Product supply chain optimization method for goods emergency complementation

Abstract

The invention discloses a product supply chain optimization method for goods emergency complementation, and the method comprises the steps: building a product supply chain model through obtaining the product information of goods, monitoring the goods inventory of each node in a supply chain, collecting the inventory data and demand data of each node in real time, and setting an inventory database, and uploading the collected data to the inventory database and setting a threshold value, when the inventory data is lower than the set threshold value, scheduling goods from other supply nodes to a shortage node, carrying out real-time monitoring on scheduling, setting a scheduling route deviation threshold value, and when scheduling route deviation occurs, giving an alarm according to the deviation degree and reminding a worker to process. According to the invention, emergency complementation can be efficiently and accurately carried out on the goods with shortage nodes, so that product supply chain optimization is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of supply chain, and in particular to a product supply chain optimization method for emergency complementary goods. Background Art

[0002] In modern supply chain management, a stable supply of goods is a key factor in ensuring a balance between production and market demand. However, due to the uncertainty of market demand, natural disasters and other emergencies, there may be shortages of goods at certain nodes in the supply chain, resulting in reduced efficiency of the entire supply chain.

[0003] The Chinese patent publication number: CN 112906173 A discloses a method for designing a fresh product supply chain network under power grid interruption. The invention aims at the problem of designing a fresh product supply chain network, considers two major factors, namely power interruption and raw material quantity discount, and establishes a closed-loop fresh supply chain network multi-objective fuzzy optimization design model to solve the uncertainty problem in supply chain network design.

[0004] The core technical solution is to design the closed-loop supply chain network structure of fresh products under power grid interruption, determine the parameters of each node at the power grid layer and the supply chain layer; establish and weight optimization models with the goals of minimizing cost, minimizing carbon emissions, and minimizing interruption time for the power grid layer and the supply layer respectively; and use the Me measure to fuzzy process the model. The above content only solves the uncertainty problem in the design of the supply chain network, and cannot efficiently and accurately provide emergency replenishment of goods at the shortage nodes when an emergency occurs and causes a shortage of goods.

[0005] The present invention proposes solutions to the above shortcomings as follows: establish a product supply chain model, set up an inventory database and set a threshold, use the inventory threshold to determine the triggering of the emergency complement mechanism to dispatch goods, and monitor the entire dispatch in real time, set a dispatch route deviation threshold, and issue an alarm when a dispatch anomaly occurs to remind staff to handle it, so as to efficiently and accurately perform emergency complementation of goods at shortage nodes. Summary of the invention

[0006] In order to solve the above-mentioned technical problems, the present invention provides a product supply chain optimization method for emergency complementary goods.

[0007] The technical solution of the present invention is implemented as follows: a product supply chain optimization method for emergency complementary goods, comprising:

[0008] S1. Collect detailed information about the goods, including specifications, shelf life, and production date, establish a product database, use machine learning algorithms, build a product supply chain model based on historical data, and predict inventory requirements at each node;

[0009] S2. Establish a product supply chain model based on the acquired product information, wherein the product supply chain model includes multiple supply nodes and demand nodes, establish an inventory database, store the inventory data and demand data of all nodes, and set an inventory threshold to determine whether an emergency complementary mechanism needs to be triggered;

[0010] S3, monitoring the inventory of goods at each node in the product supply chain model, collecting inventory data and demand data of each node in real time, using RFID wireless radio frequency identification technology, updating inventory data, setting up a data collection terminal, collecting inventory data and demand data in real time, and the data collection terminal transmits the data to the inventory database through the network;

[0011] S4, uploading the collected inventory data and demand data of each node to the inventory database, and setting the inventory node shortage threshold to determine whether scheduling needs to be started;

[0012] S5. When the inventory data before the inventory database is updated reaches the inventory threshold, the emergency complementary mechanism is triggered, and the inventory data and demand data of each node collected by the data collection terminal are uploaded to the inventory database. When the updated inventory data reaches the inventory node shortage threshold, scheduling is started;

[0013] S6. Monitor the dispatch in real time and set the dispatch route deviation threshold. When a deviation occurs, an alarm will be issued according to the degree of deviation and the staff will be reminded to handle it;

[0014] S7. Continue to collect data from step S1 to step S6 to adjust the supply chain model, and adjust the inventory threshold and scheduling strategy based on the inventory database feedback.

[0015] Furthermore, in step S1, product information is collected to establish a supply chain model:

[0016] Collect detailed information about the product, including specifications, shelf life, and production date, and establish a product database. The product information in the default product database is represented by a set O, where O = {O1, O2, …, O n}, historical data analysis uses machine learning algorithms, and machine learning methods include regression analysis or time series analysis;

[0017] Furthermore, in step S2, an inventory database is established and an inventory threshold is set:

[0018] Establish an inventory database to store the inventory data and demand data of all nodes. The inventory data in the preset inventory database is represented by a set of numbers A, where A = {a1, a2, ..., a n}, the demand data is represented by a set of numbers B, where B = {b1, b2, …, b n}; Set the inventory threshold to determine whether the emergency replenishment mechanism needs to be triggered. The preset inventory threshold number set T = {t1, t2, …, t n}.

[0019] Furthermore, in the step S3, the inventory is monitored and data is collected in real time:

[0020] Monitor the inventory of goods at each node in the product supply chain model, collect inventory data and demand data in real time, and preset the real-time collected inventory data set C = {c1, c2, ..., c n}, the real-time collected demand data set D = {d1, d2, ..., d n}, data collection uses RFID technology to automatically identify goods and update inventory data. The preset updated inventory data set A1 = {a11, a12, ..., a1 n}.

[0021] Furthermore, in the step S4, it is determined whether to enable scheduling:

[0022] The collected inventory data and demand data of each node are uploaded to the inventory database. The preset uploaded inventory data set A2 = {a21, a22, ..., a2 n}, then, determine whether to start scheduling. When the inventory data is lower than the set inventory node shortage threshold, start scheduling. The preset inventory node shortage threshold number set M = {m1, m2, …, m n}.

[0023] Furthermore, in step S5, scheduling is enabled:

[0024] The inventory data set A before the inventory database is updated is compared with the inventory threshold set T, where the threshold judgment standard is preset as output 1 for triggering and output 0 for not triggering. n <t n When the output is 1, the emergency complementary mechanism is triggered. n >t n And a n =t n When the emergency complementary mechanism is triggered, the output is 0, indicating that the emergency complementary mechanism is not triggered. The inventory database continues to collect data information of the goods. When the emergency complementary mechanism is triggered, the data collected by the data collection terminal is uploaded to the inventory database, and the updated inventory data set A2 is compared with the preset inventory node shortage threshold set M. When a2 n <m n When the output is 1, the scheduling is turned on. When a2 n >m n And a2 n =m nWhen , the output is 0, and the inventory database will continue to collect the inventory data and demand data of each node when the emergency complementary mechanism is triggered;

[0025] Among them, a n is one or more subsets of the inventory data set A before updating, t n is one or more subsets of the inventory threshold set T, a2 n One or more subsets of the inventory data set A2 updated for the inventory database, m n is one or more subsets of the inventory node shortage threshold number set M.

[0026] Furthermore, in step S6, real-time monitoring and scheduling are performed:

[0027] Real-time monitoring of the dispatching and the cargo transportation routes are performed, and the preset number set of monitored cargo transportation routes R = {r1, r2, …, r n}, determine route deviation, set the dispatch route deviation threshold, and issue an alarm when deviation occurs. The preset route deviation threshold number set N = {n1, n2, ..., n n};

[0028] Furthermore, the route deviation judgment process is as follows:

[0029] The preset monitored cargo transportation route number set R is compared with the preset route deviation threshold number set N, where the threshold judgment standard is preset as output 1 for triggering and output 0 for not triggering. n <n n When r n >n n And r n =n n When , the output is 0, it means that the route is transporting goods normally;

[0030] Among them, r n is one or more subsets of the set R of cargo transportation routes, n n is one or more subsets of the route deviation threshold number set N;

[0031] Furthermore, the alarm is issued when:

[0032] Record the dispatch route n <n n When the output is 1, it is a route deviation point, which is preset to K. Then the route deviation point subset is K = {k1, k2, ..., k n}, the alarm level is determined based on the ratio of route deviation points to the goods transportation route:

[0033] When it is the primary alarm, send a primary warning reminder.

[0034] When it is the severe alarm, immediately notify the relevant staff to take measures for handling.

[0035] Among them, 10% refers to the proportion of the route deviation point K in the goods transportation route R.

[0036] Furthermore, in the S7 step, continuously collect the data of steps S1 to S6 and adjust the supply chain model:

[0037] Continuously collect the data of steps S1 to S6 and optimize the supply chain model.

[0038] The optimization of the supply chain model is achieved by minimizing the prediction error ε and completed through iterative training of machine learning algorithms: fuse the data of steps S1 - S6 together and calculate to obtain the optimized supply chain model to achieve the S7 step.

[0039] First, define the supply chain model prediction function as f, which predicts the inventory demand Y based on the input variable X. The input variable X includes goods information O, inventory data A, demand data B, real - time inventory data C, real - time demand data D, scheduling information, and the error term ε represents the uncertainty of the prediction.

[0040] Y = f(X)+ε

[0041] Where: X = [O,A,B,C,D,R,N];

[0042] Specifically: Y = f(O,A,B,C,D,R,N)+ε;

[0043] The S7 step considers the data and calculations of the following steps:

[0044] S1 step: Goods information O and the supply chain model f based on historical data;

[0045] S2 step: Inventory data A, demand data B, and inventory threshold T;

[0046] S3 step: Real - time inventory data C and real - time demand data D;

[0047] S4 step: Updated inventory data A2 and inventory node shortage threshold M;

[0048] S5 step: Trigger conditions for scheduling, that is, A < T and A2 < M;

[0049] S6 step: Goods transportation route R and route deviation threshold N;

[0050] Construct an objective function for the optimization of the S7 step by combining the above information:

[0051]

[0052] Among them, Yi is the actual inventory demand, f(Xi) is the inventory demand predicted by the model, and Xi is the input data set containing all relevant data;

[0053] To simultaneously consider the threshold conditions in steps S5 and S6, these conditions are added as constraints to the optimization problem:

[0054]

[0055] Among them, δ S5,i and δ S6,i are indicator functions, which are 1 when the conditions are met and 0 otherwise;

[0056] Among them, Y: represents the output of the supply chain model, which refers to the predicted inventory demand or other key indicators;

[0057] f: represents the prediction function, which converts the input variable X into the output Y;

[0058] X: represents the input variable, which contains all relevant factors affecting the supply chain model, including goods information O, inventory data A, demand data B, real-time inventory data C, real-time demand data D, transportation route R, and route deviation threshold N;

[0059] ε: represents the error term, which reflects the difference between the predicted value Y and the actual value;

[0060] min: represents minimization, that is, the optimization goal is to find the values of f, T, M, and N that minimize the prediction error ε;

[0061] ∑: represents summation, that is, summing over all i values to ensure the optimization of the entire supply chain;

[0062] δS5,i: represents an indicator function used to indicate whether the condition Ai < Ti is met. When the condition is met, δS5,i = 1; otherwise, δS5,i = 0;

[0063] δS6,i: represents an indicator function used to indicate whether the condition Ri < Ni is met. When the condition is met, δS6,i = 1; otherwise, δS6,i = 0;

[0064] Finally, the optimization problem in step S7 is formulated as a minimization problem with constraints, and the prediction error ε is minimized by adjusting the model parameters f, the inventory threshold T, and the inventory node shortage threshold M.

[0065] Beneficial effects

[0066] The present invention aims at the shortcoming of the prior art that it is impossible to efficiently and accurately carry out emergency replenishment of goods at shortage nodes when an emergency occurs and causes a shortage of goods. The present invention establishes a product supply chain model by acquiring product information of goods, monitors the inventory of goods at each node in the supply chain, collects inventory data and demand data of each node in real time, and sets an inventory database. The collected data is uploaded to the inventory database and a threshold is set. When the inventory data is lower than the set threshold, goods are dispatched from other supply nodes to the shortage node, and the dispatch is monitored in real time, so as to efficiently and accurately carry out emergency replenishment of goods at the shortage node. By real-time monitoring and predicting the inventory demand of each node, the present invention can timely discover and respond to shortages of goods, thereby ensuring the stability and efficiency of the supply chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a structural block diagram of a product supply chain optimization method for emergency complementary goods in an embodiment of the present invention;

[0068] Figure 2 A flowchart of a scheduling process for a method for optimizing a product supply chain for emergency complementary goods according to an embodiment of the present invention;

[0069] Figure 3 This is a flow chart of a method for optimizing a product supply chain for emergency complementary goods according to an embodiment of the present invention. DETAILED DESCRIPTION

[0070] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0071] The preferred implementation methods of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these implementation methods are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0072] When used herein, the singular forms "a", "an", and "said / the" may also include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "include / comprise" or "have" and the like specify the presence of stated features, wholes, steps, operations, components, parts, or combinations thereof, but do not exclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof. At the same time, the term "and / or" used in this specification includes any and all combinations of the relevant listed items.

[0073] See also Figure 1-Figure 3 As shown, a product supply chain optimization method for emergency complementary goods includes:

[0074] S1. Collect detailed information about the goods, including specifications, shelf life, and production date, establish a product database, use machine learning algorithms, build a product supply chain model based on historical data, and predict inventory requirements at each node;

[0075] S2. Establish a product supply chain model based on the acquired product information, wherein the product supply chain model includes multiple supply nodes and demand nodes, establish an inventory database, store the inventory data and demand data of all nodes, and set an inventory threshold to determine whether an emergency complementary mechanism needs to be triggered;

[0076] S3, monitoring the inventory of goods at each node in the supply chain model, collecting inventory data and demand data of each node in real time, using RFID wireless radio frequency identification technology, updating inventory data, setting up data collection terminals, collecting inventory data and demand data in real time, and the data collection terminals transmitting data to the inventory database through the network;

[0077] S4, uploading the collected inventory data and demand data of each node to the inventory database, and setting the inventory node shortage threshold to determine whether scheduling needs to be started;

[0078] S5. When the inventory data before the inventory database is updated reaches the inventory threshold, the emergency complementary mechanism is triggered, and the inventory data and demand data of each node collected by the data collection terminal are uploaded to the inventory database. When the updated inventory data reaches the inventory node shortage threshold, scheduling is started;

[0079] S6. Monitor the dispatch in real time and set the dispatch route deviation threshold. When a deviation occurs, an alarm will be issued according to the degree of deviation and the staff will be reminded to handle it;

[0080] S7. Continue to collect data from step S1 to step S6 to adjust the supply chain model, and adjust the inventory threshold and scheduling strategy based on the inventory database feedback.

[0081] like Figure 1-3 As shown, in step S1, detailed information about the goods is collected, including specifications, shelf life, and production date, a goods database is established, and a machine learning algorithm is used to establish a product supply chain model based on historical data to predict inventory requirements at each node.

[0082] Specifically, detailed information of the goods, including specifications, shelf life, and production date, is collected, and a goods database is established. The goods information in the default goods database is represented by a number set O, where O = {O1, O2, ..., O n}, historical data analysis uses machine learning algorithms, and machine learning methods include regression analysis or time series analysis to establish product supply chains and predict inventory requirements at each node.

[0083] like Figure 3 As shown, in step S2, a product supply chain model is established based on the acquired product information. The product supply chain model includes multiple supply nodes and demand nodes, an inventory database is established to store the inventory data and demand data of all nodes, and an inventory threshold is set to determine whether it is necessary to trigger an emergency complementary mechanism.

[0084] Specifically, an inventory database is established to store the inventory data and demand data of all nodes. The inventory data in the preset inventory database is represented by a set of numbers A, where A = {a1, a2, ..., a n}, the demand data is represented by a set of numbers B, where B = {b1, b2, …, b n}; Set the inventory threshold to determine whether the emergency replenishment mechanism needs to be triggered. The preset inventory threshold number set T = {t1, t2, …, t n}.

[0085] like Figure 3 As shown, in step S3, the inventory of goods at each node in the supply chain model is monitored, the inventory data and demand data of each node are collected in real time, RFID wireless radio frequency identification technology is used to update the inventory data, a data collection terminal is set, the inventory data and demand data are collected in real time, and the data collection terminal transmits the data to the inventory database through the network.

[0086] Specifically, the inventory of goods at each node in the product supply chain model is monitored, inventory data and demand data are collected in real time, and a preset real-time collected inventory data set C = {c1, c2, ..., c n}, the real-time collected demand data set D = {d1, d2, ..., d n}, data collection uses RFID technology to automatically identify goods and update inventory data. The preset updated inventory data set A1 = {a11, a12, ..., a1 n}.

[0087] like Figure 3 As shown, in step S4, the collected inventory data and demand data of each node are uploaded to the inventory database, and an inventory node shortage threshold is set to determine whether scheduling needs to be started.

[0088] Specifically, the collected inventory data and demand data of each node are uploaded to the inventory database, and the preset uploaded inventory data set A2 = {a21, a22, ..., a2 n}, then, determine whether to start scheduling. When the inventory data is lower than the set inventory node shortage threshold, start scheduling. The preset inventory node shortage threshold number set M = {m1, m2, …, m n}.

[0089] like Figure 3As shown, in step S5, when the inventory data before the inventory database is updated reaches the inventory threshold, the emergency complementary mechanism is triggered, and when the updated inventory data after the inventory data and demand data of each node collected by the data collection terminal and uploaded to the inventory database reaches the inventory node shortage threshold, scheduling is started.

[0090] Specifically, the inventory data set A before the inventory database is updated is compared with the inventory threshold set T, where the threshold judgment standard is preset as output 1 for triggering and output 0 for not triggering. n <t n When the output is 1, the emergency complementary mechanism is triggered. n >t n And a n =t n When the emergency complementary mechanism is triggered, the output is 0, indicating that the emergency complementary mechanism is not triggered. The inventory database continues to collect data information of the goods. When the emergency complementary mechanism is triggered, the data collected by the data collection terminal is uploaded to the inventory database, and the updated inventory data set A2 is compared with the preset inventory node shortage threshold set M. When a2 n <m n When the output is 1, the scheduling is turned on. When a2 n >m n And a2 n =m n When , the output is 0, and the inventory database will continue to collect the inventory data and demand data of each node when the emergency complementary mechanism is triggered;

[0091] Among them, a n is one or more subsets of the inventory data set A before updating, t n is one or more subsets of the inventory threshold set T, a2 n One or more subsets of the inventory data set A2 updated for the inventory database, m n is one or more subsets of the inventory node shortage threshold number set M.

[0092] like Figure 2-Figure 3 As shown, in step S6, the dispatch is monitored in real time, and a dispatch route deviation threshold is set. When a deviation occurs, an alarm is issued according to the degree of deviation and the staff is reminded to handle it.

[0093] Specifically, the dispatch is monitored in real time, the cargo transportation routes are monitored, and the number set of monitored cargo transportation routes R = {r1, r2, ..., r n}, determine route deviation, set the dispatch route deviation threshold, and issue an alarm when deviation occurs. The preset route deviation threshold number set N = {n1, n2, ..., n n};

[0094] The route deviation judgment process is as follows:

[0095] The preset monitored cargo transportation route number set R is compared with the preset route deviation threshold number set N, where the threshold judgment standard is preset as output 1 for triggering and output 0 for not triggering. n <n n When r n >n n And r n =n n When , the output is 0, it means that the route is transporting goods normally;

[0096] Among them, r n is one or more subsets of the set R of cargo transportation routes, n n is one or more subsets of the route deviation threshold number set N;

[0097] The alarm is judged as:

[0098] Record the dispatch route n <n n When the output is 1, it is a route deviation point, which is preset to K. Then the route deviation point subset is K = {k1, k2, ..., k n}, the alarm level is determined based on the ratio of route deviation points to the goods transportation route:

[0099] When it is a primary alarm, a primary warning reminder is sent;

[0100] If it is a serious alarm, immediately notify the relevant staff to take measures to deal with it;

[0101] 10% refers to the proportion of route deviation points K to the goods transportation route R;

[0102] The overall scheduling process is:

[0103] S601, the inventory database determines the triggering of the emergency complementary mechanism according to the inventory threshold;

[0104] S602: Collect inventory data and demand data through the data collection terminal and upload to update the inventory database, and the inventory database starts scheduling according to the shortage threshold of the inventory node;

[0105] S603, the inventory database monitors the dispatch route and performs route deviation assessment;

[0106] S604: When the route deviation is greater than the route deviation threshold, the inventory database issues an alarm and reminds the staff that the dispatch route has deviated.

[0107] like Figure 3 As shown, continuously collect the data from step S1 to step S6 to adjust the supply chain model. According to the feedback from the inventory database, adjust the inventory threshold and scheduling strategy.

[0108] Specifically, continuously collect the data from step S1 to step S6, continuously optimize the supply chain model, improve the prediction accuracy, and adjust the inventory threshold and scheduling strategy according to the feedback from the inventory database to achieve the dynamic optimization of the supply chain.

[0109] The continuous collection of the data from step S1 to step S6 and the optimization of the supply chain model are as follows:

[0110] The optimization of the supply chain model is achieved by minimizing the prediction error ε and is completed through the iterative training of machine learning algorithms: fuse the data of step S1 - step S6 and calculate to obtain the optimized supply chain model to achieve step S7:

[0111] First, define the supply chain model prediction function as f, which predicts the inventory demand Y based on the input variable X. The input variable X includes item information O, inventory data A, demand data B, real - time inventory data C, real - time demand data D, scheduling information, and the error term ε represents the uncertainty of the prediction.

[0112] Y = f(X)+ε

[0113] where: X = [O,A,B,C,D,R,N];

[0114] Specifically: Y = f(O,A,B,C,D,R,N)+ε;

[0115] Step S7 considers the data and calculations of the following steps:

[0116] Step S1: Item information O and the supply chain model f based on historical data;

[0117] Step S2: Inventory data A, demand data B, and inventory threshold T;

[0118] Step S3: Real - time inventory data C and real - time demand data D;

[0119] Step S4: Updated inventory data A2 and inventory node shortage threshold M;

[0120] Step S5: Trigger conditions for scheduling, i.e., A < T and A2 < M;

[0121] Step S6: Goods transportation route R and route deviation threshold N;

[0122] Combine the above information to construct an objective function for the optimization of step S7:

[0123]

[0124] Wherein, Yi is the actual inventory demand, f(Xi) is the inventory demand predicted by the model, and Xi is the input data set containing all relevant data;

[0125] To simultaneously consider the threshold conditions in steps S5 and S6, these conditions are added as constraints to the optimization problem:

[0126]

[0127] Wherein, δ S5,i and δ S6,i are indicator functions, which are 1 when the conditions are met and 0 otherwise;

[0128] Wherein, Y represents the output of the supply chain model, which refers to the predicted inventory demand or other key indicators;

[0129] f represents the prediction function, which converts the input variable X into the output Y;

[0130] X represents the input variable, which contains all relevant factors affecting the supply chain model, including item information O, inventory data A, demand data B, real-time inventory data C, real-time demand data D, transportation route R, and route deviation threshold N;

[0131] ε represents the error term, which reflects the difference between the predicted value Y and the actual value;

[0132] min represents minimization, that is, the optimization objective is to find the values of f, T, M, and N that minimize the prediction error ε;

[0133] ∑ represents summation, that is, summing over all possible i values to ensure the optimization of the entire supply chain;

[0134] δS5,i represents an indicator function used to indicate whether the condition Ai < Ti is met. When the condition is met, δS5,i = 1; otherwise, δS5,i = 0;

[0135] δS6,i represents an indicator function used to indicate whether the condition Ri < Ni is met. When the condition is met, δS6,i = 1; otherwise, δS6,i = 0;

[0136] Finally, the optimization problem in step S7 is formulated as a minimization problem with constraints, and the prediction error ε is minimized by adjusting the model parameter f, the inventory threshold T, and the inventory node shortage threshold M.

[0137] As Figure 1-Figure 3 shown, the present invention works as follows in the application scenario of solving the drawback in the prior art that it is impossible to efficiently and accurately perform emergency complementarity on the goods at the shortage nodes when a sudden event causes a shortage of goods:

[0138] Collect detailed information about the goods, including specifications, shelf life, and production date, establish a product database, use machine learning algorithms, build a product supply chain model based on historical data, and predict inventory requirements at each node;

[0139] A product supply chain model is established based on the acquired product information. The product supply chain model includes multiple supply nodes and demand nodes. An inventory database is established to store inventory data and demand data of all nodes. An inventory threshold is set to determine whether an emergency complementary mechanism needs to be triggered.

[0140] Monitor the inventory of goods at each node in the supply chain model, collect inventory data and demand data of each node in real time, use RFID wireless radio frequency identification technology to automatically identify goods and update inventory data, set up data collection terminals, collect inventory data and demand data in real time, and the data collection terminals transmit data to the inventory database through the network;

[0141] Upload the collected inventory data and demand data of each node to the inventory database, and set the inventory node shortage threshold to determine whether scheduling needs to be enabled;

[0142] When the inventory data before the inventory database is updated reaches the inventory threshold, the emergency complementary mechanism is triggered, and the inventory data and demand data of each node collected by the data collection terminal are uploaded to the inventory database. When the updated inventory data reaches the inventory node shortage threshold, scheduling is started;

[0143] Monitor the dispatch in real time and set the dispatch route deviation threshold. When a deviation occurs, an alarm will be issued according to the degree of deviation and the staff will be reminded to handle it.

[0144] The data from step S1 to step S6 are continuously collected to adjust the supply chain model, and the inventory threshold and scheduling strategy are adjusted according to the feedback from the inventory database.

[0145] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0146] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and rules of the present invention shall be included in the protection scope of the present invention.

Claims

1. A product supply chain optimization method for emergency complementary goods. Features: S1. Collect detailed information about the goods, including specifications, shelf life, and production date, establish a product database, use machine learning algorithms, build a product supply chain model based on historical data, and predict inventory requirements at each node; S2. Establish a product supply chain model based on the acquired product information, wherein the product supply chain model includes multiple supply nodes and demand nodes, establish an inventory database, store the inventory data and demand data of all nodes, and set an inventory threshold to determine whether an emergency complementary mechanism needs to be triggered; S3, monitoring the inventory of goods at each node in the product supply chain model, collecting inventory data and demand data of each node in real time, using RFID wireless radio frequency identification technology, updating inventory data, setting up a data collection terminal, collecting inventory data and demand data in real time, and the data collection terminal transmits the data to the inventory database through the network; S4, uploading the collected inventory data and demand data of each node to the inventory database, and setting the inventory node shortage threshold to determine whether scheduling needs to be enabled; S5. When the inventory data before the inventory database is updated reaches the inventory threshold, the emergency complementary mechanism is triggered, and the inventory data and demand data of each node collected by the data collection terminal are uploaded to the inventory database. When the updated inventory data reaches the inventory node shortage threshold, scheduling is started; S6. Monitor the dispatch in real time and set the dispatch route deviation threshold. When a deviation occurs, an alarm will be issued according to the degree of deviation and the staff will be reminded to handle it; S7. Continue to collect data from step S1 to step S6 to adjust the supply chain model, and adjust the inventory threshold and scheduling strategy based on the inventory database feedback.

2. A product supply chain optimization method for emergency complementary goods according to claim 1, Features: In the step S1, detailed information of the goods is collected, including specifications, shelf life, and production date, and a goods database is established as follows: The product information in the preset product database is represented by a set O, where O = {O 1 ,O 2 ,…,O n }.

3. A product supply chain optimization method for emergency complementary goods according to claim 1, Features: In the step S2, an inventory database is established to store the inventory data and demand data of all nodes, and an inventory threshold is set to determine whether an emergency complementary mechanism needs to be triggered, specifically: The inventory data in the preset inventory database is represented by a set of numbers A, where A = {a 1 ,a 2 ,…,a n }, the demand data is represented by a set of numbers B, where B = {b 1 ,b 2 ,…,b n }; Set the inventory threshold to determine whether the emergency replenishment mechanism needs to be triggered. The preset inventory threshold number set T = {t 1 ,t 2 ,…,t n }.

4. A product supply chain optimization method for emergency complementary goods according to claim 1, Features: In the step S3, the inventory of goods at each node in the product supply chain model is monitored, inventory data and demand data are collected in real time, and the data collection terminal transmits the data to the inventory database through the network as follows: The preset real-time collected inventory data set C = {c 1 ,c 2 ,…,c n }, the real-time collected demand data set D = {d 1 ,d 2 ,…,d n }, data collection uses RFID technology to update inventory data, and the updated inventory data set A1 is preset to be {a1 1 ,a1 2 ,…,a1 n }.

5. The method for optimizing the supply chain of products for emergency complementarity of goods according to claim 1, Features: In the step S4, the collected inventory data and demand data of each node are uploaded to the inventory database to determine whether scheduling needs to be enabled: The default uploaded inventory data set A2 = {a2 1 ,a2 2 ,…,a2 n }, determine whether to start scheduling, when the inventory data is lower than the set inventory node shortage threshold, start scheduling, the preset inventory node shortage threshold number set M = {m 1 ,m 2 ,…,m n }.

6. The method for optimizing the supply chain of products for emergency complementarity of goods according to claim 1, Features: The scheduling is started in step S5 as follows: The inventory data set A before the inventory database is updated is compared with the inventory threshold set T, where the threshold judgment standard is preset as output 1 for triggering and output 0 for not triggering. n <t n When the output is 1, the emergency complementary mechanism is triggered. n >t n And a n =t n When the emergency complementary mechanism is triggered, the output is 0, indicating that the emergency complementary mechanism is not triggered. The inventory database continues to collect data information of the goods. When the emergency complementary mechanism is triggered, the data collected by the data collection terminal is uploaded to the inventory database, and the updated inventory data set A2 is compared with the preset inventory node shortage threshold set M. When a2 n <m n When the output is 1, the scheduling is turned on. When a2 n >m n And a2 n =m n When , the output is 0, and the inventory database will continue to collect the inventory data and demand data of each node when the emergency complementary mechanism is triggered.

7. The method for optimizing the supply chain of products for emergency complementarity of goods according to claim 1, It is characterized in that: The real-time monitoring and scheduling in step S6 is as follows: Real-time monitoring of dispatching and goods transportation routes is performed, and the number set of goods transportation routes monitored is preset to be R = {r 1 ,r 2 ,…,r n }, determine route deviation, set the dispatch route deviation threshold, and issue an alarm when deviation occurs. The preset route deviation threshold number set N = {n 1 ,n 2 ,…,n n }; The process of judging route deviation is as follows: The preset monitored cargo transportation route number set R is compared with the preset route deviation threshold number set N, where the threshold judgment standard is preset as output 1 for triggering and output 0 for not triggering. n <n n When r n >n n And r n =n n When , the output is 0, it means that the route is transporting goods normally; Among them, r n is one or more subsets of the set R of cargo transportation routes, n n is one or more subsets of the route deviation threshold number set N; The alarm judgment is as follows: Record the dispatch route n <n n When the output is 1, it is a route deviation point, which is preset to K. Then the route deviation point subset is K = {k 1 ,k 2 ,…,k n }, the alarm level is determined based on the ratio of route deviation points to the goods transportation route: When it is a primary alarm, a primary warning reminder is sent; If it is a serious alarm, immediately notify the relevant staff to take measures to deal with it; Among them, 10% refers to the proportion of the number of route deviation points K in the goods transportation route R.

8. A method for optimizing a product supply chain with emergency complementarity of goods according to claim 1, It is characterized in that: The adjustment of the supply chain model in step S7 is as follows: Define the supply chain model prediction function as f, which predicts the inventory demand Y based on the input variable X. The input variable X includes goods information O, inventory data A, demand data B, real-time inventory data C, real-time demand data D, scheduling information, and the error term ε represents the uncertainty of the prediction; Y = f(X) + ε; X = [O, A, B, C, D, R, N]; Y = f(O, A, B, C, D, R, N) + ε; Step S7 considers the data and calculations of the following steps: Step S1: Goods information O and the supply chain model f based on historical data; Step S2: Inventory data A, demand data B, and inventory threshold T; Step S3: Real-time inventory data C and real-time demand data D; Step S4: Updated inventory data A2 and inventory node shortage threshold M; Step S5: Trigger conditions for scheduling, i.e., A < T and A2 < M; Step S6: Goods transportation route R and route deviation threshold N; Construct an objective function for optimization in step S7.

9. A method for optimizing a product supply chain with emergency complementarity of goods according to claim 8, It is characterized in that: The construction of the objective function for optimization in step S7 is as follows: Among them, Yi is the actual inventory demand, f(Xi) is the inventory demand predicted by the model, and Xi is the input data set containing all relevant data.

10. A method for optimizing a product supply chain with emergency complementarity of goods according to claim 9, It is characterized in that: The constraint conditions of the optimization objective function are as follows: Among them, δS5,i and δS6,i are indicator functions, which are 1 when the conditions are met, otherwise 0; Among them, Y: represents the output of the supply chain model, which refers to the predicted inventory demand or other key indicators; f: represents the prediction function, which converts the input variable X into the output Y; X: represents the input variable, which includes all relevant factors affecting the supply chain model, including goods information O, inventory data A, demand data B, real-time inventory data C, real-time demand data D, transportation route R, and route deviation threshold N; ε: represents the error term, which reflects the difference between the predicted value Y and the actual value; min: represents minimization, that is, the optimization objective is to find the values of f, T, M, and N that minimize the prediction error ε; ∑: represents summation, that is, summing over all i values; δS5,i: represents an indicator function used to indicate whether the condition Ai < Ti is met. When the condition is met, δS5,i = 1; otherwise, δS5,i = 0; δS6,i: represents an indicator function used to indicate whether the condition Ri < Ni is met. When the condition is met, δS6,i = 1; otherwise, δS6,i = 0.

Images