Express logistics risk mining processing method, device and equipment and storage medium

Abstract

The invention relates to the technical field of information processing, in particular to an express logistics risk mining processing method, device and equipment and a storage medium, and aims to predict the trend information of the number of problem items of an express service in a future period of time by using a problem item number prediction model, and calculate transportation and storage data by using a statistical analysis method. Carrying out risk analysis based on the trend information and the descriptive statistics to obtain a risk analysis result, improving the risk prediction capability by using big data and artificial intelligence technologies, and optimizing the transportation route and the storage layout based on the risk analysis result to obtain transportation and storage optimization information. According to the method, the visual processing suggestion report is generated according to the transportation and storage optimization information, the visual processing suggestion report is sent to the management terminal, potential market risks are prepared to be dealt with in advance, the rationality of transportation routes and storage layouts is improved, and then the express logistics risk is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of information processing, and in particular, to a method, device, equipment and storage medium for mining and processing express logistics risks. Background Art

[0002] The express delivery industry has witnessed rapid development in recent years and has become an important part of modern logistics. However, with the expansion of its scale and the growth of service demands, the express delivery industry also faces a series of problems in terms of security, efficiency and risk management. During the express delivery process, the security of packages cannot be fully guaranteed. Especially for valuable and fragile items, the risks are even higher. Packages may be lost, damaged, stolen or abandoned during transportation, warehousing and sorting. Especially in cases where logistics nodes are busy or supervision is relatively lax, packages may be mishandled during handling, resulting in damage or loss of items. In addition, some lawbreakers may take advantage of loopholes in the express delivery network to steal, causing huge economic losses to consumers and express delivery enterprises. At the same time, express delivery delays are also one of the common complaints from consumers. Especially during peak periods, the volume of express deliveries surges, easily leading to problems such as blockages in the logistics chain and shortages of personnel, resulting in package delays or failure to be delivered in a timely manner. Express delivery vehicles face a relatively high risk of traffic accidents during transportation, especially in cases where urban road traffic is complex and road conditions are poor. Therefore, there is a certain correlation between the rationality of transportation route setting and warehouse layout and the occurrence of risks. However, the current express delivery industry is unable to make reasonable settings for transportation routes and warehouse layouts, thus increasing the risks of express logistics. Summary of the Invention

[0003] In order to overcome the deficiencies of the prior art, the purpose of the present invention is to provide a method, device, equipment and storage medium for mining and processing express logistics risks, which uses big data and artificial intelligence technologies to improve the risk prediction ability, prepare in advance to deal with potential market risks, improve the rationality of transportation routes and warehouse layouts, and thus reduce the risks of express logistics.

[0004] The first aspect of the present invention provides a method for mining and processing express logistics risks, including: collecting time series data of the number of problem parcels in historical express delivery operations, and constructing a prediction model for the number of problem parcels based on the time series data; using the prediction model for the number of problem parcels to predict the trend information of the number of problem parcels in express delivery operations in a future period, and obtaining transportation and warehousing data in the express logistics process in real time; calculating descriptive statistics on the transportation and warehousing data by using statistical analysis methods, and performing risk analysis based on the trend information and the descriptive statistics to obtain a risk analysis result; optimizing the transportation route and warehousing layout based on the risk analysis result to obtain transportation and warehousing optimization information, generating a visual processing suggestion report according to the transportation and warehousing optimization information; sending the visual processing suggestion report to a management terminal and uploading the visual processing suggestion report to a blockchain.

[0005] Optionally, in the first implementation manner of the first aspect of the present invention, the collecting time series data of the number of problem parcels in historical express delivery operations and constructing a prediction model for the number of problem parcels based on the time series data includes: collecting time series data of the number of problem parcels in historical express delivery operations; performing data cleaning on the time series data to obtain time series cleaning data, and filling missing values in the time series cleaning data to obtain time series filled data; performing format conversion on the time series filled data based on a preset target standard format to obtain time series standard data; constructing a prediction model for the number of problem parcels according to the time series standard data.

[0006] Optionally, in the second implementation manner of the first aspect of the present invention, the using the prediction model for the number of problem parcels to predict the trend information of the number of problem parcels in express delivery operations in a future period and obtaining transportation and warehousing data in the express logistics process in real time includes: setting a future time period range value and inputting the future time period range value into the prediction model for the number of problem parcels; using the prediction model for the number of problem parcels to predict the trend information of the number of problem parcels in the express delivery operations within the future time period range value; performing smoothing processing on the trend information; obtaining transportation and warehousing data in the express logistics process in real time.

[0007] Optionally, in the third implementation manner of the first aspect of the present invention, the calculating descriptive statistics on the transportation and warehousing data by using statistical analysis methods and performing risk analysis based on the trend information and the descriptive statistics to obtain a risk analysis result includes: calculating descriptive statistics on the transportation and warehousing data by using statistical analysis methods; respectively extracting key information of the trend information and the descriptive statistics by using a preset data mining method; creating a knowledge graph of the risk relationship between transportation and warehousing; performing risk analysis on the key information based on the knowledge graph to obtain a risk analysis result.

[0008] Optionally, in the fourth implementation manner of the first aspect of the present invention, optimizing the transportation route and warehousing layout based on the risk analysis result to obtain transportation and warehousing optimization information, and generating a visual processing suggestion report according to the transportation and warehousing optimization information, including: inputting the risk analysis result into a preset optimization model, and using the optimization model to optimize the transportation route and warehousing layout to obtain transportation and warehousing optimization information; identifying the risk level of the risk analysis result, and calling a preset report template based on the risk level; filling the transportation and warehousing optimization information into the report template to generate a visual processing suggestion report.

[0009] Optionally, in the fifth implementation manner of the first aspect of the present invention, sending the visual processing suggestion report to a management terminal and uploading the visual processing suggestion report to a blockchain, including: sending the visual processing suggestion report to the management terminal; encrypting the visual processing suggestion report to obtain an encrypted visual processing suggestion report; uploading the encrypted visual processing suggestion report to the blockchain.

[0010] Optionally, in the sixth implementation manner of the first aspect of the present invention, after sending the visual processing suggestion report to the management terminal and uploading the visual processing suggestion report to the blockchain, further including: creating a listener, and using the listener to listen to the processing effect feedback information sent by the management terminal; when the listener listens to the processing effect feedback information, obtaining the current processing effect feedback information; analyzing the processing effect feedback information to obtain a processing effectiveness analysis result; and iteratively updating the optimization model based on the processing effectiveness analysis result.

[0011] The second aspect of the present invention provides an express logistics risk mining and processing device, including: a collection and construction module, configured to collect time series data of the number of problem parcels in historical express delivery operations, and construct a problem parcel number prediction model according to the time series data; a prediction and acquisition module, configured to use the problem parcel number prediction model to predict the trend information of the number of problem parcels in express delivery operations in a future period of time, and real-time acquire transportation and warehousing data in the express logistics process; a calculation and analysis module, configured to calculate the transportation and warehousing data by using a statistical analysis method to obtain descriptive statistics, and perform risk analysis based on the trend information and the descriptive statistics to obtain a risk analysis result; an optimization and generation module, configured to optimize the transportation route and warehousing layout based on the risk analysis result to obtain transportation and warehousing optimization information, and generate a visual processing suggestion report according to the transportation and warehousing optimization information; a sending and uploading module, configured to send the visual processing suggestion report to a management terminal and upload the visual processing suggestion report to a blockchain.

[0012] Optionally, in the first implementation manner of the second aspect of the present invention, the collection and construction module includes: a collection unit for collecting time series data of the number of problem items in historical express delivery operations; a cleaning and filling unit for cleaning the time series data to obtain time series cleaning data, and filling missing values in the time series cleaning data to obtain time series filled data; a conversion unit for converting the format of the time series filled data based on a preset target standard format to obtain time series standard data; and a construction unit for constructing a problem item quantity prediction model according to the time series standard data.

[0013] Optionally, in the second implementation manner of the second aspect of the present invention, the prediction and acquisition module includes: a setting input unit for setting a future time period range value and inputting the future time period range value into the problem item quantity prediction model; a prediction unit for using the problem item quantity prediction model to predict the trend information of the number of problem items in express delivery operations within the future time period range value; a smoothing processing unit for smoothing the trend information; and an acquisition unit for real-time acquiring transportation and warehousing data in the express delivery logistics process.

[0014] Optionally, in the third implementation manner of the second aspect of the present invention, the calculation and analysis module includes: a calculation unit for calculating the transportation and warehousing data using statistical analysis methods to obtain descriptive statistics; an extraction unit for respectively extracting key information of the trend information and the descriptive statistics using preset data mining methods; a creation unit for creating a knowledge graph of the relationship between transportation and warehousing risks; and an analysis unit for performing risk analysis on the key information based on the knowledge graph to obtain a risk analysis result.

[0015] Optionally, in the fourth implementation manner of the second aspect of the present invention, the optimization and generation module includes: an input optimization unit for inputting the risk analysis result into a preset optimization model and using the optimization model to optimize the transportation route and warehousing layout to obtain transportation and warehousing optimization information; an identification and call unit for identifying the risk level of the risk analysis result and calling a preset report template based on the risk level; and a filling and generation unit for filling the transportation and warehousing optimization information into the report template to generate a visual processing suggestion report.

[0016] Optionally, in the fifth implementation manner of the second aspect of the present invention, the sending and uploading module includes: a sending unit, configured to send the visualization processing suggestion report to the management terminal; an encryption unit, configured to encrypt the visualization processing suggestion report to obtain a visualization processing suggestion encrypted report; an uploading unit, configured to upload the visualization processing suggestion encrypted report to the blockchain.

[0017] Optionally, in the sixth implementation manner of the second aspect of the present invention, it further includes: a creating and listening module, configured to create a listener and use the listener to listen to the processing effect feedback information sent by the management terminal; an obtaining module, configured to obtain the current processing effect feedback information when the listener listens to the processing effect feedback information; an analyzing module, configured to analyze the processing effect feedback information to obtain a processing effectiveness analysis result; an iterative updating module, configured to iteratively update the optimization model based on the processing effectiveness analysis result.

[0018] The third aspect of the present invention provides an express logistics risk mining and processing device, where the express logistics risk mining and processing device includes: a memory and at least one processor, and instructions are stored in the memory; at least one of the processors calls the instructions in the memory so that the express logistics risk mining and processing device executes each step of the express logistics risk mining and processing method described in any one of the above.

[0019] The fourth aspect of the present invention provides a computer-readable storage medium, where instructions are stored on the computer-readable storage medium, and when the instructions are executed by a processor, each step of the express logistics risk mining and processing method described in any one of the above is implemented.

[0020] In the technical solution of the present invention, by using the problem parcel quantity prediction model to predict the trend information of the number of problem parcels in the express delivery business in a future period of time, using statistical analysis methods to calculate the transportation and warehousing data to obtain descriptive statistics, performing risk analysis based on the trend information and descriptive statistics to obtain a risk analysis result, using big data and artificial intelligence technologies to improve the risk prediction ability, optimizing the transportation route and warehousing layout based on the risk analysis result to obtain transportation and warehousing optimization information, generating a visualization processing suggestion report according to the transportation and warehousing optimization information, sending the visualization processing suggestion report to the management terminal, preparing in advance to deal with potential market risks, improving the rationality of the transportation route and warehousing layout, and thereby reducing the express logistics risk. Description of the Drawings

[0021] Figure 1 It is the first flowchart of the express logistics risk mining and processing method provided by the embodiment of the present invention;

[0022] Figure 2The second flowchart of the express logistics risk mining and processing method provided by the embodiment of the present invention;

[0023] Figure 3 The third flowchart of the express logistics risk mining and processing method provided by the embodiment of the present invention;

[0024] Figure 4 The fourth flowchart of the express logistics risk mining and processing method provided by the embodiment of the present invention;

[0025] Figure 5 A structural schematic diagram of the express logistics risk mining and processing device provided by the embodiment of the present invention;

[0026] Figure 6 Another structural schematic diagram of the express logistics risk mining and processing device provided by the embodiment of the present invention;

[0027] Figure 7 A structural schematic diagram of the express logistics risk mining and processing equipment provided by the embodiment of the present invention. Detailed implementation manners

[0028] The present invention provides an express logistics risk mining and processing method, device, equipment and storage medium, which uses big data and artificial intelligence technologies to improve the risk prediction ability, prepare in advance to cope with potential market risks, improve the rationality of transportation routes and warehousing layouts, and thus reduce express logistics risks.

[0029] The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments described herein can be implemented in an order other than those illustrated or described herein. In addition, the term "comprising" or "having" and any deformation thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or equipment comprising a series of steps or units does not necessarily need to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or equipment.

[0030] For ease of understanding, the specific processes of the embodiments of the present invention are described below. Please refer to Figure 1 , an embodiment of the express logistics risk mining and processing method in the embodiments of the present invention includes:

[0031] 101. Collect time series data of the number of problem parcels in historical express delivery operations, and construct a prediction model for the number of problem parcels based on the time series data;

[0032] In this embodiment, the historical number of problematic parcels is obtained from the internal express delivery management system of the company. The system records the processing status of each order, including whether it is a problematic parcel. The time series data of the number of problematic parcels needs to be collected according to timestamps. Common time granularities include days, weeks, months, quarters, etc. According to the actual situation, the best time granularity is determined. Consider collecting data by region. The express delivery and logistics environment in different regions may affect the generation of problematic parcels. Duplicate data in the historical data is removed, and possible duplicate records are deleted. If there are missing values in the data, they can be filled by methods such as mean filling and interpolation, or if the missing values are severe, the data for relevant time periods can be considered for deletion. The historical time series data is divided into a training set and a test set. After selecting a model, the training set data is used for fitting, and the test set is used for evaluation to obtain a prediction model for the number of problematic parcels.

[0033] 102. Use the prediction model for the number of problematic parcels to predict the trend information of the number of problematic parcels in the express delivery business in the next period of time, and obtain the transportation and warehousing data in the express delivery and logistics process in real time;

[0034] In this embodiment, according to business requirements, select the prediction time period (such as 1 day, 1 week, 1 month, etc.). Through the time series prediction function of the model, predict the values of the next time step or multiple time steps, and display the prediction results in the form of charts, tables, etc., so that the business department can quickly understand the future change trend of the number of problematic parcels and track the transportation status and warehousing status of goods in real time. The data in the warehousing process includes data on links such as inbound, outbound, inventory counting, and picking.

[0035] 103. Use statistical analysis methods to calculate the transportation and warehousing data to obtain descriptive statistics, and perform risk analysis based on the trend information and descriptive statistics to obtain the risk analysis results;

[0036] In this embodiment, use statistical analysis methods to calculate the transportation and warehousing data. The calculations include statistics such as maximum value, minimum value, mean, median, skewness, and kurtosis to obtain descriptive statistics. Risk analysis needs to be carried out by combining the trend information and descriptive statistics, including key risk factors such as the risk of transportation delays, warehousing management problems, damage or loss of goods, and the risk of high demand fluctuations. Based on the trend information and descriptive statistics, perform risk analysis in different scenarios. According to the above risk analysis indicators, each risk can be classified to obtain the risk analysis results.

[0037] 104. Optimize the transportation routes and warehousing layouts based on the risk analysis results to obtain transportation and warehousing optimization information, and generate a visualization processing suggestion report according to the transportation and warehousing optimization information;

[0038] In this embodiment, specific countermeasures are formulated according to the results of risk analysis. For example, for the risk of transportation delay, the transparency of the transportation link can be improved, transportation route monitoring can be strengthened, the transportation schedule can be optimized, the transportation route can be optimized, traffic bottlenecks can be reduced, and the accuracy of the transportation plan can be enhanced. For the risk of warehousing management, an advanced warehousing management system can be introduced, inventory scheduling and early warning mechanisms can be optimized to avoid excessive or insufficient inventory. For the risk of goods damage or loss, packaging technology can be improved, the goods transportation route can be optimized, and insurance coverage can be increased. Based on the above optimization measures, the following transportation and warehousing optimization information is obtained, including listing the shortest transportation route and the optimized warehouse area division. The warehouse area division shows the locations of the hot zone and the cold zone. A visual processing suggestion report is generated according to the transportation and warehousing optimization information.

[0039] 105. Send the visual processing suggestion report to the management terminal and upload the visual processing suggestion report to the blockchain;

[0040] In this embodiment, the visual processing suggestion report is pushed to the management terminal using the API interface. The report is transmitted in an easily parsable format, such as PDF, Excel, HTML, JSON, or image format. Users of the management terminal (such as warehouse managers, transportation schedulers, etc.) can make decisions based on the data in the report, such as adjusting the transportation route, modifying the warehousing layout, etc. The management terminal can provide interaction functions with the report, such as allowing users to click on the chart to view detailed data, or putting forward improvement opinions or performing operations according to the content of the report. At the same time, the generated visual report is converted into a format suitable for storage on the blockchain. The report or the summary of the report (such as the hash value of the report) is encapsulated into a blockchain transaction, and the transaction is encrypted and signed to ensure the authenticity of the data source of the uploaded data and prevent forgery. Then, this transaction is broadcast to the blockchain network. The transaction enters the blockchain network and is confirmed through the consensus mechanism. Once confirmed, the transaction is added to a new block of the blockchain, and the relevant information of the report is permanently stored in the blockchain.

[0041] In the embodiment of the present invention, by using the problem parcel quantity prediction model to predict the trend information of the problem parcel quantity in the express delivery business in the next period of time, statistical analysis methods are used to calculate the transportation and warehousing data to obtain descriptive statistics. Risk analysis is carried out based on the trend information and descriptive statistics to obtain the risk analysis results. Big data and artificial intelligence technologies are used to improve the risk prediction ability. The transportation route and warehousing layout are optimized based on the risk analysis results to obtain the transportation and warehousing optimization information. A visual processing suggestion report is generated according to the transportation and warehousing optimization information, and the visual processing suggestion report is sent to the management terminal to prepare in advance for potential market risks, improve the rationality of the transportation route and warehousing layout, and thus reduce the express delivery logistics risk.

[0042] Please refer toFigure 2 , the second embodiment of the express logistics risk mining and processing method in the embodiments of the present invention includes:

[0043] 201. Collect time series data on the number of problem parcels in historical express delivery operations;

[0044] In this embodiment, data on the number of problem parcels is extracted from the database of the express delivery management system through an SQL query. The query conditions include order status, delivery problem types, etc. Or, if the management system provides an API interface, data is extracted to the data collection platform as needed through API calls. API calls can regularly obtain data at time intervals, thereby collecting time series data on the number of problem parcels in historical express delivery operations.

[0045] 202. Clean the time series data to obtain cleaned time series data, and fill in missing values in the cleaned time series data to obtain filled time series data;

[0046] In this embodiment, inconsistent, duplicate, or incorrect time series data is removed to obtain cleaned time series data. Duplicate items can be removed based on timestamps and other unique identifiers (such as express delivery numbers). If there are multiple records at the same time point, they can be merged (for example, taking the average, maximum, or minimum, etc.). Missing values in the time series may be data for certain time points that are completely missing, or abnormal missing due to abnormal events (such as system maintenance). Before filling in missing values, it is first necessary to check whether the missing time points belong to a certain pattern to ensure whether they can be filled in according to the time series rule. Different filling methods are selected according to the characteristics of the missing values. For example, use the data before and after the missing point to fill in. For regular time series data, linear interpolation can be used to fill in missing values. If the data has obvious seasonal variations, missing values can be filled in according to the seasonal pattern, or the average value of several time points before and after can be used to fill in missing values. If the time series data is complex and there are many missing values, a prediction model can be considered to fill in the missing values, and finally filled time series data is obtained.

[0047] 203. Based on a preset target standard format, convert the format of the filled time series data to obtain standard time series data;

[0048] In this embodiment, the column names, data types, and arrangement order of fields in the data table are defined. For example, the data may need to include information such as timestamps, measurement values (such as the number of express problem parcels), units, status, etc. The target standard format is clarified, and the filled time series data is converted to the target standard format to obtain standard time series data.

[0049] 204. Construct a prediction model for the number of problem parcels based on the standard time series data;

[0050] In this embodiment, in-depth analysis and feature extraction are performed on the time series standard data to understand the nature of the data and potential influencing factors. According to the characteristics of the data and the prediction requirements of the number of problem cases, a suitable time series prediction model is selected. The time series standard data is divided into a training set, a validation set, and a test set. The selected model is trained using the training set, the model is verified on the validation set, and the performance of the model is evaluated using the test set. Once the prediction model for the number of problem cases is obtained after training, verification, and evaluation, the prediction model for the number of problem cases is deployed for predicting the number of future problem cases.

[0051] 205. Set the future time period range value and input the future time period range value into the prediction model for the number of problem cases;

[0052] In this embodiment, the future time period range value is set. The selection of the time period should be directly related to the business requirements, such as quarterly reports, sales cycles, product life cycles, etc. of a certain industry. Select the starting time point of the prediction, set the end time according to the business requirements, or obtain a reasonable end point through the analysis of historical data. The set future time period is used as the input and input into the prediction model for the number of problem cases to predict the number of problem cases within this time period.

[0053] 206. Use the prediction model for the number of problem cases to predict the trend information of the number of problem cases in the express delivery business within the future time period range value;

[0054] In this embodiment, with the set time period as the input, the model will generate a trend prediction of the number of problem cases in the express delivery business within the future time period based on the trained parameters and features. Through the prediction results, the increasing or decreasing trend of the number of problem cases within the future time period can be identified, and the trend information of the number of problem cases in the express delivery business within the future time period range value can be obtained.

[0055] 207. Smooth the trend information;

[0056] In this embodiment, by smoothing the predicted trend information of the number of problematic express delivery items, the noise in the data is removed, highlighting the potential trends and periodic fluctuations. The smoothing methods include the moving average method, the exponential smoothing method, the moving median method, the locally weighted regression method, and the Savitzky-Golay filter. The moving average method reduces data fluctuations by averaging the data within a certain time window. The exponential smoothing method assigns gradually decreasing weights to historical data, making newer data points have a greater impact on the prediction result. The moving median method replaces the values in the original data by calculating the median of each window using a sliding window in the data sequence. The locally weighted regression method smooths the data by performing weighted regression around each data point, with the weights decaying as the distance increases. The Savitzky-Golay filter smooths the data using local polynomial fitting.

[0057] 208. Obtain the transportation and warehousing data in the express delivery logistics process in real time;

[0058] In this embodiment, a stream processing platform is used to track a large amount of transportation and warehousing data in real time. The transportation management system will record various data during the transportation process in real time, such as departure time, arrival time, transportation mode, route selection, and cargo status. The warehousing management system can record data such as the storage status of goods in the warehouse, inbound and outbound situations, inventory quantity, and sorting process in real time, and integrate the transportation and warehousing data.

[0059] In the embodiment of the present invention, by collecting and cleaning historical data, a solid foundation is provided for subsequent analysis, making the prediction model more accurate. Each step is closely linked, forming a complete data stream from data collection to prediction and real-time monitoring, which helps to reduce human intervention and errors. The prediction model based on historical data can identify the future trend of the number of problematic items in advance, provide actionable warnings for management, and reduce potential risks. By smoothing the prediction results, the impact of data fluctuations can be reduced, making the prediction results more stable and reliable. The real-time data acquisition in the steps can help track the dynamic changes in the current logistics process, adjust the prediction model in a timely manner, and improve accuracy and flexibility.

[0060] Please refer to Figure 3 , the third embodiment of the express delivery logistics risk mining and processing method in the embodiment of the present invention includes:

[0061] 301. Use statistical analysis methods to calculate the transportation and warehousing data to obtain descriptive statistics;

[0062] In this embodiment, statistical analysis methods are used to calculate transportation and warehousing data. The calculations include statistics such as maximum value, minimum value, mean, median, skewness, kurtosis, mode, variance, standard deviation, and range, obtaining descriptive statistics. Central tendency is used to describe the central position of the data, mainly including mean, median, and mode, etc. Dispersion is used to describe the breadth of data distribution, mainly including variance, standard deviation, range, etc. Distribution shape is used to describe the distribution characteristics of the data, mainly including skewness, kurtosis, etc.

[0063] 302. Use pre-set data mining methods to extract the key information of trend information and descriptive statistics respectively;

[0064] In this embodiment, data mining methods include classification, clustering, regression analysis, association rule mining, and time series analysis. Use pre-set data mining methods to extract the key information of trend information and descriptive statistics respectively. For example, through regression analysis methods, the relationships between key variables in transportation and warehousing data can be revealed and their future trends can be predicted. Through clustering analysis, potential patterns in descriptive statistics can be discovered and the data can be divided into different groups. Through association rule mining, potential correlations between different variables can be discovered.

[0065] 303. Create a knowledge graph of the risk relationship between transportation and warehousing;

[0066] In this embodiment, each entity in the knowledge graph is clarified, including transportation modes, warehousing facilities, risk factors, time, cargo characteristics, and logistics networks, etc. The risk relationships are determined. The "edges" in the knowledge graph represent the relationships between entities. In the knowledge graph of the risk relationship between transportation and warehousing, the edges mainly represent the potential associations and influence relationships between different entities. Risk relationships include risk associations, causal relationships, influence relationships, and temporal relationships, etc. Once the entities and relationships in the knowledge graph are determined, the next step is to use data mining techniques, graph construction methods, and natural language processing techniques to transform these data into a graph model. After the graph construction is completed, data analysis and graph analysis techniques can be used to conduct in-depth analysis of the risk relationships.

[0067] 304. Conduct risk analysis on the key information based on the knowledge graph to obtain the risk analysis results;

[0068] In this embodiment, in the transportation and warehousing risk knowledge graph, some nodes (entities) may represent more critical or influential risk factors. Through graph analysis, the following methods can be used to identify key risk nodes, namely degree centrality, betweenness centrality, and closeness centrality. Degree centrality calculates the degree of a node (the number of direct connections to other nodes). Nodes with higher degrees may be key factors in risk propagation. For example, a certain transportation route may be associated with multiple risk factors, so this route may be a key node. Betweenness centrality calculates whether a node acts as a bridge between multiple nodes. If a node is located between multiple risk factors and has many connections, then it may be a key intermediary in information dissemination. Closeness centrality measures the distance between a node and other nodes in the graph. Nodes with a closer distance may be the source of risk diffusion and can affect more links. By analyzing the causal relationships between various risk factors through the entities and relationships in the graph and using graph theory algorithms for path analysis, the propagation paths between different risks can be found, and then their impacts can be evaluated. By quantifying the probability and impact degree of each risk through graph-based analysis, the final risk analysis result can be obtained.

[0069] 305. Input the risk analysis result into a preset optimization model, and use the optimization model to optimize the transportation route and warehousing layout to obtain transportation and warehousing optimization information;

[0070] In this embodiment, when the risk analysis result is input into a preset optimization model, the risk analysis has evaluated the occurrence probability and impact degree of potential risk factors such as each transportation route, warehousing center, equipment, and personnel. The specific input data includes risk scores, key risk nodes, risk propagation paths, and timing information. The optimization model is used to optimize the transportation route and warehousing layout and output transportation and warehousing optimization information.

[0071] 306. Identify the risk level of the risk analysis result, and call a preset report template based on the risk level;

[0072] In this embodiment, according to the risk analysis data (such as occurrence probability, impact degree, etc.), the specific impact of each risk point is converted into an actionable risk level. The risk level can be divided into low risk, medium risk, high risk, and extremely high risk. Based on the identified risk level above, the next step is to call a preset report template according to different risk levels. The report template sets different contents and focuses according to different risk levels.

[0073] 307. Fill the transportation and warehousing optimization information into the report template to generate a visual processing suggestion report;

[0074] In this embodiment, the transportation and warehousing optimization information is filled into the corresponding parts of the report template one by one. For information such as transportation routes and warehousing layouts, tables can be used to present specific details. When describing the optimization effects, bar charts, line charts, pie charts, etc. are used to present the comparison data of different routes or plans. Visualization tools such as risk matrices and heat maps are used to display the severity and occurrence probability of different risks, and then a visualized processing suggestion report is generated.

[0075] In the embodiment of the present invention, through statistical analysis and data mining, key information can be extracted from a large amount of data to provide a reliable basis for optimization. Through constructing a knowledge graph and risk analysis, potential risks can be identified and their severity can be evaluated, giving early warnings and improving the forward-looking nature of decision-making. The optimization model can adjust transportation routes and warehousing layouts, helping managers improve resource utilization efficiency and reduce risks. The risk analysis results and optimization information can automatically generate a visualized report, improving management efficiency and simplifying the decision-making process, forming a complete closed loop from data collection, analysis, optimization to report generation, making transportation and warehousing management more refined and efficient.

[0076] Please refer to Figure 4 , the fourth embodiment of the express logistics risk mining and processing method in the embodiment of the present invention includes:

[0077] 401. Send the visualized processing suggestion report to the management terminal;

[0078] In this embodiment, the visualized processing suggestion report is sent to the management terminal through email, a dedicated management terminal application, or cloud platform sharing. After the report is sent to the management terminal, managers can view the visualized processing suggestion report.

[0079] 402. Encrypt the visualized processing suggestion report to obtain an encrypted visualized processing suggestion report;

[0080] In this embodiment, the visualized processing suggestion report is input into an encryption algorithm and converted into an encrypted file through the encryption process. After encryption, the output report is the encrypted visualized processing suggestion report.

[0081] 403. Upload the encrypted visualized processing suggestion report to the blockchain;

[0082] In this embodiment, a suitable blockchain platform is selected, and the encrypted report is uploaded to the blockchain through the API or smart contract provided by it. What the blockchain stores itself is the hash value of the data. The hash value is a digest of the encrypted report, which can uniquely represent the integrity of the report content. The smart contract is used to manage the encrypted visualized processing suggestion report. When it is necessary to verify or view the encrypted visualized processing suggestion report, the hash value and storage location of the report can be queried from the blockchain.

[0083] 404. Create a listener to listen for the processing effect feedback information sent by the management terminal.

[0084] In this embodiment, a listener is created based on the event-driven architecture to listen for the processing effect feedback information sent by the management terminal.

[0085] 405. When the listener detects the processing effect feedback information, obtain the current processing effect feedback information.

[0086] In this embodiment, when the listener detects the processing effect feedback information, what is actually executed is that the listener captures and reacts to the feedback information from the management terminal. The listener is in a waiting state, waiting for events or feedback from the management terminal. The listener does not actively obtain the processing effect feedback information, but listens based on the event-driven mechanism. As long as the management terminal sends the processing effect feedback information, the listener will be triggered. When the listener recognizes the arrival of the processing effect feedback information, next it needs to extract the relevant processing effect feedback information from the feedback source and parse it.

[0087] 406. Analyze the processing effect feedback information to obtain the processing effectiveness analysis result.

[0088] In this embodiment, after the processing effect feedback information is parsed, in-depth analysis of the processing effect feedback information is carried out, including task success and failure analysis, progress feedback and processing effect analysis, data and processing result analysis, etc. Based on the analysis of the feedback information, the next step is to judge the processing effectiveness of the entire task. If it is found in the processing effect analysis that the processing effect of the task is not ideal, or there are some obvious defects, optimization or adjustment suggestions can be put forward according to the analysis result to obtain the processing effectiveness analysis result.

[0089] 407. Iteratively update the optimization model based on the processing effectiveness analysis result.

[0090] In this embodiment, based on the analysis results of processing effectiveness, a full understanding is carried out, including the reasons for success and failure, the compliance of progress and quality, the consistency and accuracy of data, and other abnormal situations, to clarify the areas that need improvement. The areas that need improvement may include algorithm optimization, data optimization, feature selection and engineering, hyperparameter tuning, etc. After analyzing the defects of the model and the areas that need to be optimized, the next step is to design a specific improvement plan. The improvement plan may include selecting an updated model or method, adding new features or data sources, adjusting the model architecture and training method, etc. Retrain the updated model and evaluate the effect of the model using the validation set. After training is completed, it is necessary to evaluate the updated model and compare it with the previous model. If the new model passes the evaluation and performs well, it will be deployed to the actual system.

[0091] In the embodiment of the present invention, through encryption and blockchain uploading, the security and immutability of the report are ensured, the credibility and transparency of the information are enhanced. The listener monitors the feedback information of the management terminal in real time, can timely obtain the processing effect, and provides a basis for subsequent decision-making. Through the analysis of the processing effect and the iterative update of the optimization model, the optimization strategy can be adjusted according to the feedback to ensure continuous improvement and more efficient management. A complete closed loop is formed from report generation to feedback analysis and then to optimization iteration, ensuring the accuracy of decision-making and the flexible response to external changes.

[0092] The above describes the express logistics risk mining and processing method in the embodiment of the present invention. Next, the express logistics risk mining and processing device in the embodiment of the present invention will be described. Please refer to Figure 5 , an embodiment of the express logistics risk mining and processing device in the embodiment of the present invention includes:

[0093] A collection and construction module 501, configured to collect time series data of the number of problem parcels in historical express delivery operations, and construct a problem parcel number prediction model according to the time series data;

[0094] A prediction and acquisition module 502, configured to use the problem parcel number prediction model to predict the trend information of the number of problem parcels in express delivery operations in a future period of time, and to obtain the transportation and warehousing data in the express logistics process in real time;

[0095] A calculation and analysis module 503, configured to calculate the transportation and warehousing data using statistical analysis methods to obtain descriptive statistics, and perform risk analysis based on the trend information and descriptive statistics to obtain a risk analysis result;

[0096] An optimization and generation module 504, configured to optimize the transportation route and warehousing layout based on the risk analysis result to obtain transportation and warehousing optimization information, and generate a visual processing suggestion report according to the transportation and warehousing optimization information;

[0097] A sending and uploading module 505, configured to send the visualized processing suggestion report to a management terminal and upload the visualized processing suggestion report to a blockchain.

[0098] In this embodiment, by using the problem parcel quantity prediction model to predict the trend information of the number of problem parcels in the express delivery business within a future period of time, using statistical analysis methods to calculate the transportation and warehousing data to obtain descriptive statistics, and performing risk analysis based on the trend information and descriptive statistics to obtain a risk analysis result, using big data and artificial intelligence technologies to improve the risk prediction ability, optimizing the transportation route and warehousing layout based on the risk analysis result to obtain transportation and warehousing optimization information, generating a visualized processing suggestion report according to the transportation and warehousing optimization information, sending the visualized processing suggestion report to the management terminal, preparing in advance to cope with potential market risks, improving the rationality of the transportation route and warehousing layout, and further reducing the express delivery logistics risk.

[0099] Please refer to Figure 6 , another embodiment of the express delivery logistics risk mining and processing device in the embodiment of the present invention includes:

[0100] A collection and construction module 501, configured to collect time series data of the historical number of problem parcels in the express delivery business and construct a problem parcel quantity prediction model according to the time series data;

[0101] A prediction and acquisition module 502, configured to use the problem parcel quantity prediction model to predict the trend information of the number of problem parcels in the express delivery business within a future period of time and obtain the transportation and warehousing data in the express delivery logistics process in real time;

[0102] A calculation and analysis module 503, configured to use statistical analysis methods to calculate the transportation and warehousing data to obtain descriptive statistics, and perform risk analysis based on the trend information and descriptive statistics to obtain a risk analysis result;

[0103] An optimization and generation module 504, configured to optimize the transportation route and warehousing layout based on the risk analysis result to obtain transportation and warehousing optimization information, and generate a visualized processing suggestion report according to the transportation and warehousing optimization information;

[0104] A sending and uploading module 505, configured to send the visualized processing suggestion report to a management terminal and upload the visualized processing suggestion report to a blockchain;

[0105] In this embodiment, the collection and construction module 501 includes: a collection unit 5011, configured to collect time series data of the number of problem items in historical express delivery operations; a cleaning and filling unit 5012, configured to perform data cleaning on the time series data to obtain time series cleaned data, and perform missing value filling on the time series cleaned data to obtain time series filled data; a conversion unit 5013, configured to perform format conversion on the time series filled data based on a preset target standard format to obtain time series standard data; and a construction unit 5014, configured to construct a problem item quantity prediction model according to the time series standard data.

[0106] In this embodiment, the prediction and acquisition module 502 includes: a setting input unit 5021, configured to set a future time period range value and input the future time period range value into the problem item quantity prediction model; a prediction unit 5022, configured to use the problem item quantity prediction model to predict the trend information of the number of problem items in express delivery operations within the future time period range value; a smoothing processing unit 5023, configured to perform smoothing processing on the trend information; and an acquisition unit 5024, configured to obtain the transportation and warehousing data in the express delivery logistics process in real time.

[0107] In this embodiment, the calculation and analysis module 503 includes: a calculation unit 5031, configured to calculate the transportation and warehousing data using statistical analysis methods to obtain descriptive statistics; an extraction unit 5032, configured to respectively extract the key information of the trend information and the descriptive statistics using preset data mining methods; a creation unit 5033, configured to create a knowledge graph of the relationship between transportation and warehousing risks; and an analysis unit 5034, configured to perform risk analysis on the key information based on the knowledge graph to obtain a risk analysis result.

[0108] In this embodiment, the optimization and generation module 504 includes: an input optimization unit 5041, configured to input the risk analysis result into a preset optimization model, and use the optimization model to optimize the transportation route and warehousing layout to obtain transportation and warehousing optimization information; an identification and invocation unit 5042, configured to identify the risk level of the risk analysis result and invoke a preset report template based on the risk level; and a filling and generation unit 5043, configured to fill the transportation and warehousing optimization information into the report template to generate a visual processing suggestion report.

[0109] In this embodiment, the sending and uploading module 505 includes: a sending unit 5051, configured to send the visual processing suggestion report to a management terminal; an encryption unit 5052, configured to encrypt the visual processing suggestion report to obtain an encrypted visual processing suggestion report; and an uploading unit 5053, configured to upload the encrypted visual processing suggestion report to a blockchain.

[0110] In this embodiment, it further includes: a creation monitoring module 506, configured to create a listener, and use the listener to monitor the processing effect feedback information sent by the management terminal; an acquisition module 507, configured to acquire the current processing effect feedback information when the listener monitors the processing effect feedback information; an analysis module 508, configured to analyze the processing effect feedback information to obtain a processing effectiveness analysis result; an iterative update module 509, configured to iteratively update the optimization model based on the processing effectiveness analysis result.

[0111] Above Figure 5 and Figure 6 The express delivery logistics risk mining and processing device in the embodiment of the present invention is described in detail from the perspective of modular functional entities. Next, the express delivery logistics risk mining and processing equipment in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0112] Figure 7 FIG. is a schematic structural diagram of an express delivery logistics risk mining and processing equipment provided by an embodiment of the present invention. The express delivery logistics risk mining and processing equipment 600 may vary greatly due to different configurations or performances, and may include one or more processors (central processing units, CPUs) 610 (for example, one or more processors) and a memory 620, and one or more storage media 630 for storing application programs 633 or data 632 (for example, one or more mass storage devices). Among them, the memory 620 and the storage media 630 may be transient storage or persistent storage. The program stored in the storage media 630 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the express delivery logistics risk mining and processing equipment 600. Further, the processor 610 may be configured to communicate with the storage media 630 and execute a series of instruction operations in the storage media 630 on the express delivery logistics risk mining and processing equipment 600 to implement the steps of the express delivery logistics risk mining and processing method provided by the above method embodiments.

[0113] The express delivery logistics risk mining and processing equipment 600 may further include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input / output interfaces 660, and / or one or more operating systems 631, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art can understand that Figure 7 the shown structure of the express delivery logistics risk mining and processing equipment does not constitute a limitation on the express delivery logistics risk mining and processing equipment, and may include more or fewer components than shown, or combine certain components, or arrange different components.

[0114] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are run on a computer, the computer is caused to execute the steps of the express logistics risk mining processing method.

[0115] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described system, device, or unit can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0116] If the integrated unit 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 all or 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 described in the various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0117] Finally, it should be noted that the above are only preferred examples of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. 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 express logistics risk mining, characterized in that: include: Collecting time series data on the number of problem pieces in historical express delivery business, and building a problem piece quantity prediction model based on the time series data; The problem piece quantity prediction model is used to predict the trend information of the problem piece quantity of the express delivery business in the future period, and the transportation and warehousing data of the express delivery logistics process are obtained in real time; Using statistical analysis methods to calculate the transportation and warehousing data to obtain descriptive statistics, and performing risk analysis based on the trend information and the descriptive statistics to obtain risk analysis results; Optimize the transportation route and storage layout based on the risk analysis results to obtain transportation and storage optimization information, and generate a visualization processing suggestion report based on the transportation and storage optimization information; The visualization processing suggestion report is sent to a management terminal, and the visualization processing suggestion report is uploaded to a blockchain.

2. The express logistics risk mining and processing method according to claim 1 is characterized in that: The collecting of time series data of the number of problem pieces in historical express delivery services and constructing a problem piece number prediction model based on the time series data include: Collect time series data on the number of problem items in historical express delivery business; Performing data cleaning on the time series data to obtain time series cleaned data, and performing missing value filling on the time series cleaned data to obtain time series filled data; Based on a preset target standard format, the time series filling data is formatted to obtain time series standard data; A problem piece quantity prediction model is constructed based on the time series standard data.

3. The express logistics risk mining and processing method according to claim 1 is characterized in that: The method of using the problem piece quantity prediction model to predict the trend information of the number of problem pieces in the express delivery business in the future period of time and obtaining the transportation and warehousing data in the express logistics process in real time includes: Setting a future time period range value, and inputting the future time period range value into the problem item quantity prediction model; Using the problem piece quantity prediction model to predict the trend information of the number of problem pieces of express delivery business within the future time period range; Performing smoothing processing on the trend information; Obtain real-time transportation and warehousing data during express logistics.

4. The express logistics risk mining and processing method according to claim 1 is characterized in that: The statistical analysis method is used to calculate the transportation and warehousing data to obtain descriptive statistics, and risk analysis is performed based on the trend information and the descriptive statistics to obtain risk analysis results, including: Calculate the transportation and warehousing data using statistical analysis methods to obtain descriptive statistics; Using a preset data mining method to extract key information of the trend information and the descriptive statistics respectively; Create a knowledge graph of the relationship between transportation and warehousing risks; Based on the knowledge graph, risk analysis is performed on the key information to obtain risk analysis results.

5. The express logistics risk mining and processing method according to claim 1 is characterized in that: The optimizing of the transportation route and storage layout based on the risk analysis result to obtain the transportation and storage optimization information, and generating a visualization processing suggestion report according to the transportation and storage optimization information, including: Input the risk analysis results into a preset optimization model, and use the optimization model to optimize the transportation route and storage layout to obtain transportation and storage optimization information; Identify the risk level of the risk analysis result, and call a preset report template based on the risk level; Fill the transportation and warehousing optimization information into the report template to generate a visualization processing recommendation report.

6. The express logistics risk mining and processing method according to claim 1 is characterized in that: The step of sending the visualization processing suggestion report to a management terminal and uploading the visualization processing suggestion report to a blockchain includes: Sending the visualization processing suggestion report to a management terminal; Encrypting the visualization processing suggestion report to obtain an encrypted visualization processing suggestion report; The visualization processing suggestion encrypted report is uploaded to the blockchain.

7. The express logistics risk mining and processing method according to claim 1 is characterized in that: After sending the visualization processing suggestion report to the management terminal and uploading the visualization processing suggestion report to the blockchain, the method further includes: Creating a listener, and using the listener to monitor the processing effect feedback information sent by the management terminal; When the listener listens to the processing effect feedback information, the current processing effect feedback information is obtained; Analyzing the processing effect feedback information to obtain processing effectiveness analysis results; The optimization model is iteratively updated based on the processing effectiveness analysis results.

8. A device for processing express logistics risk mining, characterized in that: include: A collection and construction module is used to collect time series data on the number of problem pieces in historical express delivery business, and to construct a problem piece quantity prediction model based on the time series data; A prediction acquisition module is used to use the problem piece quantity prediction model to predict the trend information of the number of problem pieces in the express delivery business in the future period of time, and to obtain the transportation and warehousing data in the express logistics process in real time; A calculation and analysis module, used to calculate the transportation and warehousing data using a statistical analysis method to obtain descriptive statistics, and to perform risk analysis based on the trend information and the descriptive statistics to obtain risk analysis results; An optimization generation module, used to optimize the transportation route and storage layout based on the risk analysis results, obtain transportation and storage optimization information, and generate a visualization processing suggestion report based on the transportation and storage optimization information; The sending and uploading module is used to send the visualization processing suggestion report to the management terminal and upload the visualization processing suggestion report to the blockchain.

9. An express logistics risk mining and processing device, characterized in that: The express logistics risk mining and processing device comprises: a memory and at least one processor, wherein the memory stores instructions; At least one of the processors calls the instructions in the memory so that the express logistics risk mining and processing device executes each step of the express logistics risk mining and processing method as described in any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the various steps of the express logistics risk mining processing method as described in any one of claims 1-7 are implemented.

Images