Enterprise order purchase management method and system

Abstract

The invention provides an enterprise order purchase management method and system, and relates to the technical field of purchase management. Performance state feedback information corresponding to a purchase order is acquired; performing multi-dimensional alignment analysis on the performance state feedback information, generating performance efficiency boundaries of different purchase material types, and constructing purchase constraint rules of order purchase in each execution stage according to the performance efficiency boundaries and the user sign-in data; performing anomaly detection on a keyword extraction strategy during purchase demand identification to obtain a matching deviation situation of the purchase demand in supply chain matching, performing hierarchical verification on resources of suppliers based on the matching deviation situation and delivery sign-in data, and generating supply recommendation rules of hierarchical suppliers; and generating a target order corresponding to the purchase demand in the supply chain according to the purchase constraint rule and the purchase recommendation rule. According to the application, the performance state can be dynamically monitored and suppliers can be recommended in a graded manner under the supply chain collaboration platform, so that the precision of supply chain matching in the purchasing process is improved.

Description

Technical Field

[0001] The present application relates to the technical field of procurement management, and more specifically, to an enterprise order procurement management method and system. Background Art

[0002] Procurement management is an important part of enterprise supply chain management, involving the entire process from procurement demand identification to order fulfillment. Its core goal is to ensure that enterprises can obtain the required materials or services from reliable suppliers at the right time and at a reasonable cost, thereby ensuring the continuity of production and operations. Modern procurement management gradually introduces technologies such as big data, artificial intelligence, and blockchain to achieve intelligent and automated procurement decisions. In the face of market demand fluctuations, the procurement management system needs to have capabilities such as real-time analysis, flexible matching, and intelligent scheduling to enhance the adaptability and resilience of the supply chain, reduce procurement risks, and improve overall operational efficiency.

[0003] However, the existing enterprise order procurement management methods and systems lack real-time collection of supplier shipping data and user receipt data and performance status feedback, making it difficult to accurately monitor the performance progress during the procurement process, resulting in information lags, untimely identification of anomalies, and inaccurate evaluation of supplier performance capabilities during procurement order execution, thereby increasing supply chain uncertainty and procurement risks. Therefore, how to dynamically monitor the performance status and grade supplier recommendations under the supply chain collaboration platform to improve the accuracy of supply chain matching in the procurement process is a problem faced by the industry. Summary of the invention

[0004] The present application provides an enterprise order procurement management method and system, which can dynamically monitor the fulfillment status and make graded recommendations on suppliers under a supply chain collaboration platform to improve the accuracy of supply chain matching in the procurement process.

[0005] In a first aspect, the present application provides an enterprise order procurement management method, the procurement management method comprising the following steps: Collect supplier's shipping data and user's receipt data from the supply chain collaboration platform, and obtain the fulfillment status feedback information corresponding to the purchase order in real time; In order procurement management, the fulfillment status feedback information is subjected to multi-dimensional alignment analysis to generate the fulfillment efficiency boundary of different procurement material types, and the procurement constraint rules of order procurement at each execution stage are constructed according to the fulfillment efficiency boundary and the user receipt data; Perform anomaly detection on the keyword extraction strategy during procurement demand identification to obtain the matching deviation situation of procurement demand in supply chain matching, perform hierarchical verification on supplier resources based on the matching deviation situation and the shipment receipt data, and generate supply recommendation rules for hierarchical suppliers; A target order corresponding to the procurement demand in the supply chain is generated according to the procurement constraint rule and the procurement recommendation rule.

[0006] In this embodiment, in order procurement management, the fulfillment status feedback information is subjected to multi-dimensional alignment analysis to generate fulfillment efficiency boundaries of different procurement material types, specifically including: Determining the supplier's supply response strength when supplying the order based on the fulfillment status feedback information; Perform multi-dimensional feature extraction on the supply response intensity to obtain dynamic coupling information of different types of purchased materials; Constructing a performance performance gradient for different types of purchased materials according to the dynamic coupling information; The performance performance gradient is used to determine the performance performance boundaries of different types of purchased materials.

[0007] In this embodiment, constructing procurement constraint rules for order procurement at each execution stage according to the performance performance boundary and the user receipt data specifically includes: Determine the dynamic correlation deviation when purchasing an order based on the performance boundary and the user receipt data; generating performance risk characteristics at different procurement stages according to the dynamic correlation deviation; The procurement constraint rules for order procurement at each execution stage are determined by the performance risk characteristics.

[0008] In this embodiment, the procurement constraint rules refer to the control conditions for successful performance of the contract in different procurement execution stages.

[0009] In this embodiment, anomaly detection is performed on the keyword extraction strategy during procurement demand identification to obtain the matching deviation situation of procurement demand in supply chain matching, which specifically includes: Obtain keyword extraction strategies for purchasing demand identification; Extracting the matching evolution path of procurement demand in supply chain matching from the keyword extraction strategy; Determining a deviation level map of procurement demand in supply chain matching according to the matching evolution path; Obtain the responsiveness characteristics of supply chain nodes; The matching deviation situation of the procurement demand in the supply chain matching is determined according to the deviation level map and the response capability characteristics.

[0010] In this embodiment, the matching deviation situation refers to the matching deviation status of procurement demand in each link of the supply chain.

[0011] In this embodiment, based on the matching deviation situation and the shipment receipt data, the supplier's resources are graded and verified, and the supply recommendation rules for graded suppliers are generated, which specifically include: Extracting collaborative supply parameters for resource matching of tiered suppliers based on the matching deviation situation and the shipment receipt data; Determining the quality fluctuation compensation amount of the supplier during cross-cycle delivery according to the collaborative supply parameters; Determine the resource adaptation confidence interval of the graded supplier through the quality fluctuation compensation amount; A modified scheduling level for the tiered suppliers is determined based on the resource adaptation confidence interval.

[0012] In this embodiment, the modified scheduling level refers to a scheduling strategy for adjusting the supplier's delivery plan at each node in the supply chain.

[0013] In this embodiment, generating a target order corresponding to a procurement demand in a supply chain according to the procurement constraint rule and the procurement recommendation rule specifically includes: Determine the elastic matching path corresponding to the procurement demand in the supply chain according to the procurement constraint rule and the procurement recommendation rule; Generate a candidate order set for demand matching by combining the elastic matching path with real-time supply chain disturbance parameters; The target order corresponding to the procurement demand in the supply chain is determined according to the candidate order set.

[0014] In a second aspect, the present application provides an enterprise order procurement management system for executing an enterprise order procurement management method, the procurement management system comprising: The data acquisition module is used to collect the supplier's shipping data and user receipt data from the supply chain collaboration platform, and obtain the fulfillment status feedback information corresponding to the purchase order in real time; An information analysis module is used to perform multi-dimensional alignment analysis on the fulfillment status feedback information in order procurement management, generate fulfillment efficiency boundaries for different types of purchased materials, and construct procurement constraint rules for order procurement at each execution stage based on the fulfillment efficiency boundaries and the user receipt data; A hierarchical verification module is used to perform anomaly detection on the keyword extraction strategy during the identification of procurement requirements, obtain the matching deviation situation of procurement requirements in the supply chain matching, perform hierarchical verification on the supplier's resources based on the matching deviation situation and the shipment receipt data, and generate supply recommendation rules for hierarchical suppliers; An order generation module is used to generate a target order corresponding to the procurement demand in the supply chain according to the procurement constraint rules and the procurement recommendation rules.

[0015] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects: The supplier's shipping data and user receipt data are collected from the supply chain collaboration platform, and the fulfillment status feedback information corresponding to the purchase order is obtained in real time; in order procurement management, the fulfillment status feedback information is subjected to multi-dimensional alignment analysis to generate the fulfillment performance boundary of different types of procurement materials, and the procurement constraint rules of order procurement in each execution stage are constructed according to the fulfillment performance boundary and the user receipt data; anomaly detection is performed on the keyword extraction strategy during procurement demand identification to obtain the matching deviation situation of procurement demand in supply chain matching, and the supplier's resources are graded and verified based on the matching deviation situation and the shipping receipt data to generate supply recommendation rules for graded suppliers; target orders corresponding to procurement demands in the supply chain are generated according to the procurement constraint rules and the procurement recommendation rules.

[0016] It can be seen that in this application, the intelligence level of the procurement process and the closed-loop optimization capability of fulfillment management can be improved; among them, real-time monitoring of the supply chain fulfillment process is realized, the accuracy and timeliness of the data are guaranteed, the visualization capability of procurement management for supplier shipment, logistics distribution and user receipt is improved, and the fulfillment risk caused by information lag is reduced; by multi-dimensional analysis of the fulfillment data, the fulfillment efficiency boundary of different purchased materials is formed, and based on this, the constraint rules of the procurement execution stage are constructed, so that procurement can accurately identify the matching degree between procurement demand and supplier fulfillment capability through keyword extraction anomaly detection and matching deviation analysis, optimize the supplier grading strategy, improve the scientific nature of supplier resource management, and reduce the procurement failure rate caused by supply chain matching deviation. The process is more precise and standardized, the executability of the procurement plan is improved, and the probability of fulfillment anomalies is reduced; combined with intelligent procurement constraints and supplier recommendation rules, automatic optimization configuration of orders is realized, the matching accuracy of procurement demand and supply chain resources is improved, the procurement cycle is optimized, and the fulfillment success rate is improved, thereby reducing procurement costs and improving the overall efficiency of the supply chain.

[0017] To sum up, the technical solution adopted in this application can dynamically monitor the fulfillment status and make graded recommendations on suppliers under the supply chain collaboration platform to improve the accuracy of supply chain matching in the procurement process. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0019] Figure 1 It is a flow chart of the enterprise order procurement management method provided by this application; Figure 2It is a schematic diagram of the process of determining the performance efficiency boundary according to this application; Figure 3 is a schematic diagram of a flow chart for determining supply recommendation rules provided in accordance with the present application; Figure 4 It is a module structure diagram of the enterprise order procurement management system provided according to this application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] The embodiment of the present application provides an enterprise order procurement management method and system, the core of which is to collect the supplier's shipping data and user receipt data from the supply chain collaboration platform, and obtain the fulfillment status feedback information corresponding to the purchase order in real time; in the order procurement management, the fulfillment status feedback information is subjected to multi-dimensional alignment analysis to generate the fulfillment performance boundary of different types of procurement materials, and the procurement constraint rules of the order procurement in each execution stage are constructed according to the fulfillment performance boundary and the user receipt data; the keyword extraction strategy during the procurement demand identification is subjected to anomaly detection to obtain the matching deviation situation of the procurement demand in the supply chain matching, and the supplier's resources are graded and verified based on the matching deviation situation and the shipment receipt data to generate the supply recommendation rules of the graded suppliers; the target order corresponding to the procurement demand in the supply chain is generated according to the procurement constraint rules and the procurement recommendation rules.

[0022] Embodiment 1: In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 As shown, this figure is an exemplary flow chart of the enterprise order procurement management method shown in this embodiment of the present application, and the procurement management method includes the following steps: In step S1, the supplier's shipping data and user's receipt data are collected from the supply chain collaboration platform, and the fulfillment status feedback information corresponding to the purchase order is obtained in real time.

[0023] In the specific implementation, first, through the API interface of the supply chain collaboration platform, obtain the shipping order and logistics information uploaded by the supplier, use the message queue, such as Kafka for real-time streaming, and use Airflow for data cleaning and storage in the distributed database, and obtain the supplier's shipping data by reading the distributed database; use OCR to identify the receipt, RFID to scan the goods or IOT equipment to collect the receipt time and quality inspection status, and then use NLP tools, such as BERT to parse the receipt feedback information, such as "material damage", and use the receipt feedback information as the user receipt data. In other embodiments, other methods can also be used to collect the supplier's shipping data and user receipt data, which are not limited here. Then, through the supply chain collaboration platform and the logistics service provider interface, collect transportation information, including shipment, in transit, delivery, receipt and other status, and then use electronic data exchange to receive the performance progress provided by the supplier, such as production completion, quality inspection qualified, warehouse delivery, etc., and then parse the performance evaluation (such as delay, damage) of the receipt, email, and customer service system, and use the parsed results as the performance status feedback information corresponding to the purchase order.

[0024] It should be noted that in this application, the shipping data refers to the material shipment information provided by the supplier during the order fulfillment process, including time, location, list of items, and mode of transportation; the user receipt data refers to the receipt time, acceptance status, quality inspection results and feedback information recorded when the user receives the materials; the fulfillment status feedback information refers to the status update of the purchase order at each stage of the fulfillment process, including shipment, transportation, receipt, quality inspection and abnormal situations.

[0025] In step S2, in order procurement management, a multi-dimensional alignment analysis is performed on the fulfillment status feedback information to generate fulfillment performance boundaries for different types of procurement materials, and procurement constraint rules for order procurement at each execution stage are constructed based on the fulfillment performance boundaries and the user receipt data.

[0026] Preferably, in this embodiment, in order procurement management, the fulfillment status feedback information is subjected to multi-dimensional alignment analysis to generate fulfillment efficiency boundaries of different procurement material types, with reference to Figure 2 As shown, this figure is a schematic diagram of the process of determining the performance efficiency boundary in some embodiments of the present application. In this embodiment, the performance efficiency boundary can be determined by the following steps: In step S21, the supply response strength of the supplier when supplying the order is determined according to the fulfillment status feedback information; In step S22, multi-dimensional feature extraction is performed on the supply response intensity to obtain dynamic coupling information of different types of purchased materials; In step S23, a performance performance gradient of different types of purchased materials is constructed according to the dynamic coupling information; In step S24, the performance performance boundaries of different types of purchased materials are determined by the performance performance gradient.

[0027] In the specific implementation, first, obtain the supplier performance-related data from the procurement system, including: order delivery time, supplier order confirmation time, order delivery time, logistics transportation time, order completion status and order performance abnormalities (delay, out of stock, quality problems, etc.), calculate the supplier's average delivery time, delivery timeliness rate and other indicators, and use regression analysis and random forest models to predict the supplier's response strength, that is, the supply response strength. Then, extract the following feature dimensions: supplier response time, fulfillment cycle, order delay rate; qualified rate of delivered products, quality complaint rate; historical order fulfillment fluctuations, supplier delivery consistency; supplier's responsiveness to emergency orders, and the degree to which delivery capabilities adapt to changes in market demand. Use principal component analysis to reduce the dimension of the extracted feature dimensions, and use time series to predict the results of the dimensionality reduction analysis, and use the prediction results as dynamic coupling information for different types of purchased materials. Then, the mapping relationship between supply response intensity and fulfillment results is established, and the decision tree model is used to classify the fulfillment modes of different types of materials. The weights of the impact of different dimensions (time, quality, stability, etc.) on fulfillment performance are constructed, and the Markov decision process is used to model the changing trend of supplier fulfillment status. The output results are used as the fulfillment performance gradient of different types of purchased materials, where the fulfillment performance gradient includes efficient suppliers, medium-efficiency suppliers, and inefficient suppliers. Finally, the minimum standard for supplier response capability is set, inefficient suppliers are screened, the distribution of supplier fulfillment capability is calculated, the boundary values ​​of high efficiency, medium efficiency, and low efficiency are determined, and the optimal fulfillment capability cutoff point is determined by the constrained optimization algorithm, and the optimal fulfillment capability cutoff point is used as the fulfillment performance boundary of different types of purchased materials.

[0028] It should be noted that, in this application, supply response intensity refers to the supplier's ability to respond to changes in demand during the order supply process; dynamic coupling information refers to the correlation information between the supplier's performance capability, quality performance, and supply stability under different types of purchased materials; the performance performance gradient refers to the hierarchical division of different suppliers in terms of performance capabilities; and the performance performance boundary refers to the range of performance capabilities of different categories of suppliers.

[0029] In this embodiment, constructing the purchase constraint rules of the order purchase at each execution stage according to the performance performance boundary and the user receipt data can be implemented by the following steps: Determine the dynamic correlation deviation when purchasing an order based on the performance boundary and the user receipt data; generating performance risk characteristics at different procurement stages according to the dynamic correlation deviation; The procurement constraint rules for order procurement at each execution stage are determined by the performance risk characteristics.

[0030] In the specific implementation, first, obtain the performance boundary data, including supplier performance capability, delivery timeliness, performance quality and user receipt data, including receipt time, receipt status, and abnormal feedback; use time series analysis to time match the performance boundary with the user receipt data, calculate the deviation between the actual delivery time and the predicted delivery time, form the timeliness deviation index, and then calculate the deviation between the receipt quality and the performance boundary to form the quality deviation index. Linearly fit the timeliness deviation index and the quality deviation index, and use the fitting result as the dynamic correlation deviation. Then, divide the procurement execution process into several key stages, such as procurement application, order confirmation, material transportation, warehousing acceptance, and final receipt; analyze historical performance data to identify the fluctuations in the performance capability of suppliers at different stages, such as supply instability and delay rate, and then calculate the probability of transportation delay at different procurement stages based on historical transportation data, and identify high-risk material types in combination with quality inspection data and user feedback data. Among them, high-risk material types include products that are easily damaged and have a high return rate. Through the market demand forecasting model, evaluate the impact of demand fluctuations on performance capability. K-means cluster analysis or principal component analysis is used to reduce the dimension of risk factors in different procurement stages to form a set of key performance risk characteristics, and performance risk characteristics are obtained from the set of key performance risk characteristics. Finally, based on the performance efficiency boundary and dynamic deviation analysis, the delivery time windows of different stages are set, including: the longest supplier confirmation time and the shortest transportation time; combined with the user receipt data, the minimum acceptable quality standards are set, including: the upper limit of the non-conformity rate and the threshold of the user complaint rate; based on the performance history data, the minimum supplier performance standards are set for different types of purchased materials, such as the on-time delivery rate>95%. For high-risk procurement stages, such as the risk of supply chain disruption, an alternative supplier trigger mechanism is set, and reinforcement learning is used to dynamically adjust procurement constraints to adapt to market demand fluctuations. The adaptability of procurement constraint rules is verified through simulation tests to ensure its feasibility in actual procurement execution, and finally the procurement constraint rules for order procurement at each execution stage are output.

[0031] It should be noted that in this application, dynamic correlation deviation refers to the difference between the fulfillment performance boundary at different procurement stages and the actual user receipt situation during the order procurement process; fulfillment risk characteristics refer to the potential risks in the procurement execution process; procurement constraint rules refer to the control conditions for successful fulfillment at different procurement execution stages.

[0032] In step S3, anomaly detection is performed on the keyword extraction strategy during procurement demand identification to obtain the matching deviation situation of procurement demand in supply chain matching, and based on the matching deviation situation and the shipment receipt data, the supplier's resources are graded and verified to generate supply recommendation rules for graded suppliers.

[0033] In this embodiment, the keyword extraction strategy in the purchase demand identification is detected for abnormality, and the matching deviation situation of the purchase demand in the supply chain matching can be obtained by the following steps: Obtain keyword extraction strategies for purchasing demand identification; Extracting the matching evolution path of procurement demand in supply chain matching from the keyword extraction strategy; Determining a deviation level map of procurement demand in supply chain matching according to the matching evolution path; Obtain the responsiveness characteristics of supply chain nodes; The matching deviation situation of the procurement demand in the supply chain matching is determined according to the deviation level map and the response capability characteristics.

[0034] In the specific implementation, first, use the word frequency-inverse document frequency to extract keywords, or use the deep learning model to extract keywords after context understanding. According to the context of the procurement demand, extract the key material type, demand quantity, time requirement and other information. Through the extracted keywords, establish a benchmark keyword set, and record the keyword features of normal procurement demand, such as demand vocabulary, product classification, quantity unit, etc., and then construct the feature distribution of normal and abnormal procurement demand. The feature distribution of normal and abnormal procurement demand is used as the keyword extraction strategy. Then, according to the keywords of the procurement demand, combined with the nodes in the supply chain, where the nodes in the supply chain include suppliers, warehouses, and transportation, a matching path is established. For example, the procurement demand may go through the process of "demand identification → supplier selection → supplier quotation → delivery". The matching of each node can be mapped as a part of the evolution path. The graph algorithm is used to analyze the path evolution that different procurement demands may experience in the supply chain, identify the matching path deviation, and use the time series analysis method to model the change trend in the matching path. The result of the model output is used as the matching evolution path of the procurement demand in the supply chain matching. Next, according to the matching deviation of different path nodes, the matching deviation of different paths includes: time delay, the difference between the demand quantity and the supplier's delivery quantity to define the deviation level, and the severity of the matching deviation is classified by K-means cluster analysis to obtain a deviation level map. Then, a heat map or radar map is used to visualize the deviation distribution of procurement demand in the matching process to form a deviation level map. Thirdly, according to the supplier's delivery time, inventory level, and transportation capacity, the response capability characteristics are extracted for each supply chain node. The data analysis method is used to reduce the dimension of these characteristics, and the most representative response capability indicators are extracted. The extracted indicators are used as the response capability characteristics of the supply chain node. Finally, based on the deviation level map and response capability characteristics, a model is established in combination with multivariate linear regression to predict the matching deviation situation of different procurement demands, and the prediction results are used as the matching deviation situation of procurement demands in supply chain matching.

[0035] It should be noted that, in this application, the keyword extraction strategy refers to the process of extracting important descriptive information from procurement requirements through natural language processing technology; the matching evolution path refers to the evolving matching status of procurement requirements in the entire supply chain process; the deviation level map refers to a diagram of the degree of deviation extracted from procurement requirements in the supply chain matching path; the responsiveness characteristic refers to the execution capability of each supply chain link in the fulfillment process; the matching deviation situation refers to the matching deviation status of procurement requirements in each link of the supply chain.

[0036] Preferably, in this embodiment, based on the matching deviation situation and the shipment receipt data, the supplier's resources are graded and verified to generate a supply recommendation rule for the graded supplier, referring to Figure 3 As shown, this figure is a schematic diagram of the process of determining the supply recommendation rules in some embodiments of the present application. In this embodiment, determining the supply recommendation rules can be implemented by the following steps: In step S31, based on the matching deviation situation and the shipment receipt data, collaborative supply parameters for resource matching of the hierarchical suppliers are extracted; In step S32, the quality fluctuation compensation amount of the supplier during cross-cycle delivery is determined according to the collaborative supply parameter; In step S33, the resource adaptation confidence interval of the graded supplier is determined by the quality fluctuation compensation amount; In step S34, a modified scheduling level of the hierarchical supplier is determined according to the resource adaptation confidence interval.

[0037] In the specific implementation, first, collect the shipment receipt data, among which the shipment receipt data includes: transportation time, receipt feedback, distribution data and matching deviation situation data, among which the matching deviation situation data includes: time delay, quantity error, quality problem, use data fusion method to integrate the two types of data, build global supplier matching characteristics, extract the supplier's resource coordination, such as response speed, inventory management ability, transportation capacity, etc. in the delivery process, and then analyze the advantages and disadvantages of each supplier in resource matching based on historical matching data to form a score of collaborative supply capability. For example, the scoring criteria are: high collaboration, high response, and high stability. The weighted average method is used to evaluate the collaborative supply capability of each supplier, and the collaborative supply capability of each supplier is used as the collaborative supply parameter when matching resources for graded suppliers. Then, based on historical delivery data, a quality regression analysis is used to establish a prediction model for quality fluctuations. The model considers factors including the supplier's delivery history, seasonal fluctuations, market demand fluctuations, etc., and obtains the quantitative value of quality fluctuations. Then, according to the quality fluctuation prediction of each supplier during the cross-cycle delivery process, the required compensation amount is calculated, that is, the quality fluctuation compensation amount of the supplier during the cross-cycle delivery. For example, if the quality fluctuation exceeds the predetermined threshold, it is necessary to add additional inventory, adjust the delivery time or add alternative supplier resources, and use the rolling forecast model to update the quality fluctuation compensation in real time to ensure timely adjustment within the delivery cycle. Then, the supplier's historical performance data and quality fluctuation compensation are combined to analyze the resource adaptability of each supplier under given conditions, and the normal distribution is used to calculate the possible resource adaptation range of the supplier within the delivery cycle. For example, under the premise of meeting the quality fluctuation compensation, the supplier's resource supply capacity interval is defined, and the suppliers are graded according to their resource adaptability. Suppliers with higher adaptability are classified as high priority, and suppliers with lower adaptability are classified as low priority. A hierarchical decision tree is used to classify suppliers, and different resource adaptation intervals are set for different levels, and the resource adaptation interval is used as the resource adaptation confidence interval. Finally, a time series forecasting model or machine learning method is used to predict the future changes in the resources supplied by suppliers. The scheduling level of suppliers can be graded according to their ability to change the resources they supply. High-priority suppliers: suppliers with larger adaptation intervals and stronger adaptability to changes in the resources they supply. In the case of large changes in the resources supplied, these suppliers can take on more tasks and delivery responsibilities. Medium priority suppliers: suppliers with certain adaptability, but may need to be adjusted when the resources they supply change greatly. Low priority suppliers: suppliers with weaker adaptability, who can only participate in supply tasks when the changes in the resources they supply are small or the demand is relatively stable. The scheduling level of high priority suppliers can be adjusted to the main supplier in the supply chain plan, and resources are allocated preferentially. Medium priority suppliers can be arranged among the backup suppliers and are in the second place in the scheduling level.Low-priority suppliers can be scheduled only under secondary demand, or dynamically allocated according to specific resource supply conditions. For example, when the resource adaptation interval of a high-priority supplier changes, the algorithm will automatically adjust the task allocation to balance the resource allocation in the supply chain, that is, to obtain the revised scheduling level of the hierarchical supplier.

[0038] It should be noted that, in this application, collaborative supply parameters refer to relevant indicators of synergy between suppliers during the supplier matching process; quality fluctuation compensation refers to the adjustment required to compensate for quality fluctuations that occur during the supplier's delivery process; resource adaptation confidence interval refers to the fluctuation range of the supply quantity and delivery time of resources set based on the quality fluctuation compensation to meet the supply demand during the supplier's delivery process; and modified scheduling level refers to the scheduling strategy for adjusting the supplier's delivery plan at each node in the supply chain.

[0039] In step S4, a target order corresponding to the procurement demand in the supply chain is generated according to the procurement constraint rule and the procurement recommendation rule.

[0040] In this embodiment, generating a target order corresponding to the procurement demand in the supply chain according to the procurement constraint rule and the procurement recommendation rule can be achieved by adopting the following steps: Determine the elastic matching path corresponding to the procurement demand in the supply chain according to the procurement constraint rule and the procurement recommendation rule; Generate a candidate order set for demand matching by combining the elastic matching path with real-time supply chain disturbance parameters; The target order corresponding to the procurement demand in the supply chain is determined according to the candidate order set.

[0041] In the specific implementation, first, parse the procurement contract and enterprise procurement strategy, extract procurement constraints, such as price upper / lower limits, delivery time window, quality standards (ISO certification, etc.), supplier rating requirements, and then use the rule engine to automatically parse these rules and store them in the procurement decision system. Based on historical procurement data, use the machine learning model to predict the degree of matching between suppliers and current demand, and combine the scoring mechanism to calculate the recommendation weights of different suppliers. Use linear programming to generate the matching path of procurement demand, and use this matching path as the elastic matching path corresponding to the procurement demand in the supply chain. Then, obtain the supply chain status in real time through IoT sensors, ERP systems, supplier platforms, etc., such as: supplier inventory changes (if the inventory is insufficient, you need to find alternative suppliers), logistics tracking information (whether the transportation is delayed), raw material market price fluctuations (price exceeds the limit and the supplier needs to be adjusted), production plan changes (supplier capacity changes); use Bayesian networks or Markov decision processes to analyze the impact of different disturbance factors on procurement matching and make predictions. Combined with the elastic matching path and real-time supply chain disturbance information, it is calculated whether each supplier can still meet the procurement demand, and a multi-objective optimization algorithm is used to generate multiple candidate order solutions, which are sorted according to the minimum cost, shortest delivery time, and highest quality score. The sorted candidate order solutions are used as the candidate order set for demand matching. Finally, the candidate orders are scored based on the comprehensive scoring model, among which the price weight (W1): the lower the price, the higher the score; the delivery time weight (W2): the shorter the delivery time, the higher the score; the quality score weight (W3): the better the supplier's historical delivery quality, the higher the score; the supply chain stability weight (W4): the orders that are less affected by disturbances have higher scores. S = W1 × price score + W2 × delivery time score + W3 × quality score + W4 × supply chain stability, S represents the target order score. Then set the threshold, for example: order with a total score of >80 is given priority. If there are multiple orders with similar scores, the order with higher supply chain stability is given priority. The intelligent decision-making algorithm is used to automatically optimize the target order selection in a dynamic environment, and the final target order is sent to the ERP system to execute the procurement process and monitor the order execution. If an exception occurs (such as the supplier cancels the order), the candidate order set is returned for re-matching.

[0042] It should be noted that in this application, the elastic matching path means that during the procurement process, a certain degree of flexible adjustment is allowed to adapt to the real-time changes in the supply chain and optimize the matching plan of procurement needs; the real-time supply chain disturbance parameters represent the factors that affect procurement matching during the operation of the supply chain, such as inventory fluctuations, transportation delays, raw material shortages, and market price changes; the candidate order set represents a set of alternative orders that meet procurement needs under different supply chain disturbances.

[0043] It can be seen that in this application, the intelligence level of the procurement process and the closed-loop optimization capability of fulfillment management can be improved; among them, real-time monitoring of the supply chain fulfillment process is realized, the accuracy and timeliness of the data are guaranteed, the visualization capability of procurement management for supplier shipment, logistics distribution and user receipt is improved, and the fulfillment risk caused by information lag is reduced; by multi-dimensional analysis of the fulfillment data, the fulfillment efficiency boundary of different purchased materials is formed, and based on this, the constraint rules of the procurement execution stage are constructed, so that procurement can accurately identify the matching degree between procurement demand and supplier fulfillment capability through keyword extraction anomaly detection and matching deviation analysis, optimize the supplier grading strategy, improve the scientific nature of supplier resource management, and reduce the procurement failure rate caused by supply chain matching deviation. The process is more precise and standardized, the executability of the procurement plan is improved, and the probability of fulfillment anomalies is reduced; combined with intelligent procurement constraints and supplier recommendation rules, automatic optimization configuration of orders is realized, the matching accuracy of procurement demand and supply chain resources is improved, the procurement cycle is optimized, and the fulfillment success rate is improved, thereby reducing procurement costs and improving the overall efficiency of the supply chain.

[0044] To sum up, the technical solution adopted in this application can dynamically monitor the fulfillment status and make graded recommendations on suppliers under the supply chain collaboration platform to improve the accuracy of supply chain matching in the procurement process.

[0045] Embodiment 2: This application provides an enterprise order procurement management system, referring to Figure 4 As shown, this figure is a module structure diagram of the enterprise order procurement management system shown in this embodiment of the present application, and the procurement management system includes: The data acquisition module 100 is used to collect the supplier's shipping data and the user's receipt data from the supply chain collaboration platform, and obtain the fulfillment status feedback information corresponding to the purchase order in real time; The information analysis module 200 is used to perform multi-dimensional alignment analysis on the fulfillment status feedback information in order procurement management, generate fulfillment performance boundaries for different types of purchased materials, and construct procurement constraint rules for order procurement at each execution stage based on the fulfillment performance boundaries and the user receipt data; The hierarchical verification module 300 is used to perform anomaly detection on the keyword extraction strategy during the identification of procurement requirements, obtain the matching deviation situation of procurement requirements in the supply chain matching, perform hierarchical verification on the supplier's resources based on the matching deviation situation and the shipment receipt data, and generate supply recommendation rules for hierarchical suppliers; The order generation module 400 is used to generate a target order corresponding to the procurement demand in the supply chain according to the procurement constraint rules and the procurement recommendation rules.

[0046] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0047] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, the storage medium including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically-erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0048] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. A method for enterprise order procurement management, characterized in that: The procurement management method comprises the following steps: Collect supplier's shipping data and user's receipt data from the supply chain collaboration platform, and obtain the fulfillment status feedback information corresponding to the purchase order in real time; In order procurement management, the fulfillment status feedback information is subjected to multi-dimensional alignment analysis to generate the fulfillment efficiency boundary of different procurement material types, and the procurement constraint rules of order procurement at each execution stage are constructed according to the fulfillment efficiency boundary and the user receipt data; Perform anomaly detection on the keyword extraction strategy during procurement demand identification to obtain the matching deviation situation of procurement demand in supply chain matching, perform hierarchical verification on supplier resources based on the matching deviation situation and the shipment receipt data, and generate supply recommendation rules for hierarchical suppliers; A target order corresponding to the procurement demand in the supply chain is generated according to the procurement constraint rule and the procurement recommendation rule.

2. The enterprise order procurement management method according to claim 1, characterized in that: In order procurement management, the fulfillment status feedback information is subjected to multi-dimensional alignment analysis to generate fulfillment efficiency boundaries for different types of procurement materials, including: Determining the supplier's supply response strength when supplying the order based on the fulfillment status feedback information; Perform multi-dimensional feature extraction on the supply response intensity to obtain dynamic coupling information of different types of purchased materials; Constructing a performance performance gradient for different types of purchased materials according to the dynamic coupling information; The performance performance gradient is used to determine the performance performance boundaries of different types of purchased materials.

3. The enterprise order procurement management method according to claim 1, characterized in that: The procurement constraint rules for order procurement at each execution stage are constructed based on the performance boundary and the user receipt data, specifically including: Determine the dynamic correlation deviation when purchasing an order based on the performance boundary and the user receipt data; generating performance risk characteristics at different procurement stages according to the dynamic correlation deviation; The procurement constraint rules for order procurement at each execution stage are determined by the performance risk characteristics.

4. The enterprise order procurement management method according to claim 1, characterized in that: The procurement constraints refer to the control conditions for successful performance of contracts in different procurement execution stages.

5. The enterprise order procurement management method according to claim 1, characterized in that: The keyword extraction strategy in the purchase demand identification is tested for anomalies, and the matching deviation situation of the purchase demand in the supply chain matching is obtained, including: Obtain keyword extraction strategies for purchasing demand identification; Extracting the matching evolution path of procurement demand in supply chain matching from the keyword extraction strategy; Determining a deviation level map of procurement demand in supply chain matching according to the matching evolution path; Obtain the responsiveness characteristics of supply chain nodes; The matching deviation situation of the procurement demand in the supply chain matching is determined according to the deviation level map and the response capability characteristics.

6. The enterprise order procurement management method according to claim 1, characterized in that: The matching deviation situation refers to the matching deviation status of procurement demand in each link of the supply chain.

7. The enterprise order procurement management method according to claim 1, characterized in that: Based on the matching deviation situation and the shipment receipt data, the supplier's resources are graded and verified to generate a supply recommendation rule for the graded supplier, specifically including: Extracting collaborative supply parameters for resource matching of tiered suppliers based on the matching deviation situation and the shipment receipt data; Determining the quality fluctuation compensation amount of the supplier during cross-cycle delivery according to the collaborative supply parameters; Determine the resource adaptation confidence interval of the graded supplier through the quality fluctuation compensation amount; A modified scheduling level for the tiered suppliers is determined based on the resource adaptation confidence interval.

8. The enterprise order procurement management method according to claim 1, characterized in that: The modified scheduling level refers to a scheduling strategy for adjusting the supplier's delivery plan at each node in the supply chain.

9. The enterprise order procurement management method according to claim 1, characterized in that: Generating a target order corresponding to the procurement demand in the supply chain according to the procurement constraint rule and the procurement recommendation rule specifically includes: Determine the elastic matching path corresponding to the procurement demand in the supply chain according to the procurement constraint rule and the procurement recommendation rule; Generate a candidate order set for demand matching by combining the elastic matching path with real-time supply chain disturbance parameters; The target order corresponding to the procurement demand in the supply chain is determined according to the candidate order set.

10. An enterprise order procurement management system, used to execute an enterprise order procurement management method as claimed in any one of claims 1 to 9, characterized in that: The procurement management system comprises: The data acquisition module is used to collect the supplier's shipping data and user receipt data from the supply chain collaboration platform, and obtain the fulfillment status feedback information corresponding to the purchase order in real time; An information analysis module is used to perform multi-dimensional alignment analysis on the fulfillment status feedback information in order procurement management, generate fulfillment efficiency boundaries for different types of purchased materials, and construct procurement constraint rules for order procurement at each execution stage based on the fulfillment efficiency boundaries and the user receipt data; A hierarchical verification module is used to perform anomaly detection on the keyword extraction strategy during the identification of procurement requirements, obtain the matching deviation situation of procurement requirements in the supply chain matching, perform hierarchical verification on the supplier's resources based on the matching deviation situation and the shipment receipt data, and generate supply recommendation rules for hierarchical suppliers; An order generation module is used to generate a target order corresponding to the procurement demand in the supply chain according to the procurement constraint rules and the procurement recommendation rules.

Images