values ​​modulo N for grouping can disperse a large number of candidate suppliers into multiple groups. By grouping candidate suppliers, distributed storage and parallel processing of data are achieved, greatly improving the ability to process large-scale supplier data. When the number of suppliers exceeds the preset threshold, the hierarchical hashing strategy is automatically triggered to cope with the dynamic changes in data scale, further optimize the grouping effect, and ensure the balance and efficiency of grouping. The range of N is limited to the set of prime numbers [8,32] because prime numbers can better ensure the uniform distribution of data in hash operations, reduce hash conflicts, and improve the accuracy and stability of grouping. The layered hashing strategy is automatically triggered when the number of suppliers in a single group after single-layer hashing exceeds a preset threshold, such as the preset threshold = 10,000. Its core goal is to recursively split large-scale data into smaller sub-groups by increasing the level of hash grouping. This solves the problem of grouping imbalance in single-layer hashing when data explodes (for example, excessive data volume in some groups leads to uneven load on computing nodes), ensures that the data size of each sub-group remains within the efficient processing range (for example, the data volume of a single group ≤ preset threshold / 10), and thus maximizes parallel computing efficiency. Because the number of suppliers within different groups can vary significantly, using a unified approach to allocating computing resources can lead to wasted resources or inefficient computation. Therefore, allocating computing nodes with corresponding computing power based on the number of suppliers within similar groups can rationally utilize computing resources and improve computational efficiency. By filtering out irrelevant groups, unnecessary computation is reduced, further improving the efficiency and accuracy of screening. Parallel computing fully utilizes computing resources and accelerates processing, enabling the system to handle complex screening tasks while meeting real-time requirements. Ultimately, it is possible to accurately identify a group of suppliers that meet the requirements, providing high-quality supplier recommendations to purchasers. The suppliers identified through intersection calculations are extracted to form a group of suppliers that meet the requirements.

[0028] In the construction industry, different projects have different characteristics and requirements. Rigid demand usually applies to projects that have strict requirements on construction period, quality, etc. and do not allow much change, such as government key projects and emergency rescue projects. Such projects must ensure the stability and timeliness of material supply, so inventory, logistics, quality and price are required to strictly meet the conditions; elastic demand takes into account that in actual procurement, some suppliers may encounter temporary shortages in inventory, but they can meet the demand by allocating resources. This demand setting gives buyers a certain degree of flexibility, broadens the range of suppliers to choose from, and increases the probability of successful procurement. Combined demand is suitable for large-scale projects. Such projects have large material requirements that may not be fully met by a single supplier, but multiple suppliers can be combined to meet the requirements. By setting the preset value C of a single supplier's inventory and the preset value D of the budget, buyers can be guided to adopt a multi-supplier cooperation model to optimize the purchase plan. Different procurement requirements have different emphases on inventory, logistics, quality, and price. Therefore, in step S3, the conditions for rigid demand are inventory ≥ demand, logistics ≤ deadline, quality ≥ standard, and price ≤ budget; the conditions for flexible demand are inventory < demand but adjustable, logistics ≤ deadline, quality ≥ standard, and price ≤ budget; the conditions for combined demand are inventory ≥ demand × preset value C, logistics ≤ deadline, quality ≥ standard, and price ≤ budget × preset value D of a single supplier. By changing the procurement demand parameters and adjusting the insertion position of the dynamic scoring node in each table, qualified suppliers can be flexibly screened according to specific needs. To provide buyers with a basis for decision-making, the comprehensive score = Inventory Match Index Score × E + Logistics Timeliness Index Score × F + Material Quality Index Score × G + Price Index Score × H, where E + F + G + H = 1. This comprehensive scoring formula considers the scores of inventory match, logistics timeliness, material quality, and price, and weights them (E + F + G + H = 1) to reflect the importance of each indicator in the purchasing decision. This allows for a comprehensive and objective evaluation of suppliers. Buyers can rank suppliers based on the comprehensive score and select the most suitable one. Furthermore, the comprehensive scoring results can be fed back to suppliers, encouraging them to focus on their inventory management, logistics distribution, material quality, and pricing strategies, continuously improving their service quality and achieving higher scores in the competition.

[0029] See also Figure 2 As shown, the second object of the present invention is to provide a material supply chain intelligent recommendation system for the construction industry, which is used to implement the above-mentioned material supply chain intelligent recommendation method for the construction industry, including: The supplier management platform receives supplier reports and extracts information, generates supplier profile data packets with hash values ​​based on business license numbers, and verifies data integrity; The procurement cloud platform is connected to the supplier management platform and includes a pre-processing module, a screening mechanism, and a ranking module. The pre-processing module is used to receive supplier archive data packets, generate industry classification tags based on the information in the supplier archive data packets, calculate the inventory matching degree, logistics timeliness, and material quality index scores according to preset rules, and form an inventory matching degree table, a logistics timeliness table, and a material quality table in descending order of the index scores. At the same time, a price table is formed according to the high and low selling prices, and a classification index system is established by material type; the screening mechanism matches the corresponding industry classification tags according to the material type, and selects suppliers that meet rigid demand, flexible demand, and combination demand in turn according to the procurement needs; the ranking module comprehensively scores the suppliers and forms a list of solutions for rigid demand, flexible demand, and combination demand in descending order of the comprehensive scores; The determination module is connected to the procurement cloud platform and is used to show the buyer a list of solutions for rigid demand, flexible demand and combination demand. The buyer compares and selects the solutions and generates the final order. The procurement cloud platform simultaneously updates the inventory and logistics status.

[0030] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely preferred examples of the present invention and are not intended to limit the present invention. Various changes and improvements may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and improvements fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A material supply chain intelligent recommendation method for the construction industry, characterized in that: The following steps are involved: S1. Suppliers upload reports containing business scope, inventory, and logistics information on the supplier management platform. The supplier management platform generates a supplier profile data package using the business license number as the primary key and synchronizes it to the procurement cloud platform. S2. After receiving the supplier's archive data package, the procurement cloud platform generates industry tags based on the business scope keywords and calculates the inventory matching degree, logistics timeliness, and material quality index scores according to preset rules. It then creates an inventory matching degree table, a logistics timeliness table, and a material quality table in descending order of index scores. Furthermore, it creates a price table based on the selling price, establishing a classification index system by material type. S3. After the buyer submits the purchase request, the following screening is performed: the supplier list is split using a hash algorithm and processed in parallel through distributed nodes; Adjust the screening rules and weight coefficients in real time based on demand parameters to select suppliers that meet rigid, flexible and combined requirements; Comprehensively score suppliers and form a list of solutions in descending order of comprehensive scores; S4. The buyer evaluates and selects the options list, and generates a final purchase order after confirmation. The procurement cloud platform simultaneously updates inventory and logistics information.

2. The intelligent recommendation method for material supply chain in the construction industry according to claim 1, characterized in that: In S1, the business scope includes building material categories, specifications and models. Inventory records the current inventory, average monthly shipments, and inventory status at the SKU granularity. Logistics information includes coverage areas, average transportation time, and carrier lists. The supplier management platform automatically verifies the data integrity of the report. When the missing rate of data in the report is greater than the preset value A, the manual review process is triggered.

3. The intelligent recommendation method for material supply chain in the construction industry according to claim 1, characterized in that: In S1, a hash value is generated with the business license number as the primary key; the data in the supplier file data package includes business scope, logistics information, inventory, upload timestamp and data version number. When the inventory change is greater than the preset value B or the logistics information is updated, the supplier file data package is automatically updated.

4. The intelligent recommendation method for material supply chain in the construction industry according to claim 1, characterized in that: In S2, the industry classification label is generated based on the building material category entity in the business scope. At the same time, the label is constructed in three layers according to the building material category, building material subcategory, and building material model.

5. The intelligent recommendation method for material supply chain in the construction industry according to claim 1, characterized in that: In S2, the index score for inventory matching is = current inventory / average daily shipment volume of similar inventory on the procurement cloud platform × 100%. The index score for logistics timeliness is = ∑ (number of cities covered by the region × timeliness coefficient) / total number of cities covered. The index score for material quality is based on historical quality inspection data. The classification index system is based on building material models, and establishes inventory matching table, logistics timeliness table, material quality table and price table respectively.

6. The intelligent recommendation method for material supply chain in the construction industry according to claim 3, characterized in that: In S3, the screening is specifically as follows: Based on procurement demand parameters, dynamic scoring nodes are used to screen data in the inventory matching table, logistics timeliness table, material quality table, and price table. The parts of each table that meet the procurement demand parameters are extracted to obtain a list of multiple candidate suppliers, completing the initial screening. For each candidate supplier list, a hash value modulo N is taken as a grouping identifier. The candidate suppliers are assigned to corresponding grouping identifiers according to their corresponding hash values ​​and stored independently to obtain a group directory for each candidate supplier list. In the modulo N grouping algorithm, a hierarchical hashing strategy is automatically triggered when the number of suppliers exceeds a preset threshold. In multiple candidate supplier lists, computing nodes with corresponding computing power are allocated according to the number of suppliers in the same group directory. After filtering out irrelevant groups through filters, the intersection calculation is performed on the group directory of each candidate supplier list of the same type to obtain suppliers that exist in multiple similar groups as the supplier group.

7. The intelligent recommendation method for material supply chain in the construction industry according to claim 6, characterized in that: Extract the supplier's exclusive data from the inventory matching table, logistics timeliness table, material quality table, and price table, and configure corresponding information nodes for the supplier's exclusive data in each table. The dynamic scoring node includes a demand receiving end, a parsing and mapping module, and a data docking end, wherein the demand receiving end is used to receive procurement demand parameters; the parsing and mapping module is provided with a screening rule library corresponding to the inventory matching table, logistics timeliness table, material quality table and price table respectively; the parsing and mapping module parses the procurement demand parameters through natural language technology, converts the parsed procurement demand parameters into specific data screening conditions, and stores the data screening conditions in the screening rule library of the corresponding table; the data docking end is used to interact with all information nodes in a single table for exclusive data information, and screens the exclusive data bound to the information node according to the data screening conditions in the corresponding table screening rule library in the parsing and mapping module to obtain information nodes that meet the data screening conditions.

8. The intelligent recommendation method for material supply chain in the construction industry according to claim 1, characterized in that: In S3, the conditions for rigid demand are inventory ≥ demand, logistics ≤ deadline, quality ≥ standard, and price ≤ budget; the conditions for elastic demand are inventory < demand but adjustable, logistics ≤ deadline, quality ≥ standard, and price ≤ budget; The conditions for combining demand are: inventory ≥ demand × preset value C, logistics ≤ deadline, quality ≥ standard, price ≤ budget × preset value D of a single supplier. By changing the procurement demand parameters and adjusting the insertion position of the dynamic scoring node in each table, different lists of candidate suppliers can be obtained. Comprehensive score = inventory matching index score × E + logistics timeliness index score × F + material quality index score × G + price index score × H, where E+F+G+H=1.

9. A material supply chain intelligent recommendation system for the construction industry, wherein the material supply chain intelligent recommendation system for the construction industry is used to implement the material supply chain intelligent recommendation method for the construction industry according to any one of claims 1 to 8, characterized in that: include: The supplier management platform receives supplier reports and extracts information, generates supplier profile data packets with hash values ​​based on business license numbers, and verifies data integrity; The procurement cloud platform is connected to the supplier management platform and includes a pre-processing module, a screening mechanism, and a ranking module. The pre-processing module is used to receive supplier archive data packets, generate industry classification tags based on the information in the supplier archive data packets, calculate the inventory matching degree, logistics timeliness, and material quality index scores according to preset rules, and form an inventory matching degree table, a logistics timeliness table, and a material quality table in descending order of the index scores. At the same time, a price table is formed according to the high and low selling prices, and a classification index system is established by material type; the screening mechanism matches the corresponding industry classification tags according to the material type, and sequentially selects suppliers that meet rigid demand, flexible demand, and combination demand according to the procurement demand; the ranking module comprehensively scores the suppliers and forms a list of solutions for rigid demand, flexible demand, and combination demand in descending order of the comprehensive scores; The determination module is connected to the procurement cloud platform and is used to show the buyer a list of solutions for rigid demand, flexible demand and combination demand. The buyer compares and selects the solutions and generates the final order. The procurement cloud platform simultaneously updates the inventory and logistics status.

Images