Intelligent supplier extension management method based on technology stack and big data

Abstract

The invention relates to the technical field of supply chain management, in particular to an intelligent supplier extension management method based on a technology stack and big data. Comprising the following steps: S1, obtaining examination and approval data and delivery data of historical suppliers, and defining the examination and approval data and the delivery data as first examination and approval data and first delivery data; dividing the first approval data and the first delivery data into structured data and unstructured data according to a timeline; s2, based on the division result of the first examination and approval data, extracting examination and approval times and examination and approval interval time of an examination and approval department; and S3, based on the auditing times and the auditing interval time, utilizing an auditing efficiency evaluation formula to obtain an auditing efficiency evaluation value of the enterprise. The supplier approval and delivery data are integrated, the analysis efficiency is improved, the bottleneck is quantified and audited, the performance capability is dynamically evaluated, the management process is optimized, the full-process automatic management and control is realized, the cooperation efficiency and the decision scientificity are enhanced, and the efficient operation of the supply chain is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of supply chain management, and particularly to an intelligent supplier expansion management method based on a technology stack and big data. Background Art

[0002] In recent years, with the increasing complexity of enterprise supply chains, supplier expansion management has gradually become a core link in enterprise operations. However, traditional management models generally rely on manual operations and decentralized data management, resulting in increasingly prominent problems such as the lack of core data support for approval processes, long cross-departmental communication links, and difficulties in data traceability. In the existing technology, supplier admission, grading, and performance management mostly adopt offline or semi-automated processes, making it difficult to integrate and analyze multi-source heterogeneous data in real time, resulting in decision-making lags and low efficiency. In addition, the lack of unstructured data processing capabilities makes it impossible to fully exploit the potential value of historical data, further exacerbating management costs and risks. In response to the above pain points, there is an urgent need for an intelligent supplier management system that can penetrate the entire life cycle and is data-driven to achieve process automation, information transparency, and decision-making scientificization. Summary of the Invention

[0003] In order to overcome the disadvantages of low approval efficiency and difficult data traceability, the present invention provides an intelligent supplier expansion management method based on a technology stack and big data.

[0004] The technical implementation plan of the present invention is as follows: An intelligent supplier expansion management method based on a technology stack and big data, comprising the following steps: S1: Obtain the approval data and delivery data of historical suppliers, and define them as the first approval data and the first delivery data; divide the first approval data and the first delivery data into structured data and unstructured data according to the time line; S2: Based on the division result of the first approval data, extract the number of audits and the audit interval time of the audit department; S3: Based on the number of audits and the audit interval time, obtain the enterprise's audit efficiency evaluation value using the approval efficiency evaluation formula; based on the division result of the first delivery data, obtain the supplier credibility using the supplier credibility formula; S4: Based on the audit efficiency evaluation value and the supplier credibility, optimize the enterprise's audit process and screen new suppliers; based on the optimized enterprise audit process and the screened new suppliers, extract the approval data and delivery data of the new suppliers, and define them as the second approval data and the second delivery data; S5: Based on the number of audits and the audit interval time of the first approval data and the second approval data, determine the approval management process of the new suppliers; based on the variance ratio of the structured data and unstructured data of the first delivery data and the second delivery data, determine the expansion management process of the new suppliers.

[0005] Preferably, obtaining the approval data and delivery data of historical suppliers and defining them as first approval data and first delivery data includes: The approval data refers to static qualification information submitted by the supplier and independently reviewed by the enterprise; The delivery data refers to multi-dimensional information dynamically interacted between the supplier and the enterprise during the order fulfillment process.

[0006] Preferably, dividing the first approval data and the first delivery data into structured data and unstructured data according to the timeline includes: The structured data refers to standardized information with a unified format and capable of direct quantitative analysis; The unstructured data refers to multi-modal information with heterogeneous forms and requiring technical parsing; Obtain the review timeline of the first approval data, and divide the review data on the review timeline into structured data and unstructured data to obtain the division result of the review timeline; Obtain the delivery timeline of the first delivery data, and divide the delivery data on the delivery timeline into structured and unstructured data to obtain the division result of the delivery timeline.

[0007] Preferably, obtaining the review timeline of the first approval data, and dividing the review data on the review timeline into structured data and unstructured data to obtain the division result of the review timeline includes: The review timeline refers to the timeline from when the enterprise receives the review data submitted by the supplier to the completion of the review; On the review timeline, obtain the review department corresponding to the retrospective timeline, and extract the structured data and unstructured data of the review department to obtain the division result of the review timeline.

[0008] Preferably, based on the division result of the first approval data, extracting the review times and review interval times of the review department includes: Record the number of times the review department appears on the review timeline, and use each review process from start to end as a sub-review timeline to obtain several sub-review timelines; Based on the several sub-review timelines, extract the review times of the review department on the several sub-review timelines, and at the same time extract the review interval time of the same review department with the most appearances in adjacent sub-review timelines.

[0009] Preferably, obtaining the delivery timeline of the first delivery data, and dividing the delivery data on the delivery timeline into structured and unstructured data to obtain the division result of the delivery timeline includes: The delivery timeline refers to the timeline from when a supplier starts delivering an order to an enterprise until the delivery is completed; Obtain N delivery timelines, extract the delivery data of the same order on the N delivery timelines, divide the delivery data into structured data and unstructured data, record the change amounts of the structured data and unstructured data of the same order, and obtain the division result of the delivery timelines.

[0010] Preferably, based on the number of reviews and the review interval time, using the approval efficiency evaluation formula to obtain the enterprise's review efficiency evaluation value, including: The approval efficiency evaluation formula is as follows, where, is the review efficiency evaluation value, is the maximum number of repeated occurrences of the same review department in the th sub-review timeline, is the th sub-review timeline and the average review interval time of the same department in the previous process, is the industry benchmark interval time constant, is the total number of sub-review timelines.

[0011] Preferably, based on the division result of the first delivery data, using the supplier credibility formula to obtain the supplier credibility, including: The supplier credibility formula is as follows, where, is the supplier credibility value, ∈(0,1], is the variance of the structured data of the same order in N deliveries, is the change frequency of the unstructured data of the same order in N deliveries, 、 are penalty coefficients.

[0012] Preferably, based on the review efficiency evaluation value and the supplier credibility, optimize the enterprise review process and screen new suppliers; based on the optimized enterprise review process and the screened new suppliers, extract the approval data and delivery data of the new suppliers, and define them as the second approval data and the second delivery data, including: If the review efficiency evaluation value is greater than or equal to the preset review efficiency evaluation threshold, merge the duplicate review departments; If the review efficiency evaluation value is less than the preset review efficiency evaluation threshold, maintain the original review process; If the credibility of the said supplier is greater than or equal to the preset supplier credibility threshold, determine the new supplier as an extended supplier; based on the extended supplier, extract the approval data and delivery data of the extended supplier, and define them as the second approval data and the second delivery data; If the credibility of the said supplier is less than the preset supplier credibility threshold, re-screen the suppliers.

[0013] Preferably, determine the approval management process of the new supplier based on the review times and review interval times of the first approval data and the second approval data; determine the extended management process of the new supplier based on the variance ratio of the structured data and unstructured data of the first delivery data and the second delivery data, including: Determine the approval management process of the new supplier through the approval decision formula. The approval decision formula is as follows, where, is the approval decision value, is the maximum repeated review times of the same department in the th sub-review timeline of the second approval data, is the average review interval time of the second approval data, is the total number of sub-review timelines of the second approval data, is the maximum repeated review times of the same department in the th sub-review timeline of the first approval data, is the average review interval time of the first approval data, is the total number of sub-review timelines of the first approval data, is the adjustment factor; Determine the extended management process of the new supplier through the extended management formula. The extended management formula is as follows, where, is the extended management value, is the variance of the structured data of the second delivery data, is the change frequency of the unstructured data of the second delivery data, is the variance of the structured data of the first delivery data, is the change frequency of the unstructured data of the first delivery data.

[0014] Beneficial effects: By integrating the approval data and delivery data of historical suppliers, the present invention constructs a data management system for the entire life cycle, providing accurate data support for the extended management of suppliers; by dividing the approval data and delivery data into structured data and unstructured data according to the time line, the parsing efficiency and integration ability of multi-source heterogeneous data are significantly improved, effectively solving the problems of data islands and information fragmentation in the traditional mode; based on the calculation of the audit efficiency evaluation value based on the number of audits and the audit interval time, the efficiency bottleneck of the enterprise audit process can be quantified, providing a scientific basis for optimizing the configuration of the audit department and reducing redundant links; at the same time, the supplier credibility formula dynamically evaluates the supplier's performance ability by analyzing the structured variance and unstructured change frequency of the delivery data of the same order, enhancing the objectivity and reliability of the screening of new suppliers; by comparing the ratio of the approval management process and the delivery data variance of new and old suppliers, the dynamic adjustment and optimization of the extended management process are further realized, ensuring the flexibility and adaptability of the supplier extension decision; finally, based on the deep integration of the technology stack and big data, the solution realizes the full-process automatic control of supplier access, grading, and performance, greatly improving the cross-departmental collaboration efficiency and the scientific nature of business decisions, and providing a systematic technical guarantee for cost reduction, efficiency improvement, and risk prevention and control in supply chain management. Brief Description of the Drawings

[0015] Figure 1 It is a flowchart of the intelligent supplier extension management method based on the technology stack and big data of the present invention; Figure 2 It is a flowchart of the division process of the audit time line of the present invention; Figure 3 It is a flowchart of the division process of the delivery time line of the present invention. Detailed Embodiments

[0016] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0017] An intelligent supplier extension management method based on the technology stack and big data, as Figure 1 shown, includes the following steps: S1: Obtain the approval data and delivery data of historical suppliers, and define them as the first approval data and the first delivery data; divide the first approval data and the first delivery data into structured data and unstructured data according to the time line; S2: Based on the division result of the first approval data, extract the number of audits and the audit interval time of the audit department; S3: Based on the number of reviews and the review interval time, obtain the evaluation value of the enterprise's review efficiency using the approval efficiency evaluation formula; based on the division result of the first delivery data, obtain the supplier credibility using the supplier credibility formula. S4: Based on the evaluation value of the review efficiency and the supplier credibility, optimize the enterprise review process and screen new suppliers; based on the optimized enterprise review process and the screened new suppliers, extract the approval data and delivery data of the new suppliers, and define them as the second approval data and the second delivery data. S5: Based on the number of reviews and the review interval time of the first approval data and the second approval data, determine the approval management process of the new suppliers; based on the variance ratio of the structured data and unstructured data of the first delivery data and the second delivery data, determine the extended management process of the new suppliers.

[0018] Obtain the approval data and delivery data of historical suppliers, and define them as the first approval data and the first delivery data, including: The approval data refers to the static qualification information submitted by the supplier and independently reviewed by the enterprise. The delivery data refers to the multi-dimensional information dynamically generated by the interaction between the supplier and the enterprise during the order fulfillment process.

[0019] It should be noted that traditional supplier management relies on manual review and scattered data, making it difficult to integrate multi-source information, resulting in lagging decision-making and low efficiency; by structurally defining the approval and delivery data, a standardized analysis foundation is constructed to support the full-life cycle management.

[0020] Approval data: Reflects the qualification compliance of the supplier, and it is necessary to quantify the review efficiency and risk. Delivery data: Reflects the supplier's performance ability, and it is necessary to dynamically evaluate the quality and stability.

[0021] Approval data: Extract static qualification documents (such as business licenses and certification certificates) from the enterprise's ERP and SRM systems, and achieve automated collection through API interfaces or direct database connections. Delivery data: Through the order management system (OMS) and Internet of Things (IoT) devices, real-time capture the interaction records during order fulfillment (such as delivery timeliness, quality inspection reports, and logistics tracks), and combine natural language processing (NLP) to parse unstructured communication logs.

[0022] Example: A certain supplier submits an ISO certification (approval data), which is automatically archived and marked with the review time; during the delivery process of a certain supplier, the delivery delay rate (structured data) of a certain batch of products and the after-sales communication emails (unstructured data) are recorded in real time, and after integration, a supplier performance portrait is generated to provide a basis for subsequent expansion decisions.

[0023] The Hadoop data lake is used to centrally store multi-source heterogeneous data (such as qualification documents and delivery logs), and the Spark engine is used to perform batch analysis on structured data (review time, delivery timeliness). NLP and machine learning models (such as LSTM) are used to parse unstructured communication records in real time, extract risk features (such as high-frequency rejection keywords), and dynamically optimize review rules and supplier portraits.

[0024] The first approval data and the first delivery data are divided into structured data and unstructured data according to the timeline, including: The structured data refers to standardized information with a unified format and capable of direct quantitative analysis; The unstructured data refers to multimodal information that is heterogeneous in form and requires technical analysis; Obtaining the review timeline of the first approval data, dividing the review data on the review timeline into structured data and unstructured data, and obtaining a division result of the review timeline; The delivery timeline of the first delivery data is obtained, and the delivery data on the delivery timeline is divided into structured data and unstructured data to obtain a division result of the delivery timeline.

[0025] It should be noted that there are significant differences between structured data and unstructured data in terms of analysis dimensions and technical processing. Structured data is convenient for direct quantitative statistics and model training; unstructured data contains multimodal information such as semantics and images, which needs to be analyzed through natural language processing (NLP) or computer vision (CV). After division, data processing efficiency and depth can be optimized in a targeted manner.

[0026] Audit timeline: records the complete cycle from supplier qualification submission to audit completion, used to locate audit efficiency bottlenecks (such as repeated approval links); Delivery timeline: Tracks the entire process of an order from initiation to fulfillment, and is used to analyze delivery stability (such as delay frequency and abnormal fluctuations).

[0027] Based on the dynamic division of the timeline, data is deeply bound to business scenarios. For example, in the audit timeline, structured data (such as audit time and department turnover times) is used to quantify efficiency, and unstructured data (such as audit opinion text and attachment scans) is used to extract risk keywords through semantic analysis. In the delivery timeline, structured data (such as on-time delivery rate and quality inspection pass rate) is directly involved in the credibility calculation, and unstructured data (such as logistics communication records and abnormal feedback emails) is used to assist decision-making through sentiment analysis.

[0028] Example: In the audit timeline of a certain supplier, the structured data includes "the qualification audit took 3 days and was transferred through 2 departments", and the unstructured data is the environmental protection certification PDF file submitted by a certain supplier (which requires OCR parsing); in the delivery timeline, the structured data is "the delivery delay rate of order A is 5%", and the unstructured data is the email from the supplier regarding logistics anomalies (which requires NLP to extract key reasons); after combining the two, the compliance risks and performance capabilities of the supplier can be accurately evaluated, providing multi-dimensional basis for expansion decisions.

[0029] Obtain the audit timeline of the first approval data, divide the audit data on the audit timeline into structured data and unstructured data, and obtain the division result of the audit timeline, including: The audit timeline refers to the timeline from when the enterprise submits audit data by the supplier to the completion of the audit; On the audit timeline, obtain the audit departments corresponding to the retrospective timeline, extract the structured data and unstructured data of the audit departments, and obtain the division result of the audit timeline.

[0030] It should be noted that as Figure 2 shown, the retrospective timeline: refers to the abnormal path in the approval process where the process is rolled back to a previous node due to failed audit or incomplete information; for example, the normal process should be "submission → preliminary review → final review", but actually due to the rejection in the preliminary review, "submission → preliminary review → submission → preliminary review → final review" is repeatedly executed, forming redundant links.

[0031] By tracking such rollback paths, extract the structured data (such as the number of rollbacks and time consumption) and unstructured data (such as the rejection reason text) of the repeated nodes, identify the process bottlenecks (such as the departments with high-frequency rejections), and provide a basis for merging or optimizing redundant steps.

[0032] Example: During the audit of a certain supplier, the preliminary review was rejected twice due to "incomplete environmental protection qualifications", and the retrospective timeline shows "submission → preliminary review (rejected) → submission → preliminary review (passed) → final review"; the structured data statistics show that the repeated time consumption of the preliminary review is 3 days, and the unstructured data is parsed from the rejection opinion PDF, and it is found that the ISO certificate is missing; after optimizing the pre-audit rules accordingly, the process is shortened to "submission → final review", forming a synergistic effect with the optimization of the aforementioned delivery data.

[0033] Based on the division result of the first approval data, extract the number of audits and the audit interval time of the audit departments, including: Record the number of occurrences of the audit departments on the audit timeline, and use each start to end of the approval process as a sub-audit timeline to obtain several sub-audit timelines; Based on the several sub-audit timelines, extract the number of audits of the audit departments on the several sub-audit timelines, and at the same time extract the audit interval of the same audit department with the most occurrences in adjacent sub-audit timelines.

[0034] It should be noted that: Sub-audit timeline: refers to two consecutive independent audit cycles in chronological order (for example, the first process is "submission → preliminary review → rejection", and the second process is "submission → preliminary review → final review").

[0035] Audit count extraction: Count the total number of participations of each audit department in all sub-audit timelines (for example: the preliminary review department appears 3 times in 5 processes).

[0036] Audit interval extraction: High-frequency department screening: For each pair of adjacent sub-audit timelines, count the number of occurrences of each department (for example: the preliminary review department appears 2 times in adjacent processes), and select the department with the most occurrences; Interval calculation: Extract the last audit timestamp of the selected department in adjacent processes, and calculate the time difference (for example, the preliminary review time of the first process is Day 1, and the preliminary review time of the second process is Day 3, and the interval is 2 days); Tie handling: If the number of occurrences of departments is the same, give priority to the department that appears first in the process.

[0037] Example: A certain supplier experienced two sub-audit timelines due to incomplete qualifications. After merging the preliminary review and final review rules, the audit count decreased from 2 times to 1 time, and the interval time was cleared.

[0038] Obtain the delivery timeline of the first delivery data, divide the delivery data on the delivery timeline into structured and unstructured data, and obtain the division result of the delivery timeline, including: The delivery timeline refers to the timeline from when the supplier starts to deliver an order to the enterprise until the delivery is completed; Obtain N delivery timelines, extract the delivery data of the same order on the N delivery timelines, divide the delivery data into structured data and unstructured data, record the change amounts of the structured data and unstructured data of the same order, and obtain the division result of the delivery timeline.

[0039] It should be noted that, as Figure 3 shown, the division of the delivery timeline aims to quantify the stability and abnormal fluctuations of the supplier's performance behavior by tracking the complete cycle of the order from start to finish; structured data (such as delivery timeliness, quality inspection pass rate) can directly participate in model calculations, while unstructured data (such as logistics communication records, abnormal feedback texts) need to parse semantic and image information with the help of NLP or OCR. The combination of the two can comprehensively evaluate the delivery quality and potential risks.

[0040] Example illustration: In the delivery timeline of order A from a certain supplier, the structured data shows that the "delivery delay rate is 5%", and the unstructured data is an abnormal description email from the logistics company (the keyword "weather reason" needs to be parsed); combining with the preliminary review rules for optimizing the review process in the previous example, it is found that the frequent delivery anomalies of this supplier are due to lax prequalification. After strengthening the prequalification link, the subsequent order delay rate of this supplier has dropped to 2%, achieving the closed-loop optimization of review and delivery data.

[0041] Based on the number of reviews and the review interval time, the review efficiency evaluation value of the enterprise is obtained using the approval efficiency evaluation formula, including: The approval efficiency evaluation formula is as follows. Among them, is the review efficiency evaluation value. is the maximum number of repeated occurrences of the same review department in the th sub-review timeline. is the average review interval time between the th sub-review timeline and the same department in the previous process. is the industry benchmark interval time constant. is the total number of sub-review timelines.

[0042] It should be noted that the approval efficiency evaluation formula reflects the review efficiency of the enterprise by quantifying the repeatability and time delay in the review process. : The maximum number of repeated reviews of the same department in the th sub-process (for example, the preliminary review is triggered 2 times). : The average interval time of this department between adjacent sub-processes (for example, the interval between two preliminary reviews is 1 day). : The industry benchmark interval time (for example, the industry standard is 1 day). : The total number of sub-processes.

[0043] The higher the number of repetitions ( ), the lower the efficiency; the longer the interval time ( ), the greater the efficiency loss; the natural logarithm ln is used to weaken the influence of extreme values and ensure calculation stability.

[0044] Example: Suppose in 3 sub-processes of an enterprise, the of department A are 2, 1, and 3 times respectively, are 2, 1, and 3 days respectively, = 1 day; the calculated result is: = 2ln(3) + 1ln(2) + 3ln(4) ≈ 7.05; if the industry high-efficiency threshold is < 5, the current value of 7.05 indicates that optimization is needed: then reduce the repeated reviews: combine the preliminary review and final review rules, and make Reduce to 1; and shorten the interval time: Through automated approval, make approach .

[0045] Based on the division result of the first delivery data, obtain the supplier credibility using the supplier credibility formula, including: The supplier credibility formula is as follows, where, is the supplier credibility value, ∈(0,1], is the variance of structured data in N deliveries of the same order, is the change frequency of unstructured data in N deliveries of the same order, , are the penalty coefficients.

[0046] It should be noted that the supplier credibility formula evaluates the reliability of supplier performance by quantifying the stability and change frequency of delivery data, (Variance of structured data): Acquisition method: For N deliveries of the same order, extract structured metrics (such as delivery timeliness, quality inspection pass rate), and calculate the variance. For example, for an order with 3 delivery times of 10 days, 12 days, and 11 days respectively, the average is 11 days, and the variance = . (Change frequency of unstructured data): Acquisition method: Count the number of modifications or content change frequency of unstructured data (such as logistics communication records, exception description emails) per unit time during the delivery process of the same order. For example, if the logistics record has changed 2 times due to "weather reasons" and "equipment failures", then =2; , : Penalty coefficients, set according to business requirements (such as =0.5, =0.3), used to adjust the influence weights of the two types of data on credibility; in the formula, (Variance of structured data) and (Change frequency of unstructured data) are standardized (such as normalization or z-score), and the balance of influence is achieved through the penalty coefficients , .

[0047] Example calculation: A certain supplier has completed 3 deliveries, =0.67, =2, substitute into the formula: =1 / 1.935≈0.517, credibility ∈(0,1], the closer the value is to 1, the more reliable it is; in this example, 0.517 indicates that the delivery stability needs to be optimized (reduce ), and reduce changes (reduce ).

[0048] It should be noted that to achieve the dynamic optimization of the above review process (such as merging redundant review departments), the Flowable workflow engine is adopted to build an automated approval process based on the BPMN2.0 standard: Visual modeling: Map the qualification review and cross-department transfer nodes into configurable processes (such as "preliminary review → final review"), and support drag-and-drop adjustment (such as merging the preliminary review and final review nodes); Automated event triggering: The process nodes automatically execute operations (such as notifying the final review department after the preliminary review is passed and sending an email reminder when rejected), reducing manual intervention; Full-link traceability: Through distributed transaction management (Seata) and event sourcing, record logs such as the reason for rejection and review time consumption, and support process bottleneck analysis (such as departments with high-frequency rejections); Quality verification and monitoring: Embed a rule engine (such as qualification integrity check) in the node, and monitor the node time consumption in real time through Prometheus, and trigger an alarm when an exception occurs (such as review timeout).

[0049] Based on the review efficiency evaluation value and the supplier credibility, optimize the enterprise review process and screen new suppliers; based on the optimized enterprise review process and the screened new suppliers, extract the approval data and delivery data of the new suppliers, and define them as the second approval data and the second delivery data, including: If the review efficiency evaluation value is greater than or equal to the preset review efficiency evaluation threshold, merge duplicate review departments; If the review efficiency evaluation value is less than the preset review efficiency evaluation threshold, maintain the original review process; If the supplier credibility is greater than or equal to the preset supplier credibility threshold, determine the new supplier as an extended supplier; based on the extended supplier, extract the approval data and delivery data of the extended supplier, and define them as the second approval data and the second delivery data; If the supplier credibility is less than the preset supplier credibility threshold, re-screen the suppliers.

[0050] It should be noted that for the threshold setting method, the review efficiency evaluation threshold: Based on historical data or industry benchmarks, by statistically calculating the average efficiency value of the enterprise's past efficient review processes (such as =5), combined with the business tolerance (such as allowing 20% redundancy) to set the threshold (such as =6). The supplier credibility threshold: According to the lowest reliable level of historical cooperative suppliers (such as ≥0.7), or obtained by reverse-inferring the characteristics of high-quality suppliers through a machine learning model (e.g., with 0.65 as the dividing line).

[0051] Dynamically trigger process optimization and supplier screening through thresholds; when the audit efficiency value exceeds the standard, merge duplicate departments to shorten the cycle; when the credibility meets the standard, lock in high-quality suppliers and collect high-quality supplier data (second data) to form a closed-loop feedback.

[0052] Example illustration: An enterprise sets = 6, and the audit efficiency value of a certain supplier = 7.05 (calculated value in the previous example), triggering the merger of the preliminary and final audit departments. After optimization, drops to 4.2; at the same time, the credibility of this supplier = 0.517 (below the threshold of 0.65), and it is automatically excluded and re-screened; the credibility of the new supplier B = 0.82, and it is included in the extended suppliers. The approval and delivery data of the new supplier B are defined as the second data for subsequent process iteration.

[0053] Based on the number of audits and the audit interval time of the first approval data and the second approval data, determine the approval management process for new suppliers; based on the variance ratio of the structured data and unstructured data of the first delivery data and the second delivery data, determine the extended management process for new suppliers, including: Determine the approval management process for new suppliers through an approval decision formula. The approval decision formula is as follows,[[]] where is the approval decision value, is the maximum number of repeated audits of the same department in the th sub-audit timeline of the second approval data, is the average audit interval time of the second approval data, is the total number of sub-audit timelines of the second approval data, is the maximum number of repeated audits of the same department in the th sub-audit timeline of the first approval data, is the average audit interval time of the first approval data, is the total number of sub-audit timelines of the first approval data, is the adjustment factor; It should be noted that the approval decision formula quantifies the optimization degree of the new process by comparing the audit efficiency differences between new and old suppliers, : the ratio of the number of repeated audits of new and old suppliers. The smaller the ratio, the lower the redundancy of the new process; : the ratio of the average audit interval times of new and old. The smaller the ratio, the higher the timeliness of the new process; : A regulatory factor used to control decision-making sensitivity (e.g., When = 0.1, it emphasizes efficiency, When = 0.2, it emphasizes stability).

[0054] Decision-making logic: →1 (close to 1): Indicates that the new process has few repeated reviews and short time, and can be adopted; →0 (close to 0): Indicates that the efficiency of the new process has not been improved and needs to be adjusted.

[0055] Example: Old supplier data: = 10, = 5 days; New supplier data: = 8, = 4 days; Take = 0.1, calculate to get: ≈0.852, because > 0.7 (preset threshold), determine that the new process is efficient and determine it as the standard approval management process.

[0056] Determine the extended management process of the new supplier through the extended management formula. The extended management formula is as follows, Among them, is the extended management value, is the variance of the structured data of the second delivery data, is the change frequency of the unstructured data of the second delivery data, is the variance of the structured data of the first delivery data, is the change frequency of the unstructured data of the first delivery data.

[0057] It should be noted that the extended management formula quantifies the improvement degree of the reliability of the new supplier by comparing the delivery stability differences between the old and new suppliers. 、 : The structured variance and unstructured change frequency of the old supplier represent historical delivery volatility; 、 : The corresponding values of the new supplier reflect the performance stability of the new supplier; : The compressed volatility ratio difference to avoid the influence of extreme values and ensure the robustness of the result; and are greater than or equal to 0; In the extended management formula, 、 、 and have been processed by maximum-minimum normalization to ensure that the value range is [0,1] to eliminate the influence of dimension differences on volatility comparison.

[0058] Decision Logic: The larger it is: the ratio of new to old fluctuations approaches 0, indicating that the stability of the new supplier is significantly better than the historical level and cooperation can be expanded; The smaller it is: the ratio of new to old fluctuations is greater than the preset fluctuation ratio threshold, indicating that the new supplier fails to meet expectations and the management process needs to be adjusted.

[0059] Example: Old supplier data: = 2.5, = 3; New supplier data: = 1.2, = 1; Calculated: = 1 / ln(1.4) ≈ 2.47. If the threshold is set to > 2, it is determined that the stability of the new supplier meets the standard, the new supplier is identified as an expanding supplier, and the optimized management process (such as shortening the delivery cycle) is adopted.

[0060] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A smart supplier extension management method based on technology stack and big data, characterized in that It includes the following steps: S1: Obtain the approval data and delivery data of historical suppliers, and define them as the first approval data and the first delivery data; Divide the first approval data and the first delivery data into structured data and unstructured data according to the time line; S2: Based on the division result of the first approval data, extract the number of reviews and the review interval time of the review department; S3: Based on the number of reviews and the review interval time, obtain the review efficiency evaluation value of the enterprise by using the approval efficiency evaluation formula; Based on the division result of the first delivery data, obtain the supplier credibility by using the supplier credibility formula; S4: Based on the review efficiency evaluation value and the supplier credibility, optimize the enterprise review process and screen new suppliers; Based on the optimized enterprise review process and the screened new suppliers, extract the approval data and delivery data of the new suppliers, and define them as the second approval data and the second delivery data; S5: Based on the number of reviews and the review interval time of the first approval data and the second approval data, determine the approval management process of the new suppliers; Based on the variance ratio of the structured data and unstructured data of the first delivery data and the second delivery data, determine the extended management process of the new suppliers.

2. The intelligent supplier extension management method based on technology stack and big data according to claim 1, characterized in that, The obtaining of the approval data and delivery data of historical suppliers and defining them as the first approval data and the first delivery data includes: The approval data refers to the static qualification information submitted by the supplier and independently reviewed by the enterprise; The delivery data refers to the multi-dimensional information dynamically interacted between the supplier and the enterprise during the order fulfillment process.

3. The intelligent supplier extension management method based on technology stack and big data according to claim 1, characterized in that, The dividing of the first approval data and the first delivery data into structured data and unstructured data according to the time line includes: The structured data refers to the standardized information with a unified format and capable of direct quantitative analysis; The unstructured data refers to the multi-modal information with heterogeneous forms and requiring technical parsing; Obtain the review time line of the first approval data, divide the review data on the review time line into structured data and unstructured data, and obtain the division result of the review time line; Obtain the delivery time line of the first delivery data, divide the delivery data on the delivery time line into structured and unstructured data, and obtain the division result of the delivery time line.

4. A method for intelligent supplier extension management based on technology stack and big data according to claim 3, characterized in that, The obtaining of the review time line of the first approval data, dividing the review data on the review time line into structured data and unstructured data, and obtaining the division result of the review time line includes: The review time line refers to the time line from when the enterprise receives the review data submitted by the supplier to the completion of the review; On the review time line, obtain the review department corresponding to the retrospective time line, and extract the structured data and unstructured data of the review department to obtain the division result of the review time line.

5. A method for intelligent supplier extension management based on technology stack and big data according to claim 1, characterized in that, The extracting of the number of reviews and the review interval time of the review department based on the division result of the first approval data includes: Record the number of times the review department appears on the review time line, and take each review process from start to end as a sub-review time line to obtain several sub-review time lines; Based on the several sub-audit timelines, extract the number of audits of the audit departments on the several sub-audit timelines, and at the same time extract the audit interval time of the same audit department with the most occurrences in adjacent sub-audit timelines.

6. The intelligent supplier expansion management method based on technology stack and big data according to claim 3, characterized in that, Obtain the delivery timeline of the first delivery data, divide the delivery data on the delivery timeline into structured and unstructured data, and obtain the division result of the delivery timeline, including: The delivery timeline refers to the timeline from when the supplier starts to deliver an order to the enterprise until the delivery is completed; Obtain N delivery timelines, extract the delivery data of the same order on the N delivery timelines, divide the delivery data into structured data and unstructured data, record the change amounts of the structured data and unstructured data of the same order, and obtain the division result of the delivery timeline.

7. A method for intelligent supplier extension management based on technology stack and big data according to claim 1, characterized in that Based on the number of audits and the audit interval time, use the approval efficiency evaluation formula to obtain the enterprise's approval efficiency evaluation value, including: The approval efficiency evaluation formula is as follows, Among them, is the audit efficiency evaluation value, is the maximum number of repeated occurrences of the same audit department in the th sub-audit timeline, is the average audit interval time between the th sub-audit timeline and the same department in the previous process, is the industry benchmark interval time constant, is the total number of sub-audit timelines.

8. A method for intelligent supplier extension management based on technology stack and big data according to claim 1, characterized in that, Based on the division result of the first delivery data, use the supplier credibility formula to obtain the supplier credibility, including: The supplier credibility formula is as follows, Among them, is the supplier credibility value, ∈(0,1], is the variance of structured data in N deliveries of the same order, is the change frequency of unstructured data in N deliveries of the same order, and is the penalty coefficient.

9. The intelligent supplier extension management method based on technology stack and big data according to claim 1, characterized in that Based on the approval efficiency evaluation value and the supplier credibility, optimize the enterprise audit process and screen new suppliers; Based on the optimized enterprise audit process and the screened new suppliers, extract the approval data and delivery data of the new suppliers, and define them as the second approval data and the second delivery data, including: If the approval efficiency evaluation value is greater than or equal to the preset approval efficiency evaluation threshold, merge duplicate audit departments; If the approval efficiency evaluation value is less than the preset approval efficiency evaluation threshold, maintain the original audit process; If the supplier credibility is greater than or equal to the preset supplier credibility threshold, determine the new supplier as an extended supplier; Based on the extended supplier, extract the approval data and delivery data of the extended supplier, and define them as the second approval data and the second delivery data; If the supplier credibility is less than the preset supplier credibility threshold, re-screen the suppliers.

10. A method for intelligent supplier extension management based on technology stack and big data according to claim 1, characterized in that Based on the number of audits and the audit interval time of the first approval data and the second approval data, determine the approval management process of the new supplier; Based on the variance ratio of the structured data and unstructured data of the first delivery data and the second delivery data, determine the extended management process of the new supplier, including: Determine the approval management process of the new supplier through the approval decision formula, and the approval decision formula is as follows, Among them, is the approval decision value, is the maximum number of repeated reviews by the same department in the th sub-review timeline of the second approval data, is the average review interval time of the second approval data, is the total number of sub-review timelines of the second approval data, is the maximum number of repeated reviews by the same department in the th sub-review timeline of the first approval data, is the average review interval time of the first approval data, is the total number of sub-review timelines of the first approval data, is the adjustment factor; Determine the extended management process of the new supplier through the extended management formula, and the extended management formula is as follows, Among them, is the extended management value, is the variance of the structured data of the second delivery data, is the change frequency of the unstructured data of the second delivery data, is the variance of the structured data of the first delivery data, is the change frequency of the unstructured data of the first delivery data.

Images