Intelligent supply chain management method and system based on Internet of Things

Abstract

The invention relates to the technical field of supply chain management, in particular to an intelligent supply chain management method and system based on the Internet of Things, and in the system, a supply chain toughness index analysis module analyzes a supply chain toughness index based on a constructed supply chain link feature data set and a supply chain link feature data set collected in a supply chain abnormal process in historical data; and dynamically calculating the toughness index of the current supply chain. According to the method, the concept of the supply chain toughness index is introduced to carry out quantitative integration on the supply chain multi-dimensional risk indexes, and an effective decision basis is provided for risk management; supply chain state information sharing is realized through the dynamic risk billboard, a cooperation barrier among multiple roles is broken through, and an effective risk joint defense system is formed. And on the basis of a hierarchical response mechanism triggered by multi-level risk thresholds, the timeliness of supply chain abnormity response measures can be effectively ensured, and the intelligent level and toughness of the supply chain are improved to a certain extent.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of supply chain management, in particular to an intelligent supply chain management method and system based on the Internet of Things. BACKGROUND

[0002] With the deepening of globalization and division of labor, modern supply chains have become increasingly complex, and risk events such as equipment sudden failure and logistics delay occur frequently, posing a serious challenge to the stability and resilience of the supply chain.

[0003] The existing supply chain management system, the suppliers, manufacturers, logistics companies and other roles on the supply chain usually use independent management systems, and the data standards are not the same, there is a clear information island phenomenon between the various roles, the acquisition of risk information is seriously lagging behind, and it is impossible to provide real-time and comprehensive data support for decision-making; and the existing supply chain management system is one-sided in the way of perceiving risks, often focusing on single-dimensional indicators, and cannot comprehensively grasp the overall health status and risk resistance of the supply chain from the comprehensive indicators of multi-dimensional risks; at the same time, when the supply chain anomaly is monitored, the existing response mainly relies on manual judgment and experience decision-making, and it is difficult for the roles to effectively coordinate, and the best response opportunity is easily missed. Therefore, the existing technology has great defects. SUMMARY

[0004] The purpose of the present application is to provide an intelligent supply chain management method and system based on the Internet of Things to solve the problems raised in the background art.

[0005] In order to solve the above technical problems, the present application provides the following technical scheme: an intelligent supply chain management method based on the Internet of Things, the method comprising the following steps: S100, real-time collection of raw material inventory data, equipment running state data and logistics node state data through the Internet of Things sensor nodes deployed at each link of the supply chain, construction of supply chain link feature data set; S200, dynamic calculation of the resilience index of the current supply chain based on the constructed supply chain link feature data set and the supply chain link feature data set collected in the historical data of the abnormal process of the supply chain; generation and update of a dynamic risk board for real-time display of the resilience index of the current supply chain to the multi-role terminals in the supply chain; S300, multi-level risk threshold comparison based on the resilience index of the current supply chain displayed by the dynamic risk board, matching of the risk level corresponding to the current supply chain according to the comparison result between the multi-level risk thresholds, automatic triggering of the graded response strategy corresponding to the risk level of the current supply chain in the database, and synchronous pushing of the triggered graded response strategy to the dynamic risk board of the multi-role terminals in the supply chain for coordinated defense.

[0006] Further, the S100 includes: The raw material inventory data is collected by RFID tags, weight sensors or visual recognition devices arranged in the warehouse; The device operation state data is collected by vibration sensors, temperature sensors, noise sensors or PLC controllers arranged in the production equipment; the types of sensors arranged in each device are unique, and the device operation state data of each device is the collection result of one type of sensor, and the types of sensors corresponding to the device operation state data of different devices are different; The logistics node state data is collected by GPS locators, fuel consumption sensors, temperature sensors of transport vehicles, access control systems and cameras of warehouse ports; the logistics node state data includes logistics time delay rate, in-transit environmental abnormal event occurrence rate and node throughput saturation degree; the logistics time delay rate is the quotient of the maximum value of the logistics delay time in the current supply chain divided by the preset logistics delay tolerance time; the logistics delay time represents the sum of the delay time corresponding to each logistics transport vehicle for transporting the same object; the in-transit environmental abnormal event occurrence rate represents the ratio of the number of transport vehicles that appear delay to the total number of transport vehicles based on the preset time period before the corresponding time point in the supply chain; the node throughput saturation degree represents the maximum value of the difference between the corresponding cargo receiving amount and the cargo output amount of each warehouse port in the supply chain at the corresponding time point divided by the corresponding cargo capacity of the warehouse port.

[0007] The present application avoids the delay and error of manual input through the automatic collection of Internet of Things devices (vibration sensors, temperature sensors, noise sensors or PLC controllers of production equipment, and GPS locators, fuel consumption sensors, temperature sensors of transport vehicles or access control systems and cameras of warehouse ports), ensuring the timeliness and accuracy of the risk judgment in the subsequent steps; at the same time, this method breaks the information silos in the traditional supply chain, realizes the automatic acquisition of data from raw materials to delivery, and lays a solid data foundation for accurate risk assessment.

[0008] Further, the S200 dynamically calculates the resilience index of the current supply chain, and the calculation formula involved is as follows: ; Wherein, R represents the resilience index of the current supply chain; ND represents the current raw material available days, and the value of ND is equal to the quotient of the current real-time inventory of raw materials divided by the average daily consumption of raw materials in the historical data; PF represents the device failure probability in the current supply chain; LR represents the logistics interruption risk assessment value in the current supply chain; μ represents the first preset risk factor; β represents the second preset risk factor; ε represents the third preset risk factor, and μ+β+ε=1.

[0009] Further, the calculation formula of the device failure probability in the current supply chain is as follows: ; ; Wherein, PFi represents the failure probability of the i th device in the current supply chain; n represents the number of devices in the current supply chain; T represents the interval time length of the i th device in the current supply chain from the last maintenance; PX （i，t） represents the deviation coefficient between the corresponding device running state data and the preset standard device running state data of the corresponding device after the interval time t from the last maintenance time point of the corresponding device; M represents the total number of each device failure event in the historical data whose interval time length between the failure time and the last maintenance time point of the corresponding device is less than or equal to T; PX （i，t，j） represents the deviation coefficient between the corresponding device running state data and the preset standard device running state data of the corresponding device in the j th device failure event in the historical data whose interval time length between the failure time and the last maintenance time point of the corresponding device is t; JT represents the total number of the j th device failure event in the historical data whose interval time length between the failure time and the last maintenance time point of the corresponding device is t; when PX （i，t） ≥PX （i，t，j） , then G{PX （i，t） , PX （i，t，j）}=1; otherwise, G{PX （i，t） , PX （i，t，j）}=0; The calculation formula of the logistics interruption risk assessment value in the current supply chain is as follows: ; Wherein, TY represents the logistics time delay rate in the current supply chain; CY represents the in-transit environmental abnormal event occurrence rate in the current supply chain; BY represents the node throughput saturation degree in the current supply chain, when BY>0, then F{BY}=BY; otherwise, F{BY}=0; r1, r2 and r3 respectively represent the preset first weighting coefficient, the second weighting coefficient and the third weighting coefficient.

[0010] The present application can dynamically quantify the resilience index of the supply chain at different times by introducing the quantitative analysis of the device failure probability and the forward-looking evaluation of the logistics risk, so as to issue a warning before the risk actually occurs, and realizes the forward movement of the risk management.

[0011] Further, the multi-role terminal in S200 includes a supplier role terminal, a manufacturer role terminal, a logistics merchant role terminal and a customer role terminal; The display content of the dynamic risk board corresponding to different role terminals is different; The display content of the dynamic risk board corresponding to the supplier role terminal further includes raw material available day warning; The display content of the dynamic risk board corresponding to the manufacturer role terminal further includes the failure probability of each device in the current supply chain; The display content of the dynamic risk board corresponding to the logistics merchant role terminal further includes a transportation path; The display content of the dynamic risk board corresponding to the customer role terminal further includes order fulfillment status and expected delivery time.

[0012] The dynamic risk board corresponding to the multi-role terminal in the application provides differentiated risk views for different roles, enabling each role to communicate and make decisions based on a unified and real data platform, forming a joint defense and control mechanism for risk coordination and response. The presentation mode of the visual content in the dynamic risk board corresponding to the role terminal makes it easier for existing roles to understand complex risk information, greatly shortening the cognitive time of existing decision makers.

[0013] Further, S300 includes: The multi-level risk threshold includes at least a green safety zone, a yellow warning zone, an orange warning zone and a red danger zone, and different color zones correspond to a preset supply chain resilience index interval; The risk level corresponding to the current supply chain is the color zone corresponding to the preset supply chain resilience index interval to which the resilience index of the current supply chain belongs; If the risk level corresponding to the current supply chain is the green warning zone, it is determined that the state of the current supply chain is normal, and the hierarchical response strategy is not triggered; otherwise, it is determined that the state of the current supply chain is abnormal, and the hierarchical response strategy is triggered; The hierarchical response strategy includes: If the risk level corresponding to the current supply chain is the yellow warning zone, a first-level response is triggered: sending a warning notification to the relevant role terminal, prompting attention to the risk trend; If the risk level corresponding to the current supply chain is the orange warning zone, a second-level response is triggered: automatically generating and recommending a response plan, including starting a backup supplier inquiry, adjusting the production plan schedule, and preparing a replacement transportation scheme; If the risk level corresponding to the current supply chain is the red danger zone, a third-level response is triggered: automatically executing an emergency strategy, including placing an emergency order with a backup supplier, enabling a redundant production line, switching to a prepared logistics channel, and synchronously notifying all relevant role terminals.

[0014] record each risk event and the effect data of the graded response strategy executed; Based on historical effect data, the risk assessment model and / or the graded response strategy are continuously optimized iteratively by a machine learning model.

[0015] An intelligent supply chain management system based on Internet of Things, comprising: A supply chain link feature data collection module collects raw material inventory data, equipment operation state data and logistics node state data in real time through Internet of Things sensor nodes deployed at each link of the supply chain, and constructs a supply chain link feature data set; A supply chain resilience index analysis module dynamically calculates the resilience index of the current supply chain based on the constructed supply chain link feature data set and the supply chain link feature data set collected in the historical data of the abnormal process of the supply chain; A dynamic risk board feedback module for generating and updating a dynamic risk board for real-time display of the current supply chain resilience index to the multi-role terminals in the supply chain; A supply chain joint defense management module compares the resilience index of the current supply chain based on the dynamic risk board display with multiple risk threshold values, matches the risk level of the current supply chain according to the comparison result between the multiple risk threshold values, automatically triggers the graded response strategy corresponding to the risk level of the current supply chain in the database, and synchronously pushes the triggered graded response strategy to the dynamic risk board of the multi-role terminals in the supply chain for collaborative joint defense.

[0016] Compared with the prior art, the beneficial effects achieved by the present application are: The present application realizes automatic and real-time collection of supply chain data throughout the whole process through Internet of Things technology, and completely solves the problems of information silos and hysteresis; The present application introduces the concept of supply chain resilience index to quantitatively integrate multi-dimensional risk indicators of the supply chain, providing an effective decision basis for risk management; The present application realizes supply chain state information sharing through a dynamic risk board, and breaks down the collaboration barriers between multiple roles, forming an effective risk joint defense system; The graded response mechanism triggered based on multiple risk threshold values of the present application can effectively ensure the timeliness of the abnormal response measures of the supply chain, and to a certain extent, improve the intelligent level and resilience of the supply chain. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the present application, and constitute a part of the specification, together with the embodiments of the present application, to explain the present application, and do not constitute a limitation on the present application. In the drawings: Fig. 1 is a structural schematic diagram of an intelligent supply chain management system based on Internet of Things of the present application; Fig. 2 is a flowchart of an intelligent supply chain management method based on the Internet of Things. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0019] Please refer to Figs. 1-2 , the present application provides technical solutions: as Fig. 1 shown, an intelligent supply chain management system based on the Internet of Things is provided in the embodiment, comprising: A supply chain link feature data acquisition module acquires raw material inventory data, equipment operating status data and logistics node status data in real time through Internet of Things sensor nodes deployed at each link of the supply chain, and constructs a supply chain link feature data set; A supply chain resilience index analysis module dynamically calculates the resilience index of the current supply chain based on the constructed supply chain link feature data set and the supply chain link feature data set collected in the historical data of the abnormal process of the supply chain; A dynamic risk board feedback module is used to generate and update a dynamic risk board that displays the resilience index of the current supply chain in real time to the multi-role terminals in the supply chain; A supply chain joint defense management module compares the resilience index of the current supply chain based on the dynamic risk board, matches the risk level corresponding to the current supply chain according to the comparison result between the multi-level risk thresholds, automatically triggers the graded response strategy corresponding to the risk level of the current supply chain in the database, and synchronously pushes the triggered graded response strategy to the dynamic risk board of the multi-role terminals in the supply chain for joint defense.

[0020] As Fig. 2 shown, an intelligent supply chain management method based on the Internet of Things is provided in the embodiment, the method comprising the following steps: S100, raw material inventory data, equipment operating status data and logistics node status data are acquired in real time through Internet of Things sensor nodes deployed at each link of the supply chain, and a supply chain link feature data set is constructed; The S100 comprises: The raw material inventory data is acquired by RFID tags, weight sensors or visual recognition devices arranged in the warehouse; The equipment running state data is collected by a vibration sensor, a temperature sensor, a noise sensor or a PLC controller arranged on the production equipment; the types of the sensors arranged in each equipment are unique, and the equipment running state data of each equipment is the collection result of one type of sensor, and the types of the sensors corresponding to the equipment running state data of different equipment are different; The logistics node state data is collected by a GPS locator, an oil consumption sensor, a temperature sensor of a transport vehicle, or an access control system and a camera of a warehouse port; the logistics node state data includes a logistics time delay rate, an in-transit environmental abnormal event occurrence rate and a node throughput saturation degree; the logistics time delay rate is a quotient of a maximum value of a logistics delay time in the current supply chain divided by a preset logistics delay tolerance time; the logistics delay time represents a sum of delay times of respective transport vehicles transporting the same object; the in-transit environmental abnormal event occurrence rate represents a ratio of a number of transport vehicles that delay to a total number of transport vehicles in the supply chain based on a preset time period before a corresponding time point; and the node throughput saturation degree represents a maximum value of a difference between a cargo receiving amount and a cargo output amount of each warehouse port in the supply chain at a corresponding time point divided by a cargo capacity corresponding to the corresponding warehouse port.

[0021] S200, based on the constructed supply chain link feature data set and the supply chain link feature data set collected in the historical data, dynamically calculates the resilience index of the current supply chain; generates and updates a dynamic risk board for real-time display of the resilience index of the current supply chain to a multi-role terminal in the supply chain; The dynamic calculation of the resilience index of the current supply chain in S200 involves the following calculation formula: ; Wherein, R represents the resilience index of the current supply chain; ND represents the current raw material available days, and the value of ND is equal to the quotient of the current real-time inventory of the raw material divided by the average daily consumption of the raw material in the historical data; PF represents the equipment failure probability in the current supply chain; The calculation formula of the equipment failure probability in the current supply chain is as follows: ; ; Wherein, PFi represents the failure probability of the i-th equipment in the current supply chain; n represents the number of equipment in the current supply chain; T represents the interval time of the i-th equipment in the current supply chain from the last maintenance; PX （i，t）represents the deviation coefficient between the corresponding device running state data and the standard device running state data preset by the corresponding device when the interval time t after the last maintenance time point of the ith device in the current supply chain is reached, and the deviation coefficient is equal to the difference between the corresponding device running state data and the standard device running state data preset by the corresponding device divided by the standard device running state data preset by the corresponding device; M represents the total number of device failure events in the historical data in which the interval length between the failure time and the last maintenance time point of the corresponding device is less than or equal to T; PX （i，t，j） represents the deviation coefficient between the corresponding device running state data and the standard device running state data preset by the corresponding device in the jth device failure event in which the interval length between the failure time and the last maintenance time point of the corresponding device in the historical data is t; JT represents the total number of the jth device failure events in which the interval length between the failure time and the last maintenance time point of the corresponding device in the historical data is t; when PX （i，t） ≥ PX （i，t，j） , then it is determined that G{PX （i，t） , PX （i，t，j）} = 1; otherwise, it is determined that G{PX （i，t） , PX （i，t，j）} = 0. LR represents the logistics interruption risk assessment value in the current supply chain. The logistics interruption risk assessment value in the current supply chain is obtained, and the calculation formula is as follows: ; wherein, TY represents the logistics timeliness delay rate in the current supply chain; CY represents the in-transit environmental abnormal event occurrence rate in the current supply chain; BY represents the node throughput saturation degree in the current supply chain, when BY > 0, it is determined that F{BY} = BY; otherwise, it is determined that F{BY} = 0; r1, r2 and r3 respectively represent the preset first weighting coefficient, the second weighting coefficient and the third weighting coefficient.

[0022] μ represents the first risk factor preset; β represents the second risk factor preset; ε represents the third risk factor preset, and μ + β + ε = 1.

[0023] The multi-role terminal in the S200 includes a supplier role terminal, a manufacturer role terminal, a logistics role terminal and a customer role terminal. The display content of the dynamic risk board corresponding to different role terminals is different; The display content of the dynamic risk board corresponding to the supplier role terminal further includes raw material available day warning; The display content of the dynamic risk board corresponding to the manufacturer role terminal further includes the failure probability of each device in the current supply chain; The display content of the dynamic risk dashboard corresponding to the terminal of the logistics company role also includes the transportation path; The display content of the dynamic risk dashboard corresponding to the terminal of the customer role also includes the order fulfillment status and the expected delivery time.

[0024] S300, based on the current supply chain resilience index displayed by the dynamic risk dashboard, a multi-level risk threshold comparison is performed, according to the comparison result between the multi-level risk threshold, the risk level corresponding to the current supply chain is matched, and the database corresponding to the risk level of the current supply chain is automatically triggered. Response strategy, and synchronously push the triggered hierarchical response strategy to the dynamic risk dashboard of the multi-role terminal in the supply chain for cooperative defense; The S300 includes: The multi-level risk threshold includes at least a green safe zone, a yellow warning zone, an orange warning zone, and a red danger zone, and different color zones correspond to a preset supply chain resilience index interval; The risk level corresponding to the current supply chain is the color zone corresponding to the preset supply chain resilience index interval to which the resilience index of the current supply chain belongs; If the risk level corresponding to the current supply chain is the green warning zone, it is determined that the current supply chain state is normal, and no hierarchical response strategy is triggered; otherwise, it is determined that the current supply chain state is abnormal, and the hierarchical response strategy is triggered; The hierarchical response strategy includes: If the risk level corresponding to the current supply chain is the yellow warning zone, trigger a first-level response: send a warning notification to the relevant role terminal, and prompt to pay attention to the risk trend; If the risk level corresponding to the current supply chain is the orange warning zone, trigger a second-level response: automatically generate and recommend a response plan, including starting a backup supplier inquiry, adjusting the production plan schedule, and preparing a replacement transportation plan; If the risk level corresponding to the current supply chain is the red danger zone, trigger a third-level response: automatically execute an emergency strategy, including placing an emergency order to a backup supplier, enabling a redundant production line, switching to a prepared logistics channel, and synchronously notifying all relevant role terminals.

[0025] In this embodiment, the effect data of each risk event and the executed hierarchical response strategy is recorded; Based on the historical effect data, the risk assessment model and / or the hierarchical response strategy are continuously optimized and iterated through a machine learning model.

[0026] The embodiment further provides an intelligent supply chain management device based on the Internet of Things, which comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the intelligent supply chain management method based on the Internet of Things provided above when executing the computer program. The memory can be a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), or other types of dynamic storage devices that can store information and instructions, and can also be a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage, magnetic disk storage medium, or other magnetic storage device, or any other medium capable of carrying or storing desired program codes in the form of instructions or data structures and capable of being accessed by a computer, but is not limited thereto. The memory can be integrated with the processor or exist independently.

[0027] It should be noted that, in this document, relational terms such as first and second and the like can merely be used to distinguish one entity or action from another, without necessarily requiring or implying any actual such relationship or order between or among the entities or actions. Also, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0028] Finally, it should be noted that: the above only describes the preferred embodiments of the present application, and is not used to limit the present application, although the present application is described in detail with reference to the foregoing embodiments, for those skilled in the art, the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced equivalently. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An Internet of Things-based intelligent supply chain management method, characterized in that, The method comprises the following steps: S100, collecting raw material inventory data, equipment running state data and logistics node state data in real time through Internet of Things sensor nodes deployed at each link of the supply chain, and constructing a supply chain link feature data set; S200, dynamically calculating the resilience index of the current supply chain based on the constructed supply chain link feature data set and the supply chain link feature data set collected in the historical data of the abnormal process of the supply chain; generating and updating a dynamic risk board for real-time display of the resilience index of the current supply chain to the multi-role terminals in the supply chain; S300, comparing the resilience index of the current supply chain displayed based on the dynamic risk board with multiple risk threshold values, matching the risk level corresponding to the current supply chain according to the comparison result between the multiple risk threshold values, and automatically triggering the graded response strategy corresponding to the risk level of the current supply chain in the database, and synchronously pushing the triggered graded response strategy to the dynamic risk board of the multi-role terminal in the supply chain for collaborative defense. 2.The intelligent supply chain management method based on the Internet of Things according to claim 1, characterized in that: The S100 comprises: The raw material inventory data is collected by RFID tags, weight sensors or visual recognition devices arranged in the warehouse; The equipment running state data is collected by vibration sensors, temperature sensors, noise sensors or PLC controllers arranged in the production equipment; the types of sensors arranged in each equipment are unique, and the equipment running state data of each equipment is the collection result of one type of sensor, and the types of sensors corresponding to the equipment running state data of different equipment are different; The logistics node state data is collected by GPS locators, fuel consumption sensors, temperature sensors of transport vehicles, access control systems and cameras of warehouse ports; the logistics node state data includes logistics time delay rate, in-transit environmental abnormal event occurrence rate and node throughput saturation; the logistics time delay rate is the quotient of the maximum value of the logistics delay time in the current supply chain and the preset logistics delay tolerance time; the logistics delay time represents the sum of the delay time corresponding to each logistics transport vehicle transporting the same object; the in-transit environmental abnormal event occurrence rate represents the ratio of the number of transport vehicles that appear delay to the total number of transport vehicles within a preset time period before the corresponding time point; the node throughput saturation represents the maximum value of the quotient of the difference between the cargo receiving amount and the cargo output amount corresponding to each warehouse port in the corresponding time point of the supply chain and the cargo capacity corresponding to the corresponding warehouse port. 3.The intelligent supply chain management method based on the Internet of Things according to claim 2, characterized in that: The dynamic calculation of the resilience index of the current supply chain in S200 involves the following calculation formula: ； Wherein, R represents the resilience index of the current supply chain; ND represents the current raw material available days, and the value of ND is equal to the quotient of the current real-time inventory of raw materials and the average daily consumption of raw materials in the historical data; PF represents the equipment failure probability in the current supply chain; LR represents the logistics interruption risk assessment value in the current supply chain; μ represents a preset first risk factor; β represents a preset second risk factor; ε represents a preset third risk factor, and μ+β+ε=1. 4.The intelligent supply chain management method based on the Internet of Things according to claim 3, characterized in that: The calculation formula for obtaining the equipment failure probability in the current supply chain is as follows: ； ； wherein, PFi represents the failure probability of the i-th device in the current supply chain; n represents the number of devices in the current supply chain; T represents the interval time length of the i-th device in the current supply chain from the last maintenance; PX （i，t） represents the deviation coefficient between the corresponding device running state data and the preset standard device running state data of the corresponding device at the interval time t after the last maintenance time point of the i-th device in the current supply chain; the deviation coefficient is equal to the difference between the corresponding device running state data and the preset standard device running state data of the corresponding device divided by the preset standard device running state data of the corresponding device; M represents the total number of each device failure event in the historical data in which the interval time length between the failure time and the last maintenance time point of the corresponding device is less than or equal to T; PX （i，t，j） represents the deviation coefficient between the corresponding device running state data and the preset standard device running state data of the corresponding device in the j-th device failure event in the historical data in which the interval time length between the failure time and the last maintenance time point of the corresponding device is t; JT represents the total number of the j-th device failure event in the historical data in which the interval time length between the failure time and the last maintenance time point of the corresponding device is t; when PX （i，t） ≥ PX （i，t，j） , then it is determined that G{PX （i，t） , PX （i，t，j）}=1; otherwise, it is determined that G{PX （i，t） , PX （i，t，j）}=0. The risk assessment value of the logistics interruption in the current supply chain is obtained, and the calculation formula is as follows: ； Wherein, TY represents the logistics time delay rate in the current supply chain; CY represents the in-transit environmental abnormal event occurrence rate in the current supply chain; BY represents the node throughput saturation degree in the current supply chain, when BY>0, it is determined that F{BY}=BY; otherwise, it is determined that F{BY}=0; r1, r2 and r3 represent the preset first weighting coefficient, the second weighting coefficient and the third weighting coefficient respectively. 5.The intelligent supply chain management method based on the Internet of Things according to claim 3, characterized in that: The multi-role terminal in the S200 includes a supplier role terminal, a manufacturer role terminal, a logistics role terminal and a customer role terminal; The display content of the dynamic risk board corresponding to different role terminals is different; The display content of the dynamic risk board corresponding to the supplier role terminal further includes raw material available day warning; The display content of the dynamic risk board corresponding to the manufacturer role terminal further includes the failure probability of each device in the current supply chain; The display content of the dynamic risk board corresponding to the logistics role terminal further includes the transportation path; The display content of the dynamic risk board corresponding to the customer role terminal further includes the order fulfillment status and the expected delivery time. 6.The intelligent supply chain management method based on the Internet of Things according to claim 1, characterized in that: The S300 includes: The multi-level risk threshold includes at least a green safety zone, a yellow warning zone, an orange warning zone and a red danger zone, and different color zones correspond to a preset supply chain resilience index interval; The risk level corresponding to the current supply chain is the color zone corresponding to the preset supply chain resilience index interval to which the resilience index of the current supply chain belongs; If the risk level corresponding to the current supply chain is the green warning zone, it is determined that the state of the current supply chain is normal, and the hierarchical response strategy is not triggered; otherwise, it is determined that the state of the current supply chain is abnormal, and the hierarchical response strategy is triggered; The hierarchical response strategy includes: If the risk level corresponding to the current supply chain is the yellow warning zone, a first-level response is triggered: a warning notification is sent to the relevant role terminal, prompting to pay attention to the risk trend; If the risk level corresponding to the current supply chain is the orange warning zone, a second-level response is triggered: an automatic response plan is generated and recommended, including starting a backup supplier inquiry, adjusting the production plan scheduling, and preparing a replacement transportation scheme; If the risk level corresponding to the current supply chain is the red danger zone, a third-level response is triggered: an emergency strategy is automatically executed, including placing an emergency order to a backup supplier, enabling a redundant production line, switching to a prepared logistics channel, and synchronously notifying all relevant role terminals.

7. An intelligent supply chain management system based on Internet of Things, applying the intelligent supply chain management method based on Internet of Things in any one of claims 1-6, characterized in that, It includes: A supply chain link feature data collection module, through the Internet of Things sensor nodes deployed at each link of the supply chain, real-time collection of raw material inventory data, equipment operating status data and logistics node status data, construction of a supply chain link feature data set; A supply chain resilience index analysis module, based on the constructed supply chain link feature data set and the supply chain link feature data set collected in the historical data of the abnormal process of the supply chain, dynamically calculating the resilience index of the current supply chain; A dynamic risk board feedback module for generating and updating a dynamic risk board for real-time display of the resilience index of the current supply chain to the multi-role terminals in the supply chain; The supply chain joint defense management module performs multi-level risk threshold comparison based on the current supply chain resilience index displayed by the dynamic risk board, matches the risk level corresponding to the current supply chain according to the comparison result between the multi-level risk threshold, automatically triggers the hierarchical response strategy corresponding to the risk level of the current supply chain in the database, and synchronously pushes the triggered hierarchical response strategy to the dynamic risk board of the multi-role terminal in the supply chain for collaborative joint defense.

Images