Purchase demand and supplier intelligent matching method based on big data

Abstract

The invention relates to the technical field of supplier management, in particular to a purchase demand and supplier intelligent matching method based on big data. The purchase demand and supplier intelligent matching method based on big data comprises the following steps: S1, obtaining development related data of each supplier, and obtaining development data of a first-level supplier, basic data of the first-level supplier and development data of a second-level supplier according to the development related data of each supplier; s2, obtaining a first similarity vector, a second similarity vector and a third similarity vector according to the development data of the first-level supplier, the basic data of the first-level supplier, the development data of the second-level supplier and the development data of the purchaser; according to the method, the development data and the basic data of the first-level supplier and the second-level supplier are respectively acquired, and the development plan of the purchaser is combined, so that a full-link and full-factor supplier portrait is formed, and the comprehensiveness and the precision of supplier evaluation are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of supplier management technology, and in particular to a method for intelligently matching procurement demands with suppliers based on big data. Background Art

[0002] With the increasing complexity of global trade and industrial chain division of labor, the procurement links of various industries have put forward higher requirements for the stability and responsiveness of the supply chain. At the same time, traditional manual experience evaluation and single indicator selection methods have become difficult to adapt to the large-scale, multi-level and multi-path modern supply networks. In actual applications, buyers often face the following challenges: information asymmetry and decision-making blind spots. Buyers find it difficult to fully understand the technological development direction of second-tier suppliers and the degree of match with their own needs. They lack awareness of the proactive development of second-tier suppliers, especially the under-utilization of second-tier supplier data, which leads to increased supply chain risks; evaluation indicators are single and difficult to quantify. Traditional evaluations mainly rely on basic data on historical delivery time, quality scores and production capacity, making it difficult to measure the supplier's fit with the buyer's future product, process or technology research and development direction. Summary of the Invention

[0003] In order to overcome the shortcoming of insufficient utilization of secondary supplier data, the present invention provides a method for intelligent matching of procurement needs and suppliers based on big data.

[0004] The technical implementation scheme of the present invention is: a method for intelligently matching procurement needs and suppliers based on big data, comprising the following steps: S1: Acquire development-related data of each supplier, and obtain development data of first-tier suppliers, basic data of first-tier suppliers, and development data of second-tier suppliers based on the development-related data of each supplier; S2: obtaining a first similarity vector, a second similarity vector, and a third similarity vector based on the development data of the first-tier supplier, the basic data of the first-tier supplier, the development data of the second-tier supplier, and the development data of the buyer; S3: Obtain a first similarity score, a second similarity score, and a third similarity score based on the first similarity vector, the second similarity vector, and the third similarity vector, respectively, and obtain a comprehensive score value using a comprehensive scoring formula; S4: Use the risk quality detection formula based on the basic data of the first-tier supplier to obtain the risk quality score of the first-tier supplier; S5: Obtain the best supplier based on the risk quality score and comprehensive score of each first-tier supplier, and match the purchaser based on the best supplier.

[0005] Preferably, the acquiring of development-related data of each supplier, and acquiring the development data of first-tier suppliers, basic data of first-tier suppliers and development data of second-tier suppliers based on the development-related data of each supplier, includes: acquiring the development-related data of suppliers separately according to the type of supplier, the development-related data of suppliers including the development data of suppliers and basic data of suppliers, wherein the types of suppliers are divided into first-tier suppliers and second-tier suppliers, wherein first-tier suppliers are suppliers that directly provide procurement demand materials; and second-tier suppliers are suppliers that provide procurement demand materials to first-tier suppliers; acquiring the development data of first-tier suppliers and development data of second-tier suppliers separately according to the development data of the suppliers, and acquiring the basic data of first-tier suppliers according to the basic data of the suppliers.

[0006] Preferably, the supplier's development-related data includes the supplier's development data and the supplier's basic data, including: the supplier's development data is the supplier's planned new generation of products, processes or research directions; the supplier's basic data is the supplier's original technical direction, maximum production capacity, flexible production capacity, order response time, historical order delivery time, historical specified order delivery time and historical order quality score.

[0007] Preferably, the basic data of the supplier include the supplier's original technical direction, maximum production capacity, flexible production capacity, order response time, historical order delivery time, historical specified order delivery time and historical order quality score, including: the supplier's maximum production capacity is the supplier's ability to maintain stable supply when large quantities or sudden orders are placed; flexible production capacity is the supplier's ability to quickly adjust the process or model according to the buyer's new needs; order response time is the time required from the buyer placing an order to the supplier providing a confirmed quotation.

[0008] Preferably, the obtaining of the first similarity vector, the second similarity vector and the third similarity vector based on the development data of the first-tier supplier, the basic data of the first-tier supplier, the development data of the second-tier supplier and the development data of the purchaser includes: obtaining the development data of the purchaser, the development data of the purchaser is the new generation of products, processes or research directions that the purchaser plans to promote; obtaining the first similarity vector, the second similarity vector and the third similarity vector respectively based on the development data of the purchaser, the development data of the first-tier supplier, the basic data of the first-tier supplier and the development data of the second-tier supplier, the first similarity vector is the similarity vector between the development data of the second-tier supplier and the original technical direction of the first-tier supplier; the second similarity vector is the similarity vector between the development data of the second-tier supplier and the development data of the purchaser; the third similarity vector is the similarity vector between the development data of the second-tier supplier and the development data of the first-tier supplier.

[0009] Preferably, obtaining a first similarity score, a second similarity score, and a third similarity score respectively based on the first similarity vector, the second similarity vector, and the third similarity vector, and obtaining a comprehensive score value using a comprehensive score formula includes: using cosine similarity based on the first similarity vector, the second similarity vector, and the third similarity vector to obtain a first similarity score, a second similarity score, and a third similarity score respectively, and obtaining a comprehensive score value using a comprehensive score formula, wherein the comprehensive score formula is: ; Where, is the comprehensive score; Score the first similarity; Score the second similarity; Score the third similarity; is the weight adjustment coefficient of the comprehensive scoring formula, and .

[0010] Preferably, the step of using a risk quality detection formula based on the basic data of the first-tier supplier to obtain the risk quality score of the first-tier supplier comprises: performing data preprocessing and normalization operations on the basic data of the first-tier supplier and then using the risk quality detection formula to obtain the risk quality score of the first-tier supplier, wherein the risk quality detection formula is: ; Where, is the risk quality score value; The maximum production capacity of the supplier; Flexible production capacity for suppliers; Order response time for suppliers; For suppliers Order delivery time; For suppliers The specified order delivery time; Score the supplier's historical order quality; To adjust the parameters.

[0011] Preferably, the method of obtaining the best supplier based on the risk quality score and comprehensive score of each first-tier supplier and matching the purchaser based on the best supplier includes: taking the first-tier suppliers whose risk quality score is greater than or equal to a preset score threshold as candidate suppliers, and using the final scoring formula to obtain the final score based on the risk quality score and comprehensive score of each candidate supplier, and after obtaining the best supplier based on the final score, matching the best supplier with the purchaser.

[0012] Preferably, the final scoring value is obtained using a final scoring formula based on the risk quality score and comprehensive score of each candidate supplier, including: wherein the final scoring formula is: ; Where, is the final score value; is the risk quality score value; is the preset scoring threshold; is the candidate tolerance value; is the comprehensive score; It is the weight adjustment coefficient of the final scoring formula.

[0013] Preferably, the candidate tolerance value includes: a candidate tolerance value obtained based on historical experience, wherein the candidate tolerance value is a maximum fluctuation range within which the risk quality score value is allowed to deviate from a preset score threshold.

[0014] The present invention has the following advantages: 1. This invention obtains the development data and basic data of first-tier and second-tier suppliers respectively, and combines them with the buyer's own development plan to form a full-link and full-factor supplier portrait, significantly improving the comprehensiveness and accuracy of supplier evaluation; 2. For the three similarity vectors of "secondary development versus primary existing technology," "secondary development versus buyer needs," and "secondary development versus primary future direction," we use cosine similarity to quantify the matching degree. By combining logarithmic, exponential, and sigmoid functions with adjustable weights, we can flexibly adjust the importance of each dimension, thereby achieving a refined evaluation of the supplier's technical fit. 3. Introducing risk quality scoring formulas and final scoring formulas, combined with historical quality scores, to conduct real-time quantitative assessments of the delivery capabilities and service quality of first-tier suppliers. Through threshold screening and tolerance interval setting, proactive early warning of supply chain disruptions and quality fluctuation risks is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of the method for intelligently matching procurement needs and suppliers based on big data of the present invention; Figure 2 Schematic diagram of the structure of each data classification of the present invention. DETAILED DESCRIPTION

[0016] 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 other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0017] Intelligent matching method between procurement demand and suppliers based on big data, such as Figure 1 and Figure 2 As shown, the following steps are included: S1: Acquire development-related data of each supplier, and obtain development data of first-tier suppliers, basic data of first-tier suppliers, and development data of second-tier suppliers based on the development-related data of each supplier; The supplier's development-related data is obtained separately according to the supplier's type. The supplier's development-related data includes the supplier's development data and the supplier's basic data. The supplier types are divided into first-tier suppliers and second-tier suppliers. The first-tier suppliers are suppliers that directly provide procurement demand materials; the second-tier suppliers are suppliers that provide procurement demand materials to the first-tier suppliers. The development data of the first-tier suppliers and the development data of the second-tier suppliers are obtained separately according to the supplier's development data, and the basic data of the first-tier suppliers are obtained according to the supplier's basic data.

[0018] It should be explained that, based on the supplier type information pre-registered in the database, all suppliers are divided into two categories: first-tier suppliers and second-tier suppliers. Among them, first-tier suppliers are suppliers that directly provide procurement materials to purchasers; second-tier suppliers are suppliers that provide procurement materials to first-tier suppliers. By calling the big data interface, the development-related data of the two types of suppliers are obtained from the industry information platform, the supplier self-reporting platform and the public data warehouse respectively. The development-related data includes the supplier's development data and the supplier's basic data; the supplier's development data: refers to the supplier's planning and investment in new generation products, advanced processes or research directions; from the obtained supplier development data, further classification is carried out by supplier type identification. For first-tier supplier entries, their development data are extracted and saved to form the development data of first-tier suppliers; for second-tier supplier entries, their development data are extracted and saved to form the development data of second-tier suppliers.

[0019] The supplier's development data refers to the new generation of products, processes or research directions that the supplier plans to promote; the supplier's basic data refers to the supplier's original technical direction, maximum production capacity, flexible production capacity, order response time, historical order delivery time, historical specified order delivery time and historical order quality score.

[0020] The supplier's maximum production capacity refers to the supplier's ability to maintain stable supply when large-volume or sudden orders are placed; flexible production capacity refers to the supplier's ability to quickly adjust processes or models based on the buyer's new needs; and order response time refers to the time required from the buyer placing an order to the supplier providing a confirmed quotation.

[0021] It should be explained that the original technology direction refers to the supplier's current core technology categories and technology evolution history, which can be obtained through 1. Supplier qualification documents: requiring suppliers to provide a "Technical Capability Specification" or industry certification report to clarify the materials, processes and product types they are good at; 2. Patent / paper search: searching patent databases and academic databases by company name or core technology keywords to refine their technology layout; 3. On-site investigation / interview: the purchaser's technical team or third-party consulting agency conducts an on-site inspection of the supplier's factory to understand its main production lines, process equipment and technical personnel. Maximum production capacity: refers to the maximum daily or weekly production capacity that a supplier can achieve while maintaining a stable supply despite large or sudden orders. This capacity is obtained through production scheduling system data, equipment rated capacity and utilization calculations, or field verification. Production scheduling system data consists of retrieving production records from historical large-volume orders and calculating the maximum actual output per unit time in the absence of major equipment failures. Equipment rated capacity and utilization are calculated by multiplying the rated capacity of the main production equipment by the average annual equipment utilization rate and the number of available shifts to estimate the theoretical maximum capacity, which is then corrected based on historical operating data. Field verification: During experimental large-scale production, joint testing is conducted with suppliers to record sustained peak production during the stable operation period. Flexible production capacity refers to the supplier's ability to quickly adjust processes or models and resume mass production based on new buyer requirements. It is usually measured by switchover time or switching cost and is obtained through production switchover logs or trial production reports. Production switchover logs are the time difference before and after each production line switchover (mold replacement and process debugging) extracted from the MES system. Trial production reports are emergency trial production reports reviewed by suppliers in response to previous demand changes, and they calculate the average time from demand issuance to mass production. Order response time: This refers to the time from when a buyer formally places an order until a supplier completes technical and commercial reviews and returns a formal quotation. This information is obtained from e-procurement platform logs. The e-procurement platform logs automatically calculate the difference between "order time and quotation time" using timestamps in the ERP or procurement collaboration platform. The historical order delivery time and the historical stipulated order delivery time are read in the purchase order; Historical Order Quality Score: This refers to the average quality score of a supplier's historical orders, based on a comprehensive assessment of defective product rate, return rate, and customer complaints. This score is obtained through quality management system (QMS) data, customer satisfaction feedback, or after-sales record analysis. QMS data consists of statistically analyzing the defective rate based on inspection results after each delivery, and calculating the score according to pre-set scoring rules (e.g., 100 − defective rate × 100). Customer satisfaction feedback is a weighted composite quality score derived from a questionnaire survey conducted by buyers regarding the supplier's service and technical support. After-sales record analysis extracts the number of returns and average repair cost from after-sales repair / replacement records, converting them into negative quality deductions, which are then integrated with the QMS score.

[0022] S2: obtaining a first similarity vector, a second similarity vector, and a third similarity vector based on the development data of the first-tier supplier, the basic data of the first-tier supplier, the development data of the second-tier supplier, and the development data of the buyer; Acquire the development data of the purchaser, wherein the development data of the purchaser is the new generation of products, processes or research directions that the purchaser plans to promote; obtain a first similarity vector, a second similarity vector and a third similarity vector respectively based on the development data of the purchaser, the development data of the first-tier supplier, the basic data of the first-tier supplier and the development data of the second-tier supplier, wherein the first similarity vector is the similarity vector between the development data of the second-tier supplier and the original technical direction of the first-tier supplier; the second similarity vector is the similarity vector between the development data of the second-tier supplier and the development data of the purchaser; and the third similarity vector is the similarity vector between the development data of the second-tier supplier and the development data of the first-tier supplier.

[0023] It should be explained that the buyer's development data is extracted from the buyer's ERP or R&D management platform. This data describes the next-generation products, key processes, or core research directions that the buyer plans to promote. After uniformly encoding this information, it is stored in vector form, and a first similarity vector, a second similarity vector, and a third similarity vector are constructed. The first similarity vector is obtained by word-vectorizing the second-tier supplier's development data with the first-tier supplier's original technical direction, calculating the differences in each dimension, and obtaining a feature vector representing the technological inheritance and compatibility between the two. In other words, the potential for synergy between the second-tier supplier and the first-tier supplier's future mass production direction is determined. The second similarity vector is obtained by aligning the second-tier supplier's development data with the buyer's development data, converting the next-generation product or process directions planned by both into vectors in the same semantic space, and obtaining a feature vector representing the degree of fit between the second-tier supplier's R&D direction and the buyer's needs. In other words, it reflects the potential of the second-tier supplier to become the first-tier supplier required by the buyer, thereby ensuring the security and stability of the buyer's supply chain. The third similarity vector is obtained by comparing the second-tier supplier's development data with the first-tier supplier's development data, and generating a feature vector reflecting the future synergy potential of the upstream and downstream of the supply chain. In other words, it reflects the stability, sustainability, and synergy of the industrial collaboration between the second-tier supplier and the first-tier supplier.

[0024] S3: Obtain a first similarity score, a second similarity score, and a third similarity score based on the first similarity vector, the second similarity vector, and the third similarity vector, respectively, and obtain a comprehensive score value using a comprehensive scoring formula; The first similarity score, the second similarity score, and the third similarity score are obtained respectively using cosine similarity according to the first similarity vector, the second similarity vector, and the third similarity vector, and the comprehensive score value is obtained using the comprehensive score formula, wherein the comprehensive score formula is: ; Where, is the comprehensive score; Score the first similarity; Score the second similarity; Score the third similarity; is the weight adjustment coefficient of the comprehensive scoring formula, and .

[0025] It should be explained that the first similarity score, the second similarity score, and the third similarity score are normalized before using the comprehensive scoring formula to ensure that the dimensions of each input are consistent.

[0026] S4: Use the risk quality detection formula based on the basic data of the first-tier supplier to obtain the risk quality score of the first-tier supplier; After preprocessing and normalizing the basic data of first-tier suppliers, the risk quality detection formula is used to obtain the risk quality score of the first-tier suppliers. The risk quality detection formula is: ; Where, is the risk quality score value; The maximum production capacity of the supplier; Flexible production capacity for suppliers; Order response time for suppliers; For suppliers Order delivery time; For suppliers The specified order delivery time; Score the supplier's historical order quality; To adjust the parameters.

[0027] It should be explained that before using the risk quality test formula, Missing values ​​are interpolated using field experience or industry averages, and Min–Max normalization is used to standardize them to the [0,1] interval to ensure consistency in the dimensions of subsequent calculations, that is, the parameters used in the formula are all normalized parameters.

[0028] S5: Obtain the best supplier based on the risk quality score and comprehensive score of each first-tier supplier, and match the purchaser based on the best supplier.

[0029] First-tier suppliers whose risk quality score is greater than or equal to the preset score threshold are selected as candidate suppliers. The final score is obtained using the final scoring formula based on the risk quality score and comprehensive score of each candidate supplier. After the best supplier is obtained based on the final score, the best supplier is matched with the purchaser.

[0030] It should be explained that the risk quality score threshold is pre-set , all The first-tier suppliers are marked as candidate suppliers and enter the next step of the evaluation process; if Not considered for now.

[0031] The final scoring formula is: ; Where, is the final score value; is the risk quality score value; is the preset scoring threshold; is the candidate tolerance value; is the comprehensive score; It is the weight adjustment coefficient of the final scoring formula.

[0032] It needs to be explained that through Ensure that the risk quality score values ​​near the preset score threshold are treated equally, and focus more on the comprehensive score value, that is, the comprehensive capability level of the second-tier suppliers, to provide early perception and preparation for subsequent sustainable development.

[0033] A candidate tolerance value is obtained based on historical experience, where the candidate tolerance value is the maximum fluctuation range within which the risk quality score value is allowed to deviate from a preset score threshold.

[0034] It should be explained that, in combination with industry events and market fluctuations, appropriate statistical indicators should be selected as new , and updated synchronously to ensure that the tolerance for risk deviation is synchronized with the market environment.

[0035] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. The intelligent matching method between procurement demand and suppliers based on big data is characterized by: The following steps are involved: S1: Acquire development-related data of each supplier, and obtain development data of first-tier suppliers, basic data of first-tier suppliers, and development data of second-tier suppliers based on the development-related data of each supplier; S2: obtaining a first similarity vector, a second similarity vector, and a third similarity vector based on the development data of the first-tier supplier, the basic data of the first-tier supplier, the development data of the second-tier supplier, and the development data of the buyer; S3: Obtain a first similarity score, a second similarity score, and a third similarity score based on the first similarity vector, the second similarity vector, and the third similarity vector, respectively, and obtain a comprehensive score value using a comprehensive scoring formula; S4: Use the risk quality detection formula based on the basic data of the first-tier supplier to obtain the risk quality score of the first-tier supplier; S5: Obtain the best supplier based on the risk quality score and comprehensive score of each first-tier supplier, and match the purchaser based on the best supplier.

2. The method for intelligently matching procurement requirements and suppliers based on big data according to claim 1 is characterized in that: The method of obtaining development-related data of each supplier, and obtaining development data of first-tier suppliers, basic data of first-tier suppliers and development data of second-tier suppliers based on the development-related data of each supplier, includes: obtaining development-related data of suppliers respectively according to the type of supplier, the development-related data of suppliers including development data of suppliers and basic data of suppliers, wherein the types of suppliers are divided into first-tier suppliers and second-tier suppliers, wherein first-tier suppliers are suppliers that directly provide procurement demand materials; and second-tier suppliers are suppliers that provide procurement demand materials to first-tier suppliers; obtaining development data of first-tier suppliers and development data of second-tier suppliers respectively according to the development data of the suppliers, and obtaining basic data of first-tier suppliers according to the basic data of the suppliers.

3. The method for intelligently matching procurement requirements and suppliers based on big data according to claim 2 is characterized in that: The supplier's development-related data includes the supplier's development data and the supplier's basic data, including: the supplier's development data is the supplier's planned new generation of products, processes or research directions; the supplier's basic data is the supplier's original technical direction, maximum production capacity, flexible production capacity, order response time, historical order delivery time, historical specified order delivery time and historical order quality score.

4. The method for intelligently matching procurement requirements and suppliers based on big data according to claim 3 is characterized in that: The basic data of the supplier include the supplier's original technical direction, maximum production capacity, flexible production capacity, order response time, historical order delivery time, historical specified order delivery time and historical order quality score, including: the supplier's maximum production capacity is the supplier's ability to maintain stable supply when large quantities or sudden orders are placed; flexible production capacity is the supplier's ability to quickly adjust the process or model according to the buyer's new needs; order response time is the time required from the buyer placing an order to the supplier providing a confirmed quotation.

5. The method for intelligently matching procurement requirements and suppliers based on big data according to claim 1 is characterized in that: The method of obtaining the first similarity vector, the second similarity vector and the third similarity vector based on the development data of the first-tier supplier, the basic data of the first-tier supplier, the development data of the second-tier supplier and the development data of the purchaser includes: obtaining the development data of the purchaser, wherein the development data of the purchaser is a new generation of products, processes or research directions that the purchaser plans to promote; obtaining the first similarity vector, the second similarity vector and the third similarity vector respectively based on the development data of the purchaser, the development data of the first-tier supplier, the basic data of the first-tier supplier and the development data of the second-tier supplier, wherein the first similarity vector is the similarity vector between the development data of the second-tier supplier and the original technical direction of the first-tier supplier; the second similarity vector is the similarity vector between the development data of the second-tier supplier and the development data of the purchaser; and the third similarity vector is the similarity vector between the development data of the second-tier supplier and the development data of the first-tier supplier.

6. The method for intelligently matching procurement requirements and suppliers based on big data according to claim 5 is characterized in that: Obtaining a first similarity score, a second similarity score, and a third similarity score respectively based on the first similarity vector, the second similarity vector, and the third similarity vector, and obtaining a comprehensive score value using a comprehensive score formula includes: using cosine similarity based on the first similarity vector, the second similarity vector, and the third similarity vector to obtain a first similarity score, a second similarity score, and a third similarity score respectively, and obtaining a comprehensive score value using a comprehensive score formula, wherein the comprehensive score formula is: ； Where, is the comprehensive score; Score the first similarity; Score the second similarity; Score the third similarity; is the weight adjustment coefficient of the comprehensive scoring formula, and .

7. The method for intelligently matching procurement requirements and suppliers based on big data according to claim 1 is characterized in that: The method of using a risk quality detection formula based on the basic data of the first-tier supplier to obtain the risk quality score of the first-tier supplier includes: performing data preprocessing and normalization operations on the basic data of the first-tier supplier and then using the risk quality detection formula to obtain the risk quality score of the first-tier supplier, wherein the risk quality detection formula is: ； Where, is the risk quality score value; The maximum production capacity of the supplier; Flexible production capacity for suppliers; Order response time for suppliers; For suppliers Order delivery time; For suppliers The specified order delivery time; Score the supplier's historical order quality; To adjust the parameters.

8. The method for intelligently matching procurement requirements and suppliers based on big data according to claim 1 is characterized in that: The method of obtaining the best supplier based on the risk quality score and comprehensive score of each first-tier supplier and matching the purchaser based on the best supplier includes: taking first-tier suppliers with risk quality scores greater than or equal to a preset score threshold as candidate suppliers, and using a final scoring formula to obtain a final score based on the risk quality score and comprehensive score of each candidate supplier, and after obtaining the best supplier based on the final score, matching the best supplier with the purchaser.

9. The method for intelligently matching procurement requirements and suppliers based on big data according to claim 8 is characterized in that: According to the risk quality score and comprehensive score of each candidate supplier, a final score value is obtained using a final score formula, including: wherein the final score formula is: ； Where, is the final score value; is the risk quality score value; is the preset scoring threshold; is the candidate tolerance value; is the comprehensive score; is the weight adjustment coefficient of the final scoring formula.

10. The method for intelligently matching procurement requirements and suppliers based on big data according to claim 9 is characterized in that: The candidate tolerance value includes: a candidate tolerance value obtained based on historical experience, wherein the candidate tolerance value is a maximum fluctuation range within which the risk quality score value is allowed to deviate from a preset score threshold.

Images