Dynamic configuration method and device for ERP (Enterprise Resource Planning) system and medium

Abstract

The invention provides an ERP system dynamic configuration method and device and a medium, and relates to the technical field of resource configuration management.The method comprises the steps that a real-time order list in an ERP system is obtained through dynamic monitoring, and a preset clustering strategy is called to obtain a real-time clustering result; performing return analysis on the first clustering cluster to obtain a first cluster return index, and obtaining initial cluster weight distribution; obtaining a first cluster prediction return index of a predetermined period through a return prediction model; when the first index ratio accords with a predetermined index ratio constraint, target cluster weight distribution is obtained through adjustment; obtaining a resource database; generating a target resource allocation decision in combination with the target cluster weight allocation; and carrying out dynamic configuration processing on the ERP system. According to the resource allocation management method and device, the problem of resource utilization efficiency of existing resource allocation management can be solved, the hysteresis of resource allocation management is effectively avoided, and the technical effect of improving scientificity and effectiveness of preposed resource allocation processing of the ERP system is achieved.

Description

Technical Field

[0001] This application relates to the technical field of resource allocation management, and in particular to a dynamic configuration method, device, and medium for an ERP system. Background Art

[0002] With the development of the economy and the intensification of market competition, enterprise resource planning systems play an increasingly important role in modern enterprise management. An ERP system can integrate information from various departments within an enterprise, provide real-time and accurate data support, help enterprises optimize resource allocation, and improve management efficiency. Traditional ERP systems can only perform resource allocation management based on requirements such as the quantity and deadline of products in real-time orders. However, due to the possible lag of orders themselves and their mutability in the face of sudden hotspots, time, environment, etc., when orders change significantly, the resource allocation of existing ERP systems is prone to problems such as insufficient data analysis capabilities and lagging resource allocation decisions, and cannot meet the enterprise's needs for dynamic and efficient resource management.

[0003] In summary, there is a technical problem in the prior art that it is impossible to perform pre-emptive resource allocation based on various market order forecasts, resulting in resource allocation not meeting the requirements of actual production management, thereby affecting resource utilization efficiency and enterprise competitiveness. Summary of the Invention

[0004] The purpose of this application is to provide a dynamic configuration method, device, and medium for an ERP system to solve the technical problem in the prior art that it is impossible to perform pre-emptive configuration adjustment of enterprise resources based on the market trend analysis and prediction of various orders, resulting in resource allocation not meeting the requirements of actual production management, thereby affecting resource utilization efficiency and enterprise competitiveness.

[0005] In view of the above problems, this application provides a dynamic configuration method, device, and medium for an ERP system.

[0006] In a first aspect, the present application provides a method for dynamically configuring an ERP system. The method for dynamically configuring an ERP system includes: dynamically monitoring to obtain a real-time order list in the ERP system, and invoking a predetermined clustering strategy to perform clustering analysis on the orders in the real-time order list to obtain a real-time clustering result; performing return analysis on a first clustering cluster in the real-time clustering result to obtain a first cluster return index, and obtaining an initial cluster weight allocation based on the first cluster return index after normalization processing; performing prediction analysis on the first clustering cluster through a return prediction model to obtain a first cluster predicted return index for a predetermined period; when a first index ratio calculated by calculating the ratio of the first cluster predicted return index to the first cluster return index meets a predetermined index ratio constraint, adjusting the initial cluster weight allocation to obtain a target cluster weight allocation; obtaining a resource database, where the resource database includes data sets of various resources; under the constraint of the data sets of the various resources, generating a target resource configuration decision in combination with the target cluster weight allocation; and performing dynamic configuration processing on the ERP system according to the target resource configuration decision.

[0007] In a second aspect, the present application further provides an electronic device, including:

[0008] at least one processor;

[0009] a memory communicatively connected to the at least one processor;

[0010] wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the steps of the method for dynamically configuring an ERP system according to any one of the above first aspects.

[0011] In a third aspect, a computer-readable storage medium stores a computer program, and the computer program implements the steps of the method for dynamically configuring an ERP system according to any one of the above first aspects when executed.

[0012] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0013] Obtain the real-time order list in the ERP system through dynamic monitoring, and retrieve the predetermined clustering strategy to perform clustering analysis on the orders in the real-time order list to obtain the real-time clustering result; perform return analysis on the first clustering cluster in the real-time clustering result to obtain the first cluster return index, and obtain the initial cluster weight allocation based on the normalized first cluster return index; perform predictive analysis on the first clustering cluster through the return prediction model to obtain the first cluster predicted return index for a predetermined period; when the first index ratio calculated by calculating the ratio of the first cluster predicted return index to the first cluster return index meets the predetermined index ratio constraint, adjust the initial cluster weight allocation to obtain the target cluster weight allocation; obtain the resource database, where the resource database includes data sets of various resources; under the constraint of the data sets of the various resources, generate the target resource configuration decision in combination with the target cluster weight allocation; perform dynamic configuration processing on the ERP system according to the target resource configuration decision, that is, by monitoring the order situation in real time and performing order clustering analysis, and then obtaining the order return analysis in the real-time state, and then performing predictive adjustment on the real-time return through the return prediction model, and accordingly performing the weight allocation analysis of the order clustering clusters, and finally combining the resource situation to perform corresponding resource configuration on the order clustering clusters with different weight coefficients. By monitoring the order situation in real time and performing order clustering analysis, and then obtaining the order return analysis in the real-time state, and then performing predictive adjustment on the real-time return through the return prediction model, and accordingly performing the weight allocation analysis of the order clustering clusters, and finally combining the resource situation to perform corresponding resource configuration on the order clustering clusters with different weight coefficients, the goal of predictive configuration analysis of resource information is achieved, the scientificity and effectiveness of the pre-configuration processing of the ERP system are improved, and the technical effect of improving the resource utilization efficiency is achieved.

[0014] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically illustrates the specific embodiments of the present application. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. Brief Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings described below are only exemplary, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0016] Figure 1 It is a schematic flowchart of a method for dynamically configuring an ERP system in this application;

[0017] Figure 2 It is a schematic structural diagram of an exemplary electronic device in this application.

[0018] Description of reference numerals:

[0019] Bus 300, Receiver 301, Processor 302, Transmitter 303, Memory 304, Bus Interface 305. Detailed implementation manners

[0020] By providing a method, device and medium for dynamically configuring an ERP system in this application, the technical problem in the prior art that the enterprise resources cannot be preconfigured and adjusted based on the duration trend analysis and prediction of various orders, resulting in the resource configuration not meeting the actual production management requirements, thereby affecting the resource utilization efficiency and enterprise competitiveness is solved. By real-time monitoring the order situation and performing order clustering analysis, and then obtaining the order return analysis in the real-time state, and then making predictive adjustments to the real-time return through a return prediction model, and accordingly performing weight distribution analysis on the order clustering clusters, and finally performing corresponding resource configuration on the order clustering clusters with different weight coefficients in combination with the resource situation, the goal of predictive configuration analysis of resource information is achieved, and the technical effect of improving the scientificity and effectiveness of the preconfigured resource processing of the ERP system and further improving the resource utilization efficiency is achieved.

[0021] Next, the technical solutions in this application will be described clearly and completely with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited by the example embodiments described here. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of this application. In addition, it should be noted that for the sake of description, only the parts related to this application are shown in the accompanying drawings rather than all.

[0022] Embodiment 1, please refer to the attached Figure 1 In this application, a method for dynamically configuring an ERP system is provided, and specifically, the method for dynamically configuring an ERP system includes the following steps:

[0023] Step S10: Dynamically monitor to obtain a real-time order list in the ERP system, and retrieve a predetermined clustering strategy to perform clustering analysis on the orders in the real-time order list to obtain a real-time clustering result.

[0024] Specifically, the real-time order list in the ERP system is dynamically monitored, and a predetermined clustering strategy is used to perform clustering analysis on the orders, thereby obtaining real-time clustering results. The goal of doing so is to achieve real-time processing and analysis of order data in order to better understand the orders and the associations between them, providing data support for subsequent resource management and decision-making.

[0025] Specifically, first, the real-time order list in the ERP system is dynamically monitored to ensure the timeliness and accuracy of order data. Then, the predetermined clustering strategy is retrieved. This predetermined clustering strategy may cluster orders based on key factors such as the customers, product types, specifications, quantities, etc. of the orders. Next, clustering analysis of the orders in the real-time order list is performed based on this predetermined clustering strategy. Among them, the purpose of the clustering analysis is to group similar orders for easier management and analysis. Thereby, real-time clustering results are obtained, and these results reflect the current order distribution and patterns. Through the combination of this dynamic monitoring and clustering analysis, the ERP system can more effectively process and analyze a large amount of real-time order data, thereby improving the efficiency of resource management and optimizing the decision-making process.

[0026] Step S20: Perform return analysis on the first clustering cluster in the real-time clustering results to obtain the first cluster return index, and obtain the initial cluster weight allocation based on the normalized first cluster return index.

[0027] Specifically, perform return analysis on the first clustering cluster in the real-time clustering results to obtain the first cluster return index, and obtain the initial cluster weight allocation based on the normalized return index. The technical goal of doing so is to evaluate the return situations of the orders in different clustering clusters, so as to more precisely consider the importance of each clustering cluster in the resource allocation and decision-making process.

[0028] Specifically, first perform return analysis on the first clustering cluster in the real-time clustering results. Among them, the return analysis may include calculating the product quantity, product cost, average profit margin, or other relevant indicators of the orders in this cluster. Then, the first cluster return index is obtained based on the results of the return analysis. This index is a quantitative representation of the value of this clustering cluster. Next, the first cluster return index is normalized. Among them, normalization is to eliminate the dimensional effects between different indicators, so that the return indexes of different clustering clusters can be compared with each other. Thus, based on the normalized first cluster return index, the initial cluster weight allocation is obtained. Among them, the purpose of the weight allocation is to give corresponding attention to each clustering cluster according to its value during resource allocation and decision-making, and then to achieve the maximization of resource allocation and utilization. Through this method of return analysis and weight allocation, the ERP system can more accurately evaluate and utilize the real-time clustering results, thereby being more efficient and precise in the resource allocation and decision-making process.

[0029] Step S30: Use the return prediction model to perform predictive analysis on the first clustering cluster to obtain the first cluster prediction return index for a predetermined period.

[0030] Specifically, when using the return prediction model to analyze the clustering clusters in the ERP system, the key lies in applying the return prediction model to perform predictive analysis on the first clustering cluster to obtain the first cluster prediction return index for a predetermined period. Among them, the first clustering cluster refers to any order clustering cluster in the real-time clustering result. By performing predictive analysis on this first clustering cluster, the traversal predictive analysis of each clustering cluster in the real-time clustering result is realized. The technical goal of doing this is to predict the potential value of this clustering cluster in the future for a period of time, providing forward-looking data support for resource allocation and decision-making.

[0031] Specifically, first, use the return prediction model to analyze the first clustering cluster. Among them, the return prediction model may predict future returns based on variables such as historical data, market trends, and seasonal factors. Then, through the operation of the model, the first cluster prediction return index for a predetermined period is obtained. This index is a quantitative representation of the expected value of this clustering cluster within the predetermined period, that is, any predetermined future time. Through the application of this return prediction model, the ERP system can predict and evaluate the potential value of each order clustering cluster in the future for a period of time, thus being more forward-looking and strategic in the process of resource allocation and decision-making, helping the enterprise better respond to market changes and improve resource utilization efficiency.

[0032] Step S40: When the first index ratio calculated by calculating the ratio of the first cluster prediction return index to the first cluster return index meets the predetermined index ratio constraint, adjust the initial cluster weight allocation to obtain the target cluster weight allocation.

[0033] Specifically, calculate the ratio of the first cluster prediction return index to the first cluster return index. When this ratio meets the predetermined index ratio constraint, adjust the initial cluster weight allocation to obtain the target cluster weight allocation. That is to say, if there is a large difference between the order value return situation of the first clustering cluster analyzed in combination with the historical order situation within the predetermined period and the current situation, it indicates that there will be a large order change in this clustering cluster in the subsequent short period, that is, within the predetermined period. Therefore, it is necessary to predictively adjust the resource allocation of this clustering cluster, such as reducing or increasing the weight coefficient of this clustering cluster, that is, realizing the allocation adjustment of the corresponding resources of this clustering cluster, and then better reflecting and utilizing the future value potential of the clustering cluster.

[0034] Specifically, first, calculate the ratio of the first cluster prediction return index to the first cluster return index. This ratio reflects the relationship between the predicted return and the actual return. Then, compare this ratio with a predetermined index ratio constraint. The predetermined index ratio constraint is a standard set based on the enterprise's strategic goals and market conditions. If the calculated ratio meets this constraint, that is, there is a large deviation between the predicted return and the actual return, the initial cluster weight allocation is adjusted. The purpose of the adjustment is to reallocate resources according to the potential of the predicted return and optimize the cluster weights. Through this weight adjustment method based on the ratio of the prediction return index and the actual return index, the ERP system can manage resource allocation more flexibly and precisely, ensuring that resources can be optimized according to market changes and the predicted future value potential.

[0035] Step S50: Obtain a resource database, where the resource database includes data sets of various resources.

[0036] Specifically, collect the various resource situations of the enterprise and form a resource database, where the resource database contains data sets of various resources, providing comprehensive and detailed data references for subsequent resource allocation and decision-making of the ERP system.

[0037] Specifically, first, obtain a resource database. The resource database may be a system integrating internal and external resource information of the enterprise, including but not limited to data such as raw materials, human resources, and equipment. Among them, the resource database includes data sets of various resources, and these data sets may be classified and organized according to the types, attributes, sources, etc. of the resources. Exemplarily, automatically capture the raw data in various types of databases, such as relational databases, NoSQL databases, file systems, cloud storage, etc., according to the enterprise data source configuration list, and automatically establish corresponding data connections, and then perform data capture on each data source. Another example is that the raw material data set may include the types of raw materials, inventory levels, supplier information, etc.; the human resource data set may include employees' skills, working hours, salaries, etc. Finally, by obtaining such a resource database containing data sets of various resources, the ERP system can consider the availability, cost, and efficiency of various resources more comprehensively and accurately when performing resource allocation and decision-making, thereby improving the scientific nature and accuracy of resource management. Further, back up the collected resource database, that is, the original data of the database, to a unified temporary storage area for subsequent data recovery and verification. In addition, log the connection exceptions or data transmission errors that occur during the capture process and promptly feedback them to the system administrator for handling. Step S60: Generate a target resource allocation decision in combination with the target cluster weight allocation under the constraint of the data sets of the various resources.

[0038] Specifically, under the constraints of multiple resource datasets, a target resource configuration decision is generated in combination with the target cluster weight allocation. The technical objective of doing so is to optimize resource allocation according to the weight allocation of clustering clusters under limited resource conditions, so as to improve resource utilization efficiency and meet the strategic objectives of the enterprise.

[0039] Specifically, data preprocessing and field mapping are performed on the captured resource database to construct a resource data integration matrix. First, consider the constraints of the datasets of the multiple resources, and use the resource data integration matrix as a constraint for resource allocation, which may include resource availability, cost, quality, supplier limitations, etc. Specifically, first, the data captured from each data source is cleaned, format-converted, and standardized to eliminate data redundancy and noise. Then, according to the predefined mapping rules, similar fields in each data source are uniformly named and format-mapped to generate standardized data records. Next, based on the standardized data, a cross-data-source data integration matrix is constructed to record the association relationships and consistency information between the same data items in different data sources. Finally, the data in the data integration matrix is summarized and sorted to generate a preliminary unified data view, providing basic data for subsequent data display and business decision-making. Then, the integrated data is sorted and displayed according to preset rules to form a unified data view, providing data query and analysis services to users. That is to say, in combination with the target cluster weight allocation, that is, based on considering the value and importance of the clustering clusters, a target resource configuration decision is generated. The purpose of the target resource configuration decision is to determine how to allocate resources among different clustering clusters to maximize the overall return and meet the strategic needs of the enterprise. First, according to the data integration matrix and the preset summarization rules, all data is uniformly summarized and sorted to generate a standardized data summarization report; then the summarized data is presented to users through a visual dashboard, report, or multi-dimensional data drill-down tool, facilitating users to quickly query, analyze, and make decisions; finally, according to the interaction and query requests, the data display content is dynamically adjusted to ensure that the displayed information is updated in real time and meets the actual needs of the current order.

[0040] By generating a target resource configuration decision under the constraints of multiple resource datasets in combination with the target cluster weight allocation, the ERP system can perform resource allocation more scientifically and accurately, ensuring that resources can be optimally allocated according to the value and importance of the clustering clusters, thereby improving resource utilization efficiency, supporting the strategic objectives of the enterprise, and enhancing the market competitiveness of the enterprise.

[0041] Step S70: Perform dynamic configuration processing on the ERP system according to the target resource configuration decision.

[0042] Specifically, the ERP system is dynamically configured according to the target resource allocation decision. The dynamic configuration process may include adjusting resource allocation, updating system settings, changing work processes, etc., to ensure that the operation of the ERP system is consistent with the resource allocation decision. By dynamically configuring the ERP system according to the target resource allocation decision, the enterprise can ensure the effective implementation of its resource management strategy.

[0043] Further, step S10 of the present application includes:

[0044] Step S11: Extract the first order from the real-time order list, and the first order includes the first product;

[0045] Step S12: Match the first production data set of the first product in the production database, where the first production data set includes the first production equipment, the first production materials, and the first production personnel;

[0046] Step S13: Introduce a predetermined production vectorization scheme to perform characterization processing on the first production equipment, the first production materials, and the first production personnel to obtain a first production vector;

[0047] Step S14: Perform clustering analysis on the real-time order list with the first production vector as a constraint to obtain the real-time clustering result.

[0048] Specifically, in the ERP system, the real-time order list is processed and cluster analysis is performed on it. The purpose is to conduct a more in-depth analysis of the orders by combining order information and production data, so as to better understand production requirements and resource allocation, and thus optimize the production process and resource configuration. First, the first order in the real-time order list is extracted. The first order refers to any sales order in the real-time order list. By analyzing the specific order situation of the first order, the analysis of each order in the real-time order list is realized. Specifically, first, any sales product in this order is identified and denoted as the first product. Then, the first production data set related to the first product is matched in the production database. This data set includes information on the first production equipment, the first production materials, and the first production personnel. Next, a predetermined production vectorization scheme is introduced to perform characterization processing on the first production equipment, the first production materials, and the first production personnel, obtaining the first production vector. The purpose of this vectorization scheme is to convert production-related information into a format that can be quantified and analyzed. Finally, with the first production vector as a constraint, cluster analysis is performed on the real-time order list to obtain the real-time clustering result. Such cluster analysis takes into account the actual limitations of production resources, making the clustering result more in line with production reality. Through these steps, the ERP system can combine order information with production data. By introducing the production vector and performing cluster analysis, a more accurate and practical real-time clustering result can be obtained, thereby providing more powerful data support in production planning and resource allocation, optimizing the production process, and improving production efficiency.

[0049] Further, step S13 of the present application includes:

[0050] Step S131: Match the first equipment quantity of the first production equipment in the resource database;

[0051] Step S132: Match the first predetermined level corresponding to the first equipment quantity according to the predetermined production vectorization scheme;

[0052] Step S133: Obtain the first component of the first production equipment based on the first predetermined level;

[0053] Step S134: Sequentially obtain the second component of the first production materials and the third component of the first production personnel according to the predetermined production vectorization scheme;

[0054] Step S135: Obtain the first production vector based on the first component, the second component, and the third component.

[0055] Specifically, converting production data into production vectors is to transform complex production-related information into a quantifiable and analyzable format to facilitate cluster analysis and resource allocation decisions. First, match the first equipment quantity of the first production equipment in the resource database. Then, according to a predetermined production vectorization scheme, map the first equipment quantity to a first predetermined level. This predetermined level is a classification or quantitative representation of the equipment quantity. Next, obtain the first component of the first production equipment based on the first predetermined level. This component is an element in the production vector and represents a quantitative indicator of the equipment's production capacity. Then, sequentially obtain the second component of the first production material and the third component of the first production personnel according to the predetermined production vectorization scheme. These components respectively represent the quantitative impacts of materials and personnel in the production process. Finally, based on the first component, the second component, and the third component, obtain the first production vector. This vector synthesizes information from three aspects: equipment, materials, and personnel, providing a comprehensive data basis for cluster analysis and resource allocation. By converting key information in the production process into production vectors, these vectors not only contain information on equipment, materials, and personnel but also are standardized through a predetermined quantification scheme, making cluster analysis and resource allocation decisions more scientific and accurate.

[0056] Further, step S14 of the present application includes:

[0057] Step S141: Extract the second order in the real-time order list and obtain the second production vector of the second order;

[0058] Step S142: Perform cosine correlation analysis on the first production vector and the second production vector to obtain the first cosine similarity;

[0059] Step S143: If the first cosine similarity is within a predetermined similarity threshold, cluster the second order and the first order to obtain a second cluster;

[0060] Step S144: Compose the real-time clustering result based on the second cluster.

[0061] Specifically, clustering is performed by analyzing the similarity between orders, with the aim of identifying orders with similar production requirements so that these orders can be more effectively clustered and analyzed. Specifically, first, a second order is extracted from the real-time order list, and the corresponding second production vector of this order is obtained. This vector is obtained through a production data vectorization scheme in a previous process and represents the production characteristics of the order. Then, a cosine correlation analysis is performed on the first production vector and the second production vector to obtain the first cosine similarity. Cosine similarity is a method for measuring the difference in the directions of two vectors, and its value ranges from -1 to 1. The closer the value is to 1, the more similar the two vectors are. Next, it is determined whether the first cosine similarity reaches a predetermined similarity threshold. If the similarity is higher than the threshold, it indicates that the two orders have high similarity in production characteristics. Therefore, the second order is clustered with the first order to form a second cluster. Finally, the real-time clustering result is updated based on the composition of the second cluster. In this way, orders with similar production characteristics are grouped into the same cluster, facilitating subsequent resource allocation and decision-making. By grouping orders with similar production requirements, more targeted data support is provided for resource optimization and decision-making.

[0062] Further, step S30 of the present application includes:

[0063] Step S31: Extract a third order from the first cluster, where the third order refers to an order in which a target customer purchases a target product;

[0064] Step S32: Screen the historical order log with the target customer and the target product as screening constraints to obtain a target order log;

[0065] Step S33: Extract a first historical order at a first historical time from the target order log and calculate the first historical return index of the first historical order;

[0066] Step S34: Construct a target return time series according to the first corresponding relationship between the first historical return index and the first historical time;

[0067] Step S35: Analyze the target return time series through the return prediction model to obtain the target predicted return index for the predetermined period;

[0068] Step S36: Sum the target predicted return indices to obtain the first cluster predicted return index.

[0069] Specifically, historical order data is used to predict the future return index. By predicting the potential return of a specific order within a certain period in the future, it provides a basis for resource allocation and decision-making. First, the third order in the first cluster is extracted. This order is the order in which the target customer purchases the target product. Then, with the target customer and the target product as the screening constraints, the historical order log is screened to obtain the target order log. These logs contain the historical transaction information of all historical orders in which the target customer purchases the target product. Next, the first historical order at the first historical time in the target order log is extracted, and the first historical return index of this historical order is calculated. This return index quantifies the return of this historical order within a specific time. According to the correspondence between the first historical return index and the first historical time, a target return time series is constructed. This time series reflects the changing trend of returns over time. Then, the target return time series is analyzed through a return prediction model to predict the target predicted return index within a certain period in the future. This prediction is obtained based on the analysis of historical return data and model calculations. Finally, the target predicted return indices are summed up to obtain the predicted return index for the first cluster. This index is the overall prediction of the future returns of all orders in the first cluster.

[0070] Finally, through these steps, the ERP system can use historical order data to predict future returns, providing a prediction basis based on historical data for resource allocation and decision-making, thereby improving the foresight and accuracy of resource allocation.

[0071] Furthermore, step S35 of this application includes:

[0072] Step S351: Perform regression fitting on the target return scatter plot drawn based on the target return time series to obtain a target fitting formula;

[0073] Step S352: Use the target fitting formula and the predetermined period as the input information of the return prediction model, and obtain the target predicted return index through the return prediction model.

[0074] Specifically, the target return time series is used to predict the future return index. By analyzing the changing trend of historical return data, the potential return of a specific order in the future period is predicted, so as to provide a basis for resource allocation and decision-making. First, a target return scatter plot is drawn based on the target return time series, and regression fitting is performed on these scatter points to obtain a target fitting formula. Regression fitting is a statistical method used to analyze the relationship between variables. The data relationship formula obtained through fitting can be used to predict future data trends. Next, the target fitting formula and a predetermined period are used as input information for the return prediction model. Through the analysis and calculation of the return prediction model, the target predicted return index is obtained. Among them, the return prediction model is a mathematical model that predicts the future return index based on the input data relationship formula and time period. Through regression fitting and the return prediction model, the target predicted return index in the future period is predicted. In this way, resource allocation and decision-making can be based on the predicted return index, improving the foresight and accuracy of resource allocation.

[0075] Further, step S60 of the present application includes:

[0076] Step S61: Extract the first resource type from the multiple resources and match to obtain the first type data set of the first resource type;

[0077] Step S62: Based on the target cluster weight allocation and the first type quantity in the first type data set, obtain the first allocation quantity of the first resource type to the first clustering cluster;

[0078] Step S63: Generate the target resource allocation decision based on the first allocation quantity;

[0079] Step S64: Among them, the multiple resources at least include device resources, material resources, and personnel resources.

[0080] Specifically, based on the target cluster weight allocation and the resource type dataset, a target resource configuration decision is generated to ensure that each resource type can be optimally configured according to its importance and availability, thereby meeting order requirements and improving resource utilization efficiency. First, the first resource type among multiple resources is extracted, such as equipment resources, and the first type dataset of this resource type is obtained by matching from the resource database. This dataset contains relevant information about this resource type, such as the number of devices, specifications, etc. Next, based on the target cluster weight allocation and the first type quantity in the first type dataset, the first configuration quantity of the first resource type for the first clustering cluster is calculated. This configuration quantity reflects the demand for the first resource type by the first clustering cluster under the current weight allocation. Then, a target resource configuration decision is generated based on the first configuration quantity. This decision includes the quantity of the first resource type allocated to the first clustering cluster, ensuring that resources can be effectively allocated according to order requirements and resource importance. Finally, as described in step S64, multiple resources at least include equipment resources, material resources, and personnel resources. This means that the above process needs to be carried out separately for these three resource types to ensure that all key resources are properly configured.

[0081] Through these steps, the ERP system can generate target resource configuration decisions for each resource type based on the clustering results and the resource type dataset, thereby achieving the optimal allocation of resources, improving production efficiency, and meeting order requirements.

[0082] Furthermore, this application also includes step S80, and the step S80 includes:

[0083] Step S81: Perform dynamic configuration simulation on the ERP system based on the target resource configuration decision to obtain a target simulation record;

[0084] Step S82: Analyze the target simulation record to obtain a target return index, and use the target return index as the initial configuration fitness of the target resource configuration decision;

[0085] Step S83: Extract abnormal simulation data from the target simulation record, and analyze the inspection simulation data and fault simulation data in the abnormal simulation data to obtain a target abnormal index;

[0086] Step S84: Adjust the initial configuration fitness with the target abnormal index to obtain a target configuration fitness.

[0087] Specifically, evaluating and adjusting the target resource configuration decision through simulation and analysis is to predict and evaluate the effect of the configuration through simulation and analysis before implementing the resource configuration, so as to optimize the resource configuration decision, improve resource utilization efficiency and return rate.

[0088] First, perform dynamic configuration simulation on the ERP system based on the target resource configuration decision. This simulation process will run in a virtual environment to observe and record the effects of the configuration decision. Through simulation, target simulation records can be obtained, which contain key data during the simulation run. That is to say, the simulation automatically parses the database table structure information according to the structure definitions of each table in the database. Then, according to the parsing results, the corresponding simulation dynamic forms are automatically generated through a template engine. For example, first, automatically connect to the database according to the configuration information of all tables in the enterprise database and read the structure data of each data table. Then use SQL statements to parse the field information of each data table, including field names, data types, lengths, constraint conditions, and default values. Next, save the parsing results to an intermediate cache or configuration file for subsequent calls by the dynamic form generation module. For example, when generating a simulation dynamic form, first obtain the standardized database table structure information and call the predefined template engine to match each field information with the form template to automatically generate the corresponding input controls and display controls. Next, according to the constraint conditions and verification rules of the fields, attach the corresponding verification logic to each input control to generate a complete dynamic form page. Finally, seamlessly connect the generated dynamic form with the database to ensure the synchronization of data entry, display, and modification functions.

[0089] Next, analyze the target simulation records to obtain the target return index. This index is a quantitative evaluation of the simulation run effect and reflects the quality of the resource configuration decision. The target return index is used as the initial configuration fitness, that is, the preliminary evaluation result of the resource configuration decision. Then extract the abnormal simulation data in the target simulation records, especially the maintenance inspection simulation data and fault simulation data. Analyzing these abnormal data can obtain the target abnormal index. This index reflects the performance and efficiency of the configuration decision in dealing with abnormal situations. Finally, adjust the initial configuration fitness with the target abnormal index to obtain the target configuration fitness. This fitness is a correction of the initial configuration fitness, considering the impact of abnormal situations on the resource configuration effect.

[0090] In addition, to achieve real-time data interaction and verification and ensure that the user operations are consistent with the database status, for example, Ajax technology can be used to achieve asynchronous data transmission between the dynamic form page and the backend database, supporting real-time data saving and querying. Then, through WebSocket technology, establish a persistent data connection to ensure that each operation of the user on the page can be immediately reflected in the database and receive database status updates at the same time. Finally, integrate a data verification mechanism to immediately perform format, range, and required field validations when the user enters data to ensure data accuracy and automatically trigger data update operations.

[0091] By simulating and analyzing before implementing resource allocation, predicting and evaluating the effects of the allocation, and adjusting the fitness of the allocation decision by considering abnormal situations, the resource allocation can be optimized based on more comprehensive and accurate evaluation results, improving resource utilization efficiency and overall operation effects.

[0092] In summary, a dynamic configuration method for an ERP system provided by this application has the following technical effects:

[0093] Obtain a real-time order list in the ERP system through dynamic monitoring, and retrieve a predetermined clustering strategy to perform clustering analysis on the orders in the real-time order list to obtain a real-time clustering result; perform return analysis on the first clustering cluster in the real-time clustering result to obtain a first cluster return index, and obtain an initial cluster weight allocation based on the normalized first cluster return index; perform predictive analysis on the first clustering cluster through a return prediction model to obtain a first cluster predicted return index for a predetermined period; when the first index ratio calculated by calculating the ratio of the first cluster predicted return index to the first cluster return index meets the predetermined index ratio constraint, adjust the initial cluster weight allocation to obtain a target cluster weight allocation; obtain a resource database, where the resource database includes data sets of various resources; under the constraint of the data sets of the various resources, generate a target resource allocation decision in combination with the target cluster weight allocation; perform dynamic configuration processing on the ERP system according to the target resource allocation decision, that is, by real-time monitoring the order situation and performing order clustering analysis, and then obtaining the order return analysis in the real-time state, and then performing predictive adjustment on the real-time return through a return prediction model, and accordingly performing the weight allocation analysis of the order clustering clusters, and finally combining the resource situation to perform corresponding resource allocation on the order clustering clusters with different weight coefficients. By real-time monitoring the order situation and performing order clustering analysis, and then obtaining the order return analysis in the real-time state, and then performing predictive adjustment on the real-time return through a return prediction model, and accordingly performing the weight allocation analysis of the order clustering clusters, and finally combining the resource situation to perform corresponding resource allocation on the order clustering clusters with different weight coefficients, the goal of predictive configuration analysis of resource information is achieved, and the technical effects of improving the scientificity and effectiveness of the pre-allocation processing of the ERP system and further improving resource utilization efficiency are achieved.

[0094] Embodiment 2, based on the inventive concept of a dynamic configuration method for an ERP system in the foregoing embodiment, this application further provides an electronic device, including: at least one processor; a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of any one of the foregoing embodiment 1 of a dynamic configuration method for an ERP system.

[0095] Appendix Figure 2 is a schematic structural diagram of an exemplary electronic device of the present application. In Figure 2 , the bus architecture is represented by bus 300, and bus 300 may include any number of interconnected buses and bridges. Bus 300 connects various circuits including one or more processors represented by processor 302 and a memory represented by memory 304 together. Bus 300 can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, and thus will not be further described herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 can be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 can be used to store data used by processor 302 when performing operations.

[0096] Embodiment 3, based on the same inventive concept as the method for dynamically configuring an ERP system in the foregoing embodiment, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed, it implements the steps of any one of the methods for dynamically configuring an ERP system described in the foregoing Embodiment 1.

[0097] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0098] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and 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 equivalent technologies, the present application also intends to include these changes and modifications.

Claims

1. A method for dynamic configuration of an ERP system, characterized in that: include: Dynamically monitor and obtain a real-time order list in the ERP system, and call a predetermined clustering strategy to perform clustering analysis on the orders in the real-time order list to obtain a real-time clustering result; Performing a reward analysis on the first cluster in the real-time clustering result to obtain a first cluster reward index, and obtaining an initial cluster weight allocation based on the normalized first cluster reward index; Performing a prediction analysis on the first cluster using a return prediction model to obtain a first cluster prediction return index for a predetermined period; When a first index ratio obtained by calculating the ratio of the first cluster predicted return index to the first cluster return index meets a predetermined index ratio constraint, adjusting the initial cluster weight allocation to obtain a target cluster weight allocation; Acquire a resource database, wherein the resource database includes data sets of multiple resources; Under the constraints of the data sets of the multiple resources, generating a target resource configuration decision in combination with the target cluster weight distribution; The ERP system is dynamically configured according to the target resource configuration decision.

2. The method according to claim 1, characterized in that Dynamically monitor and obtain a real-time order list in the ERP system, and call a predetermined clustering strategy to perform clustering analysis on the orders in the real-time order list to obtain real-time clustering results, including: Extracting a first order from the real-time order list, where the first order includes a first product; matching a first production data set of the first product in a production database, wherein the first production data set includes a first production equipment, a first production material, and a first production personnel; Introducing a predetermined production vector quantization scheme to characterize the first production equipment, the first production material, and the first production personnel to obtain a first production vector; Cluster analysis is performed on the real-time order list with the first production vector as a constraint to obtain the real-time clustering result.

3. The method according to claim 2, characterized in that Introducing a predetermined production vector quantization scheme to characterize the first production equipment, the first production material, and the first production personnel to obtain a first production vector, including: matching a first device quantity of the first production device in the resource database; matching a first predetermined level corresponding to the first number of devices according to the predetermined production vectorization scheme; obtaining a first component of the first production equipment based on the first predetermined level; sequentially acquiring the second component of the first production material and the third component of the first production personnel according to the predetermined production vectorization scheme; The first production vector is obtained based on the first component, the second component and the third component.

4. The method according to claim 3, characterized in that Dynamically monitor and obtain a real-time order list in the ERP system, and call a predetermined clustering strategy to perform clustering analysis on the orders in the real-time order list to obtain real-time clustering results, including: Extracting a second order from the real-time order list, and acquiring a second production vector for the second order; Performing a cosine correlation analysis on the first production vector and the second production vector to obtain a first cosine similarity; If the first cosine similarity is within a predetermined similarity threshold, clustering the second order and the first order to obtain a second cluster; The real-time clustering result is formed based on the second clustering cluster.

5. The method according to claim 1, characterized in that The first cluster is predicted and analyzed by the reward prediction model to obtain a first cluster prediction reward index for a predetermined period, including: Extracting a third order from the first cluster, wherein the third order refers to an order for a target customer to purchase a target product; Filtering historical order logs with the target customer and the target product as filtering constraints to obtain a target order log; Extracting a first historical order placed at a first historical time in the target order log, and calculating a first historical return index of the first historical order; Constructing a target return time series according to a first corresponding relationship between the first historical return index and the first historical time; Analyze the target return time series through the return prediction model to obtain the target predicted return index of the predetermined period; The target predicted reward index is added to obtain the first cluster predicted reward index.

6. The method according to claim 5, characterized in that Analyzing the target return time series through the return prediction model to obtain the target predicted return index of the predetermined period includes: Performing regression fitting on a target return scatter plot based on the target return time series to obtain a target fitting formula; The target fitting formula and the predetermined period are used as input information of the reward prediction model, and the target predicted reward index is obtained through the reward prediction model.

7. The method according to claim 1, characterized in that Under the constraints of the data sets of the multiple resources, a target resource configuration decision is generated in combination with the target cluster weight allocation, including: Extracting a first resource type from the multiple resources, and matching to obtain a first type data set of the first resource type; Obtaining a first configuration quantity of the first resource type for the first cluster based on the target cluster weight distribution and the first type quantity in the first type data set; Based on the first configuration quantity, generating the target resource configuration decision; The various resources include at least equipment resources, material resources and personnel resources.

8. The method according to claim 1, characterized in that Before dynamically configuring the ERP system according to the target resource allocation decision, the method further includes: Performing dynamic configuration simulation on the ERP system based on the target resource configuration decision to obtain a target simulation record; Analyze the target simulation record to obtain a target return index, and use the target return index as the initial configuration fitness of the target resource configuration decision; Extracting abnormal simulation data from the target simulation record, and analyzing the maintenance and inspection simulation data and the fault simulation data in the abnormal simulation data to obtain a target abnormality index; The initial configuration fitness is adjusted according to the target abnormality index to obtain a target configuration fitness.

9. An electronic device, comprising: at least one processor; a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps of the method described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which implements the steps of the method according to any one of claims 1 to 8 when executed.

Images