Material parameter digitization method and system for full-period management

Abstract

The invention discloses a material parameter digitization method and system for full-period management, and relates to the technical field of digitization processing, and the method comprises the steps: determining a plurality of material management nodes, carrying out the period monitoring, and obtaining a full-period parameter set of materials; performing association matching on the plurality of material management nodes and the multi-stage material parameters to generate a material parameter management network; traversing the material parameter management network to carry out digital calculation, and generating a plurality of digital coefficients; performing digital compensation analysis on the material parameter management network, and formulating a digital compensation scheme; and carrying out digital verification on the material parameter management network, carrying out regular feedback on the plurality of material management nodes according to a verification result, generating digital feedback information, and carrying out full-period digital management on the multi-stage material parameters. The technical problem that accurate digital management of the material parameters cannot be effectively carried out in the prior art is solved, and the technical effect of accurate digital management of the material parameters is achieved.

Description

Technical Field

[0001] The present invention relates to the field of digital processing technology, and in particular to a material parameter digitization method and system for full-cycle management. Background Art

[0002] With the increasing complexity of modern industrial production and supply chain management, the importance of material management in various industries has become increasingly prominent. Material management not only involves multiple links such as procurement, inventory, use, and maintenance, but also requires accurate monitoring of the status, location, and life cycle of materials. However, most of the current technologies in material management are still in the traditional stage and cannot achieve accurate digital management of material parameters. Summary of the invention

[0003] The present application provides a material parameter digitization method and system for full-cycle management, which is used to solve the technical problem that the existing technology cannot effectively perform accurate digital management of material parameters.

[0004] In view of the above problems, the present application provides a material parameter digitization method and system for full-cycle management.

[0005] In a first aspect of the present application, a material parameter digitization method for full-cycle management is provided, the method comprising: The material supply chain is traversed to perform material correlation analysis, multiple material management nodes are determined, and periodic monitoring is performed according to the multiple material management nodes through a sensor device group to obtain a full-cycle parameter set of the material, wherein the full-cycle parameter set of the material includes multi-stage material parameters; the multiple material management nodes are associated and matched with the multi-stage material parameters to generate a material parameter management network, wherein the material parameter management network includes multiple node material association parameters; the material parameter management network is traversed to perform digital calculations to generate multiple digital coefficients, wherein the multiple digital coefficients correspond to the multiple node material association parameters; the material parameter management network is digitally compensated according to the multiple digital coefficients combined with the multiple node material association parameters, and a digital compensation plan is formulated; the material parameter management network is digitally verified by executing the digital compensation plan, and the multiple material management nodes are regularly fed back according to the verification results to generate digital feedback information, and the multi-stage material parameters are digitally managed throughout the entire cycle according to the digital feedback information.

[0006] The second aspect of the present application provides a material parameter digitization system for full-cycle management, the system comprising: A cycle monitoring module, wherein the cycle monitoring module traverses the material supply chain to perform material correlation analysis, determines multiple material management nodes, performs cycle monitoring according to the multiple material management nodes through a sensor device group, and obtains a full-cycle parameter set of the material, wherein the full-cycle parameter set of the material includes multi-stage material parameters; an association matching module, wherein the association matching module associates and matches the multiple material management nodes with the multi-stage material parameters to generate a material parameter management network, wherein the material parameter management network includes multiple node material association parameters; a digital calculation module, wherein the digital calculation module traverses the material parameter management network to perform digital calculations to generate multiple digital coefficients, wherein the multiple digital coefficients correspond to the multiple node material association parameters; a digital compensation analysis module, wherein the digital compensation analysis module performs digital compensation analysis on the material parameter management network according to the multiple digital coefficients combined with the multiple node material association parameters, and formulates a digital compensation plan; a digital management module, wherein the digital management module executes the digital compensation plan to perform digital verification on the material parameter management network, performs regular feedback on the multiple material management nodes according to the verification results, generates digital feedback information, and performs full-cycle digital management on the multi-stage material parameters according to the digital feedback information.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present application traverses the material supply chain to perform material correlation analysis, determines multiple material management nodes, performs periodic monitoring according to the multiple material management nodes through a sensor device group, obtains a full-cycle parameter set of the material, and the full-cycle parameter set of the material includes multi-stage material parameters; associates and matches the multiple material management nodes with the multi-stage material parameters to generate a material parameter management network, and the material parameter management network includes multiple node material association parameters; traverses the material parameter management network to perform digital calculations to generate multiple digital coefficients, and the multiple digital coefficients correspond to the multiple node material association parameters; performs digital compensation analysis on the material parameter management network based on the multiple digital coefficients combined with the multiple node material association parameters, and formulates a digital compensation plan; executes the digital compensation plan to digitally verify the material parameter management network, and based on the verification results, periodically feedback is performed on the multiple material management nodes to generate digital feedback information, and the multi-stage material parameters are digitally managed throughout the entire cycle based on the digital feedback information. The present invention solves the technical problem that the prior art cannot effectively carry out accurate digital management of material parameters. It traverses the material supply chain and performs material correlation analysis, determines multiple material management nodes, uses sensor equipment to monitor the full-cycle parameters of materials, associates the nodes with multi-stage parameters to generate a material parameter management network, calculates digital coefficients and performs compensation analysis, formulates compensation plans, and performs digital verification. Then, based on feedback information, full-cycle digital management of material parameters is carried out to achieve the technical effect of accurate digital management of material parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic diagram of the process flow of a material parameter digitization method for full-cycle management provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a material parameter digitization system for full-cycle management provided in an embodiment of the present application.

[0010] Explanation of the reference numerals: period monitoring module 11 , correlation matching module 12 , digital calculation module 13 , digital compensation analysis module 14 , digital management module 15 . DETAILED DESCRIPTION

[0011] The present application provides a material parameter digitization method and system for full-cycle management, aiming to solve the technical problem that the existing technology cannot effectively perform accurate digital management of material parameters. By traversing the material supply chain and performing material correlation analysis, multiple material management nodes are determined, and sensor equipment is used to monitor the full-cycle parameters of materials. The nodes are associated with multi-stage parameters to generate a material parameter management network, the digitization coefficients are calculated and compensation analysis is performed, a compensation plan is formulated, and after digital verification, the material parameters are digitally managed throughout the entire cycle based on the feedback information, thereby achieving the technical effect of accurate digital management of material parameters.

[0012] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0013] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0014] Embodiment 1, as Figure 1 As shown, the present application provides a material parameter digitization method for full-cycle management, the method comprising: Step S100: traverse the material supply chain to perform material correlation analysis, determine multiple material management nodes, perform periodic monitoring according to the multiple material management nodes through a sensor device group, and obtain a full-cycle parameter set of the material, wherein the full-cycle parameter set of the material includes multi-stage material parameters.

[0015] In the embodiment of the present application, the material supply chain is first traversed through material correlation analysis to identify and analyze the key characteristics and influencing factors of materials at each life cycle node. The material supply chain includes the entire process from procurement, transportation, storage, use, maintenance to scrapping. In this process, the correlation between different nodes is analyzed based on historical records and existing material data through data mining methods. For example, the relationship between the quality of materials in the procurement stage and their performance in subsequent use, or the potential impact of environmental conditions in the transportation stage on the storage and use of materials, is identified. Next, based on the results of the material relevance analysis, multiple material management nodes are identified and confirmed. These nodes cover all important stages of the material life cycle, including procurement nodes, transportation nodes, storage nodes, use nodes, maintenance nodes, and scrapping nodes.

[0016] Subsequently, periodic monitoring is performed according to multiple material management nodes through a preset sensor device group, where the sensor device group includes temperature and humidity sensors, load sensors, position sensors, and vibration sensors. Temperature and humidity sensors monitor the warehouse environment during the storage stage, position sensors help track the location and status of materials during transportation, load sensors monitor the load of equipment, and vibration sensors can record vibrations during transportation or vibrations during equipment use. Through monitoring, a full-cycle parameter set of materials is obtained, and the full-cycle parameter set of materials contains multi-stage material parameters. For example, in the procurement stage, the batch and supplier information of materials are recorded; in the transportation stage, the transportation conditions of materials, the temperature and humidity of the transportation environment, and other information are recorded; in the storage stage, the temperature and humidity, storage method, inventory quantity, etc. are recorded; in the use stage, the load, frequency of use, operation time, etc. of the equipment are recorded; in the maintenance stage, the maintenance, repair cycle and repair records are recorded; in the scrapping stage, the scrapping time and disposal method of materials are recorded.

[0017] Step S200: Associating and matching the multiple material management nodes with the multi-stage material parameters to generate a material parameter management network, wherein the material parameter management network includes multiple node material association parameters.

[0018] Furthermore, in the method provided in the embodiment of the application, the plurality of material management nodes are associated and matched with the multi-stage material parameters to generate a material parameter management network, and further includes: The multi-stage material parameters are divided according to the multiple material management nodes to generate first-stage material parameters, second-stage material parameters...N-stage material parameters, where N is an integer greater than 1; the multiple material management nodes are reversely analyzed according to the first-stage material parameters, the second-stage material parameters...the N-stage material parameters to determine node hierarchy information; based on the node hierarchy information, the first-stage material parameters, the second-stage material parameters...the N-stage material parameters are weighted to generate multiple weight coefficients; according to the multiple weight coefficients, multiple connection edges are constructed between the multiple material management nodes and the first-stage material parameters, the second-stage material parameters...the N-stage material parameters; based on the node hierarchy information, the multiple material management nodes are matched and connected with the first-stage material parameters, the second-stage material parameters...the N-stage material parameters according to the multiple connection edges to generate the multiple node material association parameters; based on the multiple node material association parameters, the material association parameters are integrated to construct the material parameter management network.

[0019] In the embodiment of the present application, firstly, the multi-stage material parameters of multiple material management nodes are divided to generate the first stage material parameters, the second stage material parameters... the Nth stage material parameters, where N represents multiple stages in the material life cycle, including relevant parameters of each stage such as procurement, transportation, storage, use, maintenance, and scrapping. The parameters of these stages involve multiple aspects such as quantity, quality, cost, and efficiency of use. They are key data for material management and affect the entire life cycle management of materials from procurement to final scrapping.

[0020] Next, based on the material parameters of each stage, the node hierarchy information is determined through the reverse analysis method. The purpose of reverse analysis is to analyze the influence of each material management node and clarify the degree of influence of each node on the materials at different stages. For example, the procurement node will directly affect the inventory and transportation stages of the materials, the use node will affect the efficiency and life of the materials, and the maintenance node will play an important role in the status of the materials in the use stage. Through reverse analysis, the role and influence of the material management node in the life cycle are identified, thereby determining the hierarchical structure of the nodes.

[0021] Then, based on the determined node hierarchy information, the weights of the material parameters at each stage are assigned. For this purpose, the analytic hierarchy process (AHP) is used. The AHP method quantifies the relative importance of each node to the material parameters at different stages by constructing a judgment matrix. In this process, experts score the importance between each two material management nodes. For example, a score of 1 means that the two nodes are equally important, a score of 3 means that the first node is more important than the second node, and a score of 5 means that the first node is obviously more important than the second node. Through matrix operations, the weight coefficient of each node is calculated using the eigenvalue method, and a weight value is assigned to each node based on the calculation results. The weight coefficient reflects the degree of influence of the node on each stage of the material life cycle and is a quantitative indicator of the relative importance of the node.

[0022] After the weight coefficients are calculated, these weight coefficients are used to construct the connection edges between the nodes and the material parameters of each stage. The weight of each connection edge is determined by the degree of influence of the node on the material parameters of that stage. Through the weighted graph, the relationship between the node and the material parameters is represented by the connection edge, and the weight coefficient is the weight of the edge. In this way, each material management node is connected to the parameters of each stage in the material life cycle. For example, the procurement node has a greater impact on the material cost in the procurement stage, so the weight of the connection edge is higher; while the use node may have a smaller impact on the scrapping stage, so the weight of the connection edge is lower.

[0023] Finally, according to the node hierarchy information, the nodes are matched and connected with the material parameters of each stage through the graph theory algorithm to generate multiple node material association parameters. This process establishes the specific association between each node and each material parameter by reasonably matching the material management nodes and the corresponding material parameter stages. For example, corresponding associations are established between the procurement node and the procurement quantity, the transportation node and the transportation time, the storage node and the storage conditions, etc. Finally, based on the multiple node material association parameters generated above, they are integrated to build a material parameter management network.

[0024] Step S300: traverse the material parameter management network to perform digital calculations and generate a plurality of digital coefficients, wherein the plurality of digital coefficients correspond to the plurality of node material associated parameters.

[0025] In an embodiment of the present application, when traversing the material parameter management network, the material association parameters of each node are first identified, and the identification results include quantitative parameters (such as inventory, purchase volume, etc.) and qualitative parameters (such as material status, frequency of use, etc.). Then, based on these quantitative and qualitative parameters, association analysis is performed to generate quantitative association coefficients and qualitative association coefficients, respectively, to represent the relationship between different material management stages. Next, these association coefficients are digitally calculated to generate multiple digital coefficients. Each digital coefficient is closely related to the corresponding node material association parameter, reflecting the quantitative relationship between different material management nodes and material parameters at each stage.

[0026] Furthermore, in the method provided in the embodiment of the application, traversing the material parameter management network to perform digital calculations and generate multiple digital coefficients also includes: The material parameter management network is traversed to perform parameter identification on the material associated parameters of the multiple nodes to obtain a material management parameter identification result, wherein the material management parameter identification result includes multiple quantitative parameters and multiple qualitative parameters; according to the multiple quantitative parameters, the first-stage material parameters, the second-stage material parameters...the N-stage material parameters are associated and analyzed to generate multiple quantitative association coefficients; according to the multiple qualitative parameters, the first-stage material parameters, the second-stage material parameters...the N-stage material parameters are associated and analyzed to generate multiple qualitative association coefficients; according to the multiple quantitative association coefficients and the multiple qualitative association coefficients, the first-stage material parameters, the second-stage material parameters...the N-stage material parameters are digitally calculated to generate the multiple digital coefficients.

[0027] In the embodiment of the present application, the material management network is first traversed to identify the material-related parameters of each node. This process usually uses sensor technology and Internet of Things devices to achieve data collection. For example, sensors and RFID technology are used to collect parameters such as the inventory and usage frequency of materials in real time during warehousing and transportation, and then determine the quantitative parameters (such as inventory, purchase volume, etc.) and qualitative parameters (such as material status, usage frequency, etc.) of the materials.

[0028] Next, the material parameters of the first stage, the material parameters of the second stage, and so on, are analyzed in association with multiple quantitative parameters. In this process, the interrelationships between different stages are analyzed by collecting and organizing historical data or real-time data. For example, the purchase volume (quantitative parameter) of the first stage may have a direct impact on the inventory volume of the second stage, and the change in inventory volume will be reflected in the subsequent frequency of use or maintenance cycle. By using correlation coefficient calculations (such as the Pearson correlation coefficient), the correlation between these quantitative parameters is quantified and multiple quantitative correlation coefficients are generated. For example, there may be a strong correlation between the purchase volume and the inventory volume. By calculating the correlation coefficient, the strength of the relationship between these parameters is quantified. In this way, a quantitative correlation coefficient is generated for each pair of material stages.

[0029] At the same time, according to qualitative parameters, such as the status of materials and the frequency of use, the material parameters at different stages are analyzed for correlation. Since qualitative parameters cannot be directly calculated numerically, the fuzzy relationship between such parameters is handled by fuzzy logic reasoning. Fuzzy logic can effectively handle the uncertainty between qualitative parameters, for example, the relationship between the status of materials (such as good, bad, and under maintenance) and the frequency of use. The specific fuzzy reasoning process includes first quantifying the qualitative parameters, for example, converting "good material status" into the membership value of the fuzzy set, such as 0.8 for "good", 0.2 for "bad", and 0.5 for "under maintenance". Then, technical experts define fuzzy rules, such as "good material status" may lead to "high frequency of use". Fuzzy reasoning algorithms (such as the Mamdani model) are used for reasoning and calculation, and finally the qualitative correlation coefficient is obtained. For example, the relationship between good material status and high frequency of use may be 0.7.

[0030] After obtaining the quantitative correlation coefficient and the qualitative correlation coefficient, these coefficients are further digitized. Specifically, first, according to multiple quantitative correlation coefficients and multiple qualitative correlation coefficients, technical experts assign different weights to the quantitative and qualitative correlation coefficients. For example, quantitative parameters such as inventory and purchase volume may have a more significant impact, so they can be assigned a higher weight, while qualitative parameters such as material status and frequency of use may be assigned a lower weight. Next, the weighted average method is used to combine and calculate multiple quantitative correlation coefficients and multiple qualitative correlation coefficients, and finally multiple digitized coefficients are obtained.

[0031] Step S400: Perform digital compensation analysis on the material parameter management network according to the multiple digital coefficients combined with the multiple node material associated parameters, and formulate a digital compensation plan.

[0032] In an embodiment of the present application, a digital compensation analysis is performed on the material parameter management network according to multiple digital coefficients and in combination with multiple node material association parameters. Specifically, first, by calculating the digital deviation, nodes whose deviation values ​​do not meet the expected digital threshold are identified. Then, the system identifies these nodes and determines them as nodes to be compensated. Next, based on the deviation value, the nodes to be compensated are dynamically compensated by a reinforcement learning method, and finally a digital compensation plan is formulated.

[0033] Furthermore, in the method provided in the embodiment of the application, a digital compensation analysis is performed on the material parameter management network according to the multiple digital coefficients combined with the multiple node material associated parameters to formulate a digital compensation plan, which also includes: Based on the multiple digital coefficients, digital deviations of the material-related parameters of the multiple nodes are calculated to obtain multiple deviation values; an expected digital threshold is set, and the material parameter management network is judged based on the multiple deviation values ​​to determine whether the multiple deviation values ​​of the multiple material management nodes meet the expected digital threshold; the material management nodes corresponding to the deviation values ​​that do not meet the expected digital threshold are identified, and multiple nodes to be compensated are determined; reinforcement learning is performed according to the multiple deviation values ​​to dynamically compensate the multiple nodes to be compensated, and the digital compensation plan is formulated.

[0034] In an embodiment of the present application, first, a digital deviation calculation is performed on the material-related parameters of each material management node. The material-related parameters of each node have a preset digital coefficient, which represents the target digital level set by the expert. The multiple digital coefficients generated by the previous steps are the values ​​actually calculated, which are used to represent the digital status of the current material management node. Then, these actually calculated digital coefficients are compared with the preset digital coefficients of the corresponding nodes to calculate the deviation value of each node. The deviation value reflects the difference between the actual digital level of each node and the preset target. The larger the deviation value, the greater the gap in the digital level.

[0035] Next, technical experts set the expected digital threshold, compare the obtained multiple deviation values ​​with the expected digital threshold, and determine whether the digital level of each node meets the preset requirements. Specifically, if the deviation value exceeds the expected digital threshold, the digital level of the node does not meet expectations. Nodes that do not meet the expected digital threshold are then identified. These nodes are "nodes to be compensated" and need to be further adjusted and optimized.

[0036] Finally, reinforcement learning is performed according to the multiple deviation values ​​to dynamically compensate the multiple nodes to be compensated, and the digital compensation plan is formulated.

[0037] Furthermore, in the method provided in the embodiment of the application, reinforcement learning is performed according to the multiple deviation values ​​to dynamically compensate the multiple nodes to be compensated, and a digital compensation plan is formulated, which also includes: Based on the multiple deviation values, the multiple material management nodes are traversed to perform status evaluation and determine the material management status information; a compensation solution space is constructed, the material management status information is mapped to the compensation solution space for search, and multiple compensation action parameters are determined to introduce a reward function, and the multiple compensation action parameters are executed in combination with the reward function for calculation to generate multiple reward values; compensation analysis is performed according to the multiple reward values ​​to obtain a digital compensation effect, and the digital compensation effect includes multiple compensation scores; the digital compensation scheme is constructed according to the multiple deviation values ​​in combination with the multiple compensation scores.

[0038] In an embodiment of the present application, the material management nodes are first traversed to perform status assessment based on multiple deviation values. Specifically, a regression analysis method is used to perform a detailed analysis of the deviation values ​​of each node. This process identifies the relationship between the deviation value and other material management parameters (such as inventory, frequency of use, maintenance cycle, etc.) through linear regression or polynomial regression analysis. Through the regression model, the specific management status of each node is estimated based on existing historical data or real-time data to ensure that the status assessment is not limited to a single dimension, but is a comprehensive assessment of the influence of multiple factors. Finally, the regression analysis results generate material management status information, which includes the specific digital management status of each node.

[0039] Next, the compensation solution space is constructed. Then, based on the constructed compensation solution space, the material management status information is mapped to the compensation solution space, and the search is performed through a heuristic search algorithm (such as the A algorithm). The A algorithm is a path search method that combines heuristic search and cost calculation, which can help find the most appropriate compensation action in the compensation solution space. By evaluating the material management status of each node, the A algorithm searches for the compensation action that is most likely to bring optimization based on the current status and determines multiple compensation action parameters.

[0040] Next, based on the reward function, multiple compensatory actions are performed and the reward value of each compensatory action is calculated. The reward function is designed by the Q-learning algorithm in reinforcement learning, which represents the effect of the compensatory action by evaluating the Q value of each state-action pair. The reward function is usually defined based on the contribution of the compensatory action to inventory changes, improved usage efficiency, or reduced failure rate. Formally, the reward function combines the changes in multiple factors, such as inventory changes, usage efficiency changes, and failure rate changes, and assigns corresponding reward values ​​to each compensatory action, ultimately generating multiple reward values ​​to measure the effectiveness of the compensatory action.

[0041] After generating multiple reward values, the weighted average method is used to perform compensation analysis on these reward values. The weighted average method weights the reward values ​​according to the weights of different compensation actions to obtain a comprehensive compensation effect score, where the weights of different compensation actions are pre-set. This score can quantify the impact of each compensation action on the node management status and provide a basis for further decision-making. Through compensation analysis, a digital compensation effect is obtained, which includes the specific scores of each compensation action and provides data support for the subsequent construction of compensation plans.

[0042] Finally, based on multiple deviation values ​​and multiple compensation scores, the analytic hierarchy process (AHP) is used to construct a digital compensation plan. The analytic hierarchy process constructs a judgment matrix, comprehensively considers the deviation value and compensation score, and evaluates the priority and impact of each compensation action. Through the AHP method, the optimal compensation action is implemented in the material management node, and the most effective digital compensation plan is formulated to ensure that the accuracy and efficiency of material management reach the optimal level.

[0043] Furthermore, in the method provided in the embodiment of the application, constructing the compensation solution space also includes: The multiple material management nodes are traversed to perform compensation analysis, a compensation target is constructed, and compensation constraints are constructed based on the compensation target in combination with the multiple deviation value definitions; discretization is performed according to the multiple material management nodes in combination with the multi-stage material parameters to determine the dimensional information of the compensation solution space; based on the dimensional information of the compensation solution space, the compensation target is updated according to the compensation constraints to construct the compensation solution space.

[0044] In an embodiment of the present application, firstly, by traversing multiple material management nodes and combining the deviation values ​​of each node, compensation analysis is performed and a compensation target is constructed. In this process, the digital difference reflected by the deviation value is used to determine the compensation target required for each node, that is, to set the expected result of digital compensation for the node. The setting of this compensation target is based on the digital deviation of each node, aiming to narrow the gap between the current digital level and the expected target. Through deviation analysis, the compensation target is finally determined, that is, the digital compensation expectation of each node.

[0045] Then, based on the compensation target, the compensation constraints are defined and constructed by combining the deviation value and resource, time and other constraints. In this step, constraint definition methods such as linear programming or nonlinear optimization are used to set the boundary conditions of the compensation operation by evaluating factors such as resources, time and cost between nodes. These constraints ensure that the compensation plan can be executed within the constraints of resources, time and budget, thereby maintaining the feasibility and practicality of the compensation plan. Through this process, the compensation constraints are finally determined, that is, the specific conditions such as resource constraints, budget constraints, time constraints, etc. that need to be followed in the compensation process.

[0046] Then, discretization is performed based on multiple material management nodes and multi-stage material parameters to determine the dimensional information of the compensation solution space. Specifically, the digital parameters of the nodes and the material management parameters are converted into discrete levels or values ​​through the discretization method to facilitate subsequent optimization and calculation. In this process, the digital level is divided into multiple discrete levels or intervals by using methods such as piecewise function method or quantitative analysis method to facilitate compensation decision-making. After discretization, clear dimensional information of the compensation solution space is obtained, which indicates the possible adjustment range in the compensation scheme, including the combination of different nodes and material parameters.

[0047] Finally, based on the compensation objectives, compensation constraints and dimensional information of the solution space, the compensation solution space is updated and constructed. In this step, the compensation solution space is searched and updated using optimization methods (such as genetic algorithms, particle swarm optimization, etc.). Unlike directly finding the optimal solution, the core of this process is to explore and determine a diverse solution space, which contains all potential compensation solutions that meet the compensation objectives and constraints. Through this method, the compensation solution space is gradually updated, and finally a solution space covering all possible compensation actions is formed for subsequent compensation decisions and optimization analysis. Through this step, the compensation solution space is constructed, that is, the set of all possible compensation solutions under the compensation objectives and constraints.

[0048] Step S500: Execute the digital compensation scheme to digitally verify the material parameter management network, perform regular feedback on the multiple material management nodes based on the verification results, generate digital feedback information, and perform full-cycle digital management of the multi-stage material parameters based on the digital feedback information.

[0049] In an embodiment of the present application, in the process of implementing the digital compensation scheme, the compensation scheme is first evaluated based on multiple compensation scores. After setting the verification indicators, the material parameter management network is verified by these indicators to generate a verification token. Then, based on the verification token, a regression analysis is performed on multiple material management nodes to obtain the digital regression results of each node. By setting a self-inspection cycle, these regression results are regularly fed back to generate improvement suggestions. According to these suggestions, the digital compensation scheme is dynamically adjusted, and finally digital feedback information is generated. Subsequently, the multi-stage material parameters are digitally managed throughout the entire cycle based on these digital feedback information to ensure the continuous optimization and refined management of material management.

[0050] Furthermore, in the method provided in the embodiment of the application, the digital compensation scheme is executed to digitally verify the material parameter management network, and regular feedback is provided to the multiple material management nodes according to the verification results to generate digital feedback information, and further includes: The digital compensation scheme is evaluated based on the multiple compensation scores, and verification indicators are set; the material parameter management network is verified according to the verification indicators to generate a verification token, and regression analysis is performed on the multiple material management nodes according to the verification token to obtain node digital regression results; a self-inspection cycle is set, and the node digital regression results are regularly fed back to the multiple material management nodes according to the self-inspection cycle to generate improvement suggestions; the digital compensation scheme is dynamically adjusted according to the improvement suggestions to generate the digital feedback information.

[0051] In an embodiment of the present application, the digital compensation scheme is evaluated based on multiple compensation scores. First, it is necessary to collect relevant data of each material management node, such as inventory, frequency of use, etc., through statistical analysis. The compensation score of each node is calculated based on these data. The higher the score, the more perfect the digital management, and the node with a lower score indicates that there is a demand for compensation. After the compensation score is obtained, predetermined verification indicators are set based on these scores. These indicators include the operating efficiency of the node, the accuracy of resource allocation, etc. Next, each material management node is verified according to the preset verification indicators, and the actual operation results of the node are compared with the set indicators using a standard verification method to ensure that the node meets the target standard. If a node does not meet the standard, a "verification token" is generated, which is an important basis for the node's compensation needs and subsequent processing.

[0052] After obtaining the verification token, a regression analysis is performed on multiple material management nodes based on the token, and a simple linear regression model is used to analyze the historical data of the material management nodes to identify potential problems in digital management. Specifically, regression analysis calculates the regression coefficient of each node, analyzes the deviation between the node's performance and the expected target, predicts possible digital management problems in the future, and obtains the digital regression results of each node. Through regression analysis, it is accurately assessed which nodes have management problems or need further compensation, and the management performance and optimization direction of each node are obtained.

[0053] Next, based on the digital regression results of the nodes, set a self-inspection cycle and provide regular feedback. The self-inspection cycle can be set to monthly, quarterly, and other time periods according to actual management needs. In each cycle, check the regression results of each node and compare the results of the regression analysis with the set goals. If the performance of certain nodes does not meet the expected standards, generate targeted improvement suggestions, which may include increasing inventory accuracy, strengthening usage frequency monitoring, etc., to help managers take timely measures to optimize the digital management of nodes.

[0054] Finally, the digital compensation plan is dynamically adjusted based on the improvement suggestions generated by regular feedback. In this step, based on the information fed back by the self-checking, the manager adjusts the key parameters in the compensation plan, such as the compensation threshold and node optimization target, to ensure that the compensation plan always meets the actual needs of current material management. The adjusted compensation plan will generate digital feedback information and provide it to the manager to evaluate the effect of the adjusted plan and provide a basis for subsequent decision-making.

[0055] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects: The present application traverses the material supply chain to perform material correlation analysis, determines multiple material management nodes, performs periodic monitoring according to the multiple material management nodes through a sensor device group, obtains a full-cycle parameter set of the material, and the full-cycle parameter set of the material includes multi-stage material parameters; associates and matches the multiple material management nodes with the multi-stage material parameters to generate a material parameter management network, and the material parameter management network includes multiple node material association parameters; traverses the material parameter management network to perform digital calculations to generate multiple digital coefficients, and the multiple digital coefficients correspond to the multiple node material association parameters; performs digital compensation analysis on the material parameter management network based on the multiple digital coefficients combined with the multiple node material association parameters, and formulates a digital compensation plan; executes the digital compensation plan to digitally verify the material parameter management network, and based on the verification results, periodically feedback is performed on the multiple material management nodes to generate digital feedback information, and the multi-stage material parameters are digitally managed throughout the entire cycle based on the digital feedback information. The present invention solves the technical problem that the prior art cannot effectively carry out accurate digital management of material parameters. It traverses the material supply chain and performs material correlation analysis, determines multiple material management nodes, uses sensor equipment to monitor the full-cycle parameters of materials, associates the nodes with multi-stage parameters to generate a material parameter management network, calculates digital coefficients and performs compensation analysis, formulates compensation plans, and performs digital verification. Then, based on feedback information, full-cycle digital management of material parameters is carried out to achieve the technical effect of accurate digital management of material parameters.

[0056] Embodiment 2 is based on the same inventive concept as the material parameter digitization method for full-cycle management in the above embodiment. Figure 2 As shown, the present application provides a material parameter digitization system for full-cycle management, and the system and method embodiments in the present application are based on the same inventive concept. The system includes: The cycle monitoring module 11 traverses the material supply chain to perform material correlation analysis, determines multiple material management nodes, performs cycle monitoring according to the multiple material management nodes through the sensor equipment group, and obtains a full-cycle parameter set of the material, and the full-cycle parameter set of the material includes multi-stage material parameters; the association matching module 12, the association matching module 12 associates and matches the multiple material management nodes with the multi-stage material parameters to generate a material parameter management network, and the material parameter management network includes multiple node material association parameters; the digital calculation module 13, the digital calculation module 13 traverses the material parameter management network to perform digital calculations, and generates multiple digital A digital coefficient, wherein the multiple digital coefficients correspond to the multiple node material-related parameters; a digital compensation analysis module 14, wherein the digital compensation analysis module 14 performs digital compensation analysis on the material parameter management network according to the multiple digital coefficients in combination with the multiple node material-related parameters, and formulates a digital compensation plan; a digital management module 15, wherein the digital management module 15 executes the digital compensation plan to digitally verify the material parameter management network, and performs regular feedback on the multiple material management nodes according to the verification results, generates digital feedback information, and performs full-cycle digital management of the multi-stage material parameters according to the digital feedback information.

[0057] Furthermore, the system is also used to implement the following functions: The multi-stage material parameters are divided according to the multiple material management nodes to generate first-stage material parameters, second-stage material parameters...N-stage material parameters, where N is an integer greater than 1; the multiple material management nodes are reversely analyzed according to the first-stage material parameters, the second-stage material parameters...the N-stage material parameters to determine node hierarchy information; based on the node hierarchy information, the first-stage material parameters, the second-stage material parameters...the N-stage material parameters are weighted to generate multiple weight coefficients; according to the multiple weight coefficients, multiple connection edges are constructed between the multiple material management nodes and the first-stage material parameters, the second-stage material parameters...the N-stage material parameters; based on the node hierarchy information, the multiple material management nodes are matched and connected with the first-stage material parameters, the second-stage material parameters...the N-stage material parameters according to the multiple connection edges to generate the multiple node material association parameters; based on the multiple node material association parameters, the material association parameters are integrated to construct the material parameter management network.

[0058] Furthermore, the system is also used to implement the following functions: The material parameter management network is traversed to perform parameter identification on the material associated parameters of the multiple nodes to obtain a material management parameter identification result, wherein the material management parameter identification result includes multiple quantitative parameters and multiple qualitative parameters; according to the multiple quantitative parameters, the first-stage material parameters, the second-stage material parameters...the N-stage material parameters are associated and analyzed to generate multiple quantitative association coefficients; according to the multiple qualitative parameters, the first-stage material parameters, the second-stage material parameters...the N-stage material parameters are associated and analyzed to generate multiple qualitative association coefficients; according to the multiple quantitative association coefficients and the multiple qualitative association coefficients, the first-stage material parameters, the second-stage material parameters...the N-stage material parameters are digitally calculated to generate the multiple digital coefficients.

[0059] Furthermore, the system is also used to implement the following functions: Based on the multiple digital coefficients, digital deviations of the material-related parameters of the multiple nodes are calculated to obtain multiple deviation values; an expected digital threshold is set, and the material parameter management network is judged based on the multiple deviation values ​​to determine whether the multiple deviation values ​​of the multiple material management nodes meet the expected digital threshold; the material management nodes corresponding to the deviation values ​​that do not meet the expected digital threshold are identified, and multiple nodes to be compensated are determined; reinforcement learning is performed according to the multiple deviation values ​​to dynamically compensate the multiple nodes to be compensated, and the digital compensation plan is formulated.

[0060] Furthermore, the system is also used to implement the following functions: Based on the multiple deviation values, the multiple material management nodes are traversed to perform status evaluation and determine the material management status information; a compensation solution space is constructed, the material management status information is mapped to the compensation solution space for search, and multiple compensation action parameters are determined to introduce a reward function, and the multiple compensation action parameters are executed in combination with the reward function for calculation to generate multiple reward values; compensation analysis is performed according to the multiple reward values ​​to obtain a digital compensation effect, and the digital compensation effect includes multiple compensation scores; the digital compensation scheme is constructed according to the multiple deviation values ​​in combination with the multiple compensation scores.

[0061] Furthermore, the system is also used to implement the following functions: The multiple material management nodes are traversed to perform compensation analysis, a compensation target is constructed, and compensation constraints are constructed based on the compensation target in combination with the multiple deviation value definitions; discretization is performed according to the multiple material management nodes in combination with the multi-stage material parameters to determine the dimensional information of the compensation solution space; based on the dimensional information of the compensation solution space, the compensation target is updated according to the compensation constraints to construct the compensation solution space.

[0062] Furthermore, the system is also used to implement the following functions: The digital compensation scheme is evaluated based on the multiple compensation scores, and verification indicators are set; the material parameter management network is verified according to the verification indicators to generate a verification token, and regression analysis is performed on the multiple material management nodes according to the verification token to obtain node digital regression results; a self-inspection cycle is set, and the node digital regression results are regularly fed back to the multiple material management nodes according to the self-inspection cycle to generate improvement suggestions; the digital compensation scheme is dynamically adjusted according to the improvement suggestions to generate the digital feedback information.

[0063] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0064] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0065] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A digital method for material parameters for full-cycle management, characterized by: The method comprises: Traversing the material supply chain to perform material correlation analysis, determine multiple material management nodes, perform periodic monitoring according to the multiple material management nodes through a sensor device group, and obtain a full-cycle parameter set of the material, wherein the full-cycle parameter set of the material includes multi-stage material parameters; Associating and matching the multiple material management nodes with the multi-stage material parameters to generate a material parameter management network, wherein the material parameter management network includes multiple node material association parameters; Traversing the material parameter management network to perform digital calculations and generate a plurality of digital coefficients, wherein the plurality of digital coefficients correspond to the plurality of node material associated parameters; Perform digital compensation analysis on the material parameter management network according to the multiple digital coefficients combined with the multiple node material associated parameters, and formulate a digital compensation plan; The digital compensation scheme is executed to digitally verify the material parameter management network, and regular feedback is provided to the multiple material management nodes based on the verification results to generate digital feedback information, and full-cycle digital management of the multi-stage material parameters is performed based on the digital feedback information.

2. The material parameter digitization method for full-cycle management according to claim 1, characterized in that: Associating and matching the multiple material management nodes with the multi-stage material parameters to generate a material parameter management network, the method comprising: Dividing the multi-stage material parameters according to the multiple material management nodes to generate first-stage material parameters, second-stage material parameters, ..., N-th-stage material parameters, where N is an integer greater than 1; According to the first-stage material parameters, the second-stage material parameters, ... the N-stage material parameters, reverse analysis is performed on the plurality of material management nodes to determine node hierarchy information; Based on the node hierarchy information, weights are assigned to the first-stage material parameters, the second-stage material parameters, ..., the N-stage material parameters to generate a plurality of weight coefficients; Constructing a plurality of connection edges between the plurality of material management nodes and the first-stage material parameters, the second-stage material parameters, ... the N-stage material parameters according to the plurality of weight coefficients; Based on the node hierarchy information, the multiple material management nodes are matched and connected according to the multiple connection edges with the first-stage material parameters, the second-stage material parameters, ... the N-stage material parameters to generate the multiple node material association parameters; The material parameter management network is constructed based on the integration of the material associated parameters of the multiple nodes.

3. The material parameter digitization method for full-cycle management according to claim 2, characterized in that: The material parameter management network is traversed to perform digital calculations to generate multiple digital coefficients, the method comprising: Traversing the material parameter management network to perform parameter identification on the material associated parameters of the plurality of nodes, and obtaining a material management parameter identification result, wherein the material management parameter identification result includes a plurality of quantitative parameters and a plurality of qualitative parameters; According to the multiple quantitative parameters, correlation analysis is performed on the first-stage material parameters, the second-stage material parameters, ... the N-stage material parameters to generate multiple quantitative correlation coefficients; According to the multiple qualitative parameters, correlation analysis is performed on the first-stage material parameters, the second-stage material parameters, ... the N-stage material parameters to generate multiple qualitative correlation coefficients; The first-stage material parameters, the second-stage material parameters, ... the N-stage material parameters are digitally calculated according to the multiple quantitative correlation coefficients and the multiple qualitative correlation coefficients to generate the multiple digital coefficients.

4. The material parameter digitization method for full-cycle management according to claim 1, characterized in that: According to the multiple digital coefficients combined with the multiple node material associated parameters, a digital compensation analysis is performed on the material parameter management network to formulate a digital compensation plan, the method comprising: Performing digital deviation calculation on the multiple node material association parameters based on the multiple digital coefficients to obtain multiple deviation values; Setting an expected digitalization threshold, and judging the material parameter management network based on the multiple deviation values ​​to determine whether the multiple deviation values ​​of the multiple material management nodes meet the expected digitalization threshold; Identify the material management nodes corresponding to the deviation values ​​that do not meet the expected digital threshold, and determine a plurality of nodes to be compensated; Reinforcement learning is performed according to the multiple deviation values ​​to dynamically compensate the multiple nodes to be compensated, and the digital compensation plan is formulated.

5. The material parameter digitization method for full-cycle management according to claim 4, characterized in that: Reinforcement learning is performed according to the multiple deviation values ​​to dynamically compensate the multiple nodes to be compensated, and a digital compensation plan is formulated, the method comprising: Based on the multiple deviation values, the multiple material management nodes are traversed to perform status evaluation to determine material management status information; Construct a compensation solution space, map the material management status information to the compensation solution space for searching, and determine multiple compensation action parameters Introducing a reward function, executing the plurality of compensation action parameters in combination with the reward function to calculate and generate a plurality of reward values; Perform compensation analysis according to the multiple reward values ​​to obtain a digital compensation effect, wherein the digital compensation effect includes multiple compensation scores; The digital compensation scheme is constructed according to the multiple deviation values ​​and the multiple compensation scores.

6. The material parameter digitization method for full-cycle management according to claim 5, characterized in that: Construct the compensation solution space, the method includes: Traversing the plurality of material management nodes to perform compensation analysis, constructing a compensation target, and constructing compensation constraint conditions based on the compensation target and the plurality of deviation value definitions; Discretization processing is performed according to the plurality of material management nodes in combination with the multi-stage material parameters to determine the compensation solution space dimension information; Based on the compensation solution space dimension information, the compensation target is updated according to the compensation constraint condition to construct the compensation solution space.

7. The material parameter digitization method for full-cycle management according to claim 5, characterized in that: The digital compensation scheme is executed to digitally verify the material parameter management network, and regular feedback is provided to the multiple material management nodes according to the verification results to generate digital feedback information. The method includes: Evaluate the digital compensation scheme based on the multiple compensation scores and set verification indicators; Verify the material parameter management network according to the verification index, generate a verification token, and perform regression analysis on the multiple material management nodes according to the verification token to obtain a node digital regression result; A self-checking cycle is set, and the digital regression results of the nodes are regularly fed back to the multiple material management nodes according to the self-checking cycle to generate improvement suggestions; The digital compensation scheme is dynamically adjusted according to the improvement suggestion to generate the digital feedback information.

8. The material parameter digital system for full-cycle management is characterized by: The system comprises: A cycle monitoring module, wherein the cycle monitoring module traverses the material supply chain to perform material correlation analysis, determines multiple material management nodes, performs cycle monitoring according to the multiple material management nodes through a sensor device group, and obtains a full cycle parameter set of the material, wherein the full cycle parameter set of the material includes multi-stage material parameters; An association matching module, wherein the association matching module associates and matches the multiple material management nodes with the multi-stage material parameters to generate a material parameter management network, wherein the material parameter management network includes multiple node material association parameters; A digital calculation module, wherein the digital calculation module traverses the material parameter management network to perform digital calculations and generate a plurality of digital coefficients, wherein the plurality of digital coefficients correspond to the plurality of node material associated parameters; A digital compensation analysis module, which performs digital compensation analysis on the material parameter management network according to the multiple digital coefficients combined with the multiple node material associated parameters, and formulates a digital compensation plan; A digital management module executes the digital compensation scheme to digitally verify the material parameter management network, performs regular feedback on the multiple material management nodes based on the verification results, generates digital feedback information, and performs full-cycle digital management of the multi-stage material parameters based on the digital feedback information.

Images