A collaborative optimization management method and system for supply chain departments

Abstract

The embodiments of the present invention relate to the field of data analysis technology, and specifically, to a collaborative optimization management method and system for a supply chain department, wherein the method can obtain a supply chain business order log to be processed; perform task event element analysis on the supply chain business order log to be processed based on a task event analysis network to obtain workflow distribution data of several links to be coordinated corresponding to at least one business order task event and cluster description vectors corresponding to several links to be coordinated; perform collaborative link clustering operations on several links to be coordinated based on the cluster description vectors to obtain a cluster of links to be coordinated corresponding to each business order task event in at least one business order task event; optimize and schedule the links to be coordinated in the cluster of collaborative links based on the workflow distribution data, thereby accurately and intelligently obtaining task collaborative optimization scheduling suggestions corresponding to each business order task event, thereby achieving comprehensive optimization and intelligent improvement of supply chain management.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a collaborative optimization management method and system for supply chain departments. Background Art

[0002] In modern supply chain management, efficient processing of business orders is the key to a company's success. However, with the development of globalization and networking, supply chain business orders have become more and more complex, involving more and more links, which has brought huge challenges to the company's order management. In order to better cope with these challenges, companies urgently need a method that can intelligently analyze order task events and optimize scheduling and coordination links.

[0003] Traditional supply chain management methods often rely on manual analysis and decision-making, which is not only inefficient but also prone to errors. In recent years, although some automated systems have been developed, they can usually only handle simple order tasks and are often unable to cope with complex supply chain business orders. Summary of the invention

[0004] In order to at least overcome the above-mentioned deficiencies in the prior art, one of the objectives of the present invention is to provide a supply chain department collaborative optimization management method and system.

[0005] An embodiment of the present invention provides a supply chain department collaborative optimization management method, which is applied to a collaborative optimization management system. The method includes:

[0006] Obtaining a pending supply chain business order log, wherein the pending supply chain business order log includes at least one business order task event;

[0007] Based on the task event parsing network, the task event elements of the to-be-processed supply chain business order log are parsed to obtain the workflow distribution data of the several to-be-coordinated links corresponding to the at least one business order task event and the cluster description vectors corresponding to the several to-be-coordinated links;

[0008] Performing a coordination link clustering operation on the plurality of to-be-coordinated links according to the clustering description vector to obtain a to-be-coordinated link cluster corresponding to each business order task event in the at least one business order task event;

[0009] The to-be-coordinated links in the to-be-coordinated link cluster are optimized and scheduled according to the workflow distribution data, so as to obtain a task collaborative optimization scheduling suggestion corresponding to each business order task event.

[0010] Preferably, the task event parsing network based on the task event parsing network performs task event element parsing on the pending supply chain business order log to obtain the workflow distribution data of the respective several to-be-coordinated links corresponding to the at least one business order task event and the cluster description vectors corresponding to the respective several to-be-coordinated links, including:

[0011] Performing element mining on the pending supply chain business order log according to the task event parsing network, obtaining initial workflow distribution data of initial collaborative links corresponding to each of several log text blocks of the pending supply chain business order log, respective cluster description vectors of the several log text blocks, and respective initial weight coefficients of the several log text blocks, wherein the initial weight coefficient represents the possibility that the log text block includes the pending collaborative link;

[0012] Determining from the plurality of log text blocks a plurality of target log text blocks whose initial weight coefficients satisfy a set weight determination index;

[0013] Based on the initial workflow distribution data of the initial coordination links of the target log text blocks and the cluster description vectors of the target log text blocks, the workflow distribution data of each of the links to be coordinated and the cluster description vectors corresponding to each of the links to be coordinated are determined.

[0014] Preferably, performing a collaborative link clustering operation on the plurality of links to be coordinated according to the cluster description vector to obtain a cluster of links to be coordinated corresponding to each business order task event in the at least one business order task event includes:

[0015] For the to-be-coordinated link binary groups generated by the plurality of to-be-coordinated links, obtaining the link description vector commonality score of the to-be-coordinated link binary groups according to the cluster description vectors;

[0016] The plurality of links to be coordinated are grouped based on the commonality scores of the link description vectors to obtain a cluster of links to be coordinated corresponding to each business order task event.

[0017] Preferably, optimizing and scheduling the to-be-coordinated links in the to-be-coordinated link cluster according to the workflow distribution data to obtain the task collaborative optimization scheduling suggestion corresponding to each business order task event includes:

[0018] Determine the workflow update interval of the link to be coordinated in the cluster of links to be coordinated according to the workflow distribution data;

[0019] On the basis that the workflow update interval is greater than the set interval, decision optimization scheduling of workflow distribution data is performed on each link to be coordinated in the cluster of links to be coordinated based on a decision tree network to obtain task collaborative optimization scheduling suggestions for the business order task events corresponding to the cluster of links to be coordinated.

[0020] Preferably, the method further comprises:

[0021] On the basis that the workflow update interval is less than or equal to the set interval, determining the target key link of the to-be-coordinated link cluster according to the workflow distribution data;

[0022] Determining a single link from each link to be coordinated in the link cluster to be coordinated according to the workflow distribution data;

[0023] Based on the target key link and the single link, a task collaborative optimization scheduling suggestion for the business order task event corresponding to the to-be-coordinated link cluster is generated.

[0024] Preferably, the method comprises:

[0025] Acquire a supply chain business order log sample including at least one business order task event, a priori workflow distribution data of a plurality of to-be-coordinated links corresponding to the business order task event, and a priori event subject of each of the plurality of to-be-coordinated links, wherein the a priori event subject represents the business order task event to which the to-be-coordinated link belongs;

[0026] Inputting the supply chain business order log sample into the initial parsing network for element mining, obtaining initial workflow distribution data of initial collaborative links of several log text blocks of the supply chain business order log sample, cluster description vectors of the several log text blocks, and initial weight coefficients of the several log text blocks, wherein the initial weight coefficients represent the possibility that the log text block includes the link to be coordinated;

[0027] The initial parsing network is debugged according to the initial workflow distribution data, the initial weight coefficient, the cluster description vector, the prior workflow distribution data and the prior event theme to obtain a task event parsing network.

[0028] Preferably, debugging the initial parsing network according to the initial workflow distribution data, the initial weight coefficient, the cluster description vector, the prior workflow distribution data and the prior event theme to obtain the task event parsing network includes:

[0029] Determining a first debugging error according to the initial workflow distribution data and the priori workflow distribution data;

[0030] Determining a priori weight coefficients of each of the plurality of log text blocks based on the a priori workflow distribution data;

[0031] Determining a second debugging error according to the initial weight coefficient and the priori weight coefficient;

[0032] determining a third debugging error according to the priori workflow distribution data, the priori event topic and the cluster description vector;

[0033] Improve the network configuration hyper-parameters of the initial analytical network based on the first debugging error, the second debugging error, and the third debugging error, and perform cyclic debugging according to the improved network configuration hyper-parameters until set debugging termination requirements are met;

[0034] An initial parsing network that meets the set debugging termination requirement is determined as the task event parsing network.

[0035] Preferably, the determining the third debugging error according to the priori workflow distribution data, the priori event topic and the cluster description vector comprises:

[0036] Determining a plurality of target log text blocks from the plurality of log text blocks based on the prior workflow distribution data, wherein the target log text blocks include the link to be coordinated;

[0037] Summarizing the plurality of target log text blocks based on the prior event theme to obtain a log text block set corresponding to each business order task event in the at least one business order task event;

[0038] Determining a self-debugging error corresponding to each log text block set and a mutual-debugging error between different log text block sets according to the cluster description vector;

[0039] The third debugging error is determined based on the self-debugging error and the mutual debugging error.

[0040] Preferably, determining the self-debugging error corresponding to each log text block set and the mutual-debugging error between different log text block sets according to the cluster description vector comprises:

[0041] Determining a cluster representative vector in each log text block set according to the cluster description vector;

[0042] Determine the cumulative vector difference between the cluster description vector of each log text block in each log text block set and the cluster representative vector to obtain a self-debugging error corresponding to each log text block set;

[0043] For the log text block set tuples generated by the log text block set corresponding to the at least one business order task event, the interaction vector differences of the log text block set tuples are determined based on the cluster representative vector to obtain the mutual debugging errors between the different log text block sets.

[0044] An embodiment of the present invention also provides a collaborative optimization management system, comprising a processor and a memory and a bus connected to the processor; wherein the processor and the memory communicate with each other through the bus; the processor is used to call program instructions in the memory to execute the above-mentioned supply chain department collaborative optimization management method.

[0045] An embodiment of the present invention further provides a computer-readable storage medium on which a program is stored, and when the program is executed by a processor, the above-mentioned supply chain department collaborative optimization management method is implemented.

[0046] Beneficial Effects

[0047] In the application of the embodiment of the present invention, first, the supply chain business order logs to be processed are obtained, and these logs contain at least one business order task event. These events are core data in the daily operation of the enterprise, and are of great significance for understanding the order processing process and optimizing operational efficiency. However, to extract valuable information from these complex log data and process them effectively, an efficient task event parsing method is required. Based on this, the present invention introduces a task event parsing network, deeply parses the supply chain business order logs to be processed, and obtains the workflow distribution data and cluster description vectors of each link to be coordinated. These data not only reveal the key links in the order processing process, but also provide an important basis for the subsequent clustering and optimization scheduling of the collaborative links. When processing complex order tasks, the existing supply chain management methods often cannot accurately identify the links to be coordinated, let alone perform refined optimization scheduling. Therefore, the present invention proposes a method for clustering the collaborative links according to the cluster description vector, and then obtains the cluster of the links to be coordinated corresponding to each business order task event. This method can more accurately identify the links that need to be coordinated, which provides a possibility for subsequent optimization scheduling. Finally, the present invention also optimizes and schedules the to-be-coordinated links in the to-be-coordinated link cluster based on the workflow distribution data, and obtains the task collaborative optimization scheduling suggestions corresponding to each business order task event. This method not only improves the efficiency of order processing, but also reduces the error rate, bringing revolutionary changes to the supply chain management of enterprises.

[0048] In summary, the present invention proposes a new supply chain business order processing method, which realizes efficient processing of complex supply chain business orders by introducing technical means such as task event analysis network, collaborative link grouping and optimized scheduling. This method not only improves the operational efficiency of enterprises, but also brings huge commercial value to enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 A flow chart of a supply chain department collaborative optimization management method provided by an embodiment of the present invention.

[0051] Figure 2 A block diagram of a collaborative optimization management system provided by an embodiment of the present invention.

[0052] icon:

[0053] 100- Collaborative optimization management system;

[0054] 101 - processor; 102 - memory; 103 - bus. DETAILED DESCRIPTION

[0055] The exemplary embodiments disclosed in the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0056] In order to better understand the above technical scheme, the technical scheme of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical scheme of the present invention, rather than limitations on the technical scheme of the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0057] Figure 1 This is a flow chart of a collaborative optimization management method for a supply chain department according to an embodiment of the present invention, which is applied to a collaborative optimization management system and includes steps 110 to 140.

[0058] Step 110: Obtain a pending supply chain business order log, wherein the pending supply chain business order log includes at least one business order task event.

[0059] Among them, the pending supply chain business order log is a record file that records in detail all the business order-related operations and events that occurred in the supply chain. These logs usually include information on key nodes such as order creation, modification, cancellation, shipment, and receipt, as well as various data and interaction records generated at these nodes. They play an important role in tracking order status, optimizing supply chain processes, monitoring supply chain health, and diagnosing problems. These logs are usually automatically generated by the supply chain management system and are an indispensable part of supply chain management.

[0060] In supply chain management, business order task events refer to specific tasks or operations directly related to business order processing. These events may include key links such as order entry, review, distribution, delivery, and receipt confirmation. Each task event contains detailed information, such as the time of the event, the executor, the event type, related data, and results. By monitoring and analyzing these task events, companies can grasp the progress of order processing in real time, discover and solve problems in a timely manner, and thus improve the operational efficiency of the supply chain and customer satisfaction.

[0061] In detail, the first step of the collaborative optimization management system is to obtain the pending supply chain business order logs. These logs are valuable data resources generated during the supply chain operation process, recording the entire process from order generation to completion. The purpose of obtaining these logs is to conduct subsequent data analysis and optimization operations. When executing this step, the system connects to the supply chain database or related data storage facilities to retrieve and download the latest business order logs. These logs usually include multiple business order task events, each of which represents a specific link or operation in the supply chain. For example, an order starts from a customer placing an order and will go through multiple links such as order confirmation, inventory management, and logistics distribution, and each link will generate corresponding log records. The log data obtained by the system includes not only basic order information (such as order number, order time, customer information, etc.), but also detailed information of each business order task event (such as event type, occurrence time, executor, execution result, etc.). This information is the basis for subsequent task event element analysis and optimization scheduling. Through this step, the collaborative optimization management system provides an accurate and comprehensive data source for subsequent operations, ensuring the scientificity and effectiveness of the optimization suggestions. At the same time, automated log acquisition has greatly improved the efficiency and accuracy of data processing, bringing great convenience to supply chain management.

[0062] Step 120: parse the task event elements of the pending supply chain business order log based on the task event parsing network to obtain the workflow distribution data of the several links to be coordinated corresponding to the at least one business order task event and the cluster description vectors corresponding to the several links to be coordinated.

[0063] Among them, the task event parsing network is used to deeply parse the task events in the supply chain business order log. The network can identify and extract key information in the task events, such as the type, time, participants, etc. of the event, and convert this information into structured data for subsequent analysis and processing. The task event parsing network is one of the core components of the collaborative optimization management system, and its accuracy and efficiency directly affect the performance of the entire system.

[0064] Task event element analysis refers to using the task event analysis network to deeply analyze the task events in the supply chain business order log to be processed and extract the key elements of the event. These elements include but are not limited to the event type, timestamp, executor, related resources, execution results, etc. Through this analysis process, the system can more comprehensively understand the connotation and extension of each task event and provide data support for subsequent optimization scheduling.

[0065] In supply chain management, the links to be coordinated refer to those links that require the collaboration of multiple departments or teams to complete. These links usually involve the coordination of multiple processes and resources, and have an important impact on the efficiency and quality of the entire supply chain. The links to be coordinated are the focus of the collaborative optimization management system. The system can improve the overall performance of the supply chain by optimizing and scheduling these links.

[0066] Workflow distribution data refers to the digital representation of the workflow and task allocation of each link in the order processing process of the supply chain business. These data reflect the position, importance and relationship of different links in the order processing process. By analyzing the workflow distribution data, the collaborative optimization management system can more accurately understand the actual operation of the supply chain and put forward more reasonable optimization suggestions.

[0067] The cluster description vector is a mathematical representation method used to describe the characteristics of the links to be coordinated. Each link to be coordinated will be converted into a vector, and each dimension of the vector represents a characteristic of the link (such as time, cost, resource requirements, etc.). Through these vectors, the collaborative optimization management system can more easily classify and compare the links, so as to find similar links and classify them. This vectorized representation method greatly improves the system's ability to process complex supply chain data.

[0068] In step 120, the collaborative optimization management system uses the task event parsing network to conduct an in-depth analysis of the supply chain business order log to be processed. This network model is specially trained to identify and extract key information of task events in the log. First, the system inputs the complete business order log into the task event parsing network. The network automatically scans the log content and identifies the various business order task events contained therein. For each identified task event, the network further extracts its key elements, such as event type, specific time, executor, related resource usage, execution result status, etc. Then, based on these extracted elements, the system generates corresponding workflow distribution data and cluster description vectors for each business order task event. The workflow distribution data describes in detail the position and role of the event in the entire supply chain process, as well as the relationship with other events; while the cluster description vector is a high-level summary of the event characteristics, which is used for subsequent link classification and optimization operations. The completion of this step provides a rich data foundation for the collaborative optimization management system, enabling it to more accurately understand each link and process in the supply chain. These data will be used for subsequent link clustering and optimization scheduling operations, thereby improving the efficiency and flexibility of supply chain management.

[0069] Step 130: perform a coordination link clustering operation on the plurality of links to be coordinated according to the cluster description vector to obtain a cluster of links to be coordinated corresponding to each business order task event in the at least one business order task event.

[0070] Among them, the operation of grouping collaborative links refers to the process of classifying and grouping the links to be coordinated in the supply chain according to certain rules and standards. The purpose of this operation is to classify links with similar characteristics or common needs into the same group or cluster for unified management and optimization. In this way, the efficiency and flexibility of supply chain management can be improved, and unnecessary waste of resources and duplication of work can be reduced. The operation of grouping collaborative links is usually based on data analysis and technical means, such as cluster analysis, machine learning, etc., to ensure the accuracy and effectiveness of grouping.

[0071] The cluster of links to be coordinated refers to a collection of links to be coordinated with similar characteristics or common needs formed after the coordinated links are divided into groups. The links in each cluster have similar functions, resource requirements or processing procedures in the supply chain, so they can be regarded as a relatively independent management unit. Through the unified management and optimization of the cluster of coordinated links, the efficiency and quality of the supply chain can be further improved, the operating costs can be reduced, and the competitiveness of the enterprise can be enhanced.

[0072] In step 130, the collaborative optimization management system will use the previously generated cluster description vector to perform collaborative link clustering operations on the identified several links to be coordinated. The core purpose of this step is to classify the links to be coordinated with similar characteristics or requirements into the same cluster of links to be coordinated, so as to facilitate subsequent unified management and optimization. The system will first analyze the cluster description vectors corresponding to each link to be coordinated. These vectors have captured the key characteristics of the links, such as processing time, resource consumption, complexity, etc. Next, the system uses advanced clustering algorithms, such as K-means or hierarchical clustering, to group the collaborative links according to the similarity of the vectors. During the clustering process, the system continuously iterates and adjusts until the best grouping method is found, that is, the links within each cluster are as similar as possible, and the differences between clusters are as large as possible. In this way, it can be ensured that the links within each cluster of links to be coordinated have a high degree of consistency in processing requirements, resource allocation and execution strategies. Finally, the system generates a corresponding cluster of links to be coordinated for each business order task event. These clusters will become the basic units for subsequent optimization scheduling, and the system can formulate more refined management strategies and optimization plans based on the characteristics of the clusters. In this way, the collaborative optimization management system can significantly improve the efficiency and responsiveness of supply chain management, reduce operating costs, and enhance the market competitiveness of enterprises.

[0073] Step 140: Optimize and schedule the to-be-coordinated links in the to-be-coordinated link cluster according to the workflow distribution data, and obtain task coordination optimization scheduling suggestions corresponding to each business order task event.

[0074] Among them, optimization scheduling refers to the rational sorting, allocation and adjustment of tasks and links to be processed through scientific methods and means according to the actual situation and goals of supply chain operations, so as to achieve the goals of improving efficiency, reducing costs, optimizing resource utilization, etc. In this process, multiple factors are usually considered, such as the urgency of the task, the availability of resources, the dependencies of the links, etc., to ensure the smooth operation and maximum benefits of the entire supply chain.

[0075] Task collaborative optimization scheduling suggestions refer to specific improvement plans and suggestions proposed by the system based on the analysis results after optimizing the collaborative links. These suggestions may include adjusting the processing order of tasks, reallocating resources, optimizing workflows, etc., aiming to improve the collaborative efficiency and overall performance of the supply chain. These suggestions are based on data analysis, algorithm optimization and professional knowledge, and can provide decision support for supply chain managers, helping them better manage and optimize the supply chain.

[0076] In step 140, the collaborative optimization management system will use the previously parsed workflow distribution data to optimize the scheduling of the to-be-coordinated links in the to-be-coordinated link cluster. The goal of this step is to propose task collaborative optimization scheduling suggestions that can improve the efficiency and response speed of the supply chain. First, the system deeply analyzes the workflow distribution data of each to-be-coordinated link cluster, which details the position, role, and relationship of each link with other links in the supply chain process. Through these data, the system can identify potential bottleneck links, resource waste points, and unreasonable aspects of the process. Next, the system uses advanced optimization algorithms, such as linear programming and genetic algorithms, to intelligently schedule the to-be-coordinated links. During the scheduling process, the system considers multiple factors, such as the urgency of the task, the priority of the customer, the availability of resources, and the transportation cost, to ensure the rationality and feasibility of the scheduling plan. Finally, after multiple iterations and optimizations, the system generates task collaborative optimization scheduling suggestions corresponding to each business order task event. These suggestions may include adjusting the processing order of tasks, optimizing resource allocation, improving workflows, etc., aiming to improve the collaborative efficiency and response speed of the supply chain.

[0077] Through this step, the collaborative optimization management system not only provides supply chain managers with specific improvement plans, but also helps them better understand and optimize the operation process of the supply chain. This will help companies reduce costs and improve efficiency, thereby gaining greater competitive advantages in the fierce market competition.

[0078] In general, when executing supply chain business optimization, the collaborative optimization management system first obtains the pending supply chain business order log. The above log contains multiple business order task events, each of which records an activity or operation in the supply chain.

[0079] Next, the collaborative optimization management system uses the task event parsing network to conduct an in-depth analysis of the above logs. This process is mainly to parse out the key elements of each business order task event, such as the workflow data of each link and the corresponding feature description. The above data is converted into workflow distribution data and cluster description vectors by the system. Simply put, the workflow distribution data shows the position and importance of each collaborative link in the entire workflow, while the cluster description vector describes the characteristics of each link, which is convenient for subsequent link classification and operation.

[0080] With the above basic data, the collaborative optimization management system further classifies all the links to be coordinated according to the cluster description vector, that is, performs the collaborative link cluster operation. The system classifies the links with similar characteristics into the same cluster of links to be coordinated based on the similarities and differences between the vectors, so that similar business links can be managed and optimized more effectively.

[0081] Finally, the collaborative optimization management system optimizes the scheduling of each link in the collaborative link cluster based on the previously analyzed workflow distribution data. The system uses intelligent algorithms to analyze the dependencies and resource requirements between each link and proposes suggestions for task collaborative optimization scheduling. The above suggestions are intended to reduce conflicts between links, balance resource allocation, and improve the efficiency of the overall supply chain. Through such optimization, each business order task event can get a more reasonable resource allocation and processing order, thereby improving the flexibility and responsiveness of the entire supply chain management.

[0082] The embodiments of the present invention provide comprehensive optimization and intelligent improvement of supply chain management. First, by obtaining the pending supply chain business order logs, the embodiments of the present invention can fully grasp the various task events in the supply chain, providing a solid foundation for subsequent data analysis and optimization operations. The logs are deeply analyzed using the task event parsing network to accurately extract the key elements of the task events, including workflow distribution data and cluster description vectors. This step not only demonstrates the efficient data processing capabilities of the present invention, but also provides scientific data support for subsequent collaborative link clustering and optimized scheduling.

[0083] Furthermore, based on the extracted cluster description vector, the embodiment of the present invention can intelligently perform cluster operations on the collaborative links, and reasonably classify the collaborative links with similar characteristics or requirements, thereby helping enterprises to more clearly identify and manage different types of collaborative tasks. This intelligent clustering method not only improves the precision and pertinence of supply chain management, but also lays a solid foundation for subsequent optimization and scheduling.

[0084] Finally, by optimizing and scheduling the links in the collaborative link cluster according to the workflow distribution data, the embodiment of the present invention can formulate a more reasonable and efficient scheduling strategy based on the specific situation and needs of each link. This step fully demonstrates the excellent ability of the present invention in optimizing supply chain management, which not only helps to improve the overall operation efficiency and response speed of the supply chain, but also effectively reduces the operating costs of enterprises and enhances market competitiveness.

[0085] In summary, the embodiments of the present invention can achieve comprehensive optimization and intelligent improvement of supply chain management through accurate data analysis, intelligent collaborative link grouping and efficient optimization scheduling.

[0086] In some optional embodiments, the task event parsing network-based task event parsing of the pending supply chain business order log to obtain the workflow distribution data of the several links to be coordinated corresponding to the at least one business order task event and the cluster description vectors corresponding to the several links to be coordinated include: performing element mining on the pending supply chain business order log according to the task event parsing network to obtain the initial workflow distribution data of the initial coordination link corresponding to the several log text blocks of the pending supply chain business order log, the cluster description vectors of the several log text blocks and the initial weight coefficients of the several log text blocks, wherein the initial weight coefficients represent the possibility that the log text blocks include the links to be coordinated; determining from the several log text blocks several target log text blocks whose initial weight coefficients meet the set weight judgment index; determining the workflow distribution data of the several links to be coordinated and the cluster description vectors corresponding to the several links to be coordinated based on the initial workflow distribution data of the initial coordination link of the several target log text blocks and the cluster description vectors of the several target log text blocks.

[0087] In some optional embodiments of the present invention, the application of the task event parsing network is further refined. This network performs in-depth task event element parsing on the supply chain business order log to be processed. First, the task event parsing network performs comprehensive element mining on the supply chain business order log to be processed. This process is intended to identify and extract key information in the log, including but not limited to detailed data of the collaborative link. Through this step, the system can obtain the initial workflow distribution data of the initial collaborative link corresponding to each of the several log text blocks in the log, which reflects the position and role of each collaborative link in the supply chain process. At the same time, the system will also generate a cluster description vector for each log text block, which is a high-level summary of the content of the text block and is used for subsequent link clustering operations. In addition, each log text block will also be assigned an initial weight coefficient, which represents the possibility that the text block contains the link to be coordinated.

[0088] Next, the system selects several target log text blocks that meet the set weight discrimination index from the mined log text blocks. This step is to remove those text blocks with low weight coefficients and low probability, so as to ensure the accuracy and efficiency of subsequent processing. The set weight discrimination index can be adjusted according to actual needs to ensure that the selected target log text blocks are sufficiently representative and important.

[0089] Finally, based on the initial workflow distribution data and cluster description vector of the initial collaborative link of the filtered target log text block, the system can determine the workflow distribution data and corresponding cluster description vector of several links to be coordinated. This step is an integration and improvement of the previous mining and screening results. By comprehensively considering the information of each target log text block, more accurate and comprehensive data of the links to be coordinated are obtained.

[0090] This series of operation processes not only demonstrates the powerful ability of the present invention in data processing and analysis, but also provides a more accurate and reliable data basis for the subsequent collaborative link grouping and optimized scheduling. In this way, enterprises can more clearly understand and grasp the various collaborative links in the supply chain, providing strong support for optimizing supply chain management.

[0091] Through the embodiments of the present invention, the system can accurately parse the task event elements in the supply chain business order log, intelligently identify and extract key information, and provide solid data support for the subsequent collaborative link grouping and optimized scheduling. This not only improves the efficiency and accuracy of supply chain management, but also brings greater competitive advantages and market share to enterprises. At the same time, the flexibility and scalability of the present invention also enable it to adapt to the actual needs of different enterprises, providing strong technical support for promoting the digital transformation and upgrading of supply chain management.

[0092] In some optional embodiments, the collaborative link clustering operation is performed on the several links to be coordinated based on the cluster description vector to obtain the cluster of links to be coordinated corresponding to each business order task event in the at least one business order task event, including: for the two-tuples of links to be coordinated generated for the several links to be coordinated, obtaining the link description vector commonality score of the two-tuple of links to be coordinated based on the cluster description vector; and clustering the several links to be coordinated based on the link description vector commonality score to obtain the cluster of links to be coordinated corresponding to each business order task event.

[0093] In some optional embodiments, the system performs the following steps for performing collaborative link grouping operations.

[0094] First, the system generates a pair of links to be coordinated for several links to be coordinated. The "pair of links to be coordinated" in the embodiment of the present invention refers to a pair consisting of two links to be coordinated. In this way, the system can comprehensively consider the relationship between each link and provide a basis for subsequent group operations.

[0095] Next, the system obtains the link description vector commonality score of each link binary to be coordinated based on the cluster description vector. The commonality score reflects the similarity between the two links in terms of characteristics or requirements. The higher the score, the greater the similarity between the two links, and the more likely they are to be classified into the same collaborative link cluster.

[0096] After obtaining the commonality scores of the link description vectors of all the binary links to be coordinated, the system performs clustering operations based on these scores. Specifically, the system uses appropriate clustering algorithms, such as K-means, hierarchical clustering, etc., to classify binary links to be coordinated with high commonality scores into the same cluster, thereby obtaining a cluster of links to be coordinated corresponding to each business order task event.

[0097] This series of operation processes not only reflects the powerful capabilities of the present invention in data processing and cluster analysis, but also provides a more accurate and reliable data basis for subsequent optimization and scheduling. In this way, enterprises can more clearly understand and grasp the relationship and characteristics between various collaborative links in the supply chain, providing strong support for optimizing supply chain management.

[0098] In this way, the system can accurately cluster the collaborative links according to the cluster description vector, and obtain the cluster of links to be coordinated corresponding to each business order task event. This not only improves the precision and pertinence of supply chain management, but also brings greater operational efficiency and cost control capabilities to enterprises. At the same time, the flexibility and scalability of the present invention also enable it to adapt to the actual needs of different enterprises, and provide strong technical support for promoting the digital transformation and upgrading of supply chain management. Specifically, by accurately clustering the collaborative links, enterprises can allocate resources and optimize processes more efficiently, thereby improving the response speed and customer satisfaction of the overall supply chain. In addition, this clustering method also helps enterprises discover and solve bottleneck problems in the supply chain, further improving operational efficiency and reducing costs.

[0099] In some optional embodiments, optimizing and scheduling the links to be coordinated in the cluster of links to be coordinated based on the workflow distribution data to obtain task collaborative optimization scheduling suggestions corresponding to each business order task event include: determining the workflow update interval of the links to be coordinated in the cluster of links to be coordinated based on the workflow distribution data; and performing decision-making optimization scheduling of the workflow distribution data on each link to be coordinated in the cluster of links to be coordinated based on a decision tree network on the basis that the workflow update interval is greater than the set interval to obtain task collaborative optimization scheduling suggestions for the business order task events corresponding to the cluster of links to be coordinated.

[0100] In some optional embodiments, the process of optimizing the scheduling of the to-be-coordinated links in the to-be-coordinated link cluster by the system is as follows.

[0101] First, the system determines the workflow update interval of each link to be coordinated in the cluster of links to be coordinated based on the workflow distribution data. The "workflow update interval" can be understood as the adjustable range of the link in the workflow, which reflects the flexibility and optimization space of the link in the workflow. By analyzing the workflow distribution data, the system can accurately grasp the workload, processing time and dependency relationship of each link, so as to define a reasonable workflow update interval for it.

[0102] Next, the system determines whether the interval of these workflow updates is greater than the set interval. The set interval is a preset threshold used to measure whether the amplitude of the workflow update is large enough to determine whether it is worth optimizing the scheduling. Only when the workflow update interval is greater than the set interval, the system will consider it necessary to optimize the scheduling.

[0103] On the basis of satisfying that the workflow update interval is greater than the set interval, the system performs decision optimization scheduling of workflow distribution data for each collaborative link in the collaborative link cluster based on the decision tree network. The decision tree network is an effective decision-making tool that can display various situations and results that may be encountered in the decision-making process through a tree diagram and help the system select the optimal decision path. Here, the system uses the decision tree network to simulate and optimize the workflow distribution of each link to achieve the goal of improving overall work efficiency and reducing resource waste.

[0104] Finally, through this series of optimization and scheduling operations, the system can obtain task coordination optimization scheduling suggestions for the business order task events corresponding to the coordinated link cluster. These suggestions are tailored to the specific conditions and needs of each link, aiming to improve the overall operational efficiency and response speed of the supply chain.

[0105] This series of operation processes not only demonstrates the powerful capabilities of the present invention in data processing and optimization decision-making, but also provides more accurate and efficient guidance and suggestions for subsequent supply chain management. In this way, enterprises can more clearly understand and grasp the working status and optimization space of each link in the supply chain, providing strong support for improving supply chain performance.

[0106] Through the embodiments of the present invention, the system can optimize the scheduling of the collaborative links according to the workflow distribution data, and obtain the task collaborative optimization scheduling suggestions corresponding to each business order task event. This not only helps to improve the overall operational efficiency and response speed of the supply chain, but also effectively reduces the operating costs of the enterprise and enhances market competitiveness. At the same time, the flexibility and scalability of the present invention also enable it to adapt to the actual needs of different enterprises, providing strong technical support for promoting the digital transformation and upgrading of supply chain management.

[0107] In some optional embodiments, the method also includes: on the basis that the workflow update interval is less than or equal to the set interval, determining the target key link of the cluster of links to be coordinated according to the workflow distribution data; determining a single link from each link to be coordinated in the cluster of links to be coordinated according to the workflow distribution data; and generating task collaborative optimization scheduling suggestions for the business order task events corresponding to the cluster of links to be coordinated based on the target key link and the single link.

[0108] In some optional embodiments, when the workflow update interval is less than or equal to the set interval, the system adopts another strategy to generate task collaborative optimization scheduling suggestions.

[0109] First, the system determines the target key links in the cluster of links to be coordinated based on the workflow distribution data. The "target key links" in the embodiment of the present invention refer to the links that play a key role in the entire workflow and have an important impact on the overall work efficiency. By analyzing the workflow distribution data, the system can identify which links have a longer processing time, occupy more resources, or have a greater impact on subsequent links, thereby determining these links as target key links.

[0110] Next, the system determines the individual links from the various links to be coordinated in the cluster of links to be coordinated based on the workflow distribution data. Individual links refer to those links that are relatively independent, have less dependence on other links, and can be optimized and scheduled separately. By determining the individual links, the system can optimize and schedule them more accurately to improve overall work efficiency.

[0111] After determining the target key links and individual links, the system combines the information of the two to generate task coordination optimization scheduling suggestions for the business order task events corresponding to the coordinated link cluster. These suggestions will focus on the optimization of the target key links and the efficient scheduling of individual links, aiming to improve the stability and efficiency of the overall workflow.

[0112] For example, in a supply chain scenario, if the raw material procurement of a certain link is a key link, because it directly affects the efficiency of the subsequent production links. At the same time, the packaging link is identified as a single link because it is relatively independent and can be flexibly adjusted. The system may recommend strengthening supplier management in the raw material procurement link to improve procurement efficiency; while in the packaging link, it can be flexibly scheduled according to the production plan and actual needs to achieve the optimal allocation of resources.

[0113] In this way, the system can still generate effective task collaborative optimization scheduling suggestions when the workflow update interval is small, helping enterprises improve the precision and efficiency of supply chain management. It can be seen that when the workflow update interval is less than or equal to the set interval, the system can still generate effective task collaborative optimization scheduling suggestions by determining the target key links and single links. This not only reflects the flexibility of the present invention in data processing and optimization decision-making, but also provides enterprises with a more comprehensive and accurate supply chain management solution. By implementing these suggestions, enterprises can further improve work efficiency, reduce costs and enhance market competitiveness.

[0114] In some optional embodiments, the method further includes: obtaining a supply chain business order log sample including at least one business order task event, a priori workflow distribution data of each of several to-be-coordinated links corresponding to the business order task event, and a priori event topics of each of the several to-be-coordinated links, wherein the priori event topics represent the business order task event to which the to-be-coordinated links belong; inputting the supply chain business order log sample into the initial parsing network for element mining to obtain the initial workflow distribution data of the initial collaborative links of several log text blocks of the supply chain business order log sample, the cluster description vectors of each of the several log text blocks, and the initial weight coefficients of each of the several log text blocks, wherein the initial weight coefficient represents the possibility that the log text block includes the to-be-coordinated link; debugging the initial parsing network based on the initial workflow distribution data, the initial weight coefficient, the cluster description vector, the prior workflow distribution data, and the prior event topics to obtain a task event parsing network.

[0115] In some optional embodiments, the method performed by the system includes the following steps.

[0116] First, the system obtains supply chain business order log samples, which contain at least one business order task event. At the same time, the system also obtains the prior workflow distribution data and prior event topics of several to-be-coordinated links corresponding to these business order task events. The "prior workflow distribution data" here refers to the distribution of links in the workflow based on historical data or experience, while the "prior event topic" refers to the topic or type of the business order task event to which the to-be-coordinated link belongs.

[0117] Next, the system inputs the supply chain business order log sample into the initial parsing network for feature mining. In this process, the system uses the initial parsing network to conduct in-depth analysis of the log sample and extract key information. Specifically, the system obtains the initial workflow distribution data, cluster description vectors, and initial weight coefficients of the initial collaborative links of several log text blocks of the supply chain business order log sample. The "initial weight coefficient" here is an important indicator, which characterizes the possibility that the log text block includes the link to be coordinated. In other words, the larger the initial weight coefficient, the higher the possibility that the log text block contains the link to be coordinated.

[0118] After obtaining these key information, the system debugs the initial parsing network based on the initial workflow distribution data, initial weight coefficients, cluster description vectors, prior workflow distribution data, and prior event topics. In this process, the system continuously adjusts and optimizes the parameters and structure of the initial parsing network to better adapt to and parse the data in the supply chain business order log sample.

[0119] Finally, through repeated debugging and optimization, the system obtained the task event parsing network. The task event parsing network is a carefully trained and optimized neural network model that can accurately parse and identify key information in the supply chain business order log sample, providing strong support for the subsequent collaborative link grouping and optimized scheduling.

[0120] By implementing this method, the system can accurately parse the supply chain business order log sample, extract key information, and obtain the optimized task event parsing network. This not only improves the intelligence level of supply chain management, but also provides enterprises with more accurate and efficient decision support. At the same time, the flexibility and scalability of this method also enable it to adapt to the actual needs and scenarios of different enterprises, providing strong technical support for promoting the digital transformation and upgrading of supply chain management. It can be seen that by obtaining supply chain business order log samples and related prior data, using the initial parsing network for factor mining, and debugging and optimizing the initial parsing network based on the mining results and prior data, the task event parsing network is finally obtained. This process not only improves the intelligence and automation level of supply chain management, but also brings greater operational efficiency and cost control capabilities to enterprises.

[0121] In some optional embodiments, debugging the initial parsing network according to the initial workflow distribution data, the initial weight coefficient, the clique description vector, the prior workflow distribution data and the prior event topic to obtain the task event parsing network includes: determining a first debugging error according to the initial workflow distribution data and the prior workflow distribution data; determining the prior weight coefficients of each of the plurality of log text blocks based on the prior workflow distribution data; determining a second debugging error according to the initial weight coefficient and the prior weight coefficient; determining a third debugging error according to the prior workflow distribution data, the prior event topic and the clique description vector; improving the network configuration hyper-parameters of the initial parsing network based on the first debugging error, the second debugging error and the third debugging error, and performing cyclic debugging according to the improved network configuration hyper-parameters until set debugging termination requirements are met; and determining the initial parsing network that meets the set debugging termination requirements as the task event parsing network.

[0122] In some optional embodiments, the process of the system debugging the initial parsing network to obtain the task event parsing network is as follows.

[0123] First, the system determines the first debugging error based on the initial workflow distribution data and the prior workflow distribution data. The first debugging error reflects the difference between the initial workflow distribution data and the prior workflow distribution data, that is, it measures the accuracy of the initial parsing network in extracting the workflow distribution data. If the initial workflow distribution data differs greatly from the prior workflow distribution data, then the first debugging error will be relatively large, indicating that the performance of the initial parsing network in this regard needs to be improved.

[0124] Next, the system determines the prior weight coefficients of several log text blocks based on the prior workflow distribution data. The prior weight coefficients are derived from historical data or experience, and they reflect the possibility that the log text block contains the link to be coordinated. This step is to compare with the initial weight coefficients later to further evaluate the performance of the initial parsing network.

[0125] Then, the system determines the second debugging error based on the initial weight coefficient and the prior weight coefficient. The second debugging error measures the difference between the initial weight coefficient and the prior weight coefficient, that is, it reflects the accuracy of the initial parsing network in identifying the possibility that the log text block contains the link to be coordinated. If the initial weight coefficient differs greatly from the prior weight coefficient, then the second debugging error will be relatively large, indicating that the performance of the initial parsing network in this regard needs to be improved.

[0126] In addition, the system will determine the third debugging error based on the prior workflow distribution data, prior event topics, and cluster description vectors. The third debugging error reflects the degree of match between the cluster description vector and the prior data, that is, it measures the ability of the initial parsing network to extract and describe the business order task event topics. If the cluster description vector is significantly different from the prior data, the third debugging error will be relatively large, indicating that the performance of the initial parsing network in this regard needs to be improved.

[0127] After determining the first debugging error, the second debugging error, and the third debugging error, the system improves the network configuration hyperparameters of the initial parsing network based on these errors. In this process, the system continuously adjusts and optimizes the network configuration hyperparameters to reduce the debugging error and improve the performance of the initial parsing network. This process is repeated until the set debugging termination requirements are met.

[0128] Finally, when the debugging process meets the set debugging termination requirements, the system determines the initial parsing network at this time as the task event parsing network. The task event parsing network is a carefully debugged and optimized neural network model that can accurately parse and identify key information in the supply chain business order log sample, providing strong support for subsequent collaborative link grouping and optimized scheduling.

[0129] By implementing this method, the system can obtain a high-performance task event parsing network that can accurately parse and identify key information in the supply chain business order log sample. This not only improves the level of intelligence in supply chain management, but also provides enterprises with more accurate and efficient decision support. At the same time, the flexibility and scalability of this method also enable it to adapt to the actual needs and scenarios of different enterprises, providing strong technical support for promoting the digital transformation and upgrading of supply chain management. It can be seen that by determining multiple debugging errors and improving and optimizing the initial parsing network based on these errors, the task event parsing network is finally obtained. This process not only improves the performance of the initial parsing network, but also provides more accurate and efficient support for subsequent business order task event parsing and collaborative link optimization.

[0130] In some optional embodiments, determining the third debugging error based on the prior workflow distribution data, the prior event subject and the cluster description vector includes: determining a plurality of target log text blocks from the plurality of log text blocks based on the prior workflow distribution data, the target log text blocks including the link to be coordinated; summarizing the plurality of target log text blocks based on the prior event subject to obtain a log text block set corresponding to each business order task event in the at least one business order task event; determining a self-debugging error corresponding to each log text block set and a mutual debugging error between different log text block sets based on the cluster description vector; and determining the third debugging error based on the self-debugging error and the mutual debugging error.

[0131] In some optional embodiments, the process of the system determining the third debugging error includes the following steps.

[0132] First, the system selects target log text blocks from several log text blocks based on prior workflow distribution data. These target log text blocks are text blocks containing the links to be coordinated, that is, they are text information closely related to the links that need to be coordinated in the business order task event.

[0133] Next, the system uses the prior event topics to summarize and classify the selected target log text blocks. In this process, the system groups the relevant target log text blocks according to the event topics to form different log text block sets. Each log text block set corresponds to a specific business order task event, so that different task events can be clearly identified and distinguished.

[0134] Then, the system determines the self-debugging error of each log text block set and the mutual debugging error between different log text block sets based on the cluster description vector. The self-debugging error reflects the consistency of the cluster description vector in describing the text blocks within the same log text block set, that is, it measures whether the cluster description vector describes each text block within the same event accurately and consistently. The mutual debugging error measures the differences in descriptions between different events (i.e., different log text block sets) to ensure that the cluster description vector can accurately distinguish different business order task events.

[0135] Finally, the system combines the self-tuning error and the mutual-tuning error to determine the third tuning error. The third tuning error is actually a comprehensive indicator that considers both the description accuracy of the cluster description vector within the same event and the ability to distinguish between different events.

[0136] Through this process, the system can more comprehensively evaluate the performance of the cluster description vector, and then guide the debugging and optimization of the initial parsing network. This not only improves the accuracy of task event parsing, but also provides more accurate data support for the subsequent optimization of collaborative links.

[0137] It can be seen that the third debugging error is determined by determining the target log text block, summarizing and classifying it, calculating the self-debugging error and the mutual debugging error. This process helps to improve the accuracy of task event analysis and the effect of collaborative link optimization, and further enhances the intelligence and refinement of supply chain management.

[0138] In some optional embodiments, determining the self-debugging error corresponding to each log text block set and the mutual-debugging error between different log text block sets based on the cluster description vector includes: determining the cluster representative vector in each log text block set based on the cluster description vector; determining the cumulative vector difference between the cluster description vector of each log text block in each log text block set and the cluster representative vector to obtain the self-debugging error corresponding to each log text block set; for the log text block set tuple generated for the log text block set corresponding to the at least one business order task event, determining the interactive vector difference of the log text block set tuple based on the cluster representative vector to obtain the mutual-debugging error between the different log text block sets.

[0139] In some optional embodiments, the detailed process of the system determining the self-debugging error corresponding to each log text block set and the mutual-debugging error between different log text block sets is as follows.

[0140] First, for each log text block set, the system determines a cluster representative vector based on the cluster description vector. The cluster representative vector can be regarded as an abstract representation of the common features or core information of all text blocks in the log text block set. It helps to capture and summarize the common characteristics of the text blocks in the set.

[0141] Next, the system calculates the difference between the cluster description vector of each text block in each log text block set and the representative vector of the cluster. The difference is measured by calculating the distance or similarity between vectors, such as cosine similarity. The system accumulates these differences to obtain the self-tuning error corresponding to each log text block set. The self-tuning error reflects the consistency of the cluster description vector in describing the text blocks within the same log text block set. The smaller the error, the more accurate the description of the log text block set by the cluster description vector.

[0142] Then, the system determines the difference of interaction vectors based on the cluster representative vector for the log text block set binary generated by the log text block set corresponding to at least one business order task event. Specifically, the system selects different log text block set binary tuples and compares the differences between their cluster representative vectors. This difference reflects the distinction between different log text block sets, that is, the differences between the different business order task events they represent.

[0143] Finally, the system calculates and accumulates the differences in these interaction vectors to obtain the mutual debugging error between different log text block sets. The mutual debugging error measures the performance of the cluster description vector in distinguishing different business order task events. The smaller the error, the more effective the cluster description vector is in distinguishing different task events.

[0144] This helps the system to more comprehensively evaluate the performance of the cluster description vector, ensuring that it can accurately describe the text blocks within the same log text block set and clearly distinguish different log text block sets. In this way, the system can more effectively perform subsequent collaborative link optimization and supply chain management. Therefore, by determining the representative vector of the cluster, calculating the self-debugging error and the mutual debugging error, a method for accurately evaluating the performance of the cluster description vector is provided. This not only improves the accuracy of task event parsing, but also provides a more solid data foundation for the optimization of collaborative links. Throughout the process, the intelligence and automation level of the system has been significantly improved, bringing greater flexibility and efficiency to supply chain management.

[0145] An embodiment of the present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, the supply chain department collaborative optimization management method is implemented.

[0146] An embodiment of the present invention provides a processor, which is used to run a program, wherein the supply chain department collaborative optimization management method is executed when the program is running.

[0147] In the embodiment of the present invention, Figure 2 As shown, the collaborative optimization management system 100 includes at least one processor 101, and at least one memory 102 and a bus 103 connected to the processor 101; wherein the processor 101 and the memory 102 communicate with each other through the bus 103; the processor 101 is used to call the program instructions in the memory 102 to execute the above-mentioned collaborative optimization management method of the supply chain department.

[0148] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, collaborative optimization management systems (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0149] In a typical configuration, the collaborative optimization management system includes one or more processors (CPU), memory and bus. The collaborative optimization management system may also include input / output interface, network interface and the like.

[0150] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.

[0151] Computer readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage computer readable storage media or any other non-transmission media that can be used to store information that can be accessed by the collaborative optimization management system. As defined in this article, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0152] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or computer-readable storage medium that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such process, method, commodity or computer-readable storage medium. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the presence of other identical elements in the process, method, commodity or computer-readable storage medium that includes the elements.

[0153] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0154] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A collaborative optimization management method for supply chain departments, characterized in that: Applied to a collaborative optimization management system, the method comprises: Obtaining a pending supply chain business order log, wherein the pending supply chain business order log includes at least one business order task event; Based on the task event parsing network, the task event elements of the to-be-processed supply chain business order log are parsed to obtain the workflow distribution data of the respective to-be-coordinated links corresponding to the at least one business order task event and the cluster description vectors corresponding to the respective to-be-coordinated links; Performing a coordination link clustering operation on the plurality of to-be-coordinated links according to the clustering description vector to obtain a to-be-coordinated link cluster corresponding to each business order task event in the at least one business order task event; Optimizing and scheduling the to-be-coordinated links in the to-be-coordinated link cluster according to the workflow distribution data, and obtaining task collaborative optimization scheduling suggestions corresponding to each business order task event; The task event parsing network based on the task event parsing performs task event element parsing on the pending supply chain business order log to obtain the workflow distribution data of the plurality of to-be-coordinated links corresponding to the at least one business order task event and the cluster description vectors corresponding to the plurality of to-be-coordinated links respectively, including: Performing element mining on the pending supply chain business order log according to the task event parsing network, obtaining initial workflow distribution data of initial collaborative links corresponding to each of several log text blocks of the pending supply chain business order log, respective cluster description vectors of the several log text blocks, and respective initial weight coefficients of the several log text blocks, wherein the initial weight coefficient represents the possibility that the log text block includes the pending collaborative link; Determining from the plurality of log text blocks a plurality of target log text blocks whose initial weight coefficients satisfy a set weight determination index; Based on the initial workflow distribution data of the initial coordination links of the target log text blocks and the cluster description vectors of the target log text blocks, the workflow distribution data of each of the links to be coordinated and the cluster description vectors corresponding to each of the links to be coordinated are determined.

2. The method according to claim 1, characterized in that The step of performing a collaborative link clustering operation on the plurality of links to be coordinated according to the cluster description vector to obtain a cluster of links to be coordinated corresponding to each business order task event in the at least one business order task event comprises: For the to-be-coordinated link binary groups generated by the plurality of to-be-coordinated links, obtaining the link description vector commonality score of the to-be-coordinated link binary groups according to the cluster description vectors; The plurality of links to be coordinated are grouped based on the commonality scores of the link description vectors to obtain a cluster of links to be coordinated corresponding to each business order task event.

3. The method according to claim 1, characterized in that The optimizing and scheduling the to-be-coordinated links in the to-be-coordinated link cluster according to the workflow distribution data to obtain the task collaborative optimization scheduling suggestion corresponding to each business order task event includes: Determine the workflow update interval of the link to be coordinated in the cluster of links to be coordinated according to the workflow distribution data; On the basis that the workflow update interval is greater than the set interval, decision optimization scheduling of workflow distribution data is performed on each link to be coordinated in the cluster of links to be coordinated based on a decision tree network to obtain task collaborative optimization scheduling suggestions for the business order task events corresponding to the cluster of links to be coordinated.

4. The method according to claim 3, characterized in that The method further comprises: On the basis that the workflow update interval is less than or equal to the set interval, determining the target key link of the to-be-coordinated link cluster according to the workflow distribution data; Determining a single link from each link to be coordinated in the link cluster to be coordinated according to the workflow distribution data; Based on the target key link and the single link, a task collaborative optimization scheduling suggestion for the business order task event corresponding to the to-be-coordinated link cluster is generated.

5. The method according to claim 1, characterized in that The method comprises: Acquire a supply chain business order log sample including at least one business order task event, a priori workflow distribution data of a plurality of to-be-coordinated links corresponding to the business order task event, and a priori event subject of each of the plurality of to-be-coordinated links, wherein the a priori event subject represents the business order task event to which the to-be-coordinated link belongs; Inputting the supply chain business order log sample into the initial parsing network for element mining, obtaining initial workflow distribution data of initial collaborative links of several log text blocks of the supply chain business order log sample, cluster description vectors of the several log text blocks, and initial weight coefficients of the several log text blocks, wherein the initial weight coefficients represent the possibility that the log text block includes the link to be coordinated; The initial parsing network is debugged according to the initial workflow distribution data, the initial weight coefficient, the cluster description vector, the prior workflow distribution data and the prior event theme to obtain a task event parsing network.

6. The method according to claim 5, characterized in that The debugging of the initial parsing network according to the initial workflow distribution data, the initial weight coefficient, the cluster description vector, the prior workflow distribution data and the prior event theme to obtain the task event parsing network comprises: Determining a first debugging error according to the initial workflow distribution data and the priori workflow distribution data; Determining a priori weight coefficients of each of the plurality of log text blocks based on the a priori workflow distribution data; Determining a second debugging error according to the initial weight coefficient and the priori weight coefficient; determining a third debugging error according to the priori workflow distribution data, the priori event topic and the cluster description vector; Improve the network configuration hyper-parameters of the initial analytical network based on the first debugging error, the second debugging error, and the third debugging error, and perform cyclic debugging according to the improved network configuration hyper-parameters until set debugging termination requirements are met; An initial parsing network that meets the set debugging termination requirement is determined as the task event parsing network.

7. The method according to claim 6, characterized in that The determining of the third debugging error according to the priori workflow distribution data, the priori event topic and the cluster description vector comprises: Determining a plurality of target log text blocks from the plurality of log text blocks based on the prior workflow distribution data, wherein the target log text blocks include the link to be coordinated; Summarizing the plurality of target log text blocks based on the prior event theme to obtain a log text block set corresponding to each business order task event in the at least one business order task event; Determining a self-debugging error corresponding to each log text block set and a mutual-debugging error between different log text block sets according to the cluster description vector; The third debugging error is determined based on the self-debugging error and the mutual debugging error.

8. The method according to claim 7, characterized in that Determining the self-debugging error corresponding to each log text block set and the mutual-debugging error between different log text block sets according to the cluster description vector comprises: Determining a cluster representative vector in each log text block set according to the cluster description vector; Determine the cumulative vector difference between the cluster description vector of each log text block in each log text block set and the cluster representative vector to obtain a self-debugging error corresponding to each log text block set; For the log text block set tuples generated by the log text block set corresponding to the at least one business order task event, the interaction vector differences of the log text block set tuples are determined based on the cluster representative vector to obtain the mutual debugging errors between the different log text block sets.

9. A collaborative optimization management system, characterized in that: It includes a processor and a memory and a bus connected to the processor; wherein the processor and the memory communicate with each other through the bus; the processor is used to call the program instructions in the memory to execute the supply chain department collaborative optimization management method described in any one of claims 1-8.

Images