Intelligent procurement system and method for supply chain

Abstract

The present invention belongs to the technical field of supply chain management and discloses an intelligent procurement system and method for a supply chain; the system comprises: collecting demand forecast data and supplier performance data; conducting in-depth mining of demand forecast data to predict future procurement demand; generating capability portraits based on supplier performance data, and conducting quantitative evaluation of the performance scores of different suppliers according to a pre-built evaluation system; obtaining historical order data, and combining the capability portraits to construct a supplier relationship network topology and identify synergy effects between suppliers; integrating performance scores, future procurement demand and synergy effects to recommend an optimal supplier combination; obtaining procurement management data, and combining the supplier performance data of the optimal supplier combination to intelligently formulate procurement strategies; the present invention can not only improve procurement efficiency, but also enhance the flexibility and resilience of the supply chain, thereby effectively improving the overall response speed, cost control capabilities and operational quality of the supply chain.

Description

Technical Field

[0001] The present invention relates to the technical field of supply chain management, and more specifically, to an intelligent procurement system and method for a supply chain. Background Art

[0002] With the deepening development of global economic integration and digital transformation, supply chain management has become an important link for enterprises to enhance their core competitiveness. Procurement, as a key link in the supply chain, is directly related to cost control, production efficiency and service levels. Traditional procurement systems mostly use manual management or rule-based static decision-making models, relying on human experience to select suppliers and formulate procurement strategies. They have many problems such as delayed response, low efficiency, and information fragmentation, and cannot form closed-loop management. Especially when facing large-scale, multi-category, and cross-regional procurement scenarios, it is difficult to support intelligent analysis and dynamic optimization of multi-dimensional data, which restricts the scientific nature and foresight of procurement decisions. Therefore, there is an urgent need for an intelligent procurement system to realize intelligent management of the entire supply chain process and improve enterprise procurement efficiency and supply chain resilience.

[0003] The patent with publication number CN118674366A discloses an intelligent procurement system and supply chain procurement method for a supply chain; it includes: a supply chain management system, a procurement system, an inventory management system and a user authority management system; the supply chain management system includes a supplier management module, a supply chain monitoring module and a supplier evaluation module; the procurement system includes a procurement demand management module, a procurement order management module, a cost control module, a data analysis and reporting module, an artificial intelligence decision support module and an automated procurement module; the inventory management system includes an inventory management module; the user management system includes a user authority management module. The present invention, by using the intelligent procurement system, can reduce manual procurement, effectively reduce procurement error rate, improve procurement efficiency, reduce procurement costs, reduce procurement risks, and enhance the competitiveness of enterprises.

[0004] However, although the above-mentioned technologies have realized intelligent procurement in the supply chain, they mainly focus on the organizational structure division of system modules and lack in-depth explanation of the means of implementing core technologies, especially in key links such as supplier evaluation and procurement decision-making, they fail to reflect specific technical methods; at the same time, the above-mentioned technologies fail to fully consider the collaborative relationship between suppliers, lack modeling and analysis of the supply chain network structure, and it is difficult to identify the potential synergy effects therein, resulting in difficulty in achieving dynamic perception and high-dimensional refined optimization in a complex and changing procurement environment.

[0005] In view of this, the present invention proposes an intelligent procurement system and method for a supply chain to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned objectives, the present invention provides the following technical solutions: a smart procurement method for a supply chain, comprising:

[0007] Collect supply chain management data, including demand forecast data and supplier performance data;

[0008] Conduct in-depth mining of demand forecast data and use deep learning technology to dynamically predict future procurement needs;

[0009] Generate capability profiles of different suppliers based on supplier performance data, and quantitatively evaluate the performance scores of different suppliers based on a pre-built evaluation system;

[0010] Obtain historical order data, integrate it with the capability profiles of different suppliers, build a supplier relationship network topology, and identify synergies between suppliers. Combine performance scores, future procurement needs, and synergies to apply intelligent matching algorithms to recommend the optimal supplier combination.

[0011] Acquire procurement management data, combine it with supplier performance data corresponding to the optimal supplier combination, and use multi-objective optimization technology to intelligently formulate personalized procurement strategies.

[0012] Furthermore, the demand forecast data includes historical procurement data, market trend data, and demand procurement categories; the historical procurement data includes historical procurement time, historical procurement categories, and historical procurement quantities; the market trend data includes raw material price fluctuation data and market demand change data; the raw material price fluctuation data includes the market prices of raw materials required by different supply chain products at different time points; the market demand change data includes the total demand for different supply chain products at different time points; the supplier performance data includes the performance data corresponding to each supplier;

[0013] Methods for dynamically forecasting future procurement needs include:

[0014] The historical purchase quantities of the same corresponding historical purchase category are grouped as a quantity set; a time interval is preset, and a time axis is constructed for each quantity set based on the time interval; wherein, on each time axis, the time difference between every two adjacent time points is equal to the time interval, and each time point corresponds to a historical purchase quantity in the corresponding quantity set;

[0015] According to the historical purchase quantity corresponding to each time point on each time axis, a quantity prediction model is constructed for each set of quantity sets. The quantity prediction model is a recurrent neural network model; the preset length is time window, is an integer greater than 1; the quantity set corresponding to each demand procurement category is marked as the demand set, and the time axis corresponding to the demand set is marked as the demand axis; starting from the last time point on each demand axis, a set of time sets is obtained from the demand axis corresponding to each set of demand sets based on the time window, and each set of time sets includes time points; input the historical purchase quantity corresponding to each time set into the corresponding quantity forecasting model to predict the corresponding future purchase quantity;

[0016] According to market trend data, calculate the first factor and the second factor corresponding to each set of demand in turn; set the weight coefficients of each first factor and each second factor respectively, multiply each first factor and each second factor by the corresponding weight coefficient in turn to obtain the influence weight, and take the average of the same influence weights of the corresponding demand sets as the comprehensive influence factor; multiply each future purchase quantity by the corresponding comprehensive influence factor to obtain the expected purchase quantity of each set of demand, and use it as the future purchase demand.

[0017] Furthermore, the method of constructing a timeline for a quantity set includes:

[0018] The earliest historical purchase time corresponding to the historical purchase quantity in the quantity set is marked as the earliest time, and the earliest time is used as the first time point on the time axis; starting from the earliest time, continuous time points are generated on the time axis according to the time interval; the time points on the time axis are compared with the historical purchase time corresponding to each historical purchase quantity in the quantity set; the historical purchase quantities corresponding to the same historical purchase time as the time point are mapped to the corresponding time points in sequence; the time points that are different from all historical purchase times are marked as interpolation points, and the historical purchase quantity corresponding to each interpolation point is calculated using the polynomial interpolation method, and mapped to the corresponding interpolation point;

[0019] The method for calculating the first factor and the second factor corresponding to each set of requirements includes:

[0020] The market trend data is mapped to each time point on each demand axis, and each time point corresponds to a set of market prices and a total demand. According to the market price, total demand and historical purchase quantity corresponding to each time point on each demand axis, a market impact model is constructed for each demand set. The market impact model is a deep neural network model. The earliest time point in each time set is marked as a temporary early point. The time point before the corresponding temporary early point on each demand axis is taken as the starting point. A set of time-front sets is obtained from each demand axis based on the time window. Each time-front set includes time points; the market price, total demand and historical purchase quantity corresponding to each time set are input into the corresponding market impact model respectively to predict the corresponding first factor; the market price, total demand and historical purchase quantity corresponding to each time set are input into the corresponding market impact model respectively to predict the corresponding second factor.

[0021] Furthermore, the method for generating capability profiles of different suppliers includes:

[0022] Based on the performance data of different suppliers, the capability indicators of each supplier are evaluated. The capability indicators include delivery capability, quality capability, price capability and service capability. According to the capability indicators of each supplier, a corresponding bar chart is constructed for each supplier, and the bar chart is used as the capability portrait of the corresponding supplier.

[0023] Furthermore, the steps to evaluate each supplier's delivery capabilities include:

[0024] Step S101: construct multiple fuzzy sets for each data in the delivery performance data;

[0025] Step S102: converting the delivery performance data of each supplier into the membership degree of each corresponding fuzzy set through fuzzification technology;

[0026] Step S103: defining fuzzy rules;

[0027] Step S104: Match each set of fuzzified technical feature data with fuzzy rules respectively, and perform fuzzy reasoning using a fuzzy reasoning method to obtain the fuzzy reasoning results corresponding to each supplier. The fuzzy reasoning results are the membership degrees of each delivery capability level.

[0028] Step S105: Set the capability interval. The capability interval range is , is an integer greater than 1; the capability interval is evenly divided into four level intervals, and the level intervals correspond one-to-one to the levels in the delivery capability level; the maximum value of each level interval plus the corresponding minimum value are divided by 2 to obtain the interval mean of each level interval;

[0029] Step S106: Multiply the membership degree of each supplier's corresponding delivery capability level by the corresponding interval mean, and then add them up in sequence to obtain the total capability value of each supplier; add the membership degree of each supplier's corresponding delivery capability level in sequence to obtain the total membership degree; divide the total capability value of each supplier by the corresponding total membership degree to obtain the delivery capability of each supplier;

[0030] The steps for evaluating each supplier's quality capability, price capability, and service capability are consistent with those for evaluating each supplier's delivery capability;

[0031] The method for quantitatively evaluating the performance scores of different suppliers includes:

[0032] A preset proportion set includes a proportion coefficient corresponding to each capability indicator; each capability indicator of each supplier is multiplied by the corresponding proportion coefficient in the proportion set, and then added up in sequence to obtain the performance score corresponding to each supplier.

[0033] Furthermore, the historical order data includes performance data corresponding to each historical cooperative order;

[0034] The method for constructing a supplier relationship network topology includes:

[0035] The multiple suppliers corresponding to each historical cooperative order are regarded as a supplier set, and the historical cooperative orders with the same supplier set are regarded as an order set. The performance data corresponding to each order set are respectively input into the trained performance evaluation model to predict the corresponding performance data. The performance evaluation model is a deep neural network model. Based on the performance data corresponding to different order sets, the capability indicators corresponding to each order set are evaluated. Each supplier is regarded as a node, and an edge is established between the nodes corresponding to every two suppliers in each supplier set. The weight of each edge is the capability indicator corresponding to each order set. Based on the nodes, edges and edge weights, the supplier relationship network topology is constructed, and the capability profile of each supplier is used as the attribute of the corresponding node.

[0036] Steps to identify synergies among suppliers include:

[0037] Step S201: Mark the capability indicators in the corresponding attributes of each node as the first indicator, and mark the corresponding capability indicators in the weight of the edge as the second indicator;

[0038] Step S202: randomly selecting a set of supplier sets that are not marked as selected sets and marking them as current sets;

[0039] Step S203: Compare each first indicator corresponding to each node in the current set with the second indicator corresponding to the corresponding order set in turn; if all first indicators are less than or equal to the corresponding second indicators, then all nodes in the corresponding current set have positive synergy effects, and the corresponding current set is marked as a synergistic set; if there is a first indicator that is greater than the corresponding second indicator, then there is a node in the corresponding current set that has negative synergy effects, and the corresponding current set is not marked;

[0040] Step S204: Mark the current set as a selected set;

[0041] Step S205: looping step S202 to step S204 until all supplier sets are marked as selected sets, the loop ends, and all collaborative sets are obtained.

[0042] Furthermore, the methods for recommending the optimal supplier combination include:

[0043] Based on historical cooperative orders, obtain the historical procurement categories corresponding to each collaborative set and mark them as cooperative procurement categories; based on historical procurement data, obtain the historical procurement categories corresponding to each supplier and mark them as independent procurement categories; compare each demand procurement category with each cooperative procurement category; if there is a demand procurement category that is the same as the cooperative procurement category, mark the corresponding collaborative set as a recommended set; if all demand procurement categories are different from the cooperative procurement categories, do not mark the corresponding collaborative set; mark all demand procurement categories that are different from each cooperative procurement category as remaining procurement categories, and mark the suppliers corresponding to the independent procurement categories that are the same as the remaining procurement categories as candidate suppliers; the candidate suppliers with the same corresponding independent procurement categories are all regarded as a group of candidate sets, and the candidate sets correspond one-to-one with the independent procurement categories;

[0044] According to future procurement needs, the estimated procurement quantity of each remaining procurement category is obtained; according to historical procurement data, the historical procurement quantity corresponding to each candidate supplier is obtained, and the maximum historical procurement quantity corresponding to each candidate supplier is marked as the maximum quantity; each maximum quantity is compared with the corresponding estimated procurement quantity, and the candidate suppliers whose maximum quantity is less than the corresponding estimated procurement quantity are deleted from the corresponding candidate set, and the candidate suppliers whose maximum quantity is greater than or equal to the estimated procurement quantity are retained in the corresponding candidate set; each candidate supplier in each candidate set is sorted from large to small according to the corresponding performance score to generate a supplier ranking table; the suppliers ranked at the top of each supplier ranking table are sorted. All candidate suppliers are marked as the best suppliers. is an integer greater than 0; each best supplier is combined with each set of recommended sets to obtain the optimal supplier combination.

[0045] Furthermore, the procurement management data includes category inventory, procurement budget, and supply cycle; the category inventory includes the inventory quantity of each required procurement category; the procurement budget includes the budget amount of each required procurement category; and the supply cycle includes the delivery cycle of each required procurement category;

[0046] Methods for developing a personalized purchasing strategy include:

[0047] Build Group different purchasing sets, The group purchase collection sets the numerical labels that increase in sequence and marks them as purchase labels. The range of purchase labels is ; Randomly select a purchase tag as the initial iteration center;

[0048] Define the iterative process, which is: based on the iteration center, generate within the scope of the procurement tag candidate solutions, and calculate the procurement performance evaluation value corresponding to each candidate solution. , the candidate solutions correspond to the procurement labels one by one; the candidate solution with the largest procurement performance evaluation value is marked as the local solution, the iteration center is moved to the local solution, and the indicator change is calculated;

[0049] Execute the iterative process. When each iterative process is completed, compare the indicator change with the preset change threshold. If the indicator change is less than the change threshold, generate a completion instruction. If the indicator change is greater than or equal to the change threshold, do not generate a completion instruction. Count the number of times the completion instruction is generated and mark it as the number of instructions. When the number of instructions is greater than or equal to the preset number threshold, stop executing the iterative process. Mark the procurement label corresponding to the iteration center as the best label, and use the procurement set corresponding to the best label as the procurement strategy.

[0050] Furthermore, the method for calculating the procurement performance evaluation value corresponding to the candidate solution includes:

[0051] Obtain the procurement set corresponding to the procurement label of the candidate solution and mark it as the calculation set; obtain the supplier performance data corresponding to each supplier in the calculation set and mark it as calculation data; use the calculation data, calculation set, and procurement management data as performance prediction data; input the performance prediction data into the trained performance prediction model to predict the corresponding procurement performance data; the performance prediction model includes a cost prediction model, a supply prediction model, and a quality prediction model, all of which are deep neural network models; procurement performance data includes procurement cost, delivery cycle, and product quality;

[0052] Subtract the procurement cost from the procurement budget to obtain the budget surplus; subtract the supply cycle from the delivery cycle to obtain the delivery deviation; preset an indicator weight set, which includes the indicator weights corresponding to the budget surplus, delivery deviation, and product quality; multiply the budget surplus, delivery deviation, and product quality by the corresponding indicator weights in the indicator weight set to obtain the budget coefficient, delivery coefficient, and quality coefficient; add the budget coefficient to the quality coefficient and then the delivery coefficient to obtain the procurement performance evaluation value;

[0053] The method for calculating the change in the indicator is: subtract the procurement performance evaluation value corresponding to the iteration center in the previous iteration from the procurement performance evaluation value corresponding to the iteration center in this iteration, and take the absolute value to obtain the change in the indicator.

[0054] A supply chain intelligent procurement system implements the supply chain intelligent procurement method, including:

[0055] Data collection module, used to collect supply chain management data, including demand forecast data and supplier performance data;

[0056] Demand forecasting module, which is used to conduct in-depth mining of demand forecasting data and dynamically predict future procurement needs using deep learning technology;

[0057] The supplier evaluation module is used to generate capability profiles of different suppliers based on supplier performance data and quantitatively evaluate the performance scores of different suppliers according to a pre-built evaluation system;

[0058] The supplier recommendation module is used to obtain historical order data, integrate it with the capability profiles of different suppliers, build a supplier relationship network topology, and identify synergies between suppliers. It also integrates performance scores, future procurement needs, and synergies to apply intelligent matching algorithms to recommend the optimal supplier combination.

[0059] The strategy formulation module is used to obtain procurement management data, and combined with the supplier performance data corresponding to the optimal supplier combination, it uses multi-objective optimization technology to intelligently formulate personalized procurement strategies.

[0060] The technical effects and advantages of the intelligent procurement system and method for supply chain of the present invention are as follows:

[0061] Through deep learning technology, it integrates multi-dimensional factors such as historical procurement data and market trend data to achieve accurate perception and prediction of future procurement needs; builds capability portraits based on supplier performance data, and uses a combination of fuzzy evaluation and quantitative analysis to comprehensively evaluate suppliers, which can more objectively quantify suppliers' performance in key capabilities such as delivery, quality, and price; by analyzing the supplier relationship network, it identifies the synergy between suppliers, providing an important basis for recommending the optimal supplier combination, which is conducive to leveraging the synergy advantages between suppliers and improving the overall efficiency of the supply chain; in the procurement strategy formulation stage, it integrates multi-dimensional constraints such as supplier performance, procurement demand, and inventory, and uses iterative optimization methods to dynamically generate personalized procurement plans, achieving refined balance and dynamic adjustment among multiple goals such as cost, delivery, and quality, to maximize the scientific nature and effectiveness of procurement decisions; it not only improves procurement efficiency and reduces costs, but also enhances the flexibility and resilience of the supply chain, thereby effectively improving the overall response speed, cost control capabilities, and operational quality of the supply chain, thereby enhancing the company's market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 This is a schematic diagram of an intelligent procurement system for a supply chain according to embodiment 1 of the present invention;

[0063] Figure 2 This is a flow chart of an intelligent procurement method for a supply chain according to embodiment 2 of the present invention. DETAILED DESCRIPTION

[0064] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0065] Example 1

[0066] See also Figure 1 As shown, this embodiment provides an intelligent procurement system for a supply chain, including a data collection module, a demand forecasting module, a supplier evaluation module, a supplier recommendation module, and a strategy formulation module; each module is connected by wired and / or wireless means to realize data transmission between modules.

[0067] The data collection module is used to collect supply chain management data, which includes demand forecast data and supplier performance data.

[0068] Demand forecast data refers to relevant data used to predict future trends in purchasing demand changes, which helps companies formulate reasonable purchasing plans in advance and achieve optimal allocation of supply chain resources; demand forecast data includes historical purchasing data, market trend data and demand purchasing categories; historical purchasing data refers to the company's historical purchasing records, which are used to reflect past purchasing behavior patterns and demand patterns; historical purchasing data includes historical purchasing time, historical purchasing categories and historical purchasing quantities; historical purchasing categories refer to the various types of supply chain products involved in the company's historical purchasing activities; market trend data refers to external macro factors related to corporate procurement, which are used to evaluate external changes that will affect purchasing demand in the future; market trend data includes raw material price fluctuation data and market demand change data. Raw material price fluctuation data refers to the market price changes of raw materials required for supply chain products, including the market prices of raw materials required by different supply chain products at different time points; market demand change data refers to the fluctuations in the total market demand for supply chain products, including the total demand for different supply chain products at different time points; demand purchasing categories refer to the various types of supply chain products involved in the company's current procurement process based on actual business needs;

[0069] Historical procurement data is obtained through the company's internal enterprise resource planning system (such as ERP system) or supply chain management system (such as SCM system); market trend data is obtained through market reports regularly released by industry analysis companies (such as TouBao Research Institute, iResearch Consulting, etc.) or public data from futures exchanges (such as Shanghai Futures Exchange, Zhengzhou Commodity Exchange, etc.).

[0070] Supplier performance data refers to data that measures the supplier's performance in various aspects of historical cooperation, which helps to quantitatively evaluate and intelligently screen suppliers, and thus provides data support for subsequent supplier recommendations and procurement strategy formulation; supplier performance data includes performance data corresponding to each supplier, including delivery performance data, quality performance data, price performance data, and service performance data; delivery performance data reflects the supplier's delivery capability and time control level during the order execution process, including on-time delivery rate, average delivery cycle, order fulfillment rate, etc.; quality performance data is used to measure the quality stability and qualification level of the products provided by the supplier, including product qualification rate, quality defect rate, return rate, etc.; price performance data reflects the supplier's performance in cost control and price stability, including average quotation, quotation fluctuation, etc.; service performance data is used to evaluate the supplier's communication efficiency, after-sales service and other soft capabilities during the cooperation process, including after-sales service satisfaction and problem handling efficiency;

[0071] Delivery performance data is obtained through the enterprise's internal enterprise resource planning system (i.e., ERP system) or supply chain management system (i.e., SCM system); quality performance data is obtained through the enterprise's internal quality management system (i.e., QMS system); price performance data is obtained through historical procurement contracts; and service performance data is obtained through the enterprise's internal supplier management system (i.e., SRM system).

[0072] The demand forecasting module is used to conduct in-depth mining of demand forecasting data and use deep learning technology to dynamically predict future procurement needs.

[0073] Methods for dynamically forecasting future procurement needs include:

[0074] The historical purchase quantities of the same corresponding historical purchase category are grouped as a quantity set, and the quantity set corresponds to the historical purchase category one-to-one; a time interval is preset, and a time axis is constructed for each quantity set based on the time interval. The time interval is preset by those skilled in the art based on actual conditions; wherein, on each time axis, the time difference between every two adjacent time points is equal to the time interval, and each time point corresponds to a historical purchase quantity in the corresponding quantity set; it should be noted that the time difference between the last time point on each time axis and the corresponding latest time is less than the time interval, and the latest time is the latest historical purchase time corresponding to the historical purchase quantity in the quantity set;

[0075] According to the historical purchase quantity corresponding to each time point on each time axis, a quantity prediction model is constructed for each quantity set, and the quantity prediction model corresponds to the quantity set one by one; among them, the quantity prediction model is a recurrent neural network model, which is an existing technology. The specific construction process is not described in detail here. The recurrent neural network model can process time series data, capture the changing trend of historical purchase quantity, and thus predict the purchase quantity at future time points; the preset length is time window, is an integer greater than 1, and the time window is pre-set by those skilled in the art according to the actual situation; the quantity set corresponding to each demand procurement category is marked as the demand set, and the time axis corresponding to the demand set is marked as the demand axis; starting from the last time point on each demand axis, a set of time sets is obtained from each demand axis based on the time window, and each set of time sets includes time points; the historical purchase quantities corresponding to each time set are input into the corresponding quantity forecasting model to predict the corresponding future purchase quantities, which correspond one-to-one to the demand purchase categories;

[0076] According to market trend data, calculate the first factor and the second factor corresponding to each set of demand in turn; set the weight coefficients of each first factor and each second factor respectively, multiply each first factor and each second factor by the corresponding weight coefficient in turn to obtain the influence weight, and take the average of the same influence weights of the corresponding demand sets as the comprehensive influence factor; multiply each future purchase quantity by the corresponding comprehensive influence factor to obtain the expected purchase quantity of each set of demand, and use it as the future purchase demand.

[0077] Methods for constructing a timeline for a collection of quantities include:

[0078] The earliest historical purchase time corresponding to the historical purchase quantity in the quantity set is marked as the earliest time, and the earliest time is used as the first time point on the time axis; starting from the earliest time, continuous time points are generated on the time axis according to the time interval; the time points on the time axis are compared with the historical purchase time corresponding to each historical purchase quantity in the quantity set; the historical purchase quantities corresponding to the historical purchase time that is the same as the time point are mapped to the corresponding time points in turn; the time points that are different from all historical purchase times are marked as interpolation points, and the polynomial interpolation method (such as Lagrange interpolation method, Newton interpolation method, etc.) is used to calculate the historical purchase quantity corresponding to each interpolation point, and mapped to the corresponding interpolation point.

[0079] The method for calculating the first factor and the second factor corresponding to each set of requirements includes:

[0080] Market trend data is mapped to each time point on each demand axis, with each time point corresponding to a set of market prices and a total demand quantity. A market impact model is constructed for each demand set based on the market price, total demand quantity, and historical purchase quantity corresponding to each time point on each demand axis. The market impact model corresponds one-to-one with the demand set. The market impact model is a deep neural network model, which is an existing technology. The specific construction process will not be elaborated on here. The deep neural network model can effectively capture the impact of nonlinear factors such as market price fluctuations and changes in total demand on purchase quantity.

[0081] The earliest time point in each time set is marked as a temporary early point. Taking the time point before the corresponding temporary early point on each demand axis as the starting point, a set of time-ahead sets is obtained from each demand axis based on the time window. Each set of time-ahead sets includes time points; the market price, total demand and historical purchase quantity corresponding to each time set are input into the corresponding market impact model respectively to predict the corresponding first factor; the market price, total demand and historical purchase quantity corresponding to each time set are input into the corresponding market impact model respectively to predict the corresponding second factor.

[0082] Exemplarily, the demand axis includes 7 time points, and the length of the time window is 3, where time point 1 is the first time point and time point 7 is the last time point; therefore, the time set includes time point 7, time point 6 and time point 5; since the earliest time point in the time set is time point 5, time point 5 is a temporary early point, and the early time set includes time point 4, time point 3 and time point 2.

[0083] The method of setting the weight coefficients of each first factor and each second factor separately includes:

[0084] The market price and total demand corresponding to each demand set corresponding to the time set are taken as a set of fluctuation analysis data, and the fluctuation analysis data correspond to the demand set one by one; each set of fluctuation analysis data is input into the trained market analysis model to predict the corresponding market volatility coefficient; wherein the market analysis model is a deep neural network model, and the market volatility coefficient is a comprehensive indicator used to quantitatively describe the degree of fluctuation of market price and market demand within the time set, which is used to reflect the stability or volatility of the market; the coefficient threshold and weight set are preset, and the coefficient threshold and weight set are pre-set by those skilled in the art according to actual conditions; wherein the weight set includes weight coefficient and weight coefficient , ,and ; Compare the market volatility coefficient with the coefficient threshold; If the market volatility coefficient is greater than the coefficient threshold, the weight coefficient As the weight coefficient of the first factor, the weight coefficient As the weight coefficient of the second factor; if the market volatility coefficient is less than or equal to the coefficient threshold, the weight coefficient As the weight coefficient of the first factor, the weight coefficient Serves as the weight coefficient for the second factor.

[0085] The supplier evaluation module is used to generate capability profiles of different suppliers based on supplier performance data, and to quantitatively evaluate the performance scores of different suppliers based on a pre-built evaluation system.

[0086] Methods for generating capability profiles of different suppliers include:

[0087] Based on the performance data of different suppliers, the capability indicators of each supplier are evaluated. The capability indicators include delivery capability, quality capability, price capability and service capability. According to the capability indicators of each supplier, a corresponding bar chart is constructed for each supplier, and the bar chart is used as the capability portrait of the corresponding supplier. Each column in the bar chart corresponds to a capability indicator, which is used to intuitively display the performance of each supplier in different capability dimensions, and show the comprehensive capability characteristics and advantages and disadvantages of the supplier.

[0088] The steps to assess each supplier's delivery capabilities include:

[0089] Step S101: Construct multiple fuzzy sets for each data point in the delivery performance data. For example, the fuzzy sets corresponding to the on-time delivery rate are high on-time delivery rate, medium on-time delivery rate, low on-time delivery rate, etc., and the fuzzy sets corresponding to the average delivery cycle are long average delivery cycle, medium average delivery cycle, short average delivery cycle, etc.

[0090] Step S102: Each supplier's delivery performance data is converted into the membership of each corresponding fuzzy set using fuzzification technology. Fuzzification technology is the process of converting precise numerical values ​​into the membership of a fuzzy set. Fuzzification technologies include triangular membership functions and trapezoidal membership functions. For example, if the on-time delivery rate is high, the membership of the high on-time delivery rate is inferred to be 0.9, the membership of the medium on-time delivery rate is 0.3, and the membership of the low on-time delivery rate is 0.

[0091] Step S103: Define fuzzy rules. The fuzzy rules are defined based on expert knowledge or relevant literature. For example, if the on-time delivery rate is high, the average delivery cycle is short, and the order fulfillment rate is high, then the corresponding supplier's delivery capability is inferred to be excellent, with a high membership degree. If the on-time delivery rate is low, the average delivery cycle is long, and the order fulfillment rate is low, then the corresponding supplier's delivery capability is inferred to be unsatisfactory, with a high membership degree.

[0092] Step S104: Each set of fuzzified technical feature data is matched with fuzzy rules, and fuzzy reasoning is performed using a fuzzy reasoning method (such as the Mamdani fuzzy reasoning model or the Sugeno fuzzy reasoning model) to obtain a fuzzy reasoning result corresponding to each supplier. The fuzzy reasoning result is the membership degree of each delivery capability level, which includes excellent, good, pass, and fail. For example, the membership degree of excellent is 0.6, the membership degree of good is 0.8, the membership degree of pass is 0.1, and the membership degree of fail is 0.

[0093] Step S105: Set the capability interval. The capability interval range is , is an integer greater than 1, and this embodiment preferably =100; evenly divide the capability interval into four level intervals, with each level interval corresponding to the level in the delivery capability level; add the maximum value of each level interval to the corresponding minimum value and divide by 2 to obtain the interval mean of each level interval;

[0094] Step S106: Multiply the membership degree of each delivery capability level corresponding to each supplier by the corresponding interval mean, and then add them up in sequence to obtain the total capability value of each supplier; add the membership degree of each delivery capability level corresponding to each supplier in sequence to obtain the total membership degree; divide the total capability value of each supplier by the corresponding total membership degree as the delivery capability of each supplier.

[0095] The steps for evaluating each supplier's quality capability, price capability, and service capability are consistent with the steps for evaluating each supplier's delivery capability.

[0096] Methods for quantitatively evaluating the performance scores of different suppliers include:

[0097] A preset proportion set includes a proportional coefficient corresponding to each capability indicator. The proportion set is pre-set by technical personnel in this field based on the actual importance of each capability indicator; each capability indicator of each supplier is multiplied by the corresponding proportional coefficient in the proportion set, and then added up in sequence to obtain the corresponding performance score of each supplier.

[0098] The supplier recommendation module is used to obtain historical order data, integrate historical order data with the capability profiles of different suppliers, build the supplier relationship network topology, and identify synergies between suppliers; it integrates performance scores, future procurement needs, and synergies, and applies intelligent matching algorithms to recommend the optimal supplier combination.

[0099] Historical order data includes the performance data corresponding to each historical cooperative order. Historical cooperative orders are orders in which multiple suppliers collaborate in historical procurement activities of an enterprise. Performance data refers to relevant data that measures the performance of multiple suppliers when collaborating in the same cooperative order, and is used for subsequent calculation of performance data when multiple suppliers collaborate. Performance data includes scheduled delivery time, delivery time, delivery cycle, number of qualified products, number of defective products, number of products purchased, product quotation, problem handling time, etc. Historical order data is obtained through the enterprise's internal enterprise resource planning system, quality management system, historical procurement contracts and supplier management system.

[0100] Methods for building supplier relationship network topology include:

[0101] The multiple suppliers corresponding to each historical cooperation order are regarded as a group of supplier sets, and the supplier sets correspond to the historical cooperation orders one-to-one; the historical cooperation orders with the same supplier set are regarded as a group of order sets, and the order sets correspond to the supplier sets one-to-one; the performance data corresponding to each group of order sets are respectively input into the trained performance evaluation model to predict the corresponding performance data. The performance evaluation model is a deep neural network model; based on the performance data corresponding to different order sets, the capability indicators corresponding to each group of order sets are evaluated; each supplier is regarded as a node, and an edge is established between the nodes corresponding to every two suppliers in each group of supplier sets. The weight of each edge is the capability indicator corresponding to each order set; based on the nodes, edges and edge weights, the supplier relationship network topology is constructed, and the capability portrait of each supplier is used as the attribute of the corresponding node.

[0102] For example, supplier A and supplier B are supplier set 1, and supplier A, supplier B and supplier C are supplier set 2; therefore, in the supplier relationship network topology, supplier A, supplier B and supplier C are each a node; since supplier A and supplier B exist in both supplier set 1 and supplier set 2, there are two edges between supplier A and supplier B, one edge between supplier B and supplier C, and one edge between supplier A and supplier C.

[0103] Steps to identify synergies among suppliers include:

[0104] Step S201: Mark the capability indicators in the corresponding attributes of each node as the first indicator, and mark the corresponding capability indicators in the weight of the edge as the second indicator;

[0105] Step S202: randomly selecting a set of supplier sets that are not marked as selected sets and marking them as current sets;

[0106] Step S203: Compare each first indicator corresponding to each node in the current set with the second indicator corresponding to the corresponding order set in turn; if all first indicators are less than or equal to the corresponding second indicators, then all nodes in the corresponding current set have positive synergy effects, and the corresponding current set is marked as a synergistic set; if there is a first indicator that is greater than the corresponding second indicator, then there is a node in the corresponding current set that has negative synergy effects, and the corresponding current set is not marked;

[0107] Step S204: Mark the current set as a selected set;

[0108] Step S205: looping step S202 to step S204 until all supplier sets are marked as selected sets, the loop ends, and all collaborative sets are obtained.

[0109] Methods for recommending the optimal supplier combination include:

[0110] Based on historical cooperative orders, obtain the historical procurement categories corresponding to each collaborative set and mark them as cooperative procurement categories; based on historical procurement data, obtain the historical procurement categories corresponding to each supplier and mark them as independent procurement categories; compare each demand procurement category with each cooperative procurement category; if there is a demand procurement category that is the same as the cooperative procurement category, mark the corresponding collaborative set as a recommended set; if all demand procurement categories are different from the cooperative procurement categories, do not mark the corresponding collaborative set; mark all demand procurement categories that are different from each cooperative procurement category as remaining procurement categories, and mark the suppliers corresponding to the independent procurement categories that are the same as the remaining procurement categories as candidate suppliers; the candidate suppliers with the same corresponding independent procurement categories are all regarded as a group of candidate sets, and the candidate sets correspond one-to-one with the independent procurement categories;

[0111] According to future procurement needs, the estimated procurement quantity of each remaining procurement category is obtained; according to historical procurement data, the historical procurement quantity corresponding to each candidate supplier is obtained, and the maximum historical procurement quantity corresponding to each candidate supplier is marked as the maximum quantity; each maximum quantity is compared with the corresponding estimated procurement quantity, and the candidate suppliers whose maximum quantity is less than the corresponding estimated procurement quantity are deleted from the corresponding candidate set, and the candidate suppliers whose maximum quantity is greater than or equal to the estimated procurement quantity are retained in the corresponding candidate set; each candidate supplier in each candidate set is sorted from large to small according to the corresponding performance score to generate a supplier ranking table; the suppliers ranked at the top of each supplier ranking table are sorted. All candidate suppliers are marked as the best suppliers. is an integer greater than 0; each best supplier is combined with each set of recommended sets to obtain the optimal supplier combination.

[0112] The strategy formulation module is used to obtain procurement management data, and combined with the supplier performance data corresponding to the optimal supplier combination, it uses multi-objective optimization technology to intelligently formulate personalized procurement strategies.

[0113] Procurement management data includes category inventory, procurement budget and supply cycle; category inventory includes the inventory quantity of each demand procurement category; procurement budget includes the budget amount of each demand procurement category; supply cycle includes the delivery cycle of each demand procurement category; procurement management data is obtained through the enterprise's internal enterprise resource planning system.

[0114] Methods for developing a personalized purchasing strategy include:

[0115] Subtract the corresponding inventory quantity in the category inventory from the estimated purchase quantity of each demand purchase category to obtain the actual purchase quantity of each demand purchase category, and set the quantity range for each demand purchase category. , is the actual purchase quantity; it is randomly selected from the quantity range corresponding to each cooperative purchase category values, and build a set of cooperative sets to build Group into sets; randomly select from the quantity interval corresponding to each independent purchase category values, and construct a set of independent sets, constructing a total of Group independent set; where, is the number of suppliers in the collaborative set, and The sum of the values ​​is , and are all integers greater than 1; randomly select a group of cooperative sets and a group of independent sets to construct a group of procurement sets. Group different purchase collections, ;right The group purchase collection sets the numerical labels that increase in sequence and marks them as purchase labels. The range of purchase labels is ; Randomly select a purchase tag as the initial iteration center;

[0116] Define the iterative process, which is: based on the iteration center, generate within the scope of the procurement tag candidate solutions, and calculate the procurement performance evaluation value corresponding to each candidate solution. , the candidate solutions correspond to the procurement labels one by one; the candidate solution with the largest procurement performance evaluation value is marked as the local solution, the iteration center is moved to the local solution, and the indicator change is calculated;

[0117] An iterative process is executed. When each iterative process is completed, the indicator change is compared with the preset change threshold; if the indicator change is less than the change threshold, a completion instruction is generated; if the indicator change is greater than or equal to the change threshold, no completion instruction is generated; the number of times the completion instruction is generated is counted and marked as the number of instructions; when the number of instructions is greater than or equal to the preset number threshold, the iterative process is stopped; the procurement label corresponding to the iteration center is marked as the best label, and the procurement set corresponding to the best label is used as the procurement strategy; the change threshold and the number threshold are both pre-set by technical personnel in this field according to actual conditions.

[0118] Methods for calculating the procurement performance evaluation value corresponding to the candidate solution include:

[0119] Obtain the procurement set corresponding to the procurement label of the candidate solution and mark it as the calculation set; obtain the supplier performance data corresponding to each supplier in the calculation set and mark it as calculation data; use the calculation data, calculation set, and procurement management data as performance prediction data; input the performance prediction data into the trained performance prediction model to predict the corresponding procurement performance data; the performance prediction model includes a cost prediction model, a supply prediction model, and a quality prediction model, and all performance prediction models are deep neural network models; procurement performance data includes procurement cost, supply cycle, and product quality; the cost prediction model is used to predict procurement cost, the supply prediction model is used to predict supply cycle, and the quality prediction model is used to predict product quality;

[0120] Subtract the procurement cost from the procurement budget to obtain the budget surplus; subtract the supply cycle from the delivery cycle to obtain the delivery deviation; preset an indicator weight set, which includes indicator weights corresponding to the budget surplus, delivery deviation, and product quality. The indicator weight set is pre-set by technical personnel in this field based on actual conditions; multiply the budget surplus, delivery deviation, and product quality by the corresponding indicator weights in the indicator weight set to obtain the budget coefficient, delivery coefficient, and quality coefficient; add the budget coefficient to the quality coefficient and then the delivery coefficient to obtain the procurement performance evaluation value;

[0121] It should be understood that the delivery lead time is the time the company expects the supplier to complete the delivery, and the supply lead time is the time the supplier estimates to complete the delivery.

[0122] The method for calculating the change in the indicator is: subtract the procurement performance evaluation value corresponding to the iteration center in the previous iteration from the procurement performance evaluation value corresponding to the iteration center in this iteration, and take the absolute value to obtain the change in the indicator.

[0123] It should be noted that the purpose of formulating personalized procurement strategies is to make flexible adjustments based on the company's actual situation such as budget, inventory and delivery cycle, so as to optimize procurement decisions, reduce procurement costs, improve delivery efficiency and ensure product quality; at the same time, through dynamic iterative optimization, improve procurement efficiency, supply chain stability and flexibility, and ultimately achieve the goals of cost control, resource optimization and supply chain risk management.

[0124] This embodiment uses deep learning technology to integrate multi-dimensional factors such as historical procurement data and market trend data to achieve accurate perception and prediction of future procurement needs; it builds capability portraits based on supplier performance data and uses a combination of fuzzy evaluation and quantitative analysis to comprehensively evaluate suppliers, which can more objectively quantify the supplier's performance in key capabilities such as delivery, quality, and price; by analyzing the supplier relationship network, it identifies the synergy between suppliers, providing an important basis for recommending the optimal supplier combination, which is conducive to leveraging the synergy advantages between suppliers and improving the overall efficiency of the supply chain; in the procurement strategy formulation stage, it integrates multi-dimensional constraints such as supplier performance, procurement demand, and inventory, and uses an iterative optimization method to dynamically generate personalized procurement plans, achieving a refined balance and dynamic adjustment between multiple objectives such as cost, delivery, and quality, thereby maximizing the scientific nature and effectiveness of procurement decisions; it not only improves procurement efficiency and reduces costs, but also enhances the flexibility and resilience of the supply chain, thereby effectively improving the overall response speed, cost control capabilities, and operational quality of the supply chain, thereby enhancing the company's market competitiveness.

[0125] Example 2

[0126] See also Figure 2 As shown, for parts not described in detail in this embodiment, please refer to the description of Example 1. A smart procurement method for a supply chain is provided, and the method includes:

[0127] Collect supply chain management data, including demand forecast data and supplier performance data;

[0128] Conduct in-depth mining of demand forecast data and use deep learning technology to dynamically predict future procurement needs;

[0129] Generate capability profiles of different suppliers based on supplier performance data, and quantitatively evaluate the performance scores of different suppliers based on a pre-built evaluation system;

[0130] Obtain historical order data, integrate it with the capability profiles of different suppliers, build a supplier relationship network topology, and identify synergies between suppliers. Combine performance scores, future procurement needs, and synergies to apply intelligent matching algorithms to recommend the optimal supplier combination.

[0131] Acquire procurement management data, combine it with supplier performance data corresponding to the optimal supplier combination, and use multi-objective optimization technology to intelligently formulate personalized procurement strategies.

[0132] Example 3

[0133] The present application also provides an electronic device. The electronic device may include one or more processors and one or more memories. The memories may store computer-readable code that, when executed by the one or more processors, may execute the intelligent procurement method for a supply chain as described above.

[0134] The method or system according to the embodiment of the present application can also be implemented with the help of the architecture of the electronic device shown in this application. The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, input / output, a hard disk, etc. The storage device in the electronic device, such as ROM or hard disk, can store a smart procurement method for a supply chain provided in this application. Furthermore, the electronic device may also include a user interface. Of course, the architecture shown in this application is only exemplary. When implementing different devices, one or more components in the electronic device shown in this application can be omitted according to actual needs.

[0135] Example 4

[0136] One embodiment of the present application discloses a computer-readable storage medium. The computer-readable storage medium stores computer-readable instructions. When the computer-readable instructions are executed by a processor, the intelligent procurement method for a supply chain according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), a hard disk, flash memory, etc.

[0137] In addition, according to embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the present application provides a non-transitory machine-readable storage medium storing machine-readable instructions that can be executed by a processor to perform instructions corresponding to the steps of the method provided in the present application, such as a smart procurement method for a supply chain. When the computer program is executed by a central processing unit (CPU), the above-described functions defined in the method of the present application are performed.

[0138] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will be able to modify the technical solutions described in the foregoing embodiments or to substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

[0139] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0140] In the description of the present invention, it should be understood that the terms "first", "second", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0141] In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0142] In the description of the present invention, “several” means one or more, and “a large number” means two or more.

[0143] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0144] The formulas in this manual are all dimensionless and calculated using numerical values. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field based on actual conditions.

[0145] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

Claims

1. A smart procurement method for a supply chain, characterized in that: include: Collect supply chain management data, including demand forecast data and supplier performance data; the demand forecast data includes historical procurement data, market trend data, and demand procurement categories; the historical procurement data includes historical procurement time, historical procurement categories, and historical procurement quantities; Conduct in-depth mining of demand forecast data and use deep learning technology to dynamically predict future procurement needs; Generate capability profiles of different suppliers based on supplier performance data, and quantitatively evaluate the performance scores of different suppliers based on a pre-built evaluation system; Obtain historical order data, integrate it with the capability profiles of different suppliers, build a supplier relationship network topology, and identify synergies between suppliers. Combine performance scores, future procurement needs, and synergies to apply intelligent matching algorithms to recommend the optimal supplier combination. The historical order data includes performance data corresponding to each historical cooperation order; The method for constructing a supplier relationship network topology includes: The multiple suppliers corresponding to each historical cooperative order are considered as a supplier set, and the historical cooperative orders with the same supplier set are considered as an order set. The performance data corresponding to each order set is input into the trained performance evaluation model to predict the corresponding performance data. Based on the performance data corresponding to different order sets, the capability indicators corresponding to each order set are evaluated. Each supplier is regarded as a node, and an edge is established between the nodes corresponding to every two suppliers in each supplier set. The weight of each edge is the capability indicator corresponding to each order set. Based on the nodes, edges, and edge weights, the supplier relationship network topology is constructed, and the capability profile of each supplier is used as the attribute of the corresponding node. Steps to identify synergies among suppliers include: Step S201: Mark the capability indicators in the corresponding attributes of each node as the first indicator, and mark the corresponding capability indicators in the weight of the edge as the second indicator; Step S202: randomly selecting a set of supplier sets that are not marked as selected sets and marking them as current sets; Step S203: Compare each first indicator corresponding to each node in the current set with the second indicator corresponding to the corresponding order set in turn; if all first indicators are less than or equal to the corresponding second indicators, then all nodes in the corresponding current set have a positive synergistic effect, and the corresponding current set is marked as a synergistic set; Step S204: Mark the current set as a selected set; Step S205: looping steps S202 to S204 until all supplier sets are marked as selected sets, the loop ends, and all collaborative sets are obtained; Based on historical cooperative orders, obtain the historical procurement categories corresponding to each collaborative set and mark them as cooperative procurement categories; based on historical procurement data, obtain the historical procurement categories corresponding to each supplier and mark them as independent procurement categories; Acquire procurement management data, combine it with supplier performance data corresponding to the optimal supplier combination, and use multi-objective optimization technology to intelligently formulate personalized procurement strategies.

2. The intelligent procurement method for supply chain according to claim 1, characterized in that: The market trend data includes raw material price fluctuation data and market demand change data. The raw material price fluctuation data includes the market prices of raw materials required by different supply chain products at different time points, and the market demand change data includes the total demand for different supply chain products at different time points. The supplier performance data includes the performance data corresponding to each supplier; Methods for dynamically forecasting future procurement needs include: The historical purchase quantities of the same corresponding historical purchase category are grouped as a quantity set; a time interval is preset, and a time axis is constructed for each quantity set based on the time interval; wherein, on each time axis, the time difference between every two adjacent time points is equal to the time interval, and each time point corresponds to a historical purchase quantity in the corresponding quantity set; Based on the historical purchase quantity corresponding to each time point on each time axis, a quantity prediction model is constructed for each quantity set, and the quantity prediction model is a recurrent neural network model; a time window of length a is preset, where a is an integer greater than 1; the quantity set corresponding to each demand purchase category is marked as a demand set, and the time axis corresponding to the demand set is marked as a demand axis; starting from the last time point on each demand axis, a set of time sets is obtained from the demand axis corresponding to each demand set based on the time window, and each time set includes a time points; the historical purchase quantity corresponding to each time set is input into the corresponding quantity prediction model, and the corresponding future purchase quantity is predicted; According to market trend data, calculate the first factor and the second factor corresponding to each set of demand in turn; set the weight coefficients of each first factor and each second factor respectively, multiply each first factor and each second factor by the corresponding weight coefficient in turn to obtain the influence weight, and take the average of the same influence weights of the corresponding demand sets as the comprehensive influence factor; multiply each future purchase quantity by the corresponding comprehensive influence factor to obtain the expected purchase quantity of each set of demand, and use it as the future purchase demand.

3. The intelligent procurement method for supply chain according to claim 2, characterized in that: Methods for constructing a timeline for a collection of quantities include: The earliest historical purchase time corresponding to the historical purchase quantity in the quantity set is marked as the earliest time, and the earliest time is used as the first time point on the time axis; starting from the earliest time, continuous time points are generated on the time axis according to the time interval; the time points on the time axis are compared with the historical purchase time corresponding to each historical purchase quantity in the quantity set; the historical purchase quantities corresponding to the same historical purchase time as the time point are mapped to the corresponding time points in sequence; the time points that are different from all historical purchase times are marked as interpolation points, and the historical purchase quantity corresponding to each interpolation point is calculated using the polynomial interpolation method, and mapped to the corresponding interpolation point; The method for calculating the first factor and the second factor corresponding to each set of requirements includes: Market trend data are mapped to each time point on each demand axis respectively, and each time point corresponds to a set of market prices and a total demand; according to the market price, total demand and historical purchase quantity corresponding to each time point on each demand axis, a market impact model is constructed for each demand set; the market impact model is a deep neural network model; the earliest time point in each time set is marked as a temporary early point, and taking the time point before the corresponding temporary early point on each demand axis as the starting point, a set of time-front sets is obtained from each demand axis based on the time window, and each time-front set includes a time points; the market price, total demand and historical purchase quantity corresponding to each time set are respectively input into the corresponding market impact model to predict the corresponding first factor; the market price, total demand and historical purchase quantity corresponding to each time set are respectively input into the corresponding market impact model to predict the corresponding second factor.

4. The intelligent procurement method for supply chain according to claim 3, characterized in that: The method for generating capability profiles of different suppliers includes: Based on the performance data of different suppliers, the capability indicators of each supplier are evaluated. The capability indicators include delivery capability, quality capability, price capability and service capability. According to the capability indicators of each supplier, a corresponding bar chart is constructed for each supplier, and the bar chart is used as the capability portrait of the corresponding supplier.

5. The intelligent procurement method for supply chain according to claim 4, characterized in that: The steps to assess each supplier's delivery capabilities include: Step S101: construct multiple fuzzy sets for each data in the delivery performance data; Step S102: converting the delivery performance data of each supplier into the membership degree of each corresponding fuzzy set through fuzzification technology; Step S103: defining fuzzy rules; Step S104: Match each set of fuzzified technical feature data with fuzzy rules respectively, and perform fuzzy reasoning using a fuzzy reasoning method to obtain the fuzzy reasoning results corresponding to each supplier. The fuzzy reasoning results are the membership degrees of each delivery capability level. Step S105: Set the capability interval, which ranges from [0, c], where c is an integer greater than 1. Evenly divide the capability interval into four level intervals, with each level interval corresponding to a level in the delivery capability level. Add the maximum value of each level interval to the corresponding minimum value and divide by 2 to obtain the interval mean of each level interval. Step S106: Multiply the membership degree of each supplier's corresponding delivery capability level by the corresponding interval mean, and then add them up in sequence to obtain the total capability value of each supplier; add the membership degree of each supplier's corresponding delivery capability level in sequence to obtain the total membership degree; divide the total capability value of each supplier by the corresponding total membership degree to obtain the delivery capability of each supplier; The steps for evaluating each supplier's quality capability, price capability, and service capability are consistent with those for evaluating each supplier's delivery capability; The method for quantitatively evaluating the performance scores of different suppliers includes: A preset ratio set, where the ratio set includes the ratio coefficients corresponding to each ability index; multiply each ability index of each supplier by the corresponding ratio coefficient in the ratio set, and then add them up in turn to obtain the performance score corresponding to each supplier.

6. The intelligent procurement method for supply chain according to claim 5, characterized in that: The performance evaluation model is a deep neural network model; If there is a first index greater than the corresponding second index, there is a reverse synergy effect in the current set of nodes corresponding to it, and the corresponding current set is not marked.

7. The intelligent procurement method for supply chain according to claim 6, characterized in that: The method for recommending the optimal supplier combination includes: Compare each demand procurement category with each cooperative procurement category; if there is a demand procurement category that is the same as the cooperative procurement category, mark the corresponding synergy set as the recommended set; if all demand procurement categories and cooperative procurement categories are different, do not mark the corresponding synergy set; mark all demand procurement categories that are different from each cooperative procurement category as the remaining procurement categories, and mark the suppliers corresponding to the independent procurement categories that are the same as the remaining procurement categories as candidate suppliers; all candidate suppliers corresponding to the same independent procurement category are used as a group of candidate sets, and the candidate sets correspond one-to-one with the independent procurement categories; According to the future procurement requirements, obtain the estimated procurement quantity of each remaining procurement category; according to the historical procurement data, obtain the historical procurement quantity corresponding to each candidate supplier, and mark the largest historical procurement quantity corresponding to each candidate supplier as the maximum quantity; compare each maximum quantity with the corresponding estimated procurement quantity, delete the candidate suppliers whose maximum quantity is less than the corresponding estimated procurement quantity from the corresponding candidate set, and the candidate suppliers whose maximum quantity is greater than or equal to the estimated procurement quantity remain in the corresponding candidate set; sort each candidate supplier in each candidate set according to the corresponding performance score from large to small to generate a supplier ranking list; mark the top d candidate suppliers in each supplier ranking list as the best suppliers, where d is an integer greater than 0; combine each best supplier with each group of recommended sets to obtain the optimal supplier combination.

8. The intelligent procurement method for supply chain according to claim 7, characterized in that: The procurement management data includes category inventory, procurement budget, and supply cycle; the category inventory includes the inventory quantity of each demand procurement category; the procurement budget includes the budget amount of each demand procurement category; the supply cycle includes the delivery cycle of each demand procurement category; The method for formulating a personalized procurement strategy includes: Construct m different procurement sets, set sequentially increasing digital labels for the m procurement sets, and mark them as procurement labels, where the range of the procurement labels is [1, m]; randomly select a procurement label as the initial iteration center; Define the iteration process, and the iteration process is: according to the iteration center, generate n candidate solutions within the range of the procurement labels, and calculate the procurement performance evaluation value corresponding to each candidate solution, where 1 < n < d, and the candidate solutions correspond one-to-one with the procurement labels; mark the candidate solution with the largest procurement performance evaluation value as the local solution, move the iteration center to the local solution, and calculate the index change amount; Execute the iterative process. When each iterative process is completed, compare the indicator change with the preset change threshold. If the indicator change is less than the change threshold, generate a completion instruction. If the indicator change is greater than or equal to the change threshold, do not generate a completion instruction. Count the number of times the completion instruction is generated and mark it as the number of instructions. When the number of instructions is greater than or equal to the preset number threshold, stop executing the iterative process. Mark the procurement label corresponding to the iteration center as the best label, and use the procurement set corresponding to the best label as the procurement strategy.

9. The intelligent procurement method for supply chain according to claim 8, characterized in that: Methods for calculating the procurement performance evaluation value corresponding to the candidate solution include: Obtain the procurement set corresponding to the procurement label of the candidate solution and mark it as the calculation set; obtain the supplier performance data corresponding to each supplier in the calculation set and mark it as calculation data; use the calculation data, calculation set, and procurement management data as performance prediction data; input the performance prediction data into the trained performance prediction model to predict the corresponding procurement performance data; the performance prediction model includes a cost prediction model, a supply prediction model, and a quality prediction model, all of which are deep neural network models; procurement performance data includes procurement cost, delivery cycle, and product quality; Subtract the procurement cost from the procurement budget to obtain the budget surplus; subtract the supply cycle from the delivery cycle to obtain the delivery deviation; preset an indicator weight set, which includes the indicator weights corresponding to the budget surplus, delivery deviation, and product quality; multiply the budget surplus, delivery deviation, and product quality by the corresponding indicator weights in the indicator weight set to obtain the budget coefficient, delivery coefficient, and quality coefficient; add the budget coefficient to the quality coefficient and then the delivery coefficient to obtain the procurement performance evaluation value; The method for calculating the change in the indicator is: subtract the procurement performance evaluation value corresponding to the iteration center in the previous iteration from the procurement performance evaluation value corresponding to the iteration center in this iteration, and take the absolute value to obtain the change in the indicator.

10. An intelligent procurement system for a supply chain, implementing the intelligent procurement method for a supply chain according to any one of claims 1 to 9, characterized in that: include: Data collection module, used to collect supply chain management data, including demand forecast data and supplier performance data; Demand forecasting module, which is used to conduct in-depth mining of demand forecasting data and dynamically predict future procurement needs using deep learning technology; The supplier evaluation module is used to generate capability profiles of different suppliers based on supplier performance data and quantitatively evaluate the performance scores of different suppliers according to a pre-built evaluation system; The supplier recommendation module is used to obtain historical order data, integrate it with the capability profiles of different suppliers, build a supplier relationship network topology, and identify synergies between suppliers. It also integrates performance scores, future procurement needs, and synergies to apply intelligent matching algorithms to recommend the optimal supplier combination. The strategy formulation module is used to obtain procurement management data, and combined with the supplier performance data corresponding to the optimal supplier combination, it uses multi-objective optimization technology to intelligently formulate personalized procurement strategies.

Images