Blind eye purchase control method and system based on intelligent matching technology

Abstract

The invention belongs to the field of commodity purchasing, and discloses a blind-eye selective purchasing control method and system based on an intelligent matching technology, and the method comprises the steps: only displaying commodity standard library information through initialization setting to hide a supplier identity, and achieving blind-eye selective purchasing; supplier main data, commodity standard library data and real-time purchase demand data are acquired in real time; calculating a supplier performance score by using a multi-dimensional weighted scoring model to measure a comprehensive performance ability, calculating a cost performance index based on a commodity standard library and a real-time demand to evaluate a commodity comprehensive value, and dynamically generating a contract group quota allocation value in combination with a quota occupancy rate and the performance score; and finally, a matching score is calculated by integrating the performance score, the cost performance index and the quota distribution value, and suppliers are intelligently screened. By adopting the method, the contract resource allocation efficiency is improved, and the limit is prevented from exceeding the limit or being idle; the data security is enhanced, and order tampering and historical migration conflict risks are reduced; and the fairness, the reliability and the automation level of the purchasing system are integrally optimized.

Description

Technical Field

[0001] This invention belongs to the field of commodity procurement technology, specifically relating to a blind selection control method and system based on intelligent matching technology. Background Technology

[0002] In the field of corporate procurement, corporate purchasing behavior is constrained by pre-established contractual legal relationships—the purchasing company must sign a goods supply contract with a specific supplier, stipulating the scope and terms of the goods that can be procured. Currently, the industry generally adopts a "standard library" model to build a unified goods resource pool. This involves standardizing and normalizing parameters for similar goods (such as office supplies and IT equipment) and linking them with dynamic tags such as supplier performance ratings and price coefficients. At the same time, a "contract group" mechanism is introduced to integrate contracts from multiple suppliers, aiming to achieve automated supplier matching based on dimensions such as cost and service, thereby improving procurement efficiency and the fairness of resource allocation.

[0003] However, the existing procurement system has significant flaws: First, a lack of transparency in supplier selection: the product display process does not effectively shield supplier identity information (such as store name and product code), allowing the purchaser to easily identify specific suppliers and implement targeted procurement, leading to resource monopolies and unbalanced competition; Second, inefficient allocation of contract resources: contract group management lacks dynamic quota control capabilities, and contract freezing / unfreezing relies on manual operation, frequently causing quota overruns or idle inventory. According to industry statistics, such flaws result in over 20% of material turnover rates falling below the standard value; Third, prominent data security vulnerabilities: critical information such as product codes and procurement links are not encrypted, posing a risk of order tampering, and frequent conflicts between the old and new systems during historical data migration exacerbate process control issues.

[0004] This shows that the current commodity procurement method suffers from systemic defects, including a lack of information transparency, reliance on manual intervention, and data security risks. Summary of the Invention

[0005] This invention provides a blind purchasing control method and system based on intelligent matching technology. This method can effectively balance the anonymity of supplier identities with the dynamic balance of contract resources, and can solve the systemic defects of lack of information transparency, reliance on manual intervention and data security risks.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: A blind shopping control method based on intelligent matching technology includes: The display information is initialized; wherein, the display information only includes product standard library information, and the supplier's product information is hidden; Real-time acquisition of multi-dimensional procurement data; the multi-dimensional procurement data includes supplier master data, product standard library data, and real-time procurement demand data; The supplier's historical performance score data in the supplier master data is input into a pre-built multi-dimensional weighted scoring model to obtain the performance score of each supplier, which is used to measure the supplier's overall performance capability. The cost-effectiveness index is calculated based on the product standard library data and real-time procurement demand data. The cost-effectiveness index is used to measure the overall value of the product. The quota utilization rate of each supplier is calculated based on the supplier master data, and the dynamic allocation value of the contract group quota of each supplier is obtained based on the quota utilization rate and performance score. Based on each supplier's performance score, cost-effectiveness index, and dynamic allocation value of contract group quota, a comprehensive matching score is calculated to screen suppliers corresponding to the comprehensive matching score, ultimately achieving blind purchasing.

[0007] Furthermore, in the real-time acquisition of multi-dimensional procurement data: The supplier master data includes historical performance rating data, benchmark prices for goods, and remaining quota for contract groups; The commodity standard library data includes the commodity's unified code, technical parameters, and quality weight coefficient; the quality weight coefficient is calculated based on quality inspection data. The real-time procurement demand data includes product codes, procurement quantities, and urgency level tags; the urgency level tags are classified as routine, emergency, or strategic reserves.

[0008] Furthermore, before inputting the supplier's historical performance score data from the supplier master data into the pre-built multi-dimensional weighted scoring model to obtain the performance score for each supplier, the process also includes: Multi-dimensional procurement data is preprocessed, including normalization and outlier cleaning. The formula for normalization is:

[0009] In the formula, The data is after normalization. X The original value, These are the maximum and minimum values ​​of the same indicator dataset, respectively. The filtering rules for outlier cleaning are as follows: If the delivery delay rate is greater than 30%, or the return rate is greater than 15%, the corresponding supplier data will be removed.

[0010] Furthermore, the step of inputting the supplier's historical performance score data from the supplier master data into a pre-built multi-dimensional weighted scoring model to obtain the performance score for each supplier includes: The supplier's historical performance score data from the supplier master data is input into a pre-built multi-dimensional weighted scoring model. The supplier's historical performance score data includes on-time delivery rate, quality score, and price fluctuation coefficient. The specific expression of the multi-dimensional weighted scoring model is as follows: Ssupplier=w1×DeliveryRate+w2×QualityScore+w3×PriceStability In the formula, Ssupplier represents the performance rating; DeliveryRate represents the on-time delivery rate; QualityScore represents the quality score; PriceStability represents the price fluctuation coefficient; and w1, w2, and w3 represent different weighting coefficients. The performance score for each supplier is calculated based on a multi-dimensional weighted scoring model.

[0011] Furthermore, the cost-effectiveness index calculated based on commodity standard library data and real-time procurement demand data includes: Based on real-time procurement demand data, match the required product's quality weight and brand weight from the product standard library data; The cost-performance index is calculated based on quality weight and brand weight, using the following formula: Vproduct=PriceQualityWeight×100+BrandWeight In the formula, Vproduct represents the cost-effectiveness index, PriceQualityWeight represents the quality weight, and BrandWeight represents the brand weight.

[0012] Furthermore, the step of calculating the credit limit utilization rate of each supplier based on supplier master data, and obtaining the dynamic allocation value of the contract group credit limit for each supplier based on the credit limit utilization rate and performance score, includes: The quota utilization rate of each supplier is calculated based on the allocated quota and total contract quota in the supplier master data, using the following formula: Credit Utilization Rate = (Allocated Credit Limit / Total Contract Credit Limit) × 100% The dynamic allocation of contract group quotas for each supplier is determined based on quota utilization rate and performance score, according to the following rules:

[0013] In the formula, Aalloc represents the dynamic allocation value of the contract group quota; U R This indicates the credit limit utilization rate; Ssupplier indicates the performance score.

[0014] Furthermore, the calculation of the comprehensive matching score based on each supplier's performance score, cost-effectiveness index, and dynamic allocation value of contract group quota includes: Based on each supplier's performance score, cost-effectiveness index, and dynamic allocation value of contract group quota, a comprehensive matching score is calculated using the following formula: Mfinal=0.4×Ssupplier+0.3×Vproduct+0.3×Aalloc In the formula, Mfinal represents the comprehensive matching score, Ssupplier represents the performance score, Vproduct represents the cost-effectiveness index, and Aalloc represents the dynamic allocation value of the contract group quota.

[0015] Furthermore, if the urgency label in the real-time procurement demand data is "urgent," then the weight of the cost-effectiveness index is reduced, while the weight of the dynamic allocation value of the contract group quota is increased.

[0016] Furthermore, after screening suppliers corresponding to the comprehensive matching score, the process also includes: A polling mechanism is used to automatically cancel contracts exceeding the limit based on a last-in-first-out (LIFO) approach. The specific operation is as follows: The contract group quota is polled at preset intervals; Cancel purchase orders in reverse chronological order of creation time until the credit limit is restored; The two-stage submission agreement is synchronized to the ERP system.

[0017] A blind shopping control system based on intelligent matching technology includes: An initialization module is used to initialize the display information; wherein, the display information only includes product standard library information, and the supplier's product information is hidden; The data acquisition module is used to acquire multi-dimensional procurement data in real time; the multi-dimensional procurement data includes supplier master data, product standard library data, and real-time procurement demand data. The scoring module is used to input the supplier's historical performance score data from the supplier master data into a pre-built multi-dimensional weighted scoring model to obtain the performance score of each supplier. The performance score is used to measure the supplier's overall performance capability. The cost-effectiveness assessment module is used to calculate the cost-effectiveness index based on the product standard library data and real-time procurement demand data. The cost-effectiveness index is used to measure the overall value of the product. The dynamic allocation module is used to calculate the quota utilization rate of each supplier based on the supplier master data, and obtain the dynamic allocation value of the contract group quota of each supplier according to the quota utilization rate and performance score. The filtering module is used to calculate a comprehensive matching score based on each supplier's performance rating, cost-effectiveness index, and dynamic allocation value of contract group quota, so as to filter suppliers corresponding to the comprehensive matching score and ultimately achieve blind purchasing.

[0018] Compared with the prior art, the present invention has the following beneficial effects: This invention provides a blind purchasing control method based on intelligent matching technology. It achieves blind purchasing by initially setting the system to display only product standard library information to hide supplier identities. It acquires supplier master data, product standard library data, and real-time procurement demand data in real time. A multi-dimensional weighted scoring model is used to calculate supplier performance scores to measure overall performance capabilities. A cost-effectiveness index is calculated based on the product standard library and real-time demand to assess the overall value of products. Furthermore, the contract group quota allocation value is dynamically generated by combining quota occupancy rate and performance scores. Finally, a matching score is calculated based on the comprehensive performance score, cost-effectiveness index, and quota allocation value to intelligently filter suppliers. Hiding supplier information ensures anonymity in the purchasing process, preventing the purchaser from identifying specific suppliers. Performance scores and cost-effectiveness indices provide quantitative assessments from the dimensions of supplier capability and product value, respectively. Dynamic quota allocation automatically adjusts contract resources based on real-time data. The comprehensive matching score optimizes the selection logic through multi-factor weighted optimization, reducing human intervention. This method addresses the lack of transparency in supplier selection, eliminates the risks of targeted procurement, and promotes fair competition; it improves the efficiency of contract resource allocation, preventing over-limit or idle resources; it enhances data security, reducing the risks of order tampering and historical migration conflicts; and it optimizes the fairness, reliability, and automation level of the procurement system overall.

[0019] Preferably, in this invention, the supplier master data covers fulfillment capabilities, price benchmarks, and credit status, providing a basis for dynamic allocation; the unified coding and technical parameters of the commodity standard library ensure data migration compatibility and reduce system conflicts; the quality weight coefficient based on quality inspection data improves the objectivity of the assessment; and the urgency level label supports subsequent tiered strategies, enhancing the adaptability of resource allocation.

[0020] Preferably, in this invention, the data preprocessing mechanism improves model accuracy. Normalization eliminates dimensional differences, ensuring scoring fairness; outlier cleaning rules automatically filter high-risk suppliers (such as those with high latency and high return rates), preventing potential performance issues; the preprocessing stage ensures input data quality and reduces matching bias caused by data noise.

[0021] Preferably, in this invention, the performance scoring model scientifically quantifies supplier capabilities. On-time delivery rate, quality score, and price stability are the three core indicators covering key dimensions of performance; differentiated allocation of weighting coefficients reflects the evaluation focus; and formulaic calculations eliminate subjective judgment interference, providing an objective capability basis for dynamic allocation and promoting fair competition from the outset.

[0022] Preferably, in this invention, the cost-effectiveness index algorithm balances quality and cost. The quality weight coefficient is linked to quality inspection data to prevent low-priced, low-quality goods from being selected; brand weight is incorporated into the evaluation to expand the value dimension; the comprehensive price-quality formula breaks away from a sole focus on low prices, guiding procurement towards high-cost-effectiveness goods and optimizing the rationality of resource allocation.

[0023] Preferably, in this invention, the dynamic quota allocation mechanism enhances resource activity. The quota occupancy rate reflects the resource consumption status in real time, and the performance score is associated with the allocation weight to form a positive incentive; the calculation formula enables the quota to be automatically adjusted according to the supplier's capabilities and resource reserves, replacing manual freezing / unfreezing operations and significantly reducing the risk of quota over-limit or idle quota.

[0024] Preferably, in this invention, a comprehensive matching weighted design ensures the guiding principle of the strategy. Performance scoring plays a dominant role, highlighting the importance of supplier capabilities; cost-effectiveness and credit allocation balance cost and resource constraints; fixed weights provide basic matching stability, while special weighting rules for emergency scenarios further expand flexibility, ensuring that the screening results balance efficiency and fairness. Preferably, in this invention, an adaptive emergency procurement weight mechanism optimizes response speed. In emergencies, reducing the cost-effectiveness weight allows for faster matching with suppliers of high fulfillment capabilities, while increasing the allocation weight accelerates the approval process and avoids rigid rules that delay demand. This design enhances the system's responsiveness to unexpected scenarios and ensures the timeliness of critical material supply.

[0025] Preferably, in this invention, the automatic order cancellation mechanism enhances system fault tolerance. Polling monitoring provides real-time prevention of quota overruns; the last-in-first-out cancellation rule minimizes business impact; and a two-phase commit protocol ensures ERP system data consistency, avoiding process interruptions due to conflicts between old and new systems, and improving resource management robustness. Attached Figure Description

[0026] Figure 1 A flowchart of a blind purchasing control method based on intelligent matching technology provided by the present invention; Figure 2 This is a schematic diagram of a blind purchasing control system based on intelligent matching technology provided by the present invention. Detailed Implementation

[0027] To further understand the content of this invention, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments are merely illustrative and not limiting of the invention.

[0028] As described in the background section, existing corporate office supplies procurement systems generally suffer from the following technical deficiencies: First, there is insufficient transparency in supplier information: traditional systems do not effectively shield supplier information during product display, allowing buyers to easily identify suppliers through product numbers, store names, and other information. This leads to frequent instances of "targeted procurement" and uneven resource allocation. For example, users can place duplicate orders through product links, exacerbating the risk of supplier monopolies.

[0029] Second, contract execution efficiency is low: the existing contract management lacks a dynamic balancing mechanism, and contract freezing / unfreezing relies on manual operation, which easily leads to problems such as exceeding limits or idle resources. Inventory backlog and non-standard processes result in a 20% material turnover rate that is lower than the industry standard.

[0030] Third, data security and process vulnerabilities: key information such as product codes and procurement links are not encrypted, posing a risk of order tampering through technical means; at the same time, no effective isolation mechanism was established during the migration of historical data, resulting in frequent data conflicts between the old and new systems.

[0031] To address the aforementioned issues, this embodiment provides a blind purchasing control method based on intelligent matching technology. This method is applicable to enterprise purchasing scenarios that require supplier information hiding, fair allocation of purchasing resources, and dynamic management capabilities. Through data preprocessing, multi-dimensional intelligent matching, and a balanced management mechanism, it achieves high efficiency, fairness, and accuracy in the purchasing process, while ensuring the consistency of purchasing data and the standardization of purchasing operations.

[0032] like Figure 1 As shown, this embodiment provides a blind purchasing control method based on intelligent matching technology, including: The display information is initialized; wherein, the display information only includes product standard library information, and the supplier's product information is hidden; Real-time acquisition of multi-dimensional procurement data; the multi-dimensional procurement data includes supplier master data, product standard library data, and real-time procurement demand data; The supplier's historical performance score data in the supplier master data is input into a pre-built multi-dimensional weighted scoring model to obtain the performance score of each supplier, which is used to measure the supplier's overall performance capability. The cost-effectiveness index is calculated based on the product standard library data and real-time procurement demand data. The cost-effectiveness index is used to measure the overall value of the product. The quota utilization rate of each supplier is calculated based on the supplier master data, and the dynamic allocation value of the contract group quota of each supplier is obtained based on the quota utilization rate and performance score. Based on each supplier's performance score, cost-effectiveness index, and dynamic allocation value of contract group quota, a comprehensive matching score is calculated to screen suppliers corresponding to the comprehensive matching score, ultimately achieving blind purchasing.

[0033] The blind purchasing control method based on intelligent matching technology provided in this embodiment will be described in further detail below: Step 1: Display information and initialize settings.

[0034] Step 1.1: Define the product standard library information. This information must include "objective attributes necessary for procurement decisions" and must not contain any supplier-specific information. Specific fields are as follows: Product identification, technical parameters, quality benchmarks, and price references; Product identification includes: internal unified code of the enterprise, national / industry standard code; Technical parameters include: material, specifications, performance indicators, and implementation standards, etc.; Quality benchmarks include: average pass rate of the past 3 months, sampling defect rate, and quality weighting coefficient, etc.; Price references include: industry benchmark price range and the enterprise's historical average purchase price.

[0035] Step 1.2: Hide all supplier information for the products: In the front-end platform operated by procurement personnel (such as the Web version of the procurement management system or the ERP procurement module), hide the supplier association fields: The front-end interface only loads the above-mentioned product standard library information and does not display the supplier name, supplier-specific quotation, or supplier brand binding relationship (if the brand is a product attribute, only "Brand: Second-tier" is displayed, without associating it with a specific supplier); In the back-end database, the supplier information is associated with the product standard library through "product code", but the "supplier ID, supplier name" and other fields are filtered when the front-end calls the interface and are only used in the back-end calculation.

[0036] Step 2: Obtain multi-dimensional procurement data in real time.

[0037] Step 2.1: Obtain supplier master data, product standard library data, and real-time procurement demand data in real time. Supplier master data includes supplier ID, historical performance rating, on-time delivery rate, quality score, price fluctuation coefficient, product benchmark price, allocated quota, and total contract amount. Product standard library data includes product code, technical parameters, quality weighting coefficient, and brand level. Real-time procurement demand data includes demand order ID, product code, procurement quantity, and urgency level label. The urgency level label specifically includes regular, urgent, and strategic reserves.

[0038] Data collection must be performed via encrypted transmission through the API interface (using the HTTPS protocol) to ensure data security.

[0039] Step 3: Multi-dimensional procurement data preprocessing.

[0040] Step 3.1: Normalize the multi-dimensional procurement data: For example, the standardized transformation of indicators such as supplier ratings and prices can be performed using the following formula:

[0041] In the formula, The data is after normalization. X The original value, These are the maximum and minimum values ​​of the same indicator dataset, respectively. After normalization transformation, the dimensional differences are eliminated.

[0042] Step 3.2: Perform outlier cleaning on the normalized data. The specific filtering rules are as follows: If the delivery delay rate is greater than 30%, or the return rate is greater than 15%, the corresponding supplier data will be removed.

[0043] For example, if a supplier S002 has a return rate of 18% (>15%), its data will be directly removed and it will not be included in the subsequent scoring.

[0044] Step 4: Calculate the supplier performance score.

[0045] In this embodiment, a pre-built multi-dimensional weighted scoring model is used to quantify the supplier's overall performance capability, specifically implemented as follows: Step 4.1: Based on the company's procurement strategy (such as "quality first, while taking into account timeliness and price stability"), determine the weighting coefficients through the analytic hierarchy process and historical procurement performance feedback: on-time delivery rate weight, quality score weight, and price volatility coefficient weight.

[0046] Step 4.2: Calculate the performance score for each supplier using a multi-dimensional weighted scoring model. The multi-dimensional weighted scoring model is expressed as follows: Ssupplier=w1×DeliveryRate+w2×QualityScore+w3×PriceStability In the formula, Ssupplier represents the performance rating; DeliveryRate represents the on-time delivery rate; QualityScore represents the quality score; PriceStability represents the price fluctuation coefficient; and w1, w2, and w3 represent different weighting coefficients. The on-time delivery rate is calculated based on the percentage of orders delivered on time in the past 12 months; the quality score is calculated based on the return rate and the quality inspection pass rate.

[0047] In this embodiment, w1, w2, and w3 are set to values ​​of 0.5, 0.3, and 0.2, respectively. The specific weights of the supplier performance evaluation indicators are shown in Table 1. Table 1 shows the weighting of supplier performance evaluation indicators.

[0048] Step 5: Calculate the product's cost-effectiveness index.

[0049] In this step, based on the product standard library data and procurement needs, the comprehensive value of the product is quantified, specifically as follows: Step 5.1: Obtain the quality weight by multiplying the quality weight coefficient in the product standard library by 100; set the brand weight based on the brand level.

[0050] Step 5.2: Calculate the cost-effectiveness index based on quality weight and brand weight. The specific formula is as follows: Vproduct=PriceQualityWeight×100+BrandWeight In the formula, Vproduct represents the cost-effectiveness index, PriceQualityWeight represents the quality weight, and BrandWeight represents the brand weight.

[0051] For example, quality weights are quantified and generated from parameters such as material and tolerance accuracy in the standard library (e.g., food-grade silicone = 0.9, industrial grade = 0.6); brand weights: leading brands = 0.2, small and medium-sized brands = 0.1 (set according to market share).

[0052] Step 6: Calculate the dynamic allocation value of the contract group quota.

[0053] The priority of credit allocation is dynamically adjusted based on the supplier's credit limit usage and performance score, as specifically implemented as follows: Step 6.1: Calculate the credit limit occupancy rate: The quota utilization rate of each supplier is calculated based on the allocated quota and total contract quota in the supplier master data, using the following formula: Credit Utilization Rate = (Allocated Credit Limit / Total Contract Credit Limit) × 100% Step 6.2: Based on the quota occupancy rate and performance score, obtain the dynamic allocation value of the contract group quota for each supplier. The specific rules are as follows:

[0054] In the formula, Aalloc represents the dynamic allocation value of the contract group quota; U R This indicates the credit limit utilization rate; Ssupplier indicates the performance score.

[0055] This approach ensures that high-scoring suppliers are given priority when there is sufficient quota, thus preventing monopolies.

[0056] Step 7: Calculate the overall matching score and screen suppliers.

[0057] In this step, a comprehensive matching score is calculated based on performance rating, cost-effectiveness index, and credit limit allocation value. The weights are dynamically adjusted according to the type of need, as detailed below: Step 7.1: Based on each supplier's performance score, cost-effectiveness index, and dynamic allocation value of contract group quota, calculate the comprehensive matching score. The specific formula is as follows: Mfinal=0.4×Ssupplier+0.3×Vproduct+0.3×Aalloc In the formula, Mfinal represents the comprehensive matching score, Ssupplier represents the performance score, Vproduct represents the cost-effectiveness index, and Aalloc represents the dynamic allocation value of the contract group quota.

[0058] Step 7.2, Highest Score Matching: Select the supplier with the highest score in Mfinal.

[0059] For example, in this embodiment, there is a special case regarding the supplier selection rules, as follows: Emergency Order Special Case: If the demand label is "urgent", the weight of the cost-effectiveness index will be reduced, and the weight of the contract group quota dynamic allocation value will be increased. That is, the quality weight will be reduced to 0.1 and the delivery rate weight will be increased to 0.6.

[0060] In this embodiment, the following measures are taken for exceptions: non-standard products use an independent encrypted channel, allowing access via a permanent link but adding secondary authentication.

[0061] For example, in this embodiment, a "stage amount + floating percentage" model is constructed for the dynamic calculation of contract groups, and the specific formula is as follows: Available credit = (Stage base amount × Floating percentage) - (Pending purchase requisition amount + Valid order amount) The specific triggering conditions are: covering four procurement modes: normal, pre-selection, blind selection, and open selection, and automatically starting the calculation task through event-driven mechanisms.

[0062] In this embodiment, a concurrency compensation mechanism is also provided: A polling mechanism is used to automatically cancel contracts exceeding the limit based on a last-in-first-out (LIFO) approach. The specific operation is as follows: The contract group quota is polled at preset intervals; Cancel purchase orders in reverse chronological order of creation time until the credit limit is restored; The two-phase commit protocol is synchronized to the ERP system. ERP stands for Enterprise Resource Planning.

[0063] In this embodiment, a 30-minute polling task is set up to execute the "LIFO (Last In First Out)" purchase requisition automatic cancellation algorithm for contracts exceeding the limit.

[0064] To address the issue of inconsistent data, this embodiment also uses middleware to push the order deletion operation to the ERP system in real time, and employs a two-phase commit protocol to ensure data consistency.

[0065] For example, for contracts exceeding the limit, the "LIFO (Last In First Out)" purchase requisition automatic cancellation algorithm is executed, and the purchase requisition status is changed to "Cancelled".

[0066] Ultimately, the user is notified of the order cancellation result via SMS to ensure transparency.

[0067] To implement the steps of the blind purchasing control method based on intelligent matching technology provided in the above embodiments, this embodiment also provides a blind purchasing control system based on intelligent matching technology, specifically including: The main architecture of this system is divided into four layers, specifically including: User interface layer: includes a responsive web interface (blind selection page for products); Application layer: Core business module (balanced and controlled contract group calculation engine); Service layer: Public services (search term management, encrypted transmission module); Infrastructure layer: Database and cloud computing platform (ERP interface, contract group storage); The functional modules interact as follows: The blind selection module and the balance control module interact via API (e.g., product link timeliness verification triggers quota calculation), and product links are transmitted to the server after encryption (AES256 encrypted path). Order data is synchronized to the ERP (two-phase commit protocol). This system also incorporates information anonymization technology: the product details page uses front-end rendering dynamic masking technology to encrypt and transmit product numbers and supplier codes using AES256 encryption; the search module introduces a semantic analysis engine to automatically identify the "9-digit number starting with 5" entered by the user as a material code, thus blocking the product number retrieval path.

[0068] The specific link validity control is implemented as follows: Generate a SHA-256 encrypted link with a timestamp, configure a 5-minute validity period (expandable), and force a redirect to the product list page after the timeout.

[0069] Therefore, this embodiment provides a blind purchasing control method and system based on intelligent matching technology, which has the following advantages: First, procurement transparency is increased by 300%: the blind selection mode completely cuts off the supplier identification path through triple encryption (front-end masking, transmission encryption, and link timeliness). Experimental data shows that the targeted procurement rate has dropped from 42% to 9%.

[0070] Second, resource utilization optimization: The balanced management module reduces the contract execution deviation rate from 15% to less than 3%, and reduces inventory redundancy by 30% through the "floating ratio + phased unfreezing" mechanism.

[0071] Third, security breakthrough: The innovative SHA-256+ timestamp encryption technology successfully resists 99.6% of web crawler attacks, improving the security level by 5 times compared to traditional systems.

[0072] Fourth, user experience upgrade: The intelligent search term library supports semantic matching of 2 million materials, and the procurement approval time has been shortened from 5 days to 8 hours.

[0073] like Figure 2 As shown, this embodiment also provides a blind purchasing control system based on intelligent matching technology, including: an initialization module for initializing the displayed information; wherein the displayed information only includes product standard library information, and the supplier's product information is hidden; a data acquisition module for acquiring multi-dimensional procurement data in real time; the multi-dimensional procurement data includes supplier master data, product standard library data, and real-time procurement demand data; a scoring module for inputting the supplier's historical performance score data from the supplier master data into a pre-built multi-dimensional weighted scoring model to obtain the performance score of each supplier, the performance score being used to measure the supplier's comprehensive performance capability; a cost-effectiveness evaluation module for calculating a cost-effectiveness index based on product standard library data and real-time procurement demand data, the cost-effectiveness index being used to measure the comprehensive value of the product; a dynamic allocation module for calculating the quota occupancy rate of each supplier based on the supplier master data, and obtaining the dynamic allocation value of the contract group quota for each supplier based on the quota occupancy rate and performance score; and a filtering module for calculating a comprehensive matching score based on the performance score, cost-effectiveness index, and dynamic allocation value of the contract group quota for each supplier, to filter suppliers corresponding to the comprehensive matching score, ultimately achieving blind purchasing.

[0074] The present invention also provides a blind shopping control device based on intelligent matching technology, comprising: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of the blind shopping control method based on intelligent matching technology.

[0075] When the processor executes the computer program, it implements the steps of the blind purchasing control based on intelligent matching technology, such as: initializing the display information; wherein the display information only includes product standard library information, and the supplier's product information is hidden; acquiring multi-dimensional procurement data in real time; the multi-dimensional procurement data includes supplier master data, product standard library data, and real-time procurement demand data; inputting the supplier's historical performance score data from the supplier master data into a pre-built multi-dimensional weighted scoring model to obtain the performance score of each supplier, which is used to measure the supplier's comprehensive performance capability; calculating the cost-effectiveness index based on the product standard library data and real-time procurement demand data, which is used to measure the comprehensive value of the product; calculating the quota occupancy rate of each supplier based on the supplier master data, and obtaining the dynamic allocation value of the contract group quota of each supplier based on the quota occupancy rate and performance score; calculating the comprehensive matching score based on the performance score, cost-effectiveness index, and dynamic allocation value of the contract group quota of each supplier, to filter the suppliers corresponding to the comprehensive matching score, and finally realize blind purchasing.

[0076] For example, the computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing preset functions, the instruction segments describing the execution process of the computer program in the blind-sight selection control device based on intelligent matching technology. For example, the computer program can be divided into an initialization module, a data acquisition module, a scoring module, a cost-effectiveness evaluation module, a dynamic allocation module, and a filtering module; the specific functions of each module are as follows: the initialization module is used to initialize the displayed information; wherein the displayed information only includes product standard library information, and the supplier's product information is hidden; the data acquisition module is used to acquire multi-dimensional procurement data in real time; the multi-dimensional procurement data includes supplier master data, product standard library data, and real-time procurement demand data; the scoring module is used to input the supplier's historical performance score data from the supplier master data into a pre-built multi-dimensional weighted scoring model. The system employs a performance evaluation module to obtain a performance score for each supplier, which measures the supplier's overall performance capability. A cost-effectiveness evaluation module calculates a cost-effectiveness index based on product standard library data and real-time procurement demand data, which measures the overall value of the product. A dynamic allocation module calculates the quota utilization rate of each supplier based on supplier master data, and obtains the dynamic allocation value of each supplier's contract group quota based on the quota utilization rate and performance score. A filtering module calculates a comprehensive matching score based on each supplier's performance score, cost-effectiveness index, and dynamic allocation value of the contract group quota, thereby filtering suppliers corresponding to the comprehensive matching score and ultimately achieving blind purchasing.

[0077] The blind-sight purchase control device based on intelligent matching technology can be a desktop computer, laptop, handheld computer, or cloud server, etc. The blind-sight purchase control device based on intelligent matching technology may include, but is not limited to, processors and memory. Those skilled in the art will understand that the above are examples of blind-sight purchase control devices based on intelligent matching technology and do not constitute a limitation on blind-sight purchase control devices based on intelligent matching technology. It may include more components than described above, or combine certain components, or use different components. For example, the blind-sight purchase control device based on intelligent matching technology may also include input / output devices, network access devices, buses, etc.

[0078] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or any conventional processor. This processor is the control center of the blind-sight selection control system based on intelligent matching technology, connecting all parts of the blind-sight selection control device based on intelligent matching technology through various interfaces and lines.

[0079] The memory can be used to store the computer program and / or modules. The processor implements various functions of the blind selection control device based on intelligent matching technology by running or executing the computer program and / or modules stored in the memory and calling the data stored in the memory.

[0080] The memory may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function (such as sound playback, image playback, etc.). The data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). Furthermore, the memory may include high-speed random access memory and non-volatile memory, such as hard disks, RAM, plug-in hard disks, smart media cards (SMC), secure digital cards (SD cards), flash cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0081] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the blind selection control method based on intelligent matching technology.

[0082] If the modules / units integrated in the blind selection control system based on intelligent matching technology are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.

[0083] Based on this understanding, the present invention can implement all or part of the processes in the above-mentioned blind selection control method based on intelligent matching technology, or it can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of the above-mentioned blind selection control method based on intelligent matching technology. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or a preset intermediate form, etc.

[0084] The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0085] It should be noted that the content contained in the computer-readable storage medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0086] The above embodiments are merely one of the implementation methods for achieving the technical solution of the present invention. The scope of protection claimed by the present invention is not limited to this embodiment, but also includes any variations, substitutions and other implementation methods that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention.

[0087] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A blind purchasing control method based on intelligent matching technology, characterized in that, include: The display information is initialized; wherein, the display information only includes product standard library information, and the supplier's product information is hidden; Real-time acquisition of multi-dimensional procurement data; the multi-dimensional procurement data includes supplier master data, product standard library data, and real-time procurement demand data; The supplier's historical performance score data in the supplier master data is input into a pre-built multi-dimensional weighted scoring model to obtain the performance score of each supplier, which is used to measure the supplier's overall performance capability. The cost-effectiveness index is calculated based on the product standard library data and real-time procurement demand data. The cost-effectiveness index is used to measure the overall value of the product. The quota utilization rate of each supplier is calculated based on the supplier master data, and the dynamic allocation value of the contract group quota of each supplier is obtained based on the quota utilization rate and performance score. Based on each supplier's performance score, cost-effectiveness index, and dynamic allocation value of contract group quota, a comprehensive matching score is calculated to screen suppliers corresponding to the comprehensive matching score, ultimately achieving blind purchasing.

2. The blind purchasing control method based on intelligent matching technology according to claim 1, characterized in that, In the real-time acquisition of multi-dimensional procurement data: The supplier master data includes historical performance rating data, benchmark prices for goods, and remaining quota for contract groups; The commodity standard library data includes the commodity's unified code, technical parameters, and quality weight coefficient; the quality weight coefficient is calculated based on quality inspection data. The real-time procurement demand data includes product codes, procurement quantities, and urgency level tags; the urgency level tags are classified as routine, emergency, or strategic reserves.

3. The blind purchasing control method based on intelligent matching technology according to claim 1, characterized in that, Before inputting the supplier's historical performance score data from the supplier master data into the pre-built multi-dimensional weighted scoring model to obtain the performance score for each supplier, the process also includes: Multi-dimensional procurement data is preprocessed, including normalization and outlier cleaning. The formula for normalization is: In the formula, The data is after normalization. X The original value, These are the maximum and minimum values ​​of the same indicator dataset, respectively. The filtering rules for outlier cleaning are as follows: If the delivery delay rate is greater than 30%, or the return rate is greater than 15%, the corresponding supplier data will be removed.

4. The blind purchasing control method based on intelligent matching technology according to claim 1, characterized in that, The step of inputting historical supplier performance score data from the supplier master data into a pre-built multi-dimensional weighted scoring model to obtain the performance score for each supplier includes: The supplier's historical performance score data from the supplier master data is input into a pre-built multi-dimensional weighted scoring model. The supplier's historical performance score data includes on-time delivery rate, quality score, and price fluctuation coefficient. The specific expression of the multi-dimensional weighted scoring model is as follows: Ssupplier=w1×DeliveryRate+w2×QualityScore+w3×PriceStability In the formula, Ssupplier represents the performance rating; DeliveryRate represents the on-time delivery rate; QualityScore represents the quality score; PriceStability represents the price fluctuation coefficient; and w1, w2, and w3 represent different weighting coefficients. The performance score for each supplier is calculated based on a multi-dimensional weighted scoring model.

5. The blind purchasing control method based on intelligent matching technology according to claim 1, characterized in that, The cost-effectiveness index, calculated based on commodity standard library data and real-time procurement demand data, includes: Based on real-time procurement demand data, match the required product's quality weight and brand weight from the product standard library data; The cost-performance index is calculated based on quality weight and brand weight, using the following formula: Vproduct=PriceQualityWeight×100+BrandWeight In the formula, Vproduct represents the cost-effectiveness index, PriceQualityWeight represents the quality weight, and BrandWeight represents the brand weight.

6. The blind purchasing control method based on intelligent matching technology according to claim 1, characterized in that, The process of calculating the credit limit utilization rate of each supplier based on supplier master data, and obtaining the dynamic allocation value of each supplier's contract group credit limit based on the credit limit utilization rate and performance score, includes: The quota utilization rate of each supplier is calculated based on the allocated quota and total contract quota in the supplier master data, using the following formula: Credit Utilization Rate = (Allocated Credit Limit / Total Contract Credit Limit) × 100% The dynamic allocation of contract group quotas for each supplier is determined based on quota utilization rate and performance score, according to the following rules: In the formula, Aalloc represents the dynamic allocation value of the contract group quota; U R This indicates the credit limit utilization rate; Ssupplier indicates the performance score.

7. The blind purchasing control method based on intelligent matching technology according to claim 1, characterized in that, The comprehensive matching score is calculated based on each supplier's performance score, cost-effectiveness index, and dynamic allocation value of contract group quota, including: Based on each supplier's performance score, cost-effectiveness index, and dynamic allocation value of contract group quota, a comprehensive matching score is calculated using the following formula: Mfinal=0.4×Ssupplier+0.3×Vproduct+0.3×Aalloc In the formula, Mfinal represents the comprehensive matching score, Ssupplier represents the performance score, Vproduct represents the cost-effectiveness index, and Aalloc represents the dynamic allocation value of the contract group quota.

8. The blind purchasing control method based on intelligent matching technology according to claim 7, characterized in that, If the urgency label in the real-time procurement demand data is "urgent," then the weight of the cost-effectiveness index will be reduced, while the weight of the dynamic allocation value of the contract group quota will be increased.

9. The blind purchasing control method based on intelligent matching technology according to claim 1, characterized in that, After selecting suppliers corresponding to the comprehensive matching score, the process also includes: A polling mechanism is used to automatically cancel contracts exceeding the limit based on a last-in-first-out (LIFO) approach. The specific operation is as follows: The contract group quota is polled at preset intervals; Cancel purchase orders in reverse chronological order of creation time until the credit limit is restored; The two-stage submission agreement is synchronized to the ERP system.

10. A blind purchasing control system based on intelligent matching technology, characterized in that, include: An initialization module is used to initialize the display information; wherein, the display information only includes product standard library information, and the supplier's product information is hidden; The data acquisition module is used to acquire multi-dimensional procurement data in real time; the multi-dimensional procurement data includes supplier master data, product standard library data, and real-time procurement demand data. The scoring module is used to input the supplier's historical performance score data from the supplier master data into a pre-built multi-dimensional weighted scoring model to obtain the performance score of each supplier. The performance score is used to measure the supplier's overall performance capability. The cost-effectiveness assessment module is used to calculate the cost-effectiveness index based on the product standard library data and real-time procurement demand data. The cost-effectiveness index is used to measure the overall value of the product. The dynamic allocation module is used to calculate the quota utilization rate of each supplier based on the supplier master data, and obtain the dynamic allocation value of the contract group quota of each supplier according to the quota utilization rate and performance score. The filtering module is used to calculate a comprehensive matching score based on each supplier's performance rating, cost-effectiveness index, and dynamic allocation value of contract group quota, so as to filter suppliers corresponding to the comprehensive matching score and ultimately achieve blind purchasing.

Images