Method and system for processing full-link data of cold chain

Abstract

The invention discloses a cold chain full-link data processing method and system, and relates to the technical field of warehouse logistics. A specific embodiment of the method comprises the steps of performing association and fusion processing on attributes of entities corresponding to different data sources based on a pre-created unified data model to obtain an aggregated data set; performing data mining and prediction on the aggregated data set, and determining a target performance index which has the greatest influence on the cold chain quality based on a decision tree algorithm; displaying the aggregated data set and the target performance index on a visual interface; and in response to a received interaction instruction sent by a user through the visual interface, updating the full-link process according to the interaction instruction. According to the implementation mode, the data of the multiple data sources are subjected to fusion analysis and visual display, the preset full-link process scheme is conveniently updated through a visual interface by applying an interactive method so as to optimize the full-link process, and processing analysis and visual analysis of the full-link data of the cold chain in the smart park are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of warehousing and logistics, and in particular to a method and system for processing cold chain full-link data. Background Art

[0002] The existing cold chain full-link data visualization systems and methods for smart logistics parks usually focus on basic statistical display of operational data collected from various links of the cold chain. Therefore, they face data silos and integration problems, and it is difficult to effectively integrate data from different data sources, and it is impossible to provide a comprehensive view of the status of goods. Secondly, the existing systems lack significant dynamics and interactivity. Data visualization is usually a static chart that users cannot adjust or explore in depth as needed. In addition, threshold-based cold chain early warning methods are usually unable to handle complex data patterns, such as predicting the arrival time of goods based on current traffic conditions or identifying abnormal patterns to prevent potential damage to goods. In summary, the existing cold chain full-link logistics data processing methods and systems are not suitable for the processing and visualization analysis of the cold chain full-link data in smart parks due to their poor adaptability to complex environments, difficulty in integrating and processing multi-source data, and weak dynamic adjustment capabilities. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a method and system for processing cold chain full-link data, which can integrate and analyze data from multiple data sources such as orders, transportation and warehousing, and visualize them. It is convenient to update the preset full-link process plan through a visual interface using an interactive method to optimize the full-link process, and provide a practical visualization framework for monitoring and early warning of the full cold chain, thereby realizing processing analysis and visualization analysis of the full-link data of the cold chain in smart parks.

[0004] To achieve the above-mentioned purpose, according to one aspect of an embodiment of the present invention, a method for processing cold chain full-link data is provided, comprising: based on a pre-created unified data model, associating and fusing the attributes of entities corresponding to different data sources to obtain an aggregated data set; performing data mining and prediction on the aggregated data set, and determining the target performance indicator that has the greatest impact on the cold chain quality based on a decision tree algorithm; displaying the aggregated data set and the target performance indicator on a visualization interface; and in response to receiving an interactive instruction sent by a user through the visualization interface, updating the full-link process according to the interactive instruction.

[0005] Optionally, based on a pre-created unified data model, the attributes of entities corresponding to different data sources are associated and fused to obtain an aggregated data set, including: based on the data source mapping rules defined in the pre-created unified data model, the attributes of entities corresponding to different data sources are determined, a list of attributes of entities corresponding to each data source is obtained, and the attribute name, data type and data format of each attribute are obtained; similar attributes are obtained from the attribute list of entities corresponding to each data source, and based on the mapping rules of attribute names, data types and data format conversion rules defined in the unified data model, the attribute names of the similar attributes are mapped to a unified attribute name, and the data type and data format of each attribute are converted; according to the mapped unified attribute name, the attributes of entities corresponding to different data sources after the conversion are associated and fused to obtain an aggregated data set.

[0006] Optionally, similar attributes are obtained from the attribute list of the entity corresponding to each data source, including: determining whether each attribute is a text attribute according to the data type of each attribute; for the text attributes in the attribute list of the entity corresponding to each data source, similar attributes are obtained through content comparison or text recognition; for the non-text attributes in the attribute list of the entity corresponding to each data source, similar attributes are obtained through data sample inspection or pattern recognition.

[0007] Optionally, data mining and prediction are performed on the aggregated data set, and the target performance indicator with the greatest impact on the cold chain quality is determined based on a decision tree algorithm, including: performing feature extraction on the aggregated data set to obtain a feature set related to the cold chain quality; using a clustering algorithm to group the cold chain products according to temperature sensitivity to obtain each group of corresponding cold chain products or the orders to which the cold chain products belong, wherein the temperature sensitivity is determined based on the cargo damage rate of different cold chain products at different temperatures in historical data; for each group of corresponding cold chain products or the orders to which the cold chain products belong, using association rule mining technology to mine the potential relationship between each feature in the feature set and the cargo damage rate; and using a graph neural network, combined with road network information and weather information, predicting the expected arrival time of the cold chain products or the orders to which the cold chain products belong; based on a decision tree algorithm, according to the potential relationship between each feature in the feature set and the cargo damage rate, and the expected arrival time of the cold chain products or the orders to which the cold chain products belong, determine the target performance indicator with the greatest impact on the cold chain quality of each group of corresponding cold chain products or the orders to which the cold chain products belong.

[0008] Optionally, before displaying the aggregated data set and the target performance indicators on the visualization interface, the method further includes: obtaining the aggregated data set, the aggregated data set including the supply location coordinates and the destination coordinates corresponding to the cold chain product or the order to which the cold chain product belongs; loading a digital map according to the supply location coordinates and the destination coordinates, and displaying basic road attributes and vehicle information corresponding to the entire cold chain link in the digital map; loading the target performance indicators and generating an indicator dashboard; determining the warning subject according to the target performance indicators, and setting a warning legend according to the warning subject.

[0009] Optionally, a digital map is loaded according to the coordinates of the supply location and the coordinates of the destination, and basic road attributes and vehicle information corresponding to the entire cold chain link are displayed in the digital map, including: loading a digital map according to the coordinates of the supply location and the coordinates of the destination, the digital map including nodes and edges, wherein the nodes include smart logistics parks, supplier nodes and destination nodes, the edges indicate that cold chain products are circulated between two nodes, and the attribute data of the edges include basic road attributes and vehicle information.

[0010] Optionally, the method further includes: in response to receiving an interaction instruction sent by the user through the visualization interface, when it is determined that a simulation interface has been entered, performing a full-link process simulation according to the interaction instruction.

[0011] According to another aspect of an embodiment of the present invention, a system for processing cold chain full-link data is provided, including: a data aggregation processing module, which is used to associate and fuse the attributes of entities corresponding to different data sources based on a pre-created unified data model to obtain an aggregated data set; a data analysis and prediction module, which is used to perform data mining and prediction on the aggregated data set, and determine the target performance indicators that have the greatest impact on the cold chain quality based on a decision tree algorithm; a visualization display module, which is used to display the aggregated data set and the target performance indicators on a visualization interface; and an interactive feedback module, which is used to respond to receiving interactive instructions sent by a user through the visualization interface and update the full-link process according to the interactive instructions.

[0012] According to another aspect of an embodiment of the present invention, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for processing cold chain full-link data provided in an embodiment of the present invention.

[0013] According to another aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the method for processing cold chain full-link data provided by an embodiment of the present invention is implemented.

[0014] An embodiment of the above invention has the following advantages or beneficial effects: by associating and fusing the attributes of entities corresponding to different data sources based on a pre-created unified data model, an aggregated data set is obtained; data mining and prediction are performed on the aggregated data set, and the target performance indicators that have the greatest impact on the cold chain quality are determined based on a decision tree algorithm; the aggregated data set and the target performance indicators are displayed on a visualization interface; in response to receiving interactive instructions sent by the user through the visualization interface, a technical solution for updating the full-link process according to the interactive instructions can be used to fuse and analyze data from multiple data sources such as orders, transportation, and warehousing, and visualize them, so that the preset full-link process solution can be updated through the visualization interface using an interactive method to optimize the full-link process, providing a practical visualization framework for monitoring and early warning of the entire cold chain, and realizing processing analysis and visualization analysis of the full-link data of the cold chain in a smart park.

[0015] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention. Figure 1 Schematic diagram of main steps of a method for processing cold chain full-link data according to an embodiment of the present invention; Figure 2 This is a diagram of the cold chain full-link data processing system architecture of an embodiment of the present invention; Figure 3 It is a schematic diagram of the processing flow of cold chain full link data according to an embodiment of the present invention; Figure 4 2 is a schematic diagram of main modules of a system for processing cold chain full-link data according to an embodiment of the present invention; Figure 5 is an exemplary system architecture diagram to which embodiments of the present invention may be applied; Figure 6 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0018] Cold chain products (such as fruits, dairy products, frozen and refrigerated products, etc.) need to maintain specific temperature and cooling conditions during manufacturing, warehousing, transportation, distribution and sales, so they need smart logistics parks to provide more accurate and efficient full-chain management. The traditional cold chain system can only manage each environment independently due to the independence of the logistics links.

[0019] With the opening of the entire chain of smart parks, the full-chain management of the cold chain has been put on the agenda. The full-chain management of the cold chain is to comprehensively utilize the transportation information, geographic information, and vehicle information in the full-chain process of the cold chain, and plan a complete set of goods status monitoring and early warning solutions from the storage to the delivery and then to the hands of customers, taking into account the status of the goods, the arrival time specified by the order, the coordination requirements of each link, the shelf life of the goods in the full-chain circulation process, the temperature and humidity conditions and other constraints. As one of the key technologies of the cold chain full-chain management system, the full-chain circulation status monitoring ensures the health of the goods in each link and the smooth fulfillment of the order. Effective circulation status monitoring can greatly improve the order completion efficiency and customer satisfaction; however, the data collection of the full chain is more multi-source, and the data processing and analysis are more complicated; the traditional visualization management of cold chain data is generally based on basic data integration, simple data display (using basic icons and maps to display real-time data) and threshold-based early warning; some more advanced systems have added trend analysis and basic prediction functions to the cold chain full-chain data visualization system, but they are basically limited to statistical methods and lack adaptability to complex scenarios and dynamic changes.

[0020] Due to the complexity of the tasks and links of the entire chain of circulation, the participation of multiple systems such as transportation, storage, distribution, and orders is required. At the same time, the details also involve multi-source heterogeneous data such as temperature and humidity of cargo transportation, vehicle performance, road network status, weather conditions, cargo status, etc., the constraints brought by the natural geographical environment, the requirements of cargo status, and the requirements of order tasks, resulting in the difficulty of full-chain circulation monitoring and early warning is the complexity of multi-source data fusion. Personnel responsible for monitoring and early warning tasks need to face a large amount of constantly changing spatiotemporal data, order data, and warehouse data extracted from multiple systems. This requires the use of data visualization technology to visualize the data generated by multiple links and the status information of goods, key nodes, and the correlation between multiple types of data to the full-chain status monitoring personnel.

[0021] The final monitoring and early warning decision needs to be adjusted and decided by the staff, so a lot of trial and error and verification of human-computer interaction is required. The initial planning generated by the system may include the estimated delivery time of goods, route selection, vehicle allocation, cargo loading order, etc. However, these automatically generated plans may need to be adjusted according to actual conditions, such as adjusting the route according to real-time traffic conditions, etc. Designing innovative data visualization and human-computer interaction methods is particularly critical. This can not only give full play to the experience and knowledge of planners, improve the accuracy and flexibility of planning, but also effectively deal with various challenges in complex and changing logistics environments.

[0022] The present invention aims to solve a series of technical challenges in the cold chain full-link data visualization system of the smart logistics park, mainly targeting the deficiencies of existing technologies in data integration, dynamic interaction and adaptability to complex environments, while meeting the high standards of smart logistics parks for accurate tracking and management. Specifically, in response to the data island and integration problems of the existing system, the present invention proposes to implement an advanced data integration platform. The platform will integrate data from different logistics links, including GPS positioning, temperature and humidity monitoring, operation trajectory, as well as road network data, vehicle operation data and weather data. Such deep data integration not only helps to fully understand the status of the supply chain, but also enables a comprehensive analysis of the impact on the arrival time and quality of goods; secondly, in response to the deficiencies of the existing system in dynamic interactivity, the present invention will develop a dynamic and interactive data visualization interface. This interface will enable users to conduct in-depth data analysis and monitoring based on real-time conditions and personal preferences, for example, dynamically tracking vehicles on a map and adjusting the data display of a specific warehouse, thereby improving the user's decision-making efficiency and accuracy; considering the limitations of the existing system in processing complex data patterns and predictive capabilities, the present invention will introduce machine learning technology to develop intelligent early warning and prediction models. These models will be able to accurately predict cargo arrival times, identify unusual patterns, and prevent potential cargo damage or delays, thereby enhancing the system’s predictive capabilities and responsiveness.

[0023] In summary, the technical solution proposed in the present invention aims to build a comprehensive and efficient data visualization system for the cold chain of smart logistics parks. This system will overcome the limitations of existing technologies and improve the operational efficiency and management level of smart logistics parks. By effectively integrating multi-source data and providing a dynamic, interactive data visualization interface and advanced intelligent early warning mechanism, the present invention will provide a comprehensive and efficient monitoring and early warning solution for the full-link cold chain management of smart parks, thereby significantly improving the transparency and responsiveness of the entire supply chain.

[0024] Figure 1 Schematic diagram of the main steps of the method for processing cold chain full link data according to an embodiment of the present invention. Figure 1As shown, the method for processing cold chain full-link data of an embodiment of the present invention mainly includes the following steps S101 to S104.

[0025] Step S101: Based on the pre-created unified data model, the attributes of the corresponding entities of different data sources are associated and merged to obtain an aggregated data set. The unified data model defines key entities and their attributes. For orders, their attributes include {order number, customer information, order date, expected and actual delivery time, order status} and other attributes shown in the following set. Capital letters are used to represent entities, and lowercase letters are used to represent their attributes, for example: represents an order entity, then ,in express No. In this unified data model, the data type and data format of each entity attribute are pre-set. Taking time-related attributes (order production date, estimated delivery time, etc. are all time-related attributes) as an example, a specific date and time format (such as the date and time format specified by ISO 8601) can be used uniformly.

[0026] According to one embodiment of the present invention, based on a pre-created unified data model, the attributes of entities corresponding to different data sources are associated and fused to obtain an aggregated data set, which may specifically include: based on the data source mapping rules defined in the pre-created unified data model, the attributes of entities corresponding to different data sources are determined, an attribute list of entities corresponding to each data source is obtained, and the attribute name, data type and data format of each attribute are obtained; similar attributes are obtained from the attribute list of entities corresponding to each data source, and based on the mapping rules of attribute names, data types and data format conversion rules defined in the unified data model, the attribute names of the similar attributes are mapped to a unified attribute name, and the data type and data format of each attribute are converted; according to the mapped unified attribute name, the attributes of entities corresponding to different data sources after the conversion are associated and fused to obtain an aggregated data set.

[0027] In the embodiment of the present invention, in the unified data model, data source mapping rules are defined to determine the attributes of corresponding entities in different data sources. The data source refers to each subsystem in the cold chain, such as the warehouse management system, order management system, vehicle management system, etc. In the embodiment of the present invention, it is necessary to correspond the data from different sources with the entities and attributes in the data model, and the data source provides attribute information for the entity. The corresponding result is, for example: warehouse entity W, , then, the attribute list of the entity corresponding to each data source can be obtained according to the key attributes in the data sources of each subsystem, wherein each attribute in the attribute list shall include but not be limited to the field name, type, format and purpose of the attribute. After that, similar attributes will be obtained from the attribute list of the entity corresponding to each data source, and based on the mapping rules, data types and data format conversion rules of the attribute names defined in the unified data model, the attribute names of the similar attributes will be mapped to unified attribute names, and the data types and data formats of each attribute will be converted; according to the mapped unified attribute names, the attributes of the entities corresponding to different data sources after the conversion will be associated and fused to obtain an aggregated data set. For example, order data and warehouse data can be associated and fused according to order numbers or other key attributes. Finally, the aggregated data set is saved in a central database or data lake.

[0028] According to one embodiment of the present invention, obtaining similar attributes from the attribute list of the entity corresponding to each data source may specifically include: determining whether each attribute is a text attribute according to the data type of each attribute; obtaining similar attributes for the text attributes in the attribute list of the entity corresponding to each data source through content comparison or text recognition; obtaining similar attributes for the non-text attributes in the attribute list of the entity corresponding to each data source through data sample inspection or pattern recognition. Specifically, for text attributes, similarity is confirmed through content comparison or text recognition. After preprocessing the text, the text can be converted into a dense vector by using a pre-trained language model such as Word2Vec (a word segmentation tool) or BERT, and the semantic similarity between the texts can be evaluated by calculating the similarity between the vectors (such as cosine similarity). For non-text attributes, the attribute list is checked for data samples or pattern recognition methods to find similar attributes. If there are two time series, the similarity of the two attributes can be calculated by dynamic time warping (DTW) or other distance calculation formulas (such as Euclidean distance, Manhattan distance); for attributes with specific patterns or structures (such as codes, etc.), pattern matching algorithms (such as regular expressions, string matching algorithms) can be used to identify similar attributes.

[0029] Step S102: performing data mining and prediction on the aggregated data set, and determining the target performance indicator with the greatest impact on the cold chain quality based on a decision tree algorithm.

[0030] According to one embodiment of the present invention, data mining and prediction are performed on the aggregated data set, and the target performance indicator with the greatest impact on the cold chain quality is determined based on a decision tree algorithm. Specifically, it may include: extracting features from the aggregated data set to obtain a feature set related to the cold chain quality; using a clustering algorithm to group the cold chain products according to temperature sensitivity to obtain the cold chain products corresponding to each group or the orders to which the cold chain products belong, wherein the temperature sensitivity is determined according to the cargo damage rate of different cold chain products at different temperatures in historical data; for each group of corresponding cold chain products or the orders to which the cold chain products belong, using association rule mining technology to mine the potential relationship between each feature in the feature set and the cargo damage rate; and predicting the expected arrival time of the cold chain products or the orders to which the cold chain products belong through a graph neural network in combination with road network information and weather information; based on a decision tree algorithm, according to the potential relationship between each feature in the feature set and the cargo damage rate, and the expected arrival time of the cold chain products or the orders to which the cold chain products belong, determine the target performance indicator with the greatest impact on the cold chain quality of each group of corresponding cold chain products or the orders to which the cold chain products belong.

[0031] According to an embodiment of the present invention, when step S102 is specifically performed, it may specifically include the following steps: Step 1: Perform data cleaning on the aggregated data set, remove outliers and noise, and perform data normalization and transformation to prepare a data set suitable for analysis; Step 2: Extract key features. According to business logic and data science methods, extract key features that determine the quality of the cold chain, such as temperature fluctuations and transportation time, and perform feature transformation to extract trends and periodic factors. Specifically, the time series can be decomposed into trends, periodicity, and random parts through time series analysis or time series decomposition. Periodicity can be defined in business as fluctuations that occur repeatedly within a fixed period, such as temperature changes, transportation frequency, etc. The purpose of feature transformation is to be better recognized and utilized by the model, and normalization and standardization is one method; Step 3: Use clustering algorithms (such as K-means or DBSCAN) to group the goods according to temperature sensitivity and find cold chain products or orders with the same model. The temperature sensitivity can be determined by the damage rate of cold chain products at different temperatures in historical data, and the temperature sensitivity of goods can also be classified according to the relevant standard freight regulations; Step 4: Apply association rule mining technology, such as Apriori or FP-Growth algorithm, to mine the potential relationship between transportation routes, commodity attributes, warehousing conditions and cargo damage (i.e., cargo damage rate). In the specific implementation, first collect data related to cold chain logistics, such as cargo (in this invention, cargo refers to cold chain products) identification ID, transportation route, transportation time, commodity type, storage temperature, cargo damage, etc. Encode the data, convert the text attributes into a numerical format suitable for algorithm processing, use the FP-Growth algorithm to mine association rules, analyze the preprocessed data set, and set appropriate support and confidence thresholds. For example, the support threshold is set to 0.05, and the confidence threshold is set to 0.6. Extract frequent item sets and generate association rules that meet the thresholds. Assume that the following association rules are obtained after analysis: Rule 1: {Transportation route = mountain road, Product type = perishable food} => {Cargo damaged = yes} (support = 0.07, confidence = 0.8); Rule 2: {Storage temperature > 25°C, Product type = medicine} => {Goods damaged = yes} (support = 0.05, confidence = 0.75); Then, from rules 1 and 2, it can be concluded that perishable foods transported via mountain roads have a high risk of spoilage. Possible reasons include long transportation routes, poor road conditions, or improper temperature control during transportation. Step 5: Use additional data such as road network information and weather information through graph neural networks to couple transportation time patterns and predict possible arrival times or delays. In specific implementations, the road network can be defined as a graph, where nodes can be intersections or road sections, and edges represent road section connections. Associate road network attributes (such as road length, traffic flow) and external data (such as weather conditions) with nodes or edges. Select a GNN architecture suitable for the task, such as Graph Convolutional Network (GCN), Graph Attention Network (GAT), or other variants. Design the corresponding network structure, number of layers, and number of neurons. Use GNN to process road network graphs, where node features include road section attributes and weather information. Use the convolutional layer of GNN to integrate the neighbor information of each node to capture the spatial relationship of the road network. Use the time-dependent characteristics of GNN to integrate past traffic data and weather data to predict future transportation time patterns; Step 6: Use decision tree analysis to identify and recommend decision points for improving transportation and storage conditions. Specifically, assume that there is a dataset containing historical transportation and storage data, which includes information such as temperature records, transportation time, route information, storage conditions, and cargo damage. To use decision tree analysis to find out the key factors affecting cargo quality, you can select potential factors affecting cargo quality as features, such as temperature, humidity, transportation time, route type, etc. Define whether the cargo is damaged as the target variable and build a model by applying the decision tree algorithm. Analyze the structure of the decision tree, understand the impact of different features on cargo quality, and identify the key decision points in the model, that is, those nodes that have the greatest impact on the prediction results. A typical example may be the decision point: If the transportation time exceeds 6 hours and the external temperature exceeds 30°C, the damage rate of perishable food increases significantly.

[0032] In an embodiment of the present invention, step S102 may, for example, be to combine key feature extraction, data clustering, data mining, prediction, and decision tree algorithm on the aggregated data set, train a machine learning model, and then determine the target performance indicator that has the greatest impact on the cold chain quality based on the machine learning model.

[0033] Step S103: displaying the aggregated data set and the target performance indicator on a visualization interface.

[0034] According to one embodiment of the present invention, before displaying the aggregated data set and the target performance indicators on a visualization interface, it may also include: obtaining the aggregated data set, the aggregated data set including the supply location coordinates and the destination coordinates corresponding to the cold chain product or the order to which the cold chain product belongs; loading a digital map according to the supply location coordinates and the destination coordinates, and displaying the basic road attributes and vehicle information corresponding to the entire cold chain link in the digital map; loading the target performance indicators and generating an indicator dashboard; determining the warning subject according to the target performance indicators, and setting a warning legend according to the warning subject.

[0035] In one embodiment, a digital map is loaded according to the coordinates of the supply site and the coordinates of the destination, and basic road attributes and vehicle information corresponding to the entire cold chain link are displayed in the digital map. Specifically, it may include: loading a digital map according to the coordinates of the supply site and the coordinates of the destination, the digital map including nodes and edges, wherein the nodes include smart logistics parks, supplier nodes and destination nodes, the edges indicate that cold chain products are circulated between two nodes, and the attribute data of the edges include basic road attributes and vehicle information.

[0036] According to an embodiment of the present invention, in specific implementation, this step may include the following steps: Step 1: Receive the supply location coordinates of the goods in the warehouse data and the destination coordinates of the goods in the order data; Step 2: Load the digital map according to the received coordinate information. The digital map is represented by G. The type of digital map can be raster map, vector map, image map, etc. The nodes in the map represent the smart logistics park V C , Supplier Node V S and the destination node V M , the edge represents the circulation of cold chain products between two nodes, and the attribute data of the edge are E S (representing the goods flow data from the supplier node to the smart logistics park), E M (representing the goods flow data from the smart logistics park to the goods destination), the overall digital map is expressed as G(V,E), and different types of nodes and edges are represented by different icon colors; Step 3: Obtain the vehicle data from suppliers to the smart logistics park in the warehouse data, and use it together with the road traffic data as features, and incorporate these features into the attribute data of the edges between nodes: , ,in, Represents the vehicle data from suppliers to the smart logistics park. The optional route data from the supplier to the smart logistics park is represented by a solid line on the map showing the route that the vehicle has traveled, and a dotted line showing the route to be completed by the vehicle. Similarly, the vehicle data and optional route data from the smart logistics park to the destination are obtained as follows: ; Step 4: The basic attributes of the road include the start time, total distance, traffic conditions, total time, road type, and weather conditions; Step 5: Vehicle information includes vehicle fuel loading, fuel consumption, vehicle speed, cargo hold capacity, temperature and humidity, loaded cargo data, and location data (i.e., current location); Step 6: Load the key performance indicator dashboard. The key performance indicators are aggregated and displayed by batch and type of goods status {in transit, in stock, delivered}, showing key data such as the quantity of goods, temperature and humidity, and usable time; an overview of the full-link indicators of goods: loss rate of goods, average delivery time, number of abnormal temperature and humidity, etc.; Step 7: Setting up the warning legend: according to the warning situations in different dimensions mentioned above, the warning legend is set up with goods, roads, areas, and vehicles as the warning subjects; if the area affects the arrival of goods, the border of the area will be marked with a striking color, etc.; Step 8: The relevant full-link process data can be exported.

[0037] Step S104: in response to receiving an interaction instruction sent by the user through the visual interface, updating the full-link process according to the interaction instruction.

[0038] According to another embodiment of the present invention, the method may further include: in response to receiving an interaction instruction sent by the user through the visualization interface, when it is determined that a simulation interface has been entered, performing a full-link process simulation according to the interaction instruction.

[0039] According to an embodiment of the present invention, during specific implementation, for example, the following steps may be included: Step 1: Full-link monitoring managers can simulate the full-link solution in the interactive control module according to the requirements of the full-link operation plan through the real-time analysis module, and adjust the cargo transportation batch, sku (in the e-commerce scenario, it represents a product) selection batch, and vehicle route selection. The data visualization module adjusts and displays the adjusted modules and updates the final completion time. The manager completes a human-computer interaction process and adjusts parameters (such as temperature thresholds and route selection) through interactive controls such as sliders and drop-down menus, and immediately sees how these adjustments affect risk assessment; Step 2: Adjust and modify the preset plan based on the actual implementation of the preset plan for full-link circulation; Step 3: Integrate user feedback mechanism to collect user experience and suggestions and use them to optimize the system.

[0040] Figure 2 FIG. 1 is a diagram of the cold chain full-link data processing system architecture of an embodiment of the present invention. Figure 2 As shown, in an embodiment of the present invention, the cold chain full-link data processing system of the smart logistics park mainly includes the following functional module layers connected in sequence.

[0041] Full-link data integration layer: responsible for collecting key data from each subsystem of the smart park, such as order data, transportation data, and warehousing data. The data collected from each system will be aggregated according to the full-link scenario requirements through the data aggregation module, and the aggregated data will conform to a unified format and standard through the data standardization module, providing a solid foundation for subsequent analysis. For example, obtaining order details from the order management system, capturing real-time location information from the transportation management system, and collecting environmental parameters such as temperature and humidity from the warehouse management system. They all collect and store data according to different data primary keys (unique identification numbers) in their respective systems. For example: sku is the unique identification number in the warehousing system, and the order number is the unique identification number in the order system. Therefore, data aggregation operations are required when integrating data.

[0042] Full-link data processing and analysis layer: The aggregated data is cleaned, normalized and converted through the data preprocessing module to ensure data quality. The processed data is input into the cold chain feature analysis module. In view of the different sensitivity coefficients of different cold chain products to temperature and time, the cold chain data is deeply analyzed according to the characteristics of the goods. For example, the temperature, humidity and time conditions of the goods are obtained from the warehousing system, the order details are obtained from the order management system, and the real-time location information is captured from the transportation management system. Advanced algorithms such as time series analysis, clustering, and association rule mining are used to conduct in-depth data fusion and analysis. For example, the vehicle location and warehouse environment data are integrated to analyze the factors that have the greatest impact on the cold chain product; at the same time, machine learning algorithms are used to identify patterns and trends in the data, such as the vehicle's operating mode, possible delay conditions, etc.; based on the analysis results, the key indicators of cold chain logistics are predicted and optimization suggestions are put forward.

[0043] Full-link data visualization output layer: In the data visualization output layer of the cold chain full-link monitoring system of the smart logistics park, the core functions focus on the data visualization cockpit, key performance indicator dashboard, risk management and early warning visualization, and customized reports and data export. This layer transforms complex data flows into intuitive visual representations, providing a comprehensive and interactive cockpit interface that enables managers to monitor key performance indicators such as transportation efficiency, temperature anomalies, etc. in real time, and display this information through dynamic charts and maps. At the same time, the risk management and early warning system can timely identify and visualize potential risks and anomalies, supplemented by intelligent early warning mechanisms to ensure timely response and intervention. In addition, the system also provides powerful customized reporting functions, allowing users to generate detailed data reports and analyses based on specific needs, which can be easily exported to support decision-making and long-term strategic planning. Through these functions, the data visualization output layer greatly enhances managers' transparency and control over the entire cold chain process, and improves the efficiency and accuracy of decision-making.

[0044] Full-link backend support layer: As the cornerstone of the safe operation of the entire system, it securely stores all aggregated and processed data and ensures data security and correct access rights; at the same time, it ensures the efficiency of data processing and visualization by detecting the overall performance of the system.

[0045] Full-link user interaction control layer: dedicated to improving user operational efficiency and experience, this layer provides an intuitive and easy-to-operate interface that allows users to interact with the system efficiently, including adjusting visualization parameters, conducting real-time data searches, and in-depth analysis. The user interaction processing module optimizes the interaction logic of the user interface to ensure that users can quickly and intuitively access the required information and functions. The real-time data query and analysis module supports users to conduct in-depth exploration and comparative analysis of real-time logistics data to help identify key trends and potential problems. The feedback and optimization module not only collects user feedback to continuously improve the system's performance and user experience, but also ensures that the system can make adaptive adjustments based on user operating habits and feedback. Through such a design, the full-link interactive control layer greatly improves managers' control capabilities and decision-making efficiency over the entire cold chain system, and enhances the system's responsiveness and flexibility.

[0046] Figure 3 FIG. 1 is a schematic diagram of the processing flow of cold chain full link data according to an embodiment of the present invention. Figure 3 As shown, in an embodiment of the present invention, the processing flow of cold chain full-link data mainly includes: determining the data source required by the platform, then determining the data collection frequency, creating a unified data model, determining the entity attribute data type and format; then, performing data source mapping, identifying key attributes to form a list, and performing similar attribute association. When performing similar attribute association, first determine whether it is time series data. If so, use distance calculation to perform similarity calculation. Otherwise, determine whether it is text data. If it is text data, perform text recognition to calculate similarity. Otherwise, manually identify and confirm. After that, according to the specific mapping rules defined by the unified data model, data association is performed to form an aggregated data set. Data cleaning is performed on the aggregated data set, and then data analysis and model construction are performed; then, coordinate data, node data, vehicle data, and traffic data are received, and a digital map is loaded to build a data cockpit, a key performance indicator dashboard is loaded, and an early warning icon is set to display a visual interface. The user performs full-link human-computer interaction through the visual interface, and the system determines whether to enter the simulation interface. If so, a full-link process simulation is performed to identify key nodes; otherwise, the difference between the planned process and the actual process is compared, and the process is manually updated.

[0047] Figure 4 Schematic diagram of the main modules of the cold chain full link data processing system according to an embodiment of the present invention. Figure 4 As shown, the cold chain full-link data processing system 400 of the embodiment of the present invention mainly includes: a data aggregation processing module 401, a data analysis and prediction module 402, a visualization display module 403 and an interactive feedback module 404.

[0048] The data aggregation processing module 401 is used to associate and fuse the attributes of entities corresponding to different data sources based on a pre-created unified data model to obtain an aggregated data set; A data analysis and prediction module 402 is used to perform data mining and prediction on the aggregated data set, and determine the target performance indicator that has the greatest impact on the cold chain quality based on a decision tree algorithm; A visualization display module 403, used to display the aggregated data set and the target performance indicator on a visualization interface; The interactive feedback module 404 is used to respond to receiving an interactive instruction sent by the user through the visual interface and update the full-link process according to the interactive instruction.

[0049] According to one embodiment of the present invention, the data aggregation processing module 401 can also be used to: determine the attributes of entities corresponding to different data sources based on the data source mapping rules defined by a pre-created unified data model, obtain the attribute list of the entity corresponding to each data source, and obtain the attribute name, data type and data format of each attribute; obtain similar attributes from the attribute list of the entity corresponding to each data source, and map the attribute names of the similar attributes to a unified attribute name based on the attribute name mapping rules, data type and data format conversion rules defined by the unified data model, and convert the data type and data format of each attribute; according to the mapped unified attribute name, associate and merge the attributes of the entities corresponding to different data sources after the conversion to obtain an aggregated data set.

[0050] According to another embodiment of the present invention, when the data aggregation processing module 401 obtains similar attributes from the attribute list of the entity corresponding to each data source, it can be specifically used to: determine whether each attribute is a text attribute according to the data type of each attribute; for the text attributes in the attribute list of the entity corresponding to each data source, obtain similar attributes through content comparison or text recognition; for the non-text attributes in the attribute list of the entity corresponding to each data source, obtain similar attributes through data sample inspection or pattern recognition.

[0051] According to another embodiment of the present invention, the data analysis and prediction module 402 can also be used for: performing feature extraction on the aggregated data set to obtain a feature set related to the cold chain quality; using a clustering algorithm to group the cold chain products according to temperature sensitivity to obtain each group of corresponding cold chain products or the orders to which the cold chain products belong, wherein the temperature sensitivity is determined according to the cargo damage rates of different cold chain products at different temperatures in historical data; for each group of corresponding cold chain products or the orders to which the cold chain products belong, using association rule mining technology to mine the potential relationship between each feature in the feature set and the cargo damage rate; and using a graph neural network, combined with road network information and weather information, predicting the expected arrival time of the cold chain products or the orders to which the cold chain products belong; based on a decision tree algorithm, according to the potential relationship between each feature in the feature set and the cargo damage rate, as well as the expected arrival time of the cold chain products or the orders to which the cold chain products belong, determining the target performance indicator that has the greatest impact on the cold chain quality of each group of corresponding cold chain products or the orders to which the cold chain products belong.

[0052] According to another embodiment of the present invention, the visualization display module 403 can also be used for: obtaining the aggregated data set before displaying the aggregated data set and the target performance indicators on the visualization interface, the aggregated data set including the supply location coordinates and the destination coordinates corresponding to the cold chain product or the order to which the cold chain product belongs; loading a digital map according to the supply location coordinates and the destination coordinates, and displaying the basic road attributes and vehicle information corresponding to the entire cold chain link in the digital map; loading the target performance indicators and generating an indicator dashboard; determining the warning subject according to the target performance indicators, and setting a warning legend according to the warning subject.

[0053] According to another embodiment of the present invention, when the visualization display module 403 loads a digital map according to the supply location coordinates and the destination coordinates, and displays the basic road attributes and vehicle information corresponding to the entire cold chain link in the digital map, it can be specifically used to: load a digital map according to the supply location coordinates and the destination coordinates, the digital map including nodes and edges, wherein the nodes include a smart logistics park, a supplier node and a destination node, the edges indicate that cold chain products are circulated between two nodes, and the attribute data of the edges include basic road attributes and vehicle information.

[0054] According to another embodiment of the present invention, the interactive feedback module 404 can also be used to: in response to receiving an interactive instruction sent by the user through the visual interface, when it is determined to enter the simulation interface, perform a full-link process simulation according to the interactive instruction.

[0055] According to the technical solution of the embodiment of the present invention, based on a pre-created unified data model, the attributes of the entities corresponding to different data sources are associated and fused to obtain an aggregated data set; data mining and prediction are performed on the aggregated data set, and the target performance indicators with the greatest impact on the cold chain quality are determined based on a decision tree algorithm; the aggregated data set and the target performance indicators are displayed on a visualization interface; in response to receiving interactive instructions sent by the user through the visualization interface, the technical solution of updating the full-link process according to the interactive instructions can perform fusion analysis and visual display of data from multiple data sources such as orders, transportation and warehousing, so that the preset full-link process scheme can be updated through the visualization interface using an interactive method to optimize the full-link process, providing a practical visualization framework for monitoring and early warning of the entire cold chain, and realizing processing analysis and visualization analysis of the full-link data of the cold chain in the smart park.

[0056] Figure 5 An exemplary system architecture 500 is shown to which a method for processing cold chain full-link data or a system for processing cold chain full-link data according to an embodiment of the present invention may be applied.

[0057] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, 503, a network 504 and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, 503 and server 505. Network 504 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0058] Users can use terminal devices 501, 502, 503 to interact with server 505 through network 504 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 501, 502, 503, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0059] The terminal devices 501 , 502 , and 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0060] Server 505 can be a server that provides various services, such as a background management server that provides support for logistics and transportation websites browsed by users using terminal devices 501, 502, and 503 (for example only). The background management server can associate and fuse the attributes of entities corresponding to different data sources based on a pre-created unified data model for the received cold chain full-link data processing request to obtain an aggregated data set; perform data mining and prediction on the aggregated data set, and determine the target performance indicators that have the greatest impact on the quality of the cold chain based on a decision tree algorithm; display the aggregated data set and the target performance indicators on a visual interface; in response to receiving an interactive instruction sent by the user through the visual interface, update the full-link process according to the interactive instruction, and feed back the processing results (such as the updated full-link process - for example only) to the terminal device.

[0061] It should be noted that the method for processing the cold chain full-link data provided in the embodiment of the present invention is generally executed by the server 505 , and accordingly, the system for processing the cold chain full-link data is generally set in the server 505 .

[0062] It should be understood that Figure 5 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0063] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 of a terminal device or a server suitable for implementing an embodiment of the present invention. Figure 6 The terminal device or server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0064] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0065] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0066] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present invention are executed.

[0067] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0068] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0069] The units or modules involved in the embodiments of the present invention may be implemented in software or in hardware. The described units or modules may also be provided in a processor. For example, they may be described as follows: a processor includes a data aggregation processing module, a data analysis and prediction module, a visualization display module, and an interactive feedback module. Among them, the names of these units or modules do not constitute a limitation on the units or modules themselves in certain circumstances. For example, the interactive feedback module may also be described as "a module for responding to receiving interactive instructions sent by a user through the visual interface and updating the full-link process according to the interactive instructions."

[0070] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs. When the above one or more programs are executed by a device, the device includes: based on a pre-created unified data model, the attributes of entities corresponding to different data sources are associated and fused to obtain an aggregated data set; data mining and prediction are performed on the aggregated data set, and the target performance indicator with the greatest impact on the quality of the cold chain is determined based on a decision tree algorithm; the aggregated data set and the target performance indicator are displayed on a visual interface; in response to receiving an interactive instruction sent by a user through the visual interface, the full-link process is updated according to the interactive instruction.

[0071] According to the technical solution of the embodiment of the present invention, based on a pre-created unified data model, the attributes of the entities corresponding to different data sources are associated and fused to obtain an aggregated data set; data mining and prediction are performed on the aggregated data set, and the target performance indicators with the greatest impact on the cold chain quality are determined based on a decision tree algorithm; the aggregated data set and the target performance indicators are displayed on a visualization interface; in response to receiving interactive instructions sent by the user through the visualization interface, the technical solution of updating the full-link process according to the interactive instructions can perform fusion analysis and visual display of data from multiple data sources such as orders, transportation and warehousing, so that the preset full-link process scheme can be updated through the visualization interface using an interactive method to optimize the full-link process, providing a practical visualization framework for monitoring and early warning of the entire cold chain, and realizing processing analysis and visualization analysis of the full-link data of the cold chain in the smart park.

[0072] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for processing cold chain full link data, characterized in that: include: Based on the pre-created unified data model, the attributes of the corresponding entities of different data sources are associated and fused to obtain an aggregated data set; Performing data mining and prediction on the aggregated data set, and determining the target performance indicator that has the greatest impact on cold chain quality based on a decision tree algorithm; Displaying the aggregated data set and the target performance indicator on a visualization interface; In response to receiving an interaction instruction sent by the user through the visualization interface, the full-link process is updated according to the interaction instruction.

2. The method according to claim 1, characterized in that Based on the pre-created unified data model, the attributes of the corresponding entities of different data sources are associated and fused to obtain an aggregated data set, including: Based on the data source mapping rules defined in the pre-created unified data model, determine the attributes of entities corresponding to different data sources, obtain the attribute list of entities corresponding to each data source, and obtain the attribute name, data type and data format of each attribute; Acquire similar attributes from the attribute list of the entity corresponding to each data source, and map the attribute names of the similar attributes to a unified attribute name based on the mapping rules, data types, and data format conversion rules of the attribute names defined in the unified data model, and convert the data type and data format of each attribute; According to the mapped unified attribute name, the attributes of the corresponding entities of different data sources after conversion are associated and fused to obtain an aggregated data set.

3. The method according to claim 2, characterized in that Obtain similar attributes from the attribute list of the entity corresponding to each data source, including: Determine whether each attribute is a text attribute according to the data type of each attribute; For the text attributes in the attribute list of the entity corresponding to each data source, similar attributes are obtained through content comparison or text recognition; For the non-text attributes in the attribute list of the entity corresponding to each data source, similar attributes are obtained through data sample inspection or pattern recognition.

4. The method according to claim 1, characterized in that: Data mining and prediction are performed on the aggregated data set to determine the target performance indicators that have the greatest impact on the cold chain quality based on a decision tree algorithm, including: Performing feature extraction on the aggregated data set to obtain a feature set related to cold chain quality; Using a clustering algorithm to group cold chain products according to temperature sensitivity, obtaining cold chain products corresponding to each group or orders to which cold chain products belong, wherein the temperature sensitivity is determined according to the damage rates of different cold chain products at different temperatures in historical data; For each group of corresponding cold chain products or orders to which the cold chain products belong, association rule mining technology is used to mine the potential relationship between each feature in the feature set and the cargo damage rate; and the expected arrival time of the cold chain products or the orders to which the cold chain products belong is predicted by combining road network information and weather information through a graph neural network; Based on the decision tree algorithm, according to the potential relationship between each feature in the feature set and the cargo damage rate, and the expected arrival time of the cold chain products or the orders to which the cold chain products belong, the target performance indicator that has the greatest impact on the cold chain quality of each group of corresponding cold chain products or the orders to which the cold chain products belong is determined.

5. The method according to claim 1, characterized in that Before displaying the aggregated data set and the target performance indicator on a visualization interface, the method further includes: Acquire the aggregated data set, where the aggregated data set includes the coordinates of the supply location and the coordinates of the destination corresponding to the cold chain product or the order to which the cold chain product belongs; Loading a digital map according to the coordinates of the supply location and the coordinates of the destination, and displaying basic road attributes and vehicle information corresponding to the entire cold chain link in the digital map; Loading the target performance indicator and generating an indicator dashboard; The warning subject is determined according to the target performance indicator, and the warning legend is set according to the warning subject.

6. The method according to claim 5, characterized in that The digital map is loaded according to the coordinates of the supply location and the coordinates of the destination, and basic road attributes and vehicle information corresponding to the entire cold chain link are displayed in the digital map, including: A digital map is loaded according to the coordinates of the supply location and the coordinates of the destination, wherein the digital map includes nodes and edges, wherein the nodes include a smart logistics park, a supplier node, and a destination node, an edge indicates that cold chain products are circulated between two nodes, and the attribute data of the edge includes basic road attributes and vehicle information.

7. The method according to claim 1, characterized in that The method further comprises: In response to receiving an interactive instruction sent by the user through the visualization interface, when it is determined that a simulation interface has been entered, a full-link process simulation is performed according to the interactive instruction.

8. A cold chain full-link data processing system, characterized in that: include: The data aggregation processing module is used to associate and fuse the attributes of entities corresponding to different data sources based on a pre-created unified data model to obtain an aggregated data set; A data analysis and prediction module, used to perform data mining and prediction on the aggregated data set, and determine the target performance indicator that has the greatest impact on the cold chain quality based on a decision tree algorithm; A visualization display module, used to display the aggregated data set and the target performance indicator on a visualization interface; The interactive feedback module is used to respond to receiving an interactive instruction sent by the user through the visual interface and update the full-link process according to the interactive instruction.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images