Full-chain risk monitoring coordination system and method for garment manufacturing

Abstract

The invention relates to the technical field of data analysis, and discloses a full-chain risk monitoring coordination system and method for garment manufacturing, and the system comprises a bidirectional risk monitoring tree construction module, a risk factor calculation module, a risk probability calculation module, a node coordination sequence generation module and a risk coordination module. Constructing a two-way risk monitoring tree of the garment manufacturing full chain; monitoring circulation monitoring data of each data node, and calculating a risk factor, risk tolerance and risk probability corresponding to each data node through the circulation monitoring data; calculating the emergency degree of each data node according to the association relationship, and determining the risk coordination degree of each data node according to the emergency degree and the risk probability; and generating a coordination factor of each data coordination node according to the risk coordination degree, generating a coordination strategy of the data coordination nodes according to the coordination factors, and performing risk coordination on the data coordination nodes according to the coordination strategy. According to the invention, the accuracy of full-chain risk monitoring coordination of garment manufacturing can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a full-chain risk monitoring and coordination system and method for clothing manufacturing. Background Art

[0002] With the complex and ever-changing market environment of the apparel industry, supply chain risk management is crucial to enterprises. From raw material procurement to product launch, unknown risks are hidden in every link. Therefore, it is necessary to accurately identify, effectively manage and reduce unknown risks in the supply chain to ensure the stable operation of the supply chain, reduce the probability and impact of risks, and improve the resilience and sustainability of the supply chain.

[0003] The existing full-chain risk monitoring and coordination technology for clothing manufacturing integrates information from all links of the supply chain to monitor the status of production equipment, inventory levels and logistics. In actual applications, relying solely on equipment to collect data leads to inaccurate data collection and no real-time monitoring of the risks brought by the full-chain data, resulting in low accuracy in the full-chain risk monitoring and coordination of clothing manufacturing. Summary of the invention

[0004] The present invention provides a full-chain risk monitoring and coordination system and method for clothing manufacturing, the main purpose of which is to solve the problem of accuracy when performing full-chain risk monitoring and coordination for clothing manufacturing.

[0005] To achieve the above objectives, the present invention provides a full-chain risk monitoring and coordination system for clothing manufacturing, comprising:

[0006] The system includes a bidirectional risk monitoring tree construction module, a risk factor calculation module, a risk probability calculation module, a node coordination sequence generation module and a risk coordination module, wherein:

[0007] The bidirectional risk monitoring tree construction module is used to obtain data nodes of the entire chain of clothing manufacturing and the association relationship between the nodes, and to construct a bidirectional risk monitoring tree of the entire chain of clothing manufacturing according to the data nodes and the association relationship;

[0008] The risk factor calculation module is used to monitor the cyclic monitoring data of each data node in the bidirectional risk monitoring tree according to a preset bidirectional cyclic time node, and calculate the risk factor corresponding to the leaf node in the bidirectional risk monitoring tree through the cyclic monitoring data;

[0009] The risk probability calculation module is used to calculate the risk tolerance of the leaf node according to the target node data corresponding to the leaf node in the bidirectional risk monitoring tree, and is used to: determine the data collection time period corresponding to the leaf node according to the time point corresponding to the bidirectional loop node in the bidirectional risk monitoring tree and the preset time collection point; extract the historical critical data corresponding to the leaf node through the data collection time period; calculate the risk tolerance of the leaf node according to the target node data and the historical critical data, wherein the risk tolerance calculation formula is:

[0010]

[0011] Among them, R kα is the risk tolerance corresponding to the kth leaf node at the αth time point, S kα is the target node data corresponding to the kth leaf node at the αth time point, L kα is the minimum value of the historical critical data corresponding to the kth leaf node at the αth time point, H kα is the maximum value of the historical critical data corresponding to the kth leaf node at the αth time point, and min is the minimum value function;

[0012] Calculate the risk probability of each data node according to the risk factor and the risk tolerance;

[0013] The node coordination sequence generation module is used to calculate the urgency of each data node according to the association relationship through a preset dynamic hierarchical association algorithm, determine the risk coordination degree of each data node according to the urgency and the risk probability, and generate a node coordination sequence of the bidirectional risk monitoring tree according to the risk coordination degree;

[0014] The risk coordination module is used to generate a coordination factor for each data coordination node in the node coordination sequence according to the risk coordination degree, generate a coordination strategy for the data coordination node according to the coordination factor, and perform risk coordination on the data coordination node according to the coordination strategy.

[0015] Optionally, when constructing the bidirectional risk monitoring tree of the entire clothing manufacturing chain according to the data nodes and the association relationships, the bidirectional risk monitoring tree construction module is used to:

[0016] Determine the bidirectional hierarchical association and the unidirectional hierarchical association of the data nodes according to the association relationship;

[0017] Determine the bidirectional circulation points of the whole chain of garment manufacturing through the bidirectional hierarchical association, and determine the unidirectional circulation points of the whole chain of garment manufacturing according to the unidirectional hierarchical association;

[0018] generating a bidirectional association path between the bidirectional cycle points according to the bidirectional hierarchical association;

[0019] Generating a unidirectional association path between the unidirectional cycle points according to the unidirectional hierarchical association;

[0020] Connecting the bidirectional loop points according to the bidirectional association path to obtain a bidirectional loop subtree, and connecting the unidirectional loop points according to the unidirectional association path to obtain a unidirectional loop subtree;

[0021] The bidirectional cycle subtree is associated with the unidirectional cycle subtree to obtain a bidirectional risk monitoring tree for the entire clothing manufacturing chain.

[0022] Optionally, when monitoring the cyclic monitoring data of each data node in the bidirectional risk monitoring tree according to a preset bidirectional cyclic time node, the risk factor calculation module is used to:

[0023] Trigger the bidirectional cycle time node according to a preset time sliding window;

[0024] Collect the real-time bidirectional monitoring data of the bidirectional circulation points and the real-time unidirectional monitoring data of the unidirectional circulation points in the bidirectional risk monitoring tree according to the time point corresponding to the bidirectional circulation time node after the triggering;

[0025] Attribute the real-time two-way monitoring data and the real-time one-way monitoring data to obtain real-time two-way monitoring attribute data and real-time one-way monitoring attribute data;

[0026] The real-time two-way monitoring attribute data and the real-time one-way monitoring attribute data are collected as cyclic monitoring data.

[0027] Optionally, when the risk factor calculation module calculates the risk factor corresponding to the leaf node in the bidirectional risk monitoring tree through the cyclic monitoring data, it is used to:

[0028] Obtain target attribute data of the leaf node at the time point;

[0029] The bidirectional risk factor corresponding to the bidirectional circulation point in the leaf node is calculated according to the real-time bidirectional monitoring attribute data and the target attribute data in the circulation monitoring data using the following preset bidirectional time factor algorithm:

[0030]

[0031] Among them, f i is the bidirectional risk factor corresponding to the i-th bidirectional cycle point, p it is the positive feedback attribute value of the real-time bidirectional monitoring attribute data corresponding to the i-th bidirectional cycle point at time point t, q itis the target attribute value of the target attribute data corresponding to the i-th bidirectional loop point at time point t, is the real-time attribute value of the real-time bidirectional monitoring attribute data corresponding to the i-th bidirectional cycle point at time point t, is the reverse feedback attribute value corresponding to the i-th bidirectional loop point at time point t;

[0032] The one-way risk factor corresponding to the one-way circulation point in the leaf node is calculated according to the real-time one-way monitoring attribute data and the target attribute data in the circulation monitoring data using the following preset one-way time factor algorithm:

[0033]

[0034] Among them, g i is the one-way risk factor corresponding to the i-th one-way cycle point, a it is the real-time attribute value of the real-time one-way monitoring attribute data corresponding to the i-th one-way cycle point at time point t, b it is the target attribute value of the target attribute data corresponding to the i-th one-way cycle point at time point t.

[0035] Optionally, when calculating the risk probability of each data node according to the risk factor and the risk tolerance, the risk probability calculation module is used to:

[0036] Determine the target risk probability corresponding to the leaf node according to the risk factor and the risk tolerance:

[0037]

[0038] Among them, Y k is the target risk probability of the kth leaf node, f k is the bidirectional risk factor corresponding to the bidirectional loop point in the kth leaf node, g k is the one-way risk factor corresponding to the one-way cycle point in the kth leaf node, R k is the risk tolerance of the kth leaf node, ∨ is the OR symbol, and ∧ is the AND symbol;

[0039] Extracting the node hierarchical relationship corresponding to the leaf node through a bidirectional risk monitoring tree;

[0040] Determine the level node corresponding to the leaf node according to the node level relationship;

[0041] Counting the node risk probabilities corresponding to the hierarchical nodes through the target risk probability;

[0042] The risk probability of each data node is determined according to the node risk probability.

[0043] Optionally, when calculating the urgency of each data node according to the association relationship by using a preset dynamic hierarchical association algorithm, the node coordination sequence generation module is used to:

[0044] Determine the node level corresponding to each data node according to the association relationship;

[0045] Determining a level emergency coefficient of each data node according to the node level;

[0046] Determine the dynamic demand data of each data node through the cycle time point corresponding to the cycle time node;

[0047] The urgency of each data node is calculated according to the number of occurrences of the dynamic demand data by using the following preset dynamic hierarchical association algorithm:

[0048]

[0049] Among them, d σ is the urgency of the σth data node, δ σ is the hierarchical emergency coefficient of the σth data node, c σε is the number of occurrences of the σth data node at the cycle time point ε, e is the exponent, λ is the time decay rate, T is the final time of the cycle time point, ε σ is the cycle time point corresponding to the σth data node, and m is the number of cycles of the cycle time point.

[0050] Optionally, when determining the risk coordination degree of each data node according to the urgency and the risk probability, the node coordination sequence generation module is used to:

[0051] Extracting the cycle urgency and the cycle risk probability corresponding to each data node at the cycle time point corresponding to the cycle time node according to the urgency and the risk probability;

[0052] Selecting the best combination parameter corresponding to the cycle urgency and the cycle risk probability under the cycle time point condition;

[0053] The risk coordination degree of each data node is determined according to the optimal combination parameters.

[0054] Optionally, when generating the coordination factor of each data coordination node in the node coordination sequence according to the risk coordination degree, the risk coordination module is used to:

[0055] Priority identification is performed on each data coordination node in the node coordination sequence according to the risk coordination degree to obtain a node priority corresponding to each data coordination node;

[0056] Determine the risk coordination type corresponding to each data coordination node according to the node priority;

[0057] A coordination factor for each data coordination node is generated according to the risk coordination type.

[0058] Optionally, when generating the coordination strategy of the data coordination node according to the coordination factor, the risk coordination module is used to:

[0059] Determining the coordination content of the data coordination node according to the coordination factor;

[0060] Generate a coordination task of the data coordination node according to the coordination content;

[0061] A coordination strategy of the data coordination node is generated according to the coordination task.

[0062] In order to solve the above problems, the present invention also provides a full-chain risk monitoring and coordination method for clothing manufacturing, the method comprising:

[0063] Acquire data nodes of the entire chain of clothing manufacturing and the association relationships between the nodes, and construct a bidirectional risk monitoring tree of the entire chain of clothing manufacturing according to the data nodes and the association relationships;

[0064] Monitoring the cyclic monitoring data of each data node in the bidirectional risk monitoring tree according to a preset bidirectional cyclic time node, and calculating the risk factor corresponding to each data node through the cyclic monitoring data;

[0065] Calculate the risk tolerance of each data node according to the target node data corresponding to each data node in the bidirectional risk monitoring tree, and calculate the risk probability of each data node according to the risk factor and the risk tolerance;

[0066] The urgency of each data node is calculated according to the association relationship by a preset dynamic hierarchical association algorithm, the risk coordination degree of each data node is determined according to the urgency and the risk probability, and the node coordination sequence of the bidirectional risk monitoring tree is generated according to the risk coordination degree;

[0067] A coordination factor of each data coordination node in the node coordination sequence is generated according to the risk coordination degree, a coordination strategy of the data coordination node is generated according to the coordination factor, and risk coordination is performed on the data coordination node according to the coordination strategy.

[0068] The embodiment of the present invention structures the complex manufacturing process by identifying the data nodes of the whole chain and their associations, which is conducive to discovering the mutual influence between each node; by setting the cycle time node, it can collect monitoring data in real time, quickly identify risk changes, and calculate the risk factor of each data node to provide data support for subsequent risk management; by calculating the risk tolerance according to the target data of each node, it can evaluate and manage the risks of different nodes in a targeted manner to avoid excessive or insufficient risk control; by calculating the urgency, the team can give priority to the most urgent problems and improve the efficiency of resource allocation, and the calculation of the risk coordination degree enables the team to flexibly adjust the response strategy to ensure rapid response when risks occur and reduce the impact. According to the coordination strategy generated by the coordination factor, each data node has clear risk response measures to enhance the effectiveness of risk management. Therefore, the full-chain risk monitoring and coordination system and method for clothing manufacturing proposed by the present invention can solve the problem of low accuracy when conducting full-chain risk monitoring and coordination of clothing manufacturing. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 A functional module diagram of a full-chain risk monitoring and coordination system for clothing manufacturing provided by an embodiment of the present invention;

[0070] Figure 2 A schematic flow chart of an operating method of a full-chain risk monitoring and coordination system for clothing manufacturing provided in one embodiment of the present invention.

[0071] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0072] 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.

[0073] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.

[0074] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0075] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0076] In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0077] In fact, the server-side device deployed by the full-chain risk monitoring and coordination system for clothing manufacturing may be composed of one or more devices. The above-mentioned full-chain risk monitoring and coordination system for clothing manufacturing can be implemented as: business instance, virtual machine, hardware device. For example, the full-chain risk monitoring and coordination system for clothing manufacturing can be implemented as a business instance deployed on one or more devices in the cloud node. In simple terms, the full-chain risk monitoring and coordination system for clothing manufacturing can be understood as a software deployed on the cloud node, which is used to provide a full-chain risk monitoring and coordination system for clothing manufacturing for each user terminal. Alternatively, the full-chain risk monitoring and coordination system for clothing manufacturing can also be implemented as a virtual machine deployed on one or more devices in the cloud node. The virtual machine is installed with application software for managing each user terminal. Alternatively, the full-chain risk monitoring and coordination system for clothing manufacturing can also be implemented as a server consisting of many hardware devices of the same or different types, and one or more hardware devices are set to provide a full-chain risk monitoring and coordination system for clothing manufacturing for each user terminal.

[0078] In terms of implementation, the full-chain risk monitoring and coordination system for clothing manufacturing and the user end are adapted to each other. That is, the full-chain risk monitoring and coordination system for clothing manufacturing is an application installed on the cloud service platform, and the user end is a client that establishes a communication connection with the application; or the full-chain risk monitoring and coordination system for clothing manufacturing is implemented as a website, and the user end is implemented as a web page; or the full-chain risk monitoring and coordination system for clothing manufacturing is implemented as a cloud service platform, and the user end is implemented as a small program in an instant messaging application.

[0079] Reference Figure 1 , which is a functional module diagram of a full-chain risk monitoring and coordination system for clothing manufacturing provided by an embodiment of the present invention.

[0080] The full-chain risk monitoring and coordination system 100 for clothing manufacturing of the present invention can be set in a cloud server. In terms of implementation, it can be used as one or more service devices, or it can be installed as an application on the cloud (such as a server of a mobile service operator, a server cluster, etc.), or it can also be developed as a website. According to the functions implemented, the full-chain risk monitoring and coordination system 100 for clothing manufacturing can include a two-way risk monitoring tree construction module 101, a risk factor calculation module 102, a risk probability calculation module 103, a node coordination sequence generation module 104 and a risk coordination module 105. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by a device processor and can complete fixed functions, which are stored in the memory of the device.

[0081] In the embodiment of the present invention, in the full chain risk monitoring and coordination system for clothing manufacturing, each of the above modules can be independently implemented and called with other modules. The call here can be understood as a module that can connect multiple modules of another type and provide corresponding services for the multiple modules connected to it. For example, the risk factor calculation module can call the two-way risk monitoring tree construction module to obtain the information collected by the two-way risk monitoring tree construction module. Based on the above characteristics, in the full chain risk monitoring and coordination system for clothing manufacturing provided by the embodiment of the present invention, the scope of application of the full chain risk monitoring and coordination system architecture for clothing manufacturing can be adjusted by adding modules and directly calling them without modifying the program code, so as to achieve cluster-type horizontal expansion, so as to achieve the purpose of quickly and flexibly expanding the full chain risk monitoring and coordination system for clothing manufacturing. In practical applications, the above modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in cloud servers.

[0082] The following is a description of each component and specific workflow of the full-chain risk monitoring and coordination system for clothing manufacturing in conjunction with a specific embodiment:

[0083] The bidirectional risk monitoring tree construction module 101 is used to obtain data nodes of the entire chain of clothing manufacturing and the association relationships between the nodes, and to construct a bidirectional risk monitoring tree of the entire chain of clothing manufacturing according to the data nodes and the association relationships.

[0084] In an embodiment of the present invention, the data node refers to a clothing manufacturing node that may have risks in the entire chain of clothing manufacturing. For example, in the entire chain of clothing manufacturing, the top-level risk node includes operational risk, financial risk, and market risk. The first-level risk is supply chain risk, production risk, and logistics risk in operational risk; cost control risk and cash flow risk in financial risk; demand change risk and price risk in market risk; and the second-level risk involves supply chain risk including supplier delayed delivery, raw material quality problems, and price fluctuations; production risk includes equipment failure, personnel loss, unstable production process, and production scheduling; logistics risk includes transportation delays, cargo damage, seasonal fluctuations, and cargo delivery links; cost control risk includes rising raw material costs and low production efficiency; cash flow risk includes delayed collection of accounts receivable and bad debts; demand change risk includes changes in consumer preferences and competitor strategies; price risk includes market price fluctuations and industry downturns; the association relationship refers to the relationship between the top-level risk node and the first-level risk node, and the relationship between the first-level risk node and the second-level risk node.

[0085] In detail, the data nodes of the entire chain of clothing manufacturing and the association relationship between the nodes can be obtained from a pre-stored storage area through a computer function with a data capture function (such as Java statements, Python statements, etc.), where the storage area includes but is not limited to a database and a blockchain.

[0086] Furthermore, in order to focus on upstream (such as raw material procurement) and downstream (such as sales and after-sales service) risks at the same time and to be able to quickly transfer risk information from one node to related nodes, it is necessary to build a bidirectional data flow to analyze node risks.

[0087] In an embodiment of the present invention, the bidirectional risk monitoring tree refers to a structured model for identifying and managing risks, which graphically displays the mutual influence and risk associations between different nodes (such as suppliers, production, logistics, etc.), organizes risk factors by level, and facilitates the analysis of risk relationships at different levels.

[0088] In the embodiment of the present invention, when constructing the bidirectional risk monitoring tree of the entire clothing manufacturing chain according to the data nodes and the association relationships, the bidirectional risk monitoring tree construction module 101 is used to:

[0089] Determine the bidirectional hierarchical association and the unidirectional hierarchical association of the data nodes according to the association relationship;

[0090] Determine the bidirectional circulation points of the whole chain of garment manufacturing through the bidirectional hierarchical association, and determine the unidirectional circulation points of the whole chain of garment manufacturing according to the unidirectional hierarchical association;

[0091] generating a bidirectional association path between the bidirectional cycle points according to the bidirectional hierarchical association;

[0092] Generating a unidirectional association path between the unidirectional cycle points according to the unidirectional hierarchical association;

[0093] Connecting the bidirectional loop points according to the bidirectional association path to obtain a bidirectional loop subtree, and connecting the unidirectional loop points according to the unidirectional association path to obtain a unidirectional loop subtree;

[0094] The bidirectional cycle subtree is associated with the unidirectional cycle subtree to obtain a bidirectional risk monitoring tree for the entire clothing manufacturing chain.

[0095] In detail, nodes that can be bidirectionally associated and unidirectionally associated between data nodes are determined based on the association relationship. For example, there is a unidirectional hierarchical association between the top-level risk node and the first-level risk node. For example, operational risk affects supply chain risk, and supply chain risk does not affect operational risk, that is, problems in operation will lead to reduced supply chain efficiency or increased costs, and fluctuations in the supply chain will not directly change the risk status in the operation process; there is a bidirectional hierarchical association between the first-level risk node and the second-level risk node. For example, the supply of raw materials directly affects production, and vice versa, the demand for production will also affect the procurement of raw materials. Then, based on the bidirectional hierarchical association, the bidirectional circulation points are determined, and the data nodes involved in the first-level risk node and the second-level risk node are all used as bidirectional circulation points. Based on the unidirectional hierarchical association, the unidirectional circulation points are determined, and the data nodes involved in the top-level risk node and the first-level risk node are all used as unidirectional circulation points, and the path between the first-level risk node and the second-level risk node is used as a bidirectional association path to represent the bidirectional influence between the nodes, and the path between the top-level risk node and the first-level risk node is used as a unidirectional association path to represent the unidirectional influence between the nodes.

[0096] Specifically, the bidirectional loop points are connected according to the bidirectional association path to form a subtree, which represents the bidirectional risk association of each node. The unidirectional loop points are connected according to the unidirectional association path to form another subtree, which represents the unidirectional risk association of each node. Then, the bidirectional loop subtree is associated with the unidirectional loop subtree to obtain a complete bidirectional risk monitoring tree for the entire clothing manufacturing chain. The bidirectional risk monitoring tree can effectively display the risk relationship of each node in the entire manufacturing chain, provide a clear perspective for risk management, and promote the flow of information and the timeliness of decision-making.

[0097] Furthermore, by monitoring the data involved in each data node in the two-way risk monitoring tree, it is possible to identify how the risk is transmitted between different nodes and timely capture the changes in risk between nodes. Therefore, it is necessary to regularly monitor the data nodes in the two-way risk monitoring tree to grasp the risk dynamics.

[0098] The risk factor calculation module 102 is used to monitor the cyclic monitoring data of each data node in the bidirectional risk monitoring tree according to a preset bidirectional cyclic time node, and calculate the risk factor corresponding to the leaf node in the bidirectional risk monitoring tree through the cyclic monitoring data.

[0099] In an embodiment of the present invention, the cyclic monitoring data refers to the detection data in the bidirectional risk monitoring tree that is continuously collected within a preset time interval. The cyclic monitoring data is regularly collected at fixed time intervals to ensure the real-time and accuracy of the information.

[0100] In the embodiment of the present invention, when monitoring the cyclic monitoring data of each data node in the bidirectional risk monitoring tree according to the preset bidirectional cyclic time node, the risk factor calculation module 102 is used to:

[0101] Trigger the bidirectional cycle time node according to a preset time sliding window;

[0102] Collect the real-time bidirectional monitoring data of the bidirectional circulation points and the real-time unidirectional monitoring data of the unidirectional circulation points in the bidirectional risk monitoring tree according to the time point corresponding to the bidirectional circulation time node after the triggering;

[0103] Attribute the real-time two-way monitoring data and the real-time one-way monitoring data to obtain real-time two-way monitoring attribute data and real-time one-way monitoring attribute data;

[0104] The real-time two-way monitoring attribute data and the real-time one-way monitoring attribute data are collected as cyclic monitoring data.

[0105] In detail, the bidirectional cycle time node is determined according to a preset time sliding window, that is, the bidirectional cycle time node is triggered at the start time of a time window. For example, the time sliding window includes the first window from time A to time B, and the second window from time B to time C, then the bidirectional cycle time node is the time A corresponding to the first window and the time B corresponding to the second window, that is, the nodes that can generate data in the bidirectional risk monitoring tree are collected at the time points corresponding to time A and the time points corresponding to time B, respectively, and the data corresponding to each time point can be collected, such as the supplier's delivery time, material quality data, price data, whether the equipment fails, the number of personnel, production process, etc. corresponding to the real-time bidirectional monitoring data; the operation data, financial data and market data in the clothing manufacturing process corresponding to the real-time unidirectional monitoring data are collected, wherein the field changes in the database can be monitored in real time through computer statements to collect real-time bidirectional monitoring data and real-time unidirectional monitoring data.

[0106] Specifically, the monitoring data is converted into a data set with analyzable attributes to form two different attribute data sets. The real-time two-way monitoring attribute data is the attribute information related to the two-way monitoring data, such as delivery time, material quality, price data, equipment failure, number of personnel, production process, transportation time, degree of damage to goods, raw material cost, production efficiency, cash flow, etc.; the real-time unidirectional monitoring attribute data is the attribute information related to the unidirectional monitoring data, such as production scheduling, finished product inspection, and delivery links. Production scheduling refers to the transmission of information from the scheduling department to the production line, and the production line does not feedback the scheduling; finished product inspection is transmitted unidirectionally to the quality management department without affecting the immediate adjustment of the original production line; the delivery link refers to the transmission of information to the logistics department after the goods are shipped, and the logistics process does not involve feedback from the production party, and then all real-time two-way monitoring attribute data and real-time unidirectional monitoring attribute data are collected into a comprehensive circular monitoring data set, so that the overall monitoring status can be evaluated and analyzed.

[0107] Furthermore, as the monitoring data is continuously updated, it is necessary to analyze the dynamic risks of the two-way risk monitoring tree in real time. Therefore, providing real-time data based on cyclic monitoring can timely discover potential risks, thereby enhancing the agility of risk management.

[0108] In the embodiment of the present invention, the risk factor is used to evaluate whether each leaf node in the bidirectional risk monitoring tree has a risk. When the leaf node has a risk, its risk factor is determined to be 1; when the leaf node does not have a risk, its risk factor is determined to be 0.

[0109] In the embodiment of the present invention, when the risk factor calculation module 102 calculates the risk factor corresponding to the leaf node in the bidirectional risk monitoring tree through the cyclic monitoring data, it is used to:

[0110] Obtain target attribute data of the leaf node at the time point;

[0111] The bidirectional risk factor corresponding to the bidirectional circulation point in the leaf node is calculated according to the real-time bidirectional monitoring attribute data and the target attribute data in the circulation monitoring data using the following preset bidirectional time factor algorithm:

[0112]

[0113] Among them, f i is the bidirectional risk factor corresponding to the i-th bidirectional cycle point, p it is the positive feedback attribute value of the real-time bidirectional monitoring attribute data corresponding to the i-th bidirectional cycle point at time point t, q it is the target attribute value of the target attribute data corresponding to the i-th bidirectional loop point at time point t, is the real-time attribute value of the real-time bidirectional monitoring attribute data corresponding to the i-th bidirectional cycle point at time point t, is the reverse feedback attribute value corresponding to the i-th bidirectional loop point at time point t;

[0114] The one-way risk factor corresponding to the one-way circulation point in the leaf node is calculated according to the real-time one-way monitoring attribute data and the target attribute data in the circulation monitoring data using the following preset one-way time factor algorithm:

[0115]

[0116] Among them, g i is the one-way risk factor corresponding to the i-th one-way cycle point, a it is the real-time attribute value of the real-time one-way monitoring attribute data corresponding to the i-th one-way cycle point at time point t, b it is the target attribute value of the target attribute data corresponding to the i-th one-way cycle point at time point t.

[0117] In detail, the target attribute data corresponding to different cycle time points are extracted, such as the original production plan and the original transportation plan for the entire chain of clothing manufacturing in the clothing manufacturing process. For example, the original production plan includes raw material data of 100, raw material quality of grade one, supplier delivery time of time A, and production scheduling as the first day after the end of production; the transportation plan includes transportation time of x days, goods cannot be damaged, and goods delivery time is the 5th day after the end of production. The raw material cost data and sales price data are compared with the target attribute data as q ijt , where the target attribute data is the data in the original production plan and the original transportation plan, and then for the real-time two-way monitoring attribute data collected by the two-way circulation node, if the leaf node includes supplier delayed delivery, raw material quality problems, price fluctuations, transportation delays, cargo damage, cargo delivery links, production processes, and production scheduling, the leaf node is divided into two-way circulation points and one-way circulation points. The two-way circulation points include supplier delayed delivery, raw material quality problems, price fluctuations, transportation delays, and cargo damage, and the one-way circulation points include cargo delivery links, production processes, and production scheduling.

[0118] Specifically, the two-way time factor algorithm is used to calculate the risk impact of the data collected at different cycle time points on each leaf node. The supplier delivery time, raw material quality grade, sales price, transportation time, and the number of damaged goods collected in real time are compared with the original target attribute data in turn. In the two-way cycle point, the real-time data collected at the time point is first compared with the original data. The positive feedback attribute value refers to the real-time data collected at the time point. At the time point, the original data may change due to customer demand. The change in the original data will be determined as the reverse feedback attribute value. The reverse feedback attribute value is compared with the data collected in real time to more accurately determine the risk factor corresponding to the bidirectional circulation point. When the result after data comparison is equal to 0, it means that the data between the two are balanced. At this time, the bidirectional circulation point is risk-free and the risk factor is 0. When the result after comparison is greater than 0, it means that the data between the two are unbalanced. At this time, the bidirectional circulation point is risky and the risk factor is 1. Similarly, for the unidirectional circulation point, only the real-time data collected by the unidirectional circulation point is compared with the target data, and then the unidirectional risk factor corresponding to the unidirectional circulation point is determined according to the comparison result.

[0119] Furthermore, in order to clearly identify the specific risk level of each leaf node, it is necessary to determine the risk tolerance of each leaf node. With limited resources, high-risk, low-tolerance nodes can be prioritized to respond to market changes more flexibly.

[0120] The risk probability calculation module 103 is used to calculate the risk tolerance of the leaf node according to the target node data corresponding to the leaf node in the bidirectional risk monitoring tree, and calculate the risk probability of each data node according to the risk factor and the risk tolerance.

[0121] In the embodiment of the present invention, the risk tolerance refers to the risk level or loss range that the leaf node can accept, reflecting the degree of risk that the node is willing to bear when facing potential threats or uncertainties.

[0122] In the embodiment of the present invention, when the risk probability calculation module 103 calculates the risk tolerance of the leaf node according to the target node data corresponding to the leaf node in the bidirectional risk monitoring tree, it is used to:

[0123] Determine the data collection time period corresponding to the leaf node according to the time point corresponding to the bidirectional loop node in the bidirectional risk monitoring tree and the preset time collection point;

[0124] Extracting the historical critical data corresponding to the leaf node through the data collection time period;

[0125] The risk tolerance of the leaf node is calculated according to the target node data and the historical critical data, wherein the risk tolerance calculation formula is:

[0126]

[0127] Among them, R kα is the risk tolerance corresponding to the kth leaf node at the αth time point, S kα is the target node data corresponding to the kth leaf node at the αth time point, L kα is the minimum value of the historical critical data corresponding to the kth leaf node at the αth time point, H kα is the maximum value of the historical critical data corresponding to the kth leaf node at the αth time point, and min is the minimum value function.

[0128] Specifically, the collection time period of the leaf node is determined according to the time point corresponding to each leaf node and the preset time collection point. For example, the time point is t, and the preset time collection point is t 1 , then the data collection time period is determined as (t 1 ,t0, that is, the time point t is the end time, and the data before the time point t to t 1 The historical critical data for this period of time includes the maximum and minimum values ​​of the data corresponding to each leaf node during the data collection period, wherein the historical critical data corresponding to the leaf node can be collected through a computer statement with a data capture function.

[0129] Specifically, the risk tolerance of each leaf node is determined according to the target node data corresponding to each leaf node and the historical critical data corresponding to each leaf node, that is, the target node data corresponding to each leaf node is compared with its corresponding historical maximum value and historical minimum value, then |S kα -L kα | indicates the current attribute value S kα With the historical minimum value L kα The gap between the current value and the past low point reflects the degree of deviation. kα -H kα | indicates the current attribute value S kα With the historical maximum value H kαThe gap between them reflects the degree of deviation between the current value and the past high point, and then the degree of deviation is calculated with the range of historical values ​​(the difference between the maximum and minimum values) to obtain the tolerance of the data collected by each leaf node in the range based on the time point t, where the value range of k is 1 to the number of leaf nodes, and the value range of α is 1 to the number of cyclic collections at the cycle time point. Then, based on the number of collections at the cycle time point, the tolerance corresponding to each leaf node in multiple time ranges is calculated, and the minimum value is selected from the tolerances of all time ranges, that is, the data with the smallest tolerance is selected as the tolerance corresponding to each leaf node. By collecting data multiple times in different time ranges, the impact of accidental factors on the results can be reduced, and the representativeness and reliability of the data can be improved. Data based on multiple time ranges can reflect the trend of data changes over time, and can more accurately assess the risks of leaf nodes.

[0130] Furthermore, as new data is continuously collected, the tolerance of each leaf node can be dynamically updated to ensure that decisions are always based on the latest information, so that the risk probability of each data node in the bidirectional risk monitoring tree can be determined more accurately.

[0131] In the embodiment of the present invention, the risk probability refers to the probability of occurrence of a specific risk event corresponding to the leaf, which measures the impact of potential risks on the entire chain of clothing manufacturing.

[0132] In the embodiment of the present invention, when calculating the risk probability of each data node according to the risk factor and the risk tolerance, the risk probability calculation module 103 is used to:

[0133] Determine the target risk probability corresponding to the leaf node according to the risk factor and the risk tolerance:

[0134]

[0135] Among them, Y k is the target risk probability of the kth leaf node, f k is the bidirectional risk factor corresponding to the bidirectional loop point in the kth leaf node, g k is the one-way risk factor corresponding to the one-way cycle point in the kth leaf node, R k is the risk tolerance of the kth leaf node, ∨ is the OR symbol, and ∧ is the AND symbol;

[0136] Extracting the node hierarchical relationship corresponding to the leaf node through a bidirectional risk monitoring tree;

[0137] Determine the level node corresponding to the leaf node according to the node level relationship;

[0138] Counting the node risk probabilities corresponding to the hierarchical nodes through the target risk probability;

[0139] The risk probability of each data node is determined according to the node risk probability.

[0140] In detail, when the risk factor of a leaf node is 1, it means that there is a risk, or when the target risk tolerance is greater than 1, it means that the risk probability corresponding to this leaf node is 1; when the risk factor of a leaf node is 0 and the target risk tolerance is less than 1 and greater than 0, it means that the risk probability corresponding to this leaf node is 0; when the risk factor of a leaf node is 0 and the target risk tolerance is greater than 1, the inverse of the target risk tolerance is used as the risk probability of the leaf node at this time, thereby obtaining the target risk probability corresponding to each leaf node in the bidirectional risk monitoring tree, and then calculating the risk probability of all data nodes in the entire bidirectional risk monitoring tree based on the target risk probability.

[0141] Specifically, the node hierarchical relationship corresponding to the leaf node is determined according to the bidirectional risk monitoring tree, and the hierarchical node corresponding to the leaf node is determined according to the hierarchical relationship. For example, the node hierarchical relationship corresponding to the leaf node A has a parent node. When the number of leaf nodes of the parent node corresponding to the leaf node is 3, and the risk probabilities of the three leaf nodes are all 1 at this time, the risk probability corresponding to the parent node is 1. If only two leaf nodes have a risk probability of 1 at this time, the risk probability corresponding to the parent node is 1 / 3. If one leaf node has a risk probability of 1, one leaf node has a risk probability of 0, and one leaf node has a risk probability of 1 / 8, the risk probability corresponding to the parent node is (1+1 / 8) / 3=3 / 8. Therefore, the risk probabilities corresponding to all data nodes in the bidirectional risk monitoring tree can be calculated based on all hierarchical nodes and the number of child nodes corresponding to the nodes.

[0142] Furthermore, in order to allocate resources and time more effectively and concentrate on dealing with the most urgent issues, the nodes that need to be processed first should be adjusted based on the latest data and associations. Therefore, it is necessary to analyze the urgency of each data node.

[0143] The node coordination sequence generation module 104 is used to calculate the urgency of each data node according to the association relationship through a preset dynamic hierarchical association algorithm, determine the risk coordination degree of each data node according to the urgency and the risk probability, and generate the node coordination sequence of the bidirectional risk monitoring tree according to the risk coordination degree.

[0144] In the embodiment of the present invention, the urgency level is to evaluate which data node needs to be resolved first, thereby optimizing resource allocation and emergency response, and improving the overall efficiency and reliability of the entire chain of clothing manufacturing.

[0145] In the embodiment of the present invention, when calculating the urgency of each data node according to the association relationship by using a preset dynamic hierarchical association algorithm, the node coordination sequence generation module 104 is used to:

[0146] Determine the node level corresponding to each data node according to the association relationship;

[0147] Determining a level emergency coefficient of each data node according to the node level;

[0148] Determine the dynamic demand data of each data node through the cycle time point corresponding to the cycle time node;

[0149] The urgency of each data node is calculated according to the number of occurrences of the dynamic demand data by using the following preset dynamic hierarchical association algorithm:

[0150]

[0151] Among them, d σ is the urgency of the σth data node, δ σ is the hierarchical emergency coefficient of the σth data node, c σε is the number of occurrences of the σth data node at the cycle time point ε, e is the exponent, λ is the time decay rate, T is the final time of the cycle time point, ε σ is the cycle time point corresponding to the σth data node, and m is the number of cycles of the cycle time point.

[0152] In detail, the level of each data node is determined according to the association relationship between the nodes, and then the level emergency coefficient of each data node is determined according to the node level. For example, if data node A is at the first level, the corresponding level emergency coefficient is n, and data node B is at the second level, the corresponding level emergency coefficient is n-1, and data node C is at the nth level, then the corresponding level emergency coefficient is 1. The level emergency coefficient reflects the importance of the node and the impact it may have on the system. The higher the level, the greater the emergency coefficient may be. Nodes with high levels have a greater impact on the stability or safety of the entire chain of clothing manufacturing.

[0153] Specifically, the dynamic demand data of each data node is determined through the cycle time node. The cycle time node refers to the data point within a specific time interval, which can be real-time data or regularly collected demand data. The number of occurrences of dynamic demand data is a key indicator, which indicates the frequency of occurrence of demand or events of each data node within a specific time period. Then, the urgency of each data node is calculated according to the number of occurrences of dynamic demand data. The time decay rate λ in the dynamic hierarchical association algorithm controls the decay speed of the node urgency over time. A larger λ value means that the urgency of the node will decrease rapidly. Taking into account the influence of time factors, the urgency of the node will gradually decrease with the passage of time, reflecting the concept that the earlier the processing, the more important it is, that is, the number of occurrences in different cycles, that is, the dynamic occurrences of dynamic demand data at different time points, and as time goes by, the urgency of the change of each dynamic demand data is attenuated, and subsequent changes in dynamic demand are evaluated first to obtain the urgency of each node, where dynamic demand data refers to the number of changes in external demand corresponding to each data node. For example, if a customer requests to add an order or request to reduce an order, the order quantity will change, and the number of occurrences of the dynamic demand data corresponding to the supply chain node will be increased by 1. If a node is requested more times at a certain point in time, it means that its demand is more urgent and the impact is greater.

[0154] Furthermore, by analyzing the importance of nodes (hierarchical urgency coefficient) and demand frequency (number of occurrences), and adjusting through the time decay rate over time, the entire chain of clothing manufacturing can flexibly adjust the attention and resource allocation to different data nodes according to real-time conditions, thereby coordinating the nodes that need to be coordinated based on the urgency of the nodes and the risk probability, so that the risks of each data node in the entire chain of clothing manufacturing can be balanced.

[0155] In an embodiment of the present invention, the risk coordination degree is an indicator that measures the contribution of each data node to the overall risk management under specific circumstances. It combines the urgency and risk probability, and is helpful in identifying which nodes in the entire chain of clothing manufacturing are reducing risks, optimizing resource allocation or improving response capabilities.

[0156] In the embodiment of the present invention, when determining the risk coordination degree of each data node according to the urgency and the risk probability, the node coordination sequence generation module 104 is used to:

[0157] Extracting the cycle urgency and the cycle risk probability corresponding to each data node at the cycle time point corresponding to the cycle time node according to the urgency and the risk probability;

[0158] Selecting the best combination parameter corresponding to the cycle urgency and the cycle risk probability under the cycle time point condition;

[0159] The risk coordination degree of each data node is determined according to the optimal combination parameters.

[0160] Specifically, the cycle urgency and cycle risk probability corresponding to each cycle time point are extracted, and the cycle urgency is selected from the urgency, and the cycle risk probability is selected from the risk probability. For example, if the cycle time point has t 1 ,t 2 ,t 3 , then at the cycle time point t1 Extract cycle urgency under condition d 1 and the cyclic risk probability Y 1 , at the cycle time point t 2 Extract cycle urgency under condition d 2 and the cyclic risk probability Y 2 , at the cycle time point t 3 Extract cycle urgency under condition d 3 and the cyclic risk probability Y 3 , and then determine the optimal combination between cycle urgency and cycle risk probability under different cycle time points.

[0161] Specifically, the risk coordination degree is obtained by multiplying the risk probability corresponding to the time point with the largest cycle urgency. When the cycle urgency is the same, the risk coordination degree is obtained by multiplying the risk probability corresponding to the time point with the smallest risk probability in the cycle risk probability. For example, at the cycle time point t 3 The corresponding cycle urgency is the largest, then the cycle time point t of data node A is 3 The corresponding cycle urgency and cycle risk probability are used as the optimal combination parameters, and then the two parameters in the optimal combination parameters are multiplied to obtain the risk coordination degree of data node A. If the cycle time point of data node A is t 1 and t 3 When the corresponding cycle urgency is the same, if the cycle time point t 1 The corresponding risk probability is the smallest, then the cycle time point t 1 The corresponding cycle urgency is multiplied by the risk probability to obtain the risk coordination degree of data node A.

[0162] Furthermore, a node coordination sequence of the bidirectional risk monitoring tree is generated according to the risk coordination degree, that is, each data node in the bidirectional risk monitoring tree is sorted in descending order of risk coordination degree, thereby obtaining a node coordination sequence.

[0163] Furthermore, risk coordination is performed based on the nodes with high risk levels based on the risk coordination degree to avoid risk diffusion and ensure the effective use of resources and minimization of risks.

[0164] The risk coordination module 105 is used to generate a coordination factor for each data coordination node in the node coordination sequence according to the risk coordination degree, generate a coordination strategy for the data coordination node according to the coordination factor, and perform risk coordination on the data coordination node according to the coordination strategy.

[0165] In the embodiment of the present invention, the coordination factor refers to an indicator type of a certain measure used to measure and optimize the degree of interaction and coordination between different nodes or resources during the risk coordination process.

[0166] In the embodiment of the present invention, when the risk coordination module 105 generates the coordination factor of each data coordination node in the node coordination sequence according to the risk coordination degree, it is used to:

[0167] Priority identification is performed on each data coordination node in the node coordination sequence according to the risk coordination degree to obtain a node priority corresponding to each data coordination node;

[0168] Determine the risk coordination type corresponding to each data coordination node according to the node priority;

[0169] A coordination factor for each data coordination node is generated according to the risk coordination type.

[0170] Specifically, each data coordination node is prioritized according to the node coordination sequence. For example, the node coordination sequence is {A 1 ,A 2 ,A 3 ,A 4}, the priority is marked according to the order of data coordination nodes, such as node A 1 The corresponding priority is 1, node A 2 The corresponding priority is 2, node A n The corresponding priority is identified as n, so as to obtain the node priority corresponding to each data node in the node coordination sequence, and then determine the risk coordination type identification corresponding to each data node according to the node priority, then the node priority is , the corresponding risk coordination type is the acceptance type; the node priority is When , the corresponding risk coordination type is the transfer type; the node priority is When , the corresponding risk coordination type is the mitigation type; the node priority is When , the corresponding risk coordination type is the avoidance type, where x represents the priority of the data node in the node coordination sequence.

[0171] Specifically, the coordination factor of each data coordination node is generated according to the risk coordination type. The coordination factor corresponding to the avoidance type is 0, the coordination factor corresponding to the mitigation type is 1, the coordination factor corresponding to the transfer type is 2, and the coordination factor corresponding to the acceptance type is 3. The acceptance type is to accept the occurrence of the risk. If it is determined that there will be a delay, communicate with relevant stakeholders and set an acceptable delay range; the transfer type is to introduce external help, such as signing an agreement with external suppliers to ensure that key components are delivered on time; the mitigation type is to start a backup plan. If the main supplier cannot deliver on time, an alternative supplier can be selected; the avoidance type is to adjust the project scope, such as reducing the delivery content to ensure on-time completion.

[0172] Furthermore, in order to ensure data consistency between different nodes and avoid decision-making errors caused by data inconsistency, it is necessary to generate coordination strategies for different data coordination nodes. Through reasonable coordination, resources can be efficiently allocated and utilized, redundancy and waste can be reduced, thereby reducing operating costs.

[0173] In the embodiment of the present invention, the coordination strategy refers to a specific policy formulated among multiple data coordination nodes to achieve effective data management and collaborative work.

[0174] In the embodiment of the present invention, when the risk coordination module 105 generates the coordination strategy of the data coordination node according to the coordination factor, it is used to:

[0175] Determining the coordination content of the data coordination node according to the coordination factor;

[0176] Generate a coordination task of the data coordination node according to the coordination content;

[0177] A coordination strategy of the data coordination node is generated according to the coordination task.

[0178] In detail, when the coordination factor is 0, the coordination content is to adjust the project scope, the coordination task is to re-evaluate the project goals, identify and reduce unnecessary functions or requirements, ensure the effective use of project resources, and the coordination strategy is to redefine the scope of the clothing manufacturing project; when the coordination factor is 1, the coordination content is to start the backup plan, the coordination task is to retrieve and prepare the existing backup plan, allocate relevant resources and personnel, ensure that the clothing manufacturing project can seamlessly switch to the backup plan, and the coordination strategy is to generate the implementation process of the backup plan; when the coordination factor is 2, the coordination content is to introduce external help, the coordination task is to determine the areas that require external support, screen suitable partners or experts, and formulate a plan to introduce external help. The coordination strategy is to select appropriate external support, sign a contract and set the cooperation period and clothing manufacturing goals; when the coordination factor is 3, the coordination content is to accept the occurrence of risks, the coordination task is to evaluate the current risk situation, formulate risk response measures, and the coordination strategy is to establish a regular risk assessment mechanism, use risk matrix analysis tools to ensure that all potential risks are identified and recorded, and formulate corresponding emergency plans for clothing manufacturing.

[0179] For example, during the progress of the project, it was found that certain design features were unnecessary, so the team decided to adjust the project scope, re-evaluate the goals, delete complex embroidery designs, and focus on simple styles to ensure effective use of resources, and finally launch a simple and easy-to-wear clothing series; during the production process, equipment failure occurred, and the team activated the backup plan, retrieved the previously formulated backup plan, allocated spare equipment and personnel, and ensured that the production line could be quickly switched to other machines to avoid production delays and ensure delivery on time; the project team realized the lack of expertise in sustainable materials and decided to introduce external help, screened several suppliers of environmentally friendly materials, developed a cooperation plan, and after signing the contract, worked with these experts to optimize material selection and launch an environmentally friendly clothing series; during market research, it was found that competition was fierce, so the team evaluated potential risks, formulated countermeasures, established a regular risk assessment mechanism, and used the risk matrix to identify market change risks to ensure that the team could quickly adjust production strategies, such as increasing online marketing and responding to consumer needs in a timely manner.

[0180] Furthermore, conducting risk coordination on data coordination nodes according to the coordination strategy, that is, conducting corresponding risk coordination on data coordination nodes according to the generated coordination strategy, can effectively reduce the uncertainty and potential losses in the execution of clothing manufacturing projects, and can respond quickly when risks occur to ensure the smooth progress of clothing manufacturing projects.

[0181] The embodiment of the present invention structures the complex manufacturing process by identifying the data nodes of the whole chain and their associations, which is conducive to discovering the mutual influence between each node; by setting the cycle time node, it can collect monitoring data in real time, quickly identify risk changes, and calculate the risk factor of each data node to provide data support for subsequent risk management; by calculating the risk tolerance according to the target data of each node, it can evaluate and manage the risks of different nodes in a targeted manner to avoid excessive or insufficient risk control; by calculating the urgency, the team can give priority to the most urgent problems and improve the efficiency of resource allocation, and the calculation of the risk coordination degree enables the team to flexibly adjust the response strategy to ensure rapid response when risks occur and reduce the impact. According to the coordination strategy generated by the coordination factor, each data node has clear risk response measures to enhance the effectiveness of risk management. Therefore, the full-chain risk monitoring and coordination system and method for clothing manufacturing proposed by the present invention can solve the problem of low accuracy when conducting full-chain risk monitoring and coordination of clothing manufacturing.

[0182] Reference Figure 2 FIG. 1 is a flow chart of an operation method of a full-chain risk monitoring and coordination system for clothing manufacturing provided by an embodiment of the present invention. In this embodiment, the operation method of the full-chain risk monitoring and coordination system for clothing manufacturing includes:

[0183] S1. Obtain data nodes of the entire chain of clothing manufacturing and the association relationship between the nodes, and construct a bidirectional risk monitoring tree of the entire chain of clothing manufacturing according to the data nodes and the association relationship;

[0184] S2. Monitoring the cyclic monitoring data of each data node in the bidirectional risk monitoring tree according to a preset bidirectional cyclic time node, and calculating the risk factor corresponding to each data node through the cyclic monitoring data;

[0185] S3, calculating the risk tolerance of each data node according to the target node data corresponding to each data node in the bidirectional risk monitoring tree, and calculating the risk probability of each data node according to the risk factor and the risk tolerance;

[0186] S4. Calculate the urgency of each data node according to the association relationship through a preset dynamic hierarchical association algorithm, determine the risk coordination degree of each data node according to the urgency and the risk probability, and generate a node coordination sequence of the bidirectional risk monitoring tree according to the risk coordination degree;

[0187] S5. Generate a coordination factor for each data coordination node in the node coordination sequence according to the risk coordination degree, generate a coordination strategy for the data coordination node according to the coordination factor, and perform risk coordination on the data coordination node according to the coordination strategy.

[0188] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0189] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0190] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is not limited only according to the above description, and it is intended that all changes within the meaning and scope of equivalent elements within the scope of protection are included in the present invention.

[0191] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in a system claim can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0192] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A full-chain risk monitoring and coordination system for clothing manufacturing, characterized in that: The system includes a bidirectional risk monitoring tree construction module, a risk factor calculation module, a risk probability calculation module, a node coordination sequence generation module and a risk coordination module, wherein: The bidirectional risk monitoring tree construction module is used to obtain data nodes of the entire chain of clothing manufacturing and the association relationship between the nodes, and to construct a bidirectional risk monitoring tree of the entire chain of clothing manufacturing according to the data nodes and the association relationship; The risk factor calculation module is used to monitor the cyclic monitoring data of each data node in the bidirectional risk monitoring tree according to a preset bidirectional cyclic time node, and calculate the risk factor corresponding to the leaf node in the bidirectional risk monitoring tree through the cyclic monitoring data; The risk probability calculation module is used to calculate the risk tolerance of the leaf node according to the target node data corresponding to the leaf node in the bidirectional risk monitoring tree, and is used to: determine the data collection time period corresponding to the leaf node according to the time point corresponding to the bidirectional loop node in the bidirectional risk monitoring tree and the preset time collection point; extract the historical critical data corresponding to the leaf node through the data collection time period; calculate the risk tolerance of the leaf node according to the target node data and the historical critical data, wherein the risk tolerance calculation formula is: Among them, R kα is the risk tolerance corresponding to the kth leaf node at the αth time point, S kα is the target node data corresponding to the kth leaf node at the αth time point, L kα is the minimum value of the historical critical data corresponding to the kth leaf node at the αth time point, H kα is the maximum value of the historical critical data corresponding to the kth leaf node at the αth time point, and min is the minimum value function; Calculate the risk probability of each data node according to the risk factor and the risk tolerance; The node coordination sequence generation module is used to calculate the urgency of each data node according to the association relationship through a preset dynamic hierarchical association algorithm, determine the risk coordination degree of each data node according to the urgency and the risk probability, and generate a node coordination sequence of the bidirectional risk monitoring tree according to the risk coordination degree; The risk coordination module is used to generate a coordination factor for each data coordination node in the node coordination sequence according to the risk coordination degree, generate a coordination strategy for the data coordination node according to the coordination factor, and perform risk coordination on the data coordination node according to the coordination strategy.

2. The full-chain risk monitoring and coordination system for clothing manufacturing as claimed in claim 1, characterized in that: When constructing a bidirectional risk monitoring tree of the entire clothing manufacturing chain according to the data nodes and the association relationships, the bidirectional risk monitoring tree construction module is used to: Determine the bidirectional hierarchical association and the unidirectional hierarchical association of the data nodes according to the association relationship; Determine the bidirectional circulation points of the whole chain of garment manufacturing through the bidirectional hierarchical association, and determine the unidirectional circulation points of the whole chain of garment manufacturing according to the unidirectional hierarchical association; generating a bidirectional association path between the bidirectional cycle points according to the bidirectional hierarchical association; Generating a unidirectional association path between the unidirectional cycle points according to the unidirectional hierarchical association; Connecting the bidirectional loop points according to the bidirectional association path to obtain a bidirectional loop subtree, and connecting the unidirectional loop points according to the unidirectional association path to obtain a unidirectional loop subtree; The bidirectional cycle subtree is associated with the unidirectional cycle subtree to obtain a bidirectional risk monitoring tree for the entire clothing manufacturing chain.

3. The full-chain risk monitoring and coordination system for clothing manufacturing as claimed in claim 1, characterized in that: When monitoring the cyclic monitoring data of each data node in the bidirectional risk monitoring tree according to a preset bidirectional cyclic time node, the risk factor calculation module is used to: Trigger the bidirectional cycle time node according to a preset time sliding window; Collect the real-time bidirectional monitoring data of the bidirectional circulation points and the real-time unidirectional monitoring data of the unidirectional circulation points in the bidirectional risk monitoring tree according to the time point corresponding to the bidirectional circulation time node after the triggering; Attribute the real-time two-way monitoring data and the real-time one-way monitoring data to obtain real-time two-way monitoring attribute data and real-time one-way monitoring attribute data; The real-time two-way monitoring attribute data and the real-time one-way monitoring attribute data are collected as cyclic monitoring data.

4. The full-chain risk monitoring and coordination system for clothing manufacturing as claimed in claim 1, characterized in that: When the risk factor calculation module calculates the risk factor corresponding to the leaf node in the bidirectional risk monitoring tree through the cyclic monitoring data, it is used to: Obtain target attribute data of the leaf node at the time point; The bidirectional risk factor corresponding to the bidirectional circulation point in the leaf node is calculated according to the real-time bidirectional monitoring attribute data and the target attribute data in the circulation monitoring data using the following preset bidirectional time factor algorithm: Among them, f i is the bidirectional risk factor corresponding to the i-th bidirectional cycle point, p it is the positive feedback attribute value of the real-time bidirectional monitoring attribute data corresponding to the i-th bidirectional cycle point at time point t, q it is the target attribute value of the target attribute data corresponding to the i-th bidirectional loop point at time point t, is the real-time attribute value of the real-time bidirectional monitoring attribute data corresponding to the i-th bidirectional cycle point at time point t, is the reverse feedback attribute value corresponding to the i-th bidirectional loop point at time point t; The one-way risk factor corresponding to the one-way circulation point in the leaf node is calculated according to the real-time one-way monitoring attribute data and the target attribute data in the circulation monitoring data using the following preset one-way time factor algorithm: Among them, g i is the one-way risk factor corresponding to the i-th one-way cycle point, a it is the real-time attribute value of the real-time one-way monitoring attribute data corresponding to the i-th one-way cycle point at time point t, b it is the target attribute value of the target attribute data corresponding to the i-th one-way cycle point at time point t.

5. The full-chain risk monitoring and coordination system for clothing manufacturing as claimed in claim 1, characterized in that: When calculating the risk probability of each data node according to the risk factor and the risk tolerance, the risk probability calculation module is used to: Determine the target risk probability corresponding to the leaf node according to the risk factor and the risk tolerance: Among them, Y k is the target risk probability of the kth leaf node, f k is the bidirectional risk factor corresponding to the bidirectional loop point in the kth leaf node, g k is the one-way risk factor corresponding to the one-way cycle point in the kth leaf node, R k is the risk tolerance of the kth leaf node, ∨ is the OR symbol, and ∧ is the AND symbol; Extracting the node hierarchical relationship corresponding to the leaf node through a bidirectional risk monitoring tree; Determine the level node corresponding to the leaf node according to the node level relationship; Counting the node risk probabilities corresponding to the hierarchical nodes through the target risk probability; The risk probability of each data node is determined according to the node risk probability.

6. The full-chain risk monitoring and coordination system for clothing manufacturing as claimed in claim 3, characterized in that: When the node coordination sequence generation module calculates the urgency of each data node according to the association relationship by using a preset dynamic hierarchical association algorithm, it is used to: Determine the node level corresponding to each data node according to the association relationship; Determining a level emergency coefficient of each data node according to the node level; Determine the dynamic demand data of each data node through the cycle time point corresponding to the cycle time node; The urgency of each data node is calculated according to the number of occurrences of the dynamic demand data by using the following preset dynamic hierarchical association algorithm: Among them, d σ is the urgency of the σth data node, δ σ is the hierarchical emergency coefficient of the σth data node, c σε is the number of occurrences of the σth data node at the cycle time point ε, e is the exponent, λ is the time decay rate, T is the final time of the cycle time point, ε σ is the cycle time point corresponding to the σth data node, and m is the number of cycles of the cycle time point.

7. The full-chain risk monitoring and coordination system for clothing manufacturing as claimed in claim 1, characterized in that: When determining the risk coordination degree of each data node according to the urgency and the risk probability, the node coordination sequence generation module is used to: Extracting the cycle urgency and the cycle risk probability corresponding to each data node at the cycle time point corresponding to the cycle time node according to the urgency and the risk probability; Selecting the best combination parameter corresponding to the cycle urgency and the cycle risk probability under the cycle time point condition; The risk coordination degree of each data node is determined according to the optimal combination parameters.

8. The full-chain risk monitoring and coordination system for clothing manufacturing as claimed in claim 1, characterized in that: When the risk coordination module generates the coordination factor of each data coordination node in the node coordination sequence according to the risk coordination degree, it is used to: Priority identification is performed on each data coordination node in the node coordination sequence according to the risk coordination degree to obtain a node priority corresponding to each data coordination node; Determine the risk coordination type corresponding to each data coordination node according to the node priority; A coordination factor for each data coordination node is generated according to the risk coordination type.

9. The full-chain risk monitoring and coordination system for clothing manufacturing as claimed in claim 1, characterized in that: When the risk coordination module generates the coordination strategy of the data coordination node according to the coordination factor, it is used to: Determining the coordination content of the data coordination node according to the coordination factor; Generate a coordination task of the data coordination node according to the coordination content; A coordination strategy of the data coordination node is generated according to the coordination task.

10. A method for operating a full-chain risk monitoring and coordination system for clothing manufacturing, characterized in that: Used to implement the full-chain risk monitoring and coordination system for clothing manufacturing as described in any one of claims 1 to 9, the method comprising: Acquire data nodes of the entire chain of clothing manufacturing and the association relationships between the nodes, and construct a bidirectional risk monitoring tree of the entire chain of clothing manufacturing according to the data nodes and the association relationships; Monitoring the cyclic monitoring data of each data node in the bidirectional risk monitoring tree according to a preset bidirectional cyclic time node, and calculating the risk factor corresponding to each data node through the cyclic monitoring data; The risk tolerance of each data node is calculated according to the target node data corresponding to each data node in the bidirectional risk monitoring tree, and is used to: determine the data collection time period corresponding to the leaf node according to the time point corresponding to the bidirectional loop node in the bidirectional risk monitoring tree and the preset time collection point; extract the historical critical data corresponding to the leaf node through the data collection time period; calculate the risk tolerance of the leaf node according to the target node data and the historical critical data, wherein the risk tolerance calculation formula is: Among them, R kα is the risk tolerance corresponding to the kth leaf node at the αth time point, S kα is the target node data corresponding to the kth leaf node at the αth time point, L kα is the minimum value of the historical critical data corresponding to the kth leaf node at the αth time point, H kα is the maximum value of the historical critical data corresponding to the kth leaf node at the αth time point, and min is the minimum value function; Calculate the risk probability of each data node according to the risk factor and the risk tolerance; The urgency of each data node is calculated according to the association relationship by a preset dynamic hierarchical association algorithm, the risk coordination degree of each data node is determined according to the urgency and the risk probability, and a node coordination sequence of the bidirectional risk monitoring tree is generated according to the risk coordination degree; A coordination factor of each data coordination node in the node coordination sequence is generated according to the risk coordination degree, a coordination strategy of the data coordination node is generated according to the coordination factor, and risk coordination is performed on the data coordination node according to the coordination strategy.

Images