Supply chain data processing method and device, storage medium and program product

Abstract

According to the supply chain data processing method and device, the storage medium and the program product provided by the invention, a server receives the original data sent by the plurality of supply chain systems, pre-processes the original data to obtain the supply chain data, and inputs the supply chain data into the big data processing framework to output the supply chain analysis data; the big data processing framework can efficiently process a large amount of supply chain data and accurately process and analyze the supply chain data; then the supply chain data is input into the pre-trained supply chain optimization model to output the supply chain optimization data, the supply chain optimization model can quickly process and accurately analyze a large amount of supply chain data, and the supply chain data processing efficiency and the accuracy of the supply chain optimization data are improved; and according to the supply chain analysis data and the supply chain optimization data, a supply chain optimization report is generated, and the supply chain optimization report is used for optimizing each supply chain, thereby realizing more efficient and accurate optimization and management of the supply chains.

Description

Technical Field

[0001] This application relates to the field of intelligent manufacturing, and particularly to a supply chain data processing method, device, storage medium, and program product. Background Art

[0002] With the rapid development of intelligent manufacturing technology and the wide application of industrial Internet, modern manufacturing is gradually transforming towards digitalization, networking, and intelligence. In this transformation process, the optimization and collaborative management of intelligent manufacturing supply chain become the key link to enhance enterprise competitiveness, reduce costs, and improve production efficiency.

[0003] Currently, in the prior art, static models and fixed rules are mainly used to optimize and manage the supply chain.

[0004] However, in the existing technical solutions for the optimization and collaborative management of intelligent manufacturing supply chain, they are often based on static models and fixed rules, which are difficult to adapt to the rapidly changing market environment, and difficult to process the increasing supply chain data. Furthermore, it is difficult to accurately optimize the supply chain, resulting in problems of low efficiency and poor accuracy in the optimization and management of the supply chain. Summary of the Invention

[0005] Embodiments of this application provide a supply chain data processing method, device, storage medium, and program product to achieve the effect of efficiently and accurately optimizing the supply chain.

[0006] In a first aspect, embodiments of this application provide a supply chain data processing method, which is applied to a server and includes:

[0007] Receiving raw data sent by multiple supply chain systems, where the raw data of the multiple supply chain systems is obtained by real-time collection of data collectors deployed in each supply chain system;

[0008] Preprocessing the raw data to obtain supply chain data;

[0009] Storing the supply chain data in a storage system;

[0010] Inputting the supply chain data into a big data processing framework to output supply chain analysis data;

[0011] Inputting the supply chain data into a pre-trained supply chain optimization model to output supply chain optimization data;

[0012] Generating a supply chain optimization report according to the supply chain analysis data and the supply chain optimization data;

[0013] Sending the supply chain optimization report to the corresponding user's terminal device, where the supply chain optimization report is used to optimize each supply chain.

[0014] In a possible implementation, the raw data is preprocessed to obtain supply chain data, including:

[0015] Performing desensitization processing and compliance inspection processing on the raw data to obtain processed raw data;

[0016] Performing at least one of cleaning, deduplication, conversion, and standardization on the processed raw data to obtain supply chain data.

[0017] In a possible implementation, the training process of the pre-trained supply chain optimization model includes:

[0018] Obtaining a preset number of historical supply chain data from the storage system;

[0019] Using the preset number of historical supply chain data as training data to train the initial supply chain optimization model to obtain the pre-trained supply chain optimization model.

[0020] In a possible implementation, after using the preset number of historical supply chain data as training data to train the initial supply chain optimization model to obtain the pre-trained supply chain optimization model, it further includes:

[0021] Receiving cross-domain supply chain data sent by the cross-domain platform;

[0022] Inputting the cross-domain supply chain data into the pre-trained supply chain optimization model to output cross-domain supply chain optimization data;

[0023] Sending the cross-domain supply chain optimization data to the cross-domain platform.

[0024] In a possible implementation, the method further includes:

[0025] Generating a visualization chart based on the supply chain data stored in the storage system;

[0026] Sending the visualization chart to the terminal device of the corresponding user, where the visualization chart is used for the user to perform analysis and interaction operations.

[0027] In a possible implementation, the server accesses one or more of a log system, a monitoring system, and an exception handling system.

[0028] In a second aspect, an embodiment of the present application provides a supply chain data processing device, which is applied to the server and includes:

[0029] An acquisition module, configured to receive raw data sent by multiple supply chain systems, where the raw data of the multiple supply chain systems is obtained by real-time collection of data collectors deployed in each supply chain system;

[0030] A processing module for preprocessing raw data to obtain supply chain data;

[0031] A storage module for storing the supply chain data in a storage system;

[0032] The processing module is also used to input the supply chain data into a big data processing framework to output supply chain analysis data;

[0033] The processing module is also used to input the supply chain data into a pre-trained supply chain optimization model to output supply chain optimization data;

[0034] A decision-making module for generating a supply chain optimization report based on the supply chain analysis data and the supply chain optimization data;

[0035] A sending module for sending the supply chain optimization report to the terminal device of the corresponding user, where the supply chain optimization report is used to optimize each supply chain.

[0036] In a possible implementation manner, the processing module is specifically used for:

[0037] Performing desensitization processing and compliance inspection processing on the raw data to obtain processed raw data;

[0038] Performing at least one of cleaning, deduplication, conversion, and standardization on the processed raw data to obtain supply chain data.

[0039] In a possible implementation manner, the processing module is specifically used for:

[0040] Obtaining a preset number of historical supply chain data from the storage system;

[0041] Using the preset number of historical supply chain data as training data to train an initial supply chain optimization model to obtain a pre-trained supply chain optimization model.

[0042] In a possible implementation manner, the processing module is specifically used for:

[0043] Receiving cross-domain supply chain data sent by a cross-domain platform;

[0044] Inputting the cross-domain supply chain data into the pre-trained supply chain optimization model to output cross-domain supply chain optimization data;

[0045] Sending the cross-domain supply chain optimization data to the cross-domain platform.

[0046] In a possible implementation manner, the storage module is specifically used for:

[0047] Generating a visualization chart based on the supply chain data stored in the storage system;

[0048] Send the visualization chart to the terminal device of the corresponding user, where the visualization chart is used for the user to perform analysis and interaction operations.

[0049] In a possible implementation, the server accesses one or more of a log system, a monitoring system, and an exception handling system.

[0050] In a third aspect, an embodiment of the present application provides a server, including: a memory, a processor;

[0051] The memory stores computer-executable instructions;

[0052] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementation manners of the first aspect.

[0053] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, they are used to implement the above first aspect and / or various possible implementation manners of the first aspect.

[0054] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which when executed by a processor, implements the above first aspect and / or various possible implementation manners of the first aspect.

[0055] A supply chain data processing method, device, storage medium, and program product provided by the present application receive raw data sent by multiple supply chain systems, preprocess the raw data to obtain supply chain data, store the supply chain data in a storage system, input the supply chain data into a big data processing framework to output supply chain analysis data. The big data processing framework can efficiently process a large amount of supply chain data and accurately process and analyze the supply chain data, thereby providing a precise and effective basis for generating a supply chain optimization report, and further improving the supply chain optimization effect; then input the supply chain data into a pre-trained supply chain optimization model to output supply chain optimization data. The supply chain optimization model can quickly process and accurately analyze a large amount of supply chain data, improve the supply chain data processing efficiency and the accuracy of the supply chain optimization data, and further improve the supply chain optimization effect; generate a supply chain optimization report according to the supply chain analysis data and the supply chain optimization data, and send the supply chain optimization report to the terminal device of the corresponding user, where the supply chain optimization report is used to optimize each supply chain, realizing more efficient and accurate optimization and management of the supply chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0057] Figure 1 A schematic diagram of the scenario provided for the embodiments of the present application;

[0058] Figure 2 A flowchart of the supply chain data processing method provided for the embodiments of the present application Figure 1 ;

[0059] Figure 3 A flowchart of the supply chain data processing method provided for the embodiments of the present application Figure 2 ;

[0060] Figure 4 A schematic structural diagram of the supply chain data processing device provided for the embodiments of the present application;

[0061] Figure 5 A schematic structural diagram of the server provided for the embodiments of the present application.

[0062] Through the above-mentioned accompanying drawings, specific embodiments of the present application have been shown, and there will be more detailed descriptions hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. Detailed implementation manners

[0063] Exemplary embodiments will be described in detail here, and examples are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0064] With the rapid development of intelligent manufacturing technology and the wide application of industrial Internet, modern manufacturing is gradually transforming towards digitalization, networking, and intelligence. In this transformation process, the optimization and collaborative management of intelligent manufacturing supply chain have become the key links to enhance enterprise competitiveness, reduce costs, and improve production efficiency. However, with the expansion of enterprise scale and the complexity of the supply chain, the traditional supply chain management model has been difficult to cope with the rapidly changing market demands, complex logistics networks, and massive data processing requirements. Especially in the big data era, the amount of data involved in the intelligent manufacturing supply chain has increased sharply, and the data types are diverse, including production data, inventory data, logistics data, sales data, etc. These data contain rich value, but how to efficiently collect, process, analyze, and apply them to supply chain optimization and collaborative management has become a major challenge for enterprises. Traditional supply chain management systems often rely on manual decision-making or simple data analysis tools, making it difficult to achieve comprehensive optimization and real-time collaboration of complex supply chain systems.

[0065] In addition, with the intensification of market competition and the changes in customer demands, the intelligent manufacturing supply chain needs to have higher flexibility and response speed. Traditional optimization methods often based on static models and fixed rules are difficult to adapt to the rapidly changing market environment. Therefore, an intelligent manufacturing supply chain optimization and collaborative management platform that can analyze data in real time, intelligently predict trends, and dynamically optimize decisions is particularly important. Against this background, an intelligent manufacturing supply chain optimization and collaborative management platform based on deep learning large models has emerged. This platform utilizes the powerful data processing and learning capabilities of deep learning large models, combines advanced optimization algorithms and collaborative management technologies, realizes the comprehensive optimization and real-time collaboration of the intelligent manufacturing supply chain, and improves the overall efficiency and competitiveness of the supply chain.

[0066] In the existing technologies, for the optimization and collaborative management of intelligent manufacturing supply chain, there are mainly the following technical solutions: systems based on traditional optimization algorithms, systems based on data analysis and prediction, systems based on cloud computing and Internet of Things, intelligent platforms, etc. However, these platforms may have deficiencies in aspects such as data processing capabilities and optimization effects, and it is difficult to fully meet the needs of enterprises.

[0067] To solve the above technical problems, the following technical conceptions are proposed: The inventor considered that the amount of original supply chain data collected in each link of the supply chain is huge, the data types are numerous, and the original supply chain data is mottled and unclear, making it difficult to accurately extract key data for analysis and processing, and thus unable to provide accurate optimization suggestions. Therefore, the inventor thought that the deep learning model has powerful data processing and learning capabilities, can efficiently process and accurately analyze the massive and complex supply chain data, and then combined with a dedicated big data processing framework, further efficiently mine and accurately analyze the supply chain data, integrate accurate optimization solutions, and thus achieve more efficient and accurate optimization of the supply chain.

[0068] The following uses specific embodiments to elaborate in detail on the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems. These several specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0069] Figure 1 This is a schematic diagram of the scenario provided by the embodiment of the present application. Refer to Figure 1 , this scenario includes: multiple supply chain systems 101, a server 102, and multiple terminal devices 103.

[0070] Among them, the supply chain system 101 is used to record the original data of each link of the supply chain collected by the data collector, such as the logistics system, inventory management system, etc. A data collector is deployed in the supply chain system 101 to collect the original data of the supply chain system.

[0071] The server 102 is used to obtain the original data of the supply chain system, and after analyzing the original data of the supply chain system, output a supply chain optimization report.

[0072] The terminal device 103 is used to receive the supply chain optimization report sent by the server. This supply chain optimization report is used to optimize each supply chain.

[0073] Figure 2 This is a schematic flowchart of the supply chain data processing method provided by the embodiment of the present application Figure 1 . As Figure 2 shown, this method is applied to the server 102 shown in Figure 1 , and this method includes:

[0074] S201. Receive the original data sent by multiple supply chain systems, where the original data of the multiple supply chain systems is collected in real time by the data collectors deployed in each supply chain system.

[0075] Exemplarily, the supply chain system can be an external supplier system, a logistics system, a market data platform system, etc.

[0076] In some possible implementation manners, multiple supply chain systems and the server adopt a unified data interface and communication protocol to adapt to multiple data formats and data sources.

[0077] Specifically, data collectors deployed in each supply chain system, such as sensors, radio frequency identification tags (RFID), barcode scanners, etc., collect and send the data in real time to the corresponding supply chain system. Possibly, the data collector and / or the supply chain system perform preliminary processing on the original data to ensure the accuracy and timeliness of the original data.

[0078] The server receives the original data sent by multiple supply chain systems through means such as application programming interfaces (APIs), file transfer, message queues, etc. The original data includes but is not limited to real-time data and historical data, etc. The data types of the original data include but are not limited to production progress, inventory status, sales orders, logistics tracking, market demand forecasting, etc.

[0079] In some possible implementation manners, before receiving the original data sent by multiple supply chain systems, the server starts basic service components, such as data access services, data processing engines, storage systems, etc. Loads pre-trained deep learning models and other necessary algorithm libraries to prepare for subsequent data processing. Reads the system configuration file and sets key configurations such as data source connections and processing flows.

[0080] S202. Perform preprocessing on the original data to obtain supply chain data.

[0081] Specifically, the original data may include some redundant data or error data, and the server can perform preprocessing on the original data to obtain more accurate supply chain data.

[0082] Exemplarily, the server can set filtering rules to filter the original data and filter out redundant data; the server can also detect and correct or delete error data by setting reasonable value ranges, data formats, and logical rules to obtain more accurate supply chain data.

[0083] S203. Store the supply chain data in the storage system.

[0084] Specifically, according to factors such as the data type, data volume, access frequency, and performance requirements of the supply chain data, select a suitable storage system and store the supply chain data in the storage system.

[0085] Exemplarily, the storage system can be a relational database, a non-relational (NoSQL) database, a data warehouse, a data lake, etc.

[0086] In some possible implementation manners, the server adopts a hierarchical storage strategy to store the supply chain data in the storage system, stores the frequently accessed "hot data" on a high-performance storage medium, and stores the infrequently accessed "cold data" on a lower-cost storage medium to optimize the storage cost and access efficiency.

[0087] In some possible implementation manners, the storage system formulates a data backup plan to back up key data regularly (such as daily or weekly) to prevent data loss or damage, and establishes a disaster recovery plan to ensure that data and services can be quickly restored in case of emergencies such as system failures and natural disasters.

[0088] In some possible implementation manners, the storage system implements a strict access control strategy. Through means such as authentication, authorization, and encryption, it ensures that only authorized users can access sensitive data, and encrypts and stores and transmits sensitive data to prevent the data from being stolen or tampered with during storage and transmission.

[0089] In some possible implementation manners, the storage system establishes a data access auditing and monitoring system to record data access behaviors and promptly discover and respond to potential security threats.

[0090] In some possible implementation manners, the storage system establishes a data quality monitoring mechanism to regularly check the accuracy, integrity, consistency, and timeliness of the data to ensure that the data quality meets the business requirements. And uniformly manage the metadata of the data (such as data structure, data source, data owner, etc.) to improve the discoverability and understandability of the data. And according to the business requirements and data value, formulate data retention and destruction strategies to ensure that the data is properly managed throughout its life cycle.

[0091] In some possible implementation manners, the storage system realizes data integration and synchronization between different data sources through data integration tools and technologies to support cross-departmental and cross-system data sharing and analysis. And establish a data sharing platform to provide a unified data access interface and permission management to promote the sharing and utilization of data within the organization.

[0092] S204. Input the supply chain data into the big data processing framework to output supply chain analysis data.

[0093] Specifically, input the supply chain data into a big data processing framework (such as Hadoop, Spark, etc.). The big data processing framework performs efficient distributed processing and analysis on the massive supply chain data, accurately extracts the correlation relationships, trend changes, outliers, etc. among the supply chain data, and outputs supply chain analysis data to provide a strong basis for generating a supply chain optimization report.

[0094] S205. Input the supply chain data into a pre-trained supply chain optimization model to output supply chain optimization data.

[0095] Specifically, input the supply chain data into a pre-trained supply chain optimization model. The pre-trained supply chain optimization model performs efficient processing and analysis on a large amount of supply chain data, considers various factors (such as seasonal changes, promotional activities, emergencies, etc.), and accurately predicts each link of the future supply chain (such as market demand, inventory level, production level, etc.) to output supply chain optimization data, thereby optimizing each link of the supply chain.

[0096] S206. Generate a supply chain optimization report based on the supply chain analysis data and the supply chain optimization data.

[0097] Among them, the content of the supply chain optimization report includes but is not limited to production plan adjustment, inventory level control, logistics route optimization, etc.

[0098] In some possible implementation manners, the server uses advanced optimization algorithms, such as genetic algorithms, simulated annealing, linear programming, etc., to globally optimize the resource allocation of each link of the supply chain. Comprehensively consider multiple objectives such as cost, time, and quality to formulate the optimal production plan, procurement plan, inventory strategy, and logistics plan. And generate a more specific supply chain optimization report based on the optimal production plan, procurement plan, inventory strategy, logistics plan, as well as the supply chain analysis data and the supply chain optimization data.

[0099] S207. Send the supply chain optimization report to the terminal device of the corresponding user, where the supply chain optimization report is used to optimize each supply chain.

[0100] In some possible implementation manners, the server sends the supply chain optimization report to the terminal device of the corresponding user. The user can view the supply chain optimization report through the terminal device, conduct interactive analysis, deeply understand the data and the model, conduct hypothesis analysis and scenario simulation, and can send operation instructions to the server according to the supply chain optimization report to optimize each supply chain, such as adjusting the production plan, placing a purchase order, etc. Possibly, the server collects the user's operation feedback for subsequent optimization and iteration.

[0101] As can be seen from the description of the above embodiments, by receiving the original data sent by multiple supply chain systems and preprocessing the original data to obtain supply chain data, storing the supply chain data in a storage system, and inputting the supply chain data into a big data processing framework to output supply chain analysis data, the big data processing framework can efficiently process a large amount of supply chain data and accurately process and analyze the supply chain data, thereby providing a precise and effective basis for generating a supply chain optimization report, and further improving the supply chain optimization effect; then inputting the supply chain data into a pre-trained supply chain optimization model to output supply chain optimization data, the supply chain optimization model can quickly process and accurately analyze a large amount of supply chain data, improve the efficiency of supply chain data processing and the accuracy of supply chain optimization data, and further improve the supply chain optimization effect; generating a supply chain optimization report according to the supply chain analysis data and the supply chain optimization data, and sending the supply chain optimization report to the terminal device of the corresponding user, where the supply chain optimization report is used to optimize each supply chain, realizing more efficient and accurate optimization and management of the supply chain.

[0102] Figure 3 Flow schematic of the supply chain data processing method provided by the embodiment of the present application Figure 2 As Figure 3 shown, this supply chain data processing method is used for the server and includes:

[0103] S301. Receive the original data sent by multiple supply chain systems, where the original data of the multiple supply chain systems is obtained by real-time collection of data collectors deployed in each supply chain system.

[0104] It should be noted that for the specific implementation manner of step S301, reference can be made to the specific implementation manner of step S201, which will not be elaborated here.

[0105] S302. Preprocess the original data to obtain supply chain data.

[0106] In some possible implementation manners, perform desensitization processing and compliance inspection processing on the original data to obtain the processed original data; perform at least one of cleaning, deduplication, conversion, and standardization on the processed original data to obtain supply chain data.

[0107] Specifically, remove the sensitive data in the original data, check the compliance of the original data, and remove the non-compliant data in the original data to obtain the processed original data, ensuring that the processed original data complies with relevant laws and regulations, industry standards, and enterprise internal policies. And perform at least one of cleaning, deduplication, conversion, and standardization on the processed original data to obtain supply chain data, ensuring the quality of the supply chain data.

[0108] S303. Store the supply chain data in the storage system.

[0109] S304. Input the supply chain data into the big data processing framework to output supply chain analysis data.

[0110] It should be noted that for the specific implementation manners of steps S303 and S304, reference can be made to the specific implementation manners of steps S203 and S204, and details will not be elaborated here.

[0111] S305. Train the initial supply chain optimization model to obtain a pre-trained supply chain optimization model.

[0112] Among them, the training process of the pre-trained supply chain optimization model includes obtaining a preset number of historical supply chain data from the storage system; using the preset number of historical supply chain data as training data to train the initial supply chain optimization model to obtain a pre-trained supply chain optimization model.

[0113] In some possible implementation manners, obtain a preset number of historical supply chain data from the storage system, and process the preset number of historical supply chain data through data cleaning, data standardization, feature scaling, feature selection, data augmentation, etc. to obtain the processed preset number of historical supply chain data, so as to improve the model accuracy.

[0114] Among them, data cleaning is to check and process missing values, outliers and duplicate values in the data. Missing values can be processed by filling the mean, median or mode, etc.; outliers can be deleted or replaced with reasonable values depending on the situation; duplicate values need to be deleted. Data standardization is to scale the data to the same magnitude through methods such as mean normalization or standard deviation normalization, which helps the model converge faster. Feature scaling is to use methods such as min-max scaling or standardization scaling to scale the features and improve the performance of the model. Feature selection is to select features with high correlation with the target variable, reduce the complexity of the model, and improve the training speed and prediction accuracy. Data augmentation is to use techniques such as random augmentation, rotation and translation to increase the diversity of the data and improve the generalization ability of the model.

[0115] According to the data type or data structure of the historical supply chain data, etc., select a suitable deep learning model as the initial supply chain optimization model, such as a convolutional neural network, a recurrent neural network, etc. And based on the actual needs of each link of the supply chain and user requirements, design a reasonable model architecture, such as adding hidden layers, adjusting the number of neurons, selecting a suitable activation function, etc., to improve the model accuracy.

[0116] Use a preset amount of historical supply chain data as training data and input it into the initial supply chain optimization model to train the initial supply chain optimization model to obtain a pre-trained supply chain optimization model.

[0117] In some possible implementation manners, during the training process of training the initial supply chain optimization model, one or more of regularization, batch normalization, learning rate adjustment, optimization algorithm selection, early stopping, hyperparameter tuning, and monitoring the training process can be used to optimize the model training to improve the model accuracy. And cross-validation can be used to evaluate the performance of the supply chain optimization model, such as K-fold cross-validation, leave-one-out cross-validation, etc., and the optimal model parameters and architecture can be selected according to the evaluation results.

[0118] Among them, regularization uses techniques such as L1 regularization and L2 regularization to reduce the overfitting risk of the model. Batch normalization is to normalize the input data in each layer of the neural network to improve the performance and stability of the model. Learning rate adjustment is to adjust the learning rate through methods such as exponential decay and adaptive learning rate to accelerate the convergence speed of the model and avoid getting stuck in local optimal solutions. Optimization algorithm selection is to select the most suitable optimization algorithm according to the specific problem, such as stochastic gradient descent, mini-batch gradient descent, etc. Early stopping is to stop training when the model performance has not improved continuously on the validation set to avoid overfitting. Hyperparameter tuning is to adjust the hyperparameters of the model through methods such as grid search and random search to improve the performance of the model. Monitoring the training process is to monitor the loss and accuracy curves during the training process and adjust the learning rate and optimization algorithm in a timely manner.

[0119] In some possible implementation manners, receive cross-domain supply chain data sent by a cross-domain platform; input the cross-domain supply chain data into the pre-trained supply chain optimization model to output cross-domain supply chain optimization data; send the cross-domain supply chain optimization data to the cross-domain platform.

[0120] Specifically, the server accesses a cross-domain platform, such as an enterprise internal platform, a customer relationship management platform, etc., receives the cross-domain supply chain data sent by the cross-domain platform, and inputs the cross-domain supply chain data into the pre-trained supply chain optimization model. The pre-trained supply chain optimization model extracts features from the cross-domain supply chain data, identifies potential patterns of key information in the cross-domain supply chain data, and analyzes the cross-domain data in ways such as classification, clustering, regression, etc. to output cross-domain supply chain optimization data. The server sends the cross-domain supply chain optimization data to the cross-domain platform to optimize the supply chain of the cross-domain platform.

[0121] S306: Input the supply chain data into the pre-trained supply chain optimization model to output supply chain optimization data.

[0122] S307. Generate a supply chain optimization report based on the supply chain analysis data and the supply chain optimization data.

[0123] It should be noted that for the specific implementation manners of steps S306 and S307, reference can be made to the specific implementation manners of steps S205 and S206, which will not be elaborated here.

[0124] S308. Send the supply chain optimization report to the terminal device of the corresponding user, where the supply chain optimization report is used to optimize each supply chain.

[0125] In some possible implementation manners, generate a visualization chart according to the supply chain data stored in the storage system; send the visualization chart to the terminal device of the corresponding user, where the visualization chart is used for the user to perform analysis and interaction operations.

[0126] Specifically, the server generates a visualization chart based on the supply chain data stored in the storage system according to a preset view format or report format. The visualization chart displays the key data indicators and trends of each link in the supply chain, such as production progress, inventory status, sales orders, etc.; the server sends the visualization chart to the terminal device of the corresponding user for the user to perform analysis and interaction operations, such as filtering key data, arranging data sizes, etc.

[0127] Possibly, the server provides rich data visualization tools, such as dashboards, charts, maps, etc., to convert complex data into intuitive visual presentations. Supports custom views and report templates to meet the personalized needs of different users. Provides interactive analysis functions, and users can deeply explore the information behind the data through operations such as dragging and zooming. And can automatically generate key business reports such as supply chain performance reports, risk assessment reports, and quality analysis reports. Supports export in multiple formats for easy sharing and reporting by users. Provides a report subscription function, and users can receive the latest reports and updates regularly.

[0128] In some possible implementation manners, the server accesses one or more of the log system, the monitoring system, and the exception handling system.

[0129] Among them, the log system is used to record the running process of the server program, establish a user feedback mechanism, and collect the problems, suggestions, and requirements encountered by users during use. Regularly summarize and analyze user feedback, evaluate the performance of the system and the user experience. Continuously optimize the deep learning large model and other algorithms according to user feedback and technological development trends. Introduce new algorithms and technologies to improve the prediction accuracy and optimization effect of the system. Regularly perform system maintenance and upgrades to ensure the stability and security of the system. Update system components and dependency libraries to fix known vulnerabilities and defects.

[0130] The monitoring system is used for performance monitoring and early warning of anomaly detection, and it monitors potential risk points in the supply chain in real time, such as supply interruptions, quality problems, and logistics cost overruns. It evaluates the identified risks and formulates corresponding response strategies and contingency plans according to the severity and impact scope of the risks. It provides a risk early warning function to reduce the probability and impact of risk occurrence.

[0131] The exception handling system is used to capture error information and ensure that supply chain activities comply with relevant laws, regulations, industry standards, and enterprise internal policies. It conducts qualification audits and regular reviews of partners such as suppliers and logistics service providers to ensure the legality and compliance of their business activities. Through real-time data collection and analysis, it monitors key quality indicators in the production process. It conducts quality inspections and tests on raw materials, semi-finished products, and finished products to ensure that the product quality meets the standards. It traces and processes non-conforming products, analyzes the causes of quality problems, and proposes improvement measures. It applies quality management methods such as statistical process control and Six Sigma to optimize the production process. It discovers the laws and trends of quality problems through data analysis and formulates targeted improvement measures.

[0132] In some possible implementation manners, the server provides a collaborative operation platform, which supports information sharing and collaborative operation among all links of the supply chain. Through functions such as task assignment, progress tracking, and collaborative editing, it improves the collaborative efficiency and response speed of the supply chain. It supports cross-departmental and cross-enterprise collaborative operations, breaks information silos, and realizes end-to-end management of the supply chain. It establishes real-time communication channels, such as instant messaging and video conferencing, to facilitate real-time communication and collaboration among all parties in the supply chain. It provides a problem feedback and solution sharing function to promote communication and cooperation among all links of the supply chain.

[0133] In some possible implementation manners, the server can provide training materials and video tutorials to the user's terminal device, which is convenient for users to learn anytime and anywhere. And it provides technical documents such as user manuals and operation guides to help users quickly get started and use the system.

[0134] In some possible implementation manners, the server integrates third-party services (such as logistics tracking, payment settlement, etc.) to enrich functions and services. And it adopts containerized deployment and automated operation and maintenance technologies to improve the flexibility and scalability of the server. It supports multi-region deployment options to ensure that supply chain activities worldwide can be efficiently managed and optimized.

[0135] As can be seen from the description of the above embodiments, by receiving the original data sent by multiple supply chain systems, preprocessing the original data to obtain supply chain data, storing the supply chain data in a storage system, and inputting the supply chain data into a big data processing framework to output supply chain analysis data, the big data processing framework can efficiently process a large amount of supply chain data and accurately process and analyze the supply chain data, thereby providing a precise and effective basis for generating a supply chain optimization report, and further improving the supply chain optimization effect; training the initial supply chain optimization model, and improving the adaptability and generalization ability of the supply chain optimization model to the supply chain data through the training method and parameter setting of the supply chain optimization model, thereby improving the accuracy of the supply chain optimization model to obtain a pre-trained supply chain optimization model with higher accuracy; then inputting the supply chain data into the pre-trained supply chain optimization model to output supply chain optimization data, the supply chain optimization model can quickly process and accurately analyze a large amount of supply chain data, improve the supply chain data processing efficiency and the accuracy of the supply chain optimization data, and further improve the supply chain optimization effect; generating a supply chain optimization report according to the supply chain analysis data and the supply chain optimization data, and sending the supply chain optimization report to the terminal device of the corresponding user, wherein the supply chain optimization report is used to optimize each supply chain, realizing more efficient and accurate optimization and management of the supply chain.

[0136] In addition, the server removes sensitive data from the original data, checks the compliance of the original data, and removes non-compliant data from the original data to obtain processed original data, ensuring that the processed original data complies with relevant laws, regulations, industry standards, and enterprise internal policies. And perform at least one of cleaning, deduplication, conversion, and standardization on the processed original data to obtain supply chain data and ensure the quality of the supply chain data.

[0137] Secondly, the server obtains a preset number of historical supply chain data from the storage system; uses the preset number of historical supply chain data as training data, selects a suitable deep learning model as the initial supply chain optimization model according to the data type or data structure of the historical supply chain data, etc., and designs a reasonable model architecture based on the actual needs of each link of the supply chain and user requirements to improve the model accuracy, thereby obtaining a better pre-trained supply chain optimization model.

[0138] The server accesses a cross-domain platform, receives cross-domain supply chain data sent by the cross-domain platform, and inputs the cross-domain supply chain data into the pre-trained supply chain optimization model. The pre-trained supply chain optimization model extracts features from the cross-domain supply chain data, identifies potential patterns of key information in the cross-domain supply chain data, analyzes the cross-domain data, and outputs cross-domain supply chain optimization data. The server sends the cross-domain supply chain optimization data to the cross-domain platform to optimize the supply chain of the cross-domain platform.

[0139] Based on the supply chain data stored in the storage system, the server generates a visualization chart based on a preset view format or report format. The visualization chart displays key data indicators and trends of each link in the supply chain, such as production progress, inventory status, sales orders, etc.; the server sends the visualization chart to the terminal device of the corresponding user to facilitate the user's analysis and interaction operations.

[0140] By accessing one or more of the log system, monitoring system, and exception handling system, the server records the operation track to assist in auditing, provides a basis for performance analysis, assists in troubleshooting, supports business analysis, can predict faults in advance, provides a reference for capacity planning, ensures service quality, enhances system stability, improves user experience, maintains data consistency, and some can achieve automatic problem recovery.

[0141] Figure 4 It is a schematic structural diagram of the supply chain data processing device provided by the embodiment of the present application. As Figure 4 shown, the supply chain data processing device 40 provided in this embodiment includes:

[0142] An acquisition module 401, configured to receive raw data sent by multiple supply chain systems, where the raw data of the multiple supply chain systems is obtained by real-time collection of data collectors deployed in each supply chain system;

[0143] A processing module 402, configured to preprocess the raw data to obtain supply chain data;

[0144] A storage module 403, configured to store the supply chain data in the storage system;

[0145] The processing module 402 is further configured to input the supply chain data into a big data processing framework to output supply chain analysis data;

[0146] The processing module 402 is further configured to input the supply chain data into a pre-trained supply chain optimization model to output supply chain optimization data;

[0147] A decision-making module 404, configured to generate a supply chain optimization report according to the supply chain analysis data and the supply chain optimization data;

[0148] A sending module 405, configured to send the supply chain optimization report to the terminal device of the corresponding user, where the supply chain optimization report is used to optimize each supply chain.

[0149] In a possible implementation manner, the processing module 402 is specifically configured to:

[0150] Perform desensitization processing and compliance inspection processing on the raw data to obtain the processed raw data;

[0151] Perform at least one of cleaning, deduplication, conversion, and standardization on the processed original data to obtain supply chain data.

[0152] In a possible implementation manner, the processing module 402 is specifically configured to:

[0153] Obtain a preset number of historical supply chain data from the storage system;

[0154] Use the preset number of historical supply chain data as training data to train the initial supply chain optimization model to obtain a pre-trained supply chain optimization model.

[0155] In a possible implementation manner, the processing module 402 is specifically configured to:

[0156] Receive cross-domain supply chain data sent by the cross-domain platform;

[0157] Input the cross-domain supply chain data into the pre-trained supply chain optimization model to output cross-domain supply chain optimization data;

[0158] Send the cross-domain supply chain optimization data to the cross-domain platform.

[0159] In a possible implementation manner, the storage module 403 is specifically configured to:

[0160] Generate a visualization chart based on the supply chain data stored in the storage system;

[0161] Send the visualization chart to the terminal device of the corresponding user, where the visualization chart is used for the user to perform analysis and interaction operations.

[0162] In a possible implementation manner, the server accesses one or more of a log system, a monitoring system, and an exception handling system.

[0163] The supply chain data processing device provided in this embodiment can execute the method provided in the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0164] Figure 5 It is a schematic structural diagram of the server provided in the embodiment of the present application. As Figure 5 shown, the server 50 provided in this embodiment includes: at least one processor 501 and a memory 502. Optionally, the device 50 further includes a communication component 503. Among them, the processor 501, the memory 502, and the communication component 503 are connected through a bus 504.

[0165] In the specific implementation process, at least one processor 501 executes the computer execution instructions stored in the memory 502, so that at least one processor 501 executes the above method.

[0166] For the specific implementation process of the processor 501, reference may be made to the foregoing method embodiments. Their implementation principles and technical effects are similar, and will not be elaborated herein.

[0167] In the foregoing embodiments, it should be understood that the processor may be a central processing unit (CPU for short), or may also be other general-purpose processors, digital signal processors (DSP for short), application specific integrated circuits (ASIC for short), etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the invention may be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.

[0168] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0169] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0170] This application also provides a computer program product, including a computer program which, when executed by a processor, implements the foregoing method.

[0171] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the foregoing method.

[0172] The above-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0173] An exemplary readable storage medium is coupled to the processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0174] The division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings or direct couplings or communication connections shown or discussed with each other can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0175] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, the functional units in various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0176] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, etc., various media that can store program codes.

[0177] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the aforementioned storage medium includes: ROMs, RAMs, magnetic disks, or optical discs, etc., various media that can store program codes.

[0178] Finally, it should be noted that: After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily think of other implementation manners of the present invention. The present invention is intended to cover any variations, uses, or adaptive changes of the present invention, which follow the general principles of the present invention and include common general knowledge or conventional technical means in the technical field not disclosed in the present invention. It is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A supply chain data processing method, characterized in that: Applied to the server, including: Receiving original data sent by multiple supply chain systems, wherein the original data of the multiple supply chain systems are collected in real time by data collectors deployed in each supply chain system; Preprocessing the raw data to obtain supply chain data; Storing the supply chain data in a storage system; Inputting the supply chain data into a big data processing framework to output supply chain analysis data; Inputting the supply chain data into a pre-trained supply chain optimization model to output supply chain optimization data; Generate a supply chain optimization report based on the supply chain analysis data and the supply chain optimization data; The supply chain optimization report is sent to a terminal device of a corresponding user, wherein the supply chain optimization report is used to optimize each supply chain.

2. The method according to claim 1, characterized in that The preprocessing of the raw data to obtain supply chain data includes: Performing desensitization processing and compliance inspection processing on the original data to obtain processed original data; The processed raw data is subjected to at least one of cleaning, deduplication, conversion, and standardization to obtain the supply chain data.

3. The method according to claim 1, characterized in that: The training process of the pre-trained supply chain optimization model includes: acquiring a preset amount of historical supply chain data from the storage system; A preset amount of historical supply chain data is used as training data to train the initial supply chain optimization model to obtain the pre-trained supply chain optimization model.

4. The method according to claim 3, characterized in that After the initial supply chain optimization model is trained by using a preset amount of historical supply chain data as training data to obtain the pre-trained supply chain optimization model, the method further includes: Receive cross-domain supply chain data sent by cross-domain platforms; Inputting the cross-domain supply chain data into a pre-trained supply chain optimization model to output cross-domain supply chain optimization data; The cross-domain supply chain optimization data is sent to the cross-domain platform.

5. The method according to claim 1, characterized in that Also includes: Generate visual charts based on supply chain data stored in the storage system; The visualization chart is sent to a terminal device of a corresponding user, wherein the visualization chart is used for the user to perform analysis and interactive operations.

6. The method according to any one of claims 1 to 5, characterized in that: The server is connected to one or more of a log system, a monitoring system and an exception handling system.

7. A supply chain data processing device, characterized in that: Applied to the server, including: An acquisition module, used to receive original data sent by multiple supply chain systems, wherein the original data of the multiple supply chain systems are collected in real time by data collectors deployed in each supply chain system; A processing module, used for preprocessing the raw data to obtain supply chain data; A storage module, used to store the supply chain data in a storage system; The processing module is further used to input the supply chain data into a big data processing framework to output supply chain analysis data; The processing module is further used to input the supply chain data into a pre-trained supply chain optimization model to output supply chain optimization data; A decision module, used to generate a supply chain optimization report based on the supply chain analysis data and the supply chain optimization data; The sending module is used to send the supply chain optimization report to the terminal device of the corresponding user, wherein the supply chain optimization report is used to optimize each supply chain.

8. A server, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 6 when being executed by a processor.

Images