Intelligent order coordination management system for supply chain sales data

Abstract

The present application relates to the technical field of intelligent order collaborative management. The present application relates to a supply chain sales data intelligent order collaborative management system. It comprises a collaborative data warehouse construction module, a site network establishment module, a candidate order generation module, a risk correction module and a logistics performance module; the collaborative data warehouse construction module is used for collecting multi-source business data of the whole link of the supply chain, standardizing and preprocessing the data, synchronizing the time and associating the index to form sales collaborative raw data, and then generating an encryption key based on the data characteristics to perform lightweight encryption on the raw data; through the collaborative data warehouse construction module, the multi-source business data of the whole link of the supply chain is standardized and preprocessed, the time is synchronized and the index is associated, and a storage mode combining dynamic encryption, hash verification and on-chain and off-chain is adopted to construct a safe and traceable sales collaborative data warehouse, thereby fundamentally eliminating the problems of multi-source data heterogeneity, different standards, security deficiencies and difficulty in tracing.

Description

Technical Field

[0001] This invention relates to the field of intelligent order collaborative management technology, and more specifically, to an intelligent order collaborative management system for supply chain sales data. Background Technology

[0002] Supply chain sales collaboration management is a core component of intelligent supply chain operations. Related order collaboration management technologies are mainly used to integrate business data from all aspects of sales, warehousing, supply, and logistics to achieve order generation, fulfillment scheduling, and multi-party collaborative control. The aim is to improve the accuracy of supply chain supply and demand matching, reduce operating costs, and ensure efficient and stable order fulfillment. It plays an important role in promoting the digital operation of enterprise supply chains and improving the collaborative efficiency of the industrial chain.

[0003] Existing supply chain order collaborative management technologies are mostly applied to control scenarios of single sites or partial business links within enterprises. They generally rely on static historical data statistics and fixed threshold judgments to carry out business decisions. The collaborative entities are limited to internal sales sites and warehousing sites. External supply collaborative sites and logistics collaborative sites only participate in basic information exchange. Various business data are stored in separate independent systems. Order demand analysis, order generation, collaborative verification, risk control and logistics fulfillment are executed in segments and independently.

[0004] In the aforementioned decentralized and static application scenarios, existing technologies have significant shortcomings: multi-source heterogeneous business data lacks a unified standardized governance and secure and reliable storage mechanism; collaborative sites have not established a hierarchical and division-of-labor collaborative mechanism; sales demand analysis relies on static rules, resulting in insufficient prediction accuracy; order collaborative verification lacks efficient collaboration based on roles; risk control can only be handled after the fact and cannot be predicted in advance; and logistics fulfillment cannot achieve dynamic path planning. These problems directly lead to distorted supply chain supply and demand matching, low efficiency of multi-party collaboration, frequent omissions in order risk assessment, and delays in fulfillment and delivery, making it difficult to support the collaborative needs of an integrated internal and external network supply chain. To mitigate these issues, an intelligent order collaborative management system for supply chain sales data is proposed. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent order collaborative management system for supply chain sales data to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, a supply chain sales data intelligent order collaborative management system is provided, including a collaborative data warehouse construction module, a site network establishment module, a candidate order generation module, a risk correction module, and a logistics fulfillment module;

[0007] The collaborative data warehouse construction module is used to collect multi-source business data from all aspects of the supply chain, perform standardized preprocessing, time synchronization and index association on the data to form sales collaborative raw data, generate encryption keys based on data characteristics to perform lightweight encryption on the raw data, complete data notarization through hash verification, and construct the sales collaborative data warehouse by using on-chain ledger to store verification parameters and off-chain node sharding to store encrypted data. The site network establishment module is used to send collaboration requests to candidate collaboration sites from the original sales site. The candidate collaboration sites complete the compatibility determination and establish collaboration connections through the cooperation evaluation model. Then, the collaboration sites are divided into levels according to the authorization results to form a hierarchical collaboration site network. The candidate order generation module is used to extract multi-dimensional sales features from the sales collaboration data warehouse and construct a quantified sales feature vector. It then performs dynamic weight calculation on the feature vector in combination with the current business scenario to obtain multi-dimensional sales demand analysis results. Finally, it integrates the real-time supply capacity of the supply chain and the risk correction coefficient to calculate the supply and demand gap, and generates a candidate order set covering multiple business types based on the gap. The risk correction module is used to send candidate orders to a hierarchical collaborative site network. The collaborative sites at different levels complete the collaborative verification of the orders and determine the target orders by assigning roles. The module extracts the behavior data of the entire order process to construct a time-series behavior sequence. The module generates a collaborative party behavior profile through time-series segmentation, identifies the associated collaborative parties and the risk transmission sequence, and predicts the risk triggering nodes. Based on this, the module generates risk control instructions to correct the target orders and obtain the risk-corrected order results. The logistics fulfillment module is used to build a logistics digital twin model based on all logistics scenario elements, dynamically plan the fulfillment path of risk-corrected orders, perform real-time rerouting during transportation, and finally write back the entire process results of order execution, logistics fulfillment, settlement and risk handling to the sales collaboration data warehouse.

[0008] As a further improvement to this technical solution, the collaborative data warehouse construction module collects multi-source business data from all stages of the supply chain, performs standardized preprocessing, time synchronization, and index association processing on the multi-source heterogeneous data in sequence to obtain well-organized and associated sales collaborative raw data; then, based on the characteristics of the sales collaborative raw data, an encryption key is generated to complete lightweight encryption, hash verification is performed on the encrypted data to obtain the verification value, the verification parameters are written into the on-chain ledger for evidence storage, and the encrypted data is sharded and stored in off-chain nodes to build a secure and traceable sales collaborative data warehouse.

[0009] As a further improvement to this technical solution, the collaborative data warehouse construction module extracts data tags from the original sales collaboration data, generates a dynamic derived key based on the data tags, and performs lightweight encryption on the original data; calculates the main hash value for the encrypted overall data and the segmented secondary hash value for the segmented data; writes the main hash value, the segmented secondary hash value, and the key derivation parameters into the on-chain ledger to complete tamper-proof storage, and stores the encrypted data in fragments on off-chain nodes to form a secure and traceable sales collaboration data warehouse.

[0010] As a further improvement to this technical solution, in the above-mentioned site network establishment module, the internal sales site of the enterprise that initiates the sales business acts as the initiator and sends a collaboration invitation to the warehousing site, supply collaboration site and logistics collaboration site with collaboration potential in the supply chain network. The site identifier carried in the collaboration request is used to uniquely distinguish each collaboration participant. The cooperation evaluation model assesses the feasibility of cooperation based on parameters such as the candidate collaborative sites' historical collaborative performance, business capability matching degree, and credit rating, and determines whether to establish a collaborative relationship. After establishing a collaborative connection, the collaborative sites are divided into direct-connection collaborative sites that can directly participate in order business, non-direct-connection collaborative sites that only provide feedback on business capabilities, and feedback collaborative sites that only provide feedback on the feasibility of order execution, forming a hierarchical collaborative site network with clear levels and division of labor.

[0011] As a further improvement to this technical solution, the candidate order generation module extracts business features that reflect the sales business status from the securely stored sales collaboration data warehouse. Business characteristics include sales volume characteristics, sales frequency characteristics, regional fluctuation characteristics, customer level characteristics, promotion intensity characteristics, inventory turnover characteristics, return deviation characteristics, delivery timeliness characteristics, and settlement cycle characteristics. After quantifying various characteristics, they are integrated into a standardized sales characteristic vector. Dynamic weights are assigned to each sales feature based on the current actual business scenario. Adaptive weight values ​​are assigned to each feature in the sales feature vector. Through weighted calculation, short-cycle sales demand, inventory replenishment demand, and abnormal sales fluctuation demand are accurately analyzed. The sales demand analysis results, which include short-cycle sales demand, replenishment demand, and abnormal fluctuation demand, are obtained through calculation.

[0012] As a further improvement to this technical solution, the candidate order generation module obtains the real-time supply capacity of the supply chain and sets a risk correction coefficient based on the internal and external risk levels of the supply chain, historical performance fluctuations, and market supply and demand trends. The real-time supply capacity is weighted and calibrated with the risk correction coefficient to obtain the calibrated effective supply capacity. The difference between the sales demand analysis results and the effective supply capacity is calculated to obtain the supply-demand gap. Based on the value and type of the supply-demand gap and the supply-demand matching relationship, a set of candidate orders that matches the gap is generated.

[0013] As a further improvement to this technical solution, the risk correction module distributes the candidate order set to the hierarchical collaborative site network, where directly connected collaborative sites directly participate in order scheduling verification, non-directly connected collaborative sites provide feedback on business capability correction information, and feedback collaborative sites provide feedback on order executability results. Integrate the verification and feedback information from the three types of collaborative sites to complete collaborative order verification and generate the target order; By extracting the behavioral data of the entire order process, the behavioral data is constructed in chronological order to obtain a time-series behavioral sequence; A recursive partitioning time window is used to perform time-series segmentation on the time-series behavior sequence, and the segmented periodic indicators and mutation indicators are extracted. Based on the indicators, a collaborative behavior profile representing the collaborative party's performance characteristics is generated.

[0014] As a further improvement to this technical solution, the risk correction module identifies associated collaborators by calculating the phase overlap of their behavioral trajectories and sorts them according to the intensity of their synchronous changes to form a risk transmission order. Based on the evolution of collaborative party behavior profiles and the risk transmission sequence, risk triggering nodes are predicted, risk control instructions are generated to modify target orders, and risk-corrected order results are obtained.

[0015] As a further improvement to this technical solution, the logistics fulfillment module constructs a logistics digital twin model through all logistics scenario elements. Based on the model, dynamic planning is performed on the fulfillment path of risk-corrected orders to obtain the target delivery path, and rerouting is performed based on the real-time logistics status during transportation. The entire process of order execution, logistics fulfillment, settlement and risk handling is written back to the sales collaboration data warehouse, and the sales demand analysis model, cooperation evaluation model and behavior profile model are iteratively updated to form a sales data-driven intelligent order collaboration closed loop.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. In this intelligent order collaborative management system for supply chain sales data, a collaborative data warehouse construction module is used to standardize, preprocess, synchronize, and index multi-source business data across the entire supply chain. Dynamic encryption, hash verification, and a combination of on-chain and off-chain storage methods are employed to build a secure and traceable sales collaborative data warehouse. This eliminates the problems of heterogeneous multi-source data, inconsistent definitions, insufficient security, and difficulty in traceability at the source, providing a unified, reliable, and trustworthy data foundation for end-to-end order collaboration and ensuring the accuracy of data for subsequent analysis and decision-making.

[0017] 2. In this intelligent order collaborative management system for supply chain sales data, the system achieves role-based and permission-based management of collaborative entities through a hierarchical collaborative site network. It generates suitable candidate orders by combining dynamic analysis of multi-dimensional sales characteristics and accurate calculation of supply and demand gaps. Furthermore, it completes intelligent order correction by relying on order behavior profiling, identification of related collaborative parties, and prediction of risk transmission order. This significantly improves the accuracy of sales demand analysis, the efficiency of order collaborative verification, and the ability to prevent and control risks. It achieves precise control over the entire process of order generation and execution, effectively reducing the probability of order misjudgment, performance anomalies, and risk omissions.

[0018] 3. In this intelligent order collaborative management system for supply chain sales data, the fulfillment path is dynamically planned and the transportation process is rerouted in real time through a logistics digital twin model, ensuring the timeliness of order delivery and the stability of logistics. At the same time, the results of order execution, logistics fulfillment, settlement and risk handling are written back to the data warehouse and the relevant models are iteratively updated to form an intelligent order collaboration closed loop driven by sales data. This enables the system to continuously optimize its demand analysis, cooperation evaluation and behavior recognition capabilities during continuous operation, and comprehensively improve the overall collaborative response speed and long-term operational stability of the supply chain. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating the intelligent order collaborative management system for supply chain sales data according to the present invention. Figure 2 This is a flowchart illustrating the collaborative data warehouse construction module of the present invention; Figure 3 A flowchart illustrating the site network establishment module of this invention; Figure 4 This is a flowchart illustrating the candidate order generation module of the present invention; Figure 5 This is a flowchart illustrating the risk correction module of the present invention; Figure 6 This is a flowchart illustrating the logistics fulfillment module of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] Please see Figures 1-6 As shown, the purpose of this embodiment is to provide a supply chain sales data intelligent order collaborative management system, including a collaborative data warehouse construction module, a site network establishment module, a candidate order generation module, a risk correction module, and a logistics fulfillment module; The collaborative data warehouse construction module is used to collect multi-source business data from all aspects of the supply chain, standardize and preprocess the data, synchronize the time and associate the index to form sales collaborative raw data, generate encryption keys based on data characteristics to perform lightweight encryption on the raw data, complete data storage through hash verification, and build the sales collaborative data warehouse by using on-chain ledger to store verification parameters and off-chain node sharding to store encrypted data. In the collaborative data warehouse construction module, multi-source business data from all stages of the supply chain are collected. The heterogeneous data from multiple sources are then subjected to standardized preprocessing, time synchronization, and index association processing to obtain well-organized and associated original sales collaborative data. Based on the characteristics of the original sales collaborative data, an encryption key is generated to complete lightweight encryption. The encrypted data is then subjected to hash verification to obtain the verification value. The verification parameters are written to the on-chain ledger for evidence storage, and the encrypted data is sharded and stored on off-chain nodes to build a secure and traceable sales collaborative data warehouse.

[0022] The platform integrates multi-source, heterogeneous business data from all stages of the supply chain. It then performs standardized preprocessing, time synchronization, and index association processing according to unified data specifications and time standards. All business data entries are traversed, and operations such as format unification, missing value imputation, outlier removal, and calibration are performed one by one. The timestamps of all data are calibrated to a unified standard time, and a mapping between data is established using common key fields, forming a complete original sales collaboration dataset. This dataset contains the standardized format, unified timestamps, and associated index information for all business data. In the collaborative data warehouse construction module, data tags are extracted from the original sales collaboration data. Based on the data tags, dynamic derived keys are generated to perform lightweight encryption on the original data. The main hash value is calculated for the overall encrypted data, and the segmented secondary hash values ​​are calculated for the segmented data. The main hash value, segmented secondary hash values ​​and key derivation parameters are written into the on-chain ledger to complete tamper-proof storage. The encrypted data is stored in fragments on off-chain nodes to form a secure and traceable sales collaboration data warehouse.

[0023] From the original sales collaboration dataset, using preset tag extraction rules, the business type, affiliated site, generation time, and core business dimension features corresponding to each data entry are located and extracted to form a data tag set. Combining the data tag set with the data timestamp and unique site identifier, a dynamically derived key is generated using the SHA-256 hash algorithm, providing security support for subsequent data encryption. Using the generated dynamically derived key, the original sales collaboration data is subjected to SM4 lightweight symmetric encryption to obtain encrypted business data. The encrypted business data is then traversed, and the master hash value is calculated for the entire encrypted data. Simultaneously, the encrypted data is segmented according to a fixed data length, and the sub-hash value is calculated for each segment to form a complete hash verification dataset. This verification dataset contains the master hash value of the entire data and the sub-hash values ​​of each segment. The main hash value, segmented secondary hash values, and key derivation parameters are written into the consortium blockchain ledger to complete the tamper-proof storage operation. At the same time, the encrypted business data is sharded according to business dimensions and the site to which it belongs, and the sharded data is stored in the local storage devices of each collaborative node in the supply chain to build a secure and traceable sales collaborative data warehouse. This data warehouse achieves secure data storage and fast access by combining on-chain verification and off-chain storage. The site network establishment module is used to send collaboration requests from the original sales site to candidate collaboration sites. The candidate collaboration sites complete the compatibility determination and establish collaboration connections through the cooperation evaluation model. Then, the collaboration sites are divided into levels according to the authorization results to form a hierarchical collaboration site network. In the collaborative data warehouse construction module, data tags are extracted from the original sales collaboration data. Based on the data tags, dynamic derived keys are generated to perform lightweight encryption on the original data. The main hash value is calculated for the overall encrypted data, and the segmented secondary hash values ​​are calculated for the segmented data. The main hash value, segmented secondary hash values ​​and key derivation parameters are written into the on-chain ledger to complete tamper-proof storage. The encrypted data is stored in fragments on off-chain nodes to form a secure and traceable sales collaboration data warehouse.

[0024] Data tags representing the core characteristics of the data are extracted from the original sales collaboration data. The data tags include business type, affiliated site, generation time and business dimension information. Based on the data tags, combined with the data timestamp and the unique site identifier, a preset hash algorithm is used to generate a dynamic derived key, which provides unique and time-sensitive key support for subsequent data encryption. The generated dynamic derived key is used to perform lightweight symmetric encryption on the original sales collaboration data. The SM4 algorithm is selected as the optimal encryption algorithm to complete the encryption operation of the original data and obtain the encrypted business data. This ensures that the data encryption process is efficient and secure, and is suitable for the low computing power consumption requirements of the supply chain collaboration network. For the obtained encrypted business data, perform a two-dimensional hash verification calculation. First, calculate the main hash value for the entire encrypted data to verify the overall integrity of the data. Then, divide the encrypted data into multiple data segments of fixed length and calculate the segment sub-hash value for each segment to accurately locate abnormal data segments and form a complete hash verification dataset. The obtained master hash value, segmented sub-hash values, and key derivation parameters are written into the consortium blockchain ledger to complete the tamper-proof storage operation, ensuring that the verification data cannot be tampered with and is traceable. At the same time, the encrypted business data is sharded according to business dimensions and the site to which it belongs, and each shard is stored in the local storage device of each collaborative node in the supply chain to build a secure and traceable sales collaborative data warehouse, realizing secure data storage and efficient access.

[0025] The candidate order generation module is used to extract multi-dimensional sales features from the sales collaboration data warehouse and construct a quantified sales feature vector. It performs dynamic weight calculation on the feature vector in combination with the current business scenario to obtain multi-dimensional sales demand analysis results. Then, it integrates the real-time supply capacity of the supply chain and the risk correction coefficient to calculate the supply and demand gap, and generates a candidate order set covering multiple business types based on the gap. In the candidate order generation module, business characteristics that reflect the status of sales operations are mined from the securely stored sales collaboration data warehouse. Business characteristics include sales volume characteristics, sales frequency characteristics, regional fluctuation characteristics, customer level characteristics, promotion intensity characteristics, inventory turnover characteristics, return deviation characteristics, delivery timeliness characteristics, and settlement cycle characteristics. After quantifying various characteristics, they are integrated into a standardized sales characteristic vector. From the securely stored sales collaboration data warehouse, business characteristics reflecting the status of sales operations are extracted. These business characteristics include sales quantity, sales frequency, regional fluctuation, customer level, promotion intensity, inventory turnover, return deviation, delivery timeliness, and settlement cycle. The optimal min-max normalization method is used to quantify various characteristics, eliminating the influence of different dimensions and orders of magnitude. The quantified characteristics are then integrated into a standardized sales feature vector, providing a unified data foundation for subsequent requirements analysis. Dynamic weights are assigned to each sales feature based on the current actual business scenario. Adaptive weight values ​​are assigned to each feature in the sales feature vector. Through weighted calculation, short-cycle sales demand, inventory replenishment demand, and abnormal sales fluctuation demand are accurately analyzed. The sales demand analysis results, which include short-cycle sales demand, replenishment demand, and abnormal fluctuation demand, are obtained through calculation.

[0026] Based on the current actual business scenario (such as regular sales, promotional scenarios, peak and off-peak season scenarios), appropriate dynamic weight values ​​are assigned to each feature in the sales feature vector; the standardized sales feature vector is processed through weighted operations to accurately analyze short-cycle sales demand, inventory replenishment demand, and abnormal sales fluctuation demand, resulting in a sales demand analysis result containing these three types of demand, as shown in the following formula: ; in, This represents the calculation result for the j-th type of sales demand (short-cycle sales demand, replenishment demand, and abnormal fluctuation demand). This refers to the dynamic weight value of the i-th business feature when corresponding to the j-th type of requirement. This is the normalized quantized value of the i-th type of business feature; In the candidate order generation module, the real-time supply capacity of the supply chain is obtained, and a risk correction coefficient is set based on the internal and external risk levels of the supply chain, historical performance fluctuations, and market supply and demand trends. To obtain the real-time supply capacity of the supply chain, an appropriate risk correction coefficient is set based on the internal and external risk levels of the supply chain, historical contract performance fluctuations, and market supply and demand trends. The real-time supply capacity is then weighted and calibrated with the risk correction coefficient to obtain the calibrated effective supply capacity, eliminating the impact of risk factors on supply capacity forecasting. The formula is as follows: ; in, To ensure effective supply capacity after calibration, To ensure the real-time supply capacity of the supply chain, This is a risk correction coefficient, and its value range is dynamically adjusted according to the risk level. In high-risk scenarios, the value tends to be 0.8, and in low-risk scenarios, the value tends to be 1.2. The real-time supply capacity is weighted and calibrated with the risk correction coefficient to obtain the calibrated effective supply capacity. The difference between the sales demand analysis results and the effective supply capacity is calculated to obtain the supply-demand gap. Based on the value and type of the supply-demand gap and the supply-demand matching relationship, a set of candidate orders that matches the gap is generated.

[0027] The supply-demand gap is obtained by calculating the difference between the total demand in the sales demand analysis results and the calibrated effective supply capacity. Based on the value and type of the supply-demand gap and the supply-demand matching relationship, a set of candidate orders that matches the gap is generated, providing a basic order plan for subsequent order collaborative verification.

[0028] The risk correction module is used to distribute candidate orders to a hierarchical collaborative site network. Different levels of collaborative sites complete the collaborative verification of orders by assigning roles and determine the target order. It extracts the behavior data of the entire order process to construct a time-series behavior sequence. After time-series segmentation, it generates a collaborative party behavior profile, identifies the associated collaborative parties and the risk transmission sequence, and predicts the risk triggering node. Based on this, it generates risk control instructions to correct the target order and obtains the risk-corrected order result. In the risk correction module, the candidate order set is distributed to the hierarchical collaborative site network. Directly connected collaborative sites directly participate in order scheduling verification, non-directly connected collaborative sites provide feedback on business capability correction information, and feedback collaborative sites provide feedback on order executability results. By integrating the verification and feedback information from the three types of collaborative sites, the order collaborative verification is completed and the target order is generated. The candidate order set is distributed to the hierarchical collaborative site network. Directly connected collaborative sites directly participate in order scheduling verification, while non-directly connected collaborative sites provide feedback on business capability correction information and feedback on order executability results. The verification results and feedback information of the three types of collaborative sites are integrated to complete the collaborative verification of the order and generate a unique executable target order. By extracting the behavioral data of the entire order process, the behavioral data is constructed in chronological order to obtain a time-series behavioral sequence; Extract the full-process behavioral data of the target order, arrange the various behavioral data in chronological order of order fulfillment time, and construct a time-series behavioral sequence to fully characterize the full-cycle fulfillment behavior of the order. A recursive partitioning time window is used to perform time-series segmentation on the time-series behavior sequence, and the segmented periodic indicators and mutation indicators are extracted. Based on the indicators, a collaborative behavior profile representing the collaborative party's performance characteristics is generated.

[0029] A recursive partitioning time window is used to perform optimal time series segmentation on the time-series behavioral sequence, and periodic indicators and abrupt change indicators are extracted from the segmentation results. Based on the periodic indicators and abrupt change indicators, a behavioral profile of the collaborating parties is generated to characterize their performance stability, performance habits, and anomaly probability. In the risk correction module, associated collaborators are identified by calculating the phase overlap of their behavioral trajectories, and the risk transmission order is formed by sorting them according to the intensity of their synchronous changes. Calculate the phase overlap of the behavioral trajectories of different collaborators, and identify collaborators whose phase overlap exceeds a preset threshold as associated collaborators; based on the intensity of synchronous changes in the behavior of associated collaborators, sort them from high to low to form a risk transmission order, as shown in the following formula: ; in, Let be the phase overlap of the behavioral trajectories of collaborators a and b. , Let be the behavioral characteristic values ​​of collaborating parties a and b at time t. , Let a be the mean of the behavioral characteristic values ​​of collaborating parties a and b. The total duration of the behavior sequence. When the value is greater than or equal to 0.8, it is determined to be a related collaborating party; Based on the evolution of collaborative party behavior profiles and the risk transmission sequence, risk triggering nodes are predicted, risk control instructions are generated to modify target orders, and risk-corrected order results are obtained.

[0030] The logistics fulfillment module is used to build a logistics digital twin model based on all logistics scenario elements, dynamically plan the fulfillment path of risk-corrected orders, perform real-time rerouting during transportation, and finally write back the full process results of order execution, logistics fulfillment, settlement and risk handling to the sales collaboration data warehouse.

[0031] In the logistics fulfillment module, a digital twin model of logistics is constructed by using all elements of the logistics scenario. Based on the model, dynamic planning is performed on the fulfillment path of risk-corrected orders to obtain the target delivery path, and rerouting is performed based on the real-time logistics status during transportation. The results of the entire process of order execution, logistics fulfillment, settlement and risk handling are written back to the sales collaboration data warehouse, and the sales demand analysis model, cooperation evaluation model and behavior profile model are iteratively updated to form a sales data-driven intelligent order collaboration closed loop.

[0032] Collect all elements of the logistics scenario, including warehouse node distribution, transportation node configuration, delivery route information, and real-time road condition information; using a one-to-one mapping between physical entities as the optimal method, link and match the above logistics elements with the virtual space to construct a logistics digital twin model that is completely synchronized with the actual logistics system. At the same time, input the delivery requirements of risk-corrected orders into the logistics digital twin model, and perform dynamic programming calculations on the order fulfillment path with the goals of optimal delivery time and minimum transportation cost, outputting the globally optimal target delivery path, as shown in the following formula: ; in, To achieve the optimal target delivery route, This represents the total transport time for a single route. This represents the total transportation cost for a single route. During the transportation of goods, real-time logistics status information is continuously collected, including road congestion, vehicle abnormalities, and weather changes. When the real-time status deviates from the preset threshold, the rerouting mechanism is immediately triggered, and the logistics digital twin model is used to recalculate and switch to a new feasible delivery route to ensure timely delivery. Order execution results, logistics fulfillment results, settlement results, and risk handling results are uniformly written back to the sales collaboration data warehouse; the returned data is used to iterate and optimize the parameters of the sales demand analysis model, cooperation evaluation model, and behavior profiling model, forming a data-driven, continuously iterating intelligent order collaboration closed loop.

[0033] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A supply chain sales data intelligent order collaborative management system, characterized in that: It includes a collaborative data warehouse construction module, a site network establishment module, a candidate order generation module, a risk correction module, and a logistics fulfillment module; The collaborative data warehouse construction module is used to collect multi-source business data from all aspects of the supply chain, perform standardized preprocessing, time synchronization and index association on the data to form sales collaborative raw data, generate encryption keys based on data characteristics to perform lightweight encryption on the raw data, complete data notarization through hash verification, and construct the sales collaborative data warehouse by using on-chain ledger to store verification parameters and off-chain node sharding to store encrypted data. The site network establishment module is used to send collaboration requests to candidate collaboration sites from the original sales site. The candidate collaboration sites complete the compatibility determination and establish collaboration connections through the cooperation evaluation model. Then, the collaboration sites are divided into levels according to the authorization results to form a hierarchical collaboration site network. The candidate order generation module is used to extract multi-dimensional sales features from the sales collaboration data warehouse and construct a quantified sales feature vector. It then performs dynamic weight calculation on the feature vector in combination with the current business scenario to obtain multi-dimensional sales demand analysis results. Finally, it integrates the real-time supply capacity of the supply chain and the risk correction coefficient to calculate the supply and demand gap, and generates a candidate order set covering multiple business types based on the gap. The risk correction module is used to send candidate orders to a hierarchical collaborative site network. The collaborative sites at different levels complete the collaborative verification of the orders and determine the target orders by assigning roles. The module extracts the behavior data of the entire order process to construct a time-series behavior sequence. The module generates a collaborative party behavior profile through time-series segmentation, identifies the associated collaborative parties and the risk transmission sequence, and predicts the risk triggering nodes. Based on this, the module generates risk control instructions to correct the target orders and obtain the risk-corrected order results. The logistics fulfillment module is used to build a logistics digital twin model based on all logistics scenario elements, dynamically plan the fulfillment path of risk-corrected orders, perform real-time rerouting during transportation, and finally write back the entire process results of order execution, logistics fulfillment, settlement and risk handling to the sales collaboration data warehouse.

2. The intelligent order collaborative management system for supply chain sales data according to claim 1, characterized in that: In the collaborative data warehouse construction module, multi-source business data from all stages of the supply chain are collected. The multi-source heterogeneous data is then subjected to standardized preprocessing, time synchronization, and index association processing to obtain well-organized and associated original sales collaborative data. Based on the characteristics of the original sales collaborative data, an encryption key is generated to complete lightweight encryption. The encrypted data is then subjected to hash verification to obtain a verification value. The verification parameters are written to the on-chain ledger for evidence storage, and the encrypted data is sharded and stored to off-chain nodes to build a secure and traceable sales collaborative data warehouse.

3. The intelligent order collaborative management system for supply chain sales data according to claim 1, characterized in that: In the collaborative data warehouse construction module, data tags are extracted from the original sales collaborative data, and dynamic derived keys are generated based on the data tags to perform lightweight encryption on the original data; the main hash value is calculated for the encrypted overall data, and the segmented secondary hash values ​​are calculated for the segmented data; The main hash value, segmented secondary hash values, and key derivation parameters are written into the on-chain ledger to complete tamper-proof notarization. Encrypted data is stored in fragments on off-chain nodes to form a secure and traceable sales collaboration data warehouse.

4. The intelligent order collaborative management system for supply chain sales data according to claim 1, characterized in that: In the site network establishment module, the internal sales site of the enterprise that initiates the sales business acts as the initiator and sends a collaboration invitation to the warehousing site, supply collaboration site and logistics collaboration site with collaboration potential in the supply chain network. The site identifier carried in the collaboration request is used to uniquely distinguish each collaboration participant. The cooperation evaluation model assesses the feasibility of cooperation based on parameters such as the candidate collaborative sites' historical collaborative performance, business capability matching degree, and credit rating, and determines whether to establish a collaborative relationship. After establishing a collaborative connection, the collaborative sites are divided into direct-connection collaborative sites that can directly participate in order business, non-direct-connection collaborative sites that only provide feedback on business capabilities, and feedback collaborative sites that only provide feedback on the feasibility of order execution, forming a hierarchical collaborative site network with clear levels and division of labor.

5. The intelligent order collaborative management system for supply chain sales data according to claim 1, characterized in that: In the candidate order generation module, business characteristics that reflect the sales business status are mined from the securely stored sales collaboration data warehouse. Business characteristics include sales volume characteristics, sales frequency characteristics, regional fluctuation characteristics, customer level characteristics, promotion intensity characteristics, inventory turnover characteristics, return deviation characteristics, delivery timeliness characteristics, and settlement cycle characteristics. After quantifying various characteristics, they are integrated into a standardized sales characteristic vector. Dynamic weights are assigned to each sales feature based on the current actual business scenario. Adaptive weight values ​​are assigned to each feature in the sales feature vector. Through weighted calculation, short-cycle sales demand, inventory replenishment demand, and abnormal sales fluctuation demand are accurately analyzed. The sales demand analysis results, which include short-cycle sales demand, replenishment demand, and abnormal fluctuation demand, are obtained through calculation.

6. The intelligent order collaborative management system for supply chain sales data according to claim 1, characterized in that: In the candidate order generation module, the real-time supply capacity of the supply chain is obtained, and a risk correction coefficient is set based on the internal and external risk levels of the supply chain, historical performance fluctuations, and market supply and demand trends. The real-time supply capacity is weighted and calibrated with the risk correction coefficient to obtain the calibrated effective supply capacity. The difference between the sales demand analysis results and the effective supply capacity is calculated to obtain the supply-demand gap. Based on the value and type of the supply-demand gap and the supply-demand matching relationship, a set of candidate orders that matches the gap is generated.

7. The intelligent order collaborative management system for supply chain sales data according to claim 1, characterized in that: In the risk correction module, the candidate order set is sent to the hierarchical collaborative site network, where directly connected collaborative sites directly participate in order scheduling verification, non-directly connected collaborative sites provide feedback on business capability correction information, and feedback collaborative sites provide feedback on order executability results. Integrate the verification and feedback information from the three types of collaborative sites to complete collaborative order verification and generate the target order; By extracting the behavioral data of the entire order process, the behavioral data is constructed in chronological order to obtain a time-series behavioral sequence; A recursive partitioning time window is used to perform time-series segmentation on the time-series behavior sequence, and the segmented periodic indicators and mutation indicators are extracted. Based on the indicators, a collaborative behavior profile representing the collaborative party's performance characteristics is generated.

8. The intelligent order collaborative management system for supply chain sales data according to claim 1, characterized in that: In the risk correction module, associated collaborators are identified by calculating the phase overlap of their behavioral trajectories, and a risk transmission order is formed by sorting the associated collaborators according to the intensity of their synchronous changes. Based on the evolution of collaborative party behavior profiles and the risk transmission sequence, risk triggering nodes are predicted, risk control instructions are generated to modify target orders, and risk-corrected order results are obtained.

9. The intelligent order collaborative management system for supply chain sales data according to claim 1, characterized in that: In the logistics fulfillment module, a logistics digital twin model is constructed through all logistics scenario elements. Based on the model, dynamic planning is performed on the fulfillment path of risk-corrected orders to obtain the target delivery path, and rerouting is performed according to the real-time logistics status during transportation. The entire process of order execution, logistics fulfillment, settlement, and risk management is written back to the sales collaboration data warehouse, and the sales demand analysis model, cooperation evaluation model, and behavioral profile model are iteratively updated to form a sales data-driven intelligent order collaboration closed loop.

Images