Method and Device for Monitoring Logistics Network Operation Data Based on Multi-level Architecture

Abstract

This invention relates to the field of data visualization and monitoring technology, and discloses a method for monitoring logistics network operation data based on a multi-level architecture. The method includes: introducing a role-based access control algorithm combined with a dynamic permission decay model based on the role type of the logged-in account; acquiring and integrating operational data from multiple data source systems; displaying core indicator modules on a data dashboard interface; performing intelligent calculations on the displayed data; using a collaborative filtering algorithm to recommend indicator modules that users are interested in; employing a frequency-based sorting algorithm to sort by access frequency, recent access time, and access duration, and arranging the indicator modules in order; and providing early warnings for abnormal situations. This invention achieves layered security management, multi-source integration, intelligent prediction, and dynamic interaction of logistics operation data, effectively improving data utilization efficiency and decision support capabilities.

Description

Technical Field

[0001] This invention relates to the field of data visualization and monitoring technology, and in particular to a method and apparatus for monitoring logistics network operation data based on a multi-level architecture. Background Technology

[0002] With the acceleration of digital transformation in the logistics industry, logistics networks are presenting a complex structure of hierarchical, multi-node, and multi-system collaboration. The need for collaboration among multiple roles such as headquarters, regional offices, business provinces, distribution centers, and outlets is becoming increasingly urgent, and efficient operational data monitoring has become the key to improving the efficiency of logistics networks. Current logistics network operation monitoring generally suffers from several pain points: First, data silos are prominent, with data from multiple systems such as reports, prepayments, work orders, and arbitration being fragmented, lacking unified integration and standardized processing. Data formats differ significantly and updates are lagging, preventing operational data from forming a complete closed loop and hindering overall decision-making. Second, data access management is rudimentary, failing to configure differentiated data display permissions based on the management scope of different roles, easily leading to data leaks or inaccurate information acquisition, which does not meet industry requirements for classified and graded management of logistics data. Third, data quality is inconsistent, with frequent missing and abnormal data, and existing processing methods are inefficient and cannot meet the needs of intelligent analysis. Fourth, the accuracy of delivery forecasts is insufficient; traditional forecasting methods do not fully incorporate multi-dimensional features, and the models have poor timeliness, making it difficult to support capacity scheduling optimization. Fifth, visualization is limited and lacks interactivity, with a lack of timely warnings for abnormal situations, resulting in operational risks not being prevented in advance, and anomaly management often remaining in a reactive "firefighting" state.

[0003] Therefore, a method and device for monitoring logistics network operation data based on a multi-level architecture are provided to solve the above problems. Summary of the Invention

[0004] The main objective of this invention is to address the technical problems in the prior art, such as prominent data silos, fragmented data across multiple systems, lack of unified integration and standardized processing, crude data access control, inconsistent data quality, insufficient accuracy in delivery prediction, poor model timeliness, and weak interactivity in visualization.

[0005] The first aspect of this invention provides a method for monitoring logistics network operation data based on a multi-level architecture, the method comprising: Based on the role type of the logged-in account, including headquarters role, regional role, business province role, distribution role and branch role, the corresponding data display level is configured, and a role-based access control algorithm combined with a dynamic permission decay model is introduced. Obtain and integrate operational data from multiple data source systems; The data dashboard interface displays core indicator modules, which include: basic account information module, network construction module, data module, outstanding amount module, weight module, ticket module, receipt module, delivery forecast module, quality module, timeliness module, and inventory module. The system performs intelligent calculations on the displayed data, including calculating the cargo volume completion rate, monthly and daily average, daily average month-on-month comparison, real-time receipt rate, average weight per shipment, average weight per piece, and shipment-to-piece ratio; and uses a time series prediction model combining a long short-term memory network and an attention mechanism to predict shipments. The system uses a collaborative filtering algorithm to recommend metrics modules that users are interested in; it also uses a frequency-based sorting algorithm to sort the metrics modules by access frequency, recent access time, and access duration, and arranges them in that order. Data for day T-1 is collected before 5 PM on day T, and data for day T is collected after 5 PM on day T; delivery forecast data is updated hourly; warnings are issued for abnormal situations such as overdue amounts exceeding 2 days, backlog exceeding 72 hours, and delayed delivery.

[0006] Optionally, the data display level corresponding to the role type in the phrase "configure corresponding data display levels according to the role type of the login account, including headquarters role, regional role, business province role, distribution role, and branch role, and introduce a role-based access control algorithm combined with a dynamic permission decay model" specifically refers to: Headquarters role displays data across the entire network; The regional role displays data for the current region and its subordinate business provinces. The business province role displays the current business province data; The distribution role displays the current distribution data; if it is a district manager, it displays the district manager level information of the next level of distribution. The branch role displays data for the current branch and its subordinate secondary branches.

[0007] Optionally, the process of acquiring and integrating operational data from multiple data source systems specifically includes: Obtain data on shipment volume, shipments, receipts, delivery time, and inventory from the reporting platform; Obtain data from the prepayment system; Obtain complaint data from the work order system; Obtain lost or damaged data from the arbitration system; The acquired data is standardized and associated with various mapping processes. A data integrity scoring algorithm is used to calculate the proportion of valid data entries to the total number of data entries. The isolated forest algorithm is used for outlier detection to identify abnormal records in the data source. The K-nearest neighbor interpolation algorithm is used to intelligently fill in missing data, and the filling value is calculated based on the distance weight.

[0008] Optionally, the module for displaying core indicators on the data dashboard interface specifically includes: The account basic information module displays information such as site structure, name and employee ID, number of outlets, order completion rate, and order ranking. The network construction module displays the number and detailed information of outlets that joined the network last month, joined the network this month, and left the network this month; The data module displays information on the daily number of data outlets, daily data revenue, monthly number of data outlets, and monthly data revenue. The "Amount in Debt" module displays the number of branches with outstanding amounts, the amount owed, data on amounts owed for more than 2 days, and information on changes compared to yesterday. The weight module displays today's / yesterday's cargo volume, the current / previous month's cumulative volume, the current / previous month's daily average, and the month-on-month comparison of the daily average. The ticket module displays the number of tickets and items for today / yesterday, cumulative for the current month / last month, daily average for the current month / last month, and daily average month-on-month comparison, as well as the average weight of tickets, average weight of items, and ticket-to-item ratio analysis information; The signing module displays the actual signing rate, number of unsigned tickets, number of overdue unsigned tickets, number of tickets that should be signed, number of signed tickets, data that does not meet the standards, and real-time signing rate information. The delivery forecast module displays the estimated weight, volume, number of tickets, and number of packages to be delivered over the next three days. The quality module displays daily and monthly data on complaints, lost items, and damages. The timeliness module displays daily and monthly data on delayed delivery and delayed receipt. The inventory module displays information on the number of items in stock, the number of originating shipments, the number of non-originating shipments, the number of items backlogged for more than 72 hours, the amount of loans received, and the amount of cash on delivery for the past seven days.

[0009] Optionally, the calculation formula for intelligent calculation of the displayed data specifically includes: Cargo volume completion rate = (Actual cargo volume completed in the current month / Target value for the current month) × 100%; Monthly average daily volume = Monthly cumulative cargo volume / (Working day coefficient 1 + Working day coefficient 2 + ... + Working day coefficient n); Daily average month-on-month change = (This month's daily average - Last month's daily average) / Last month's daily average × 100%; Real-time acceptance rate = (Number of tickets accepted in real time / Number of tickets that should be accepted in real time) × 100%; Average ticket weight = Total weight of tickets issued in the current month / Total number of tickets issued in the current month; Average weight per piece = Total weight of orders placed in the current month / Total number of orders placed in the current month; Ticket-to-item ratio = Total number of tickets issued in the current month / Total number of items issued in the current month.

[0010] Optionally, the training process of the time series prediction model using a long short-term memory network combined with an attention mechanism for delivery forecasting specifically includes: Feature engineering: Extracting historical seven-day cargo volume features, date features, holiday features, weather features, and promotional activity features; Data standardization: Standardizing data to eliminate differences in units of measurement; Model training: An adaptive moment estimation optimizer is used, with appropriate learning rate and batch size set; Forecast output: Outputs the estimated weight, volume, number of tickets, and number of packages for delivery over the next three days; Model updates: Incremental training is performed every hour to keep the model up-to-date.

[0011] Prediction principle: Multi-step prediction based on historical sequence data and contextual features.

[0012] Optionally, the introduction of a role-based access control algorithm combined with a dynamic permission decay model specifically includes: A role-based access control model is adopted for basic permission allocation, and a time decay factor is introduced to dynamically downgrade the permissions of data that have not been accessed for a long time. The permission weight is dynamically calculated based on the initial weight, decay coefficient and inaccessibility time.

[0013] A second aspect of the present invention provides a logistics network operation data monitoring device based on a multi-level architecture, the logistics network operation data monitoring device based on a multi-level architecture comprising: The permission configuration module is used to configure the corresponding data display level according to the role type of the logged-in account, which includes headquarters role, regional role, business province role, distribution role and branch role. It introduces a role-based access control algorithm combined with a dynamic permission decay model. The data acquisition and integration module is used to acquire and integrate operational data from multiple data source systems. The indicator display module is used to display core indicator modules on the data dashboard interface. The core modules include: basic account information module, network construction module, data module, outstanding amount module, weight module, ticket module, receipt module, delivery forecast module, quality module, timeliness module, and inventory module. The data calculation module is used to perform intelligent calculations on the displayed data, including calculating the cargo volume completion rate, monthly and daily average, daily average month-on-month comparison, real-time receipt rate, average weight of each shipment, average weight of each piece, and shipment-to-piece ratio; and it uses a time series prediction model that combines a long short-term memory network with an attention mechanism to predict the delivery schedule. The recommendation interaction module uses a collaborative filtering algorithm to recommend indicator modules that users are interested in; it uses a frequency-based sorting algorithm to sort the indicator modules by access frequency, recent access time, and access duration, and arranges them in order. Update the early warning module to collect data for day T-1 before 5 PM on day T and data for day T after 5 PM on day T; update delivery forecast data hourly; and provide early warnings for abnormal situations such as overdue amounts exceeding 2 days, backlog exceeding 72 hours, and delayed receipt.

[0014] A third aspect of the present invention provides an electronic device, the electronic device comprising a memory and at least one processor, wherein the memory stores instructions; The at least one processor invokes the instructions in the memory to cause the electronic device to execute the various steps of the multi-level architecture-based logistics network operation data monitoring method as described above.

[0015] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed by a processor, implement the various steps of the multi-level architecture-based logistics network operation data monitoring method described above.

[0016] The technical solution of this invention addresses the data silo problem through multi-system data integration steps, achieving unified acquisition, standardized processing, and correlation mapping of various data sources. Combined with data quality assessment algorithms, it effectively solves data missing and anomaly issues, improves data integrity and reliability, and provides solid data support for subsequent analysis and decision-making, aligning with the industry's development needs for open and interconnected logistics data. It implements refined permission control based on role-type configuration of multi-level data display permissions, ensuring that different roles accurately access operational data within their respective management scopes, guaranteeing data security while improving work efficiency, and conforming to logistics data classification and hierarchical management standards. It enhances the effectiveness of visual monitoring, with multi-dimensional core indicator modules comprehensively covering the entire logistics operation process, intuitively presenting key information such as cargo volume, timeliness, and quality. Combined with interactive operation design, it enables rapid data detail querying and personalized interface adaptation, reducing user operation costs. It strengthens intelligent decision-making capabilities by using a delivery forecasting model that combines precise indicator calculation with a long short-term memory network and attention mechanism to achieve accurate delivery data prediction. Hourly incremental training ensures model timeliness, assisting in capacity scheduling optimization, and significantly improving prediction accuracy compared to traditional LSTM models. Attached Figure Description

[0017] Figure 1 A flowchart illustrating a logistics network operation data monitoring method based on a multi-level architecture, provided in an embodiment of the present invention. Figure 2A schematic diagram of the structure of a logistics network operation data monitoring device based on a multi-level architecture provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0018] This invention provides a method for monitoring logistics network operation data based on a multi-level architecture. The method includes configuring corresponding data display levels according to the login account's role type (including headquarters, regional, provincial, distribution, and branch roles), introducing a role-based access control algorithm combined with a dynamic permission decay model; acquiring and integrating operational data from multiple data source systems; displaying core indicator modules on a data dashboard interface, including: basic account information module, network construction module, data module, outstanding amount module, weight module, shipment module, receipt module, delivery forecast module, quality module, timeliness module, and inventory module; performing intelligent calculations on the displayed data, including calculating cargo volume completion rate, monthly / daily average, daily average month-on-month change, real-time receipt rate, average shipment weight, average shipment weight, and shipment / shipment ratio; and employing... This invention employs a time-series prediction model combining a Long Short-Term Memory (LSTM) network with an attention mechanism for delivery forecasting; a collaborative filtering algorithm is used to recommend user-focused indicator modules; a frequency-based ranking algorithm is used to sort the indicator modules by access frequency, recent access time, and access duration; data for day T-1 is collected before 5 PM on day T, and data for day T is collected after 5 PM on day T; delivery forecast data is updated hourly; and warnings are issued for abnormal situations such as overdue amounts exceeding 2 days, backlog exceeding 72 hours, and delayed delivery confirmation. This invention addresses the technical problems in existing technologies, including prominent data silos, fragmented data across multiple systems, lack of unified integration and standardized processing, lax data access control, inconsistent data quality, insufficient delivery forecast accuracy, poor model timeliness, and limited visualization and interactivity.

[0019] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 The first embodiment of the method for monitoring logistics network operation data based on a multi-level architecture in this invention includes: Based on the role type of the logged-in account, including headquarters role, regional role, business province role, distribution role and branch role, the corresponding data display level is configured, and a role-based access control algorithm combined with a dynamic permission decay model is introduced. The specific data display hierarchy corresponding to the role type is as follows: Headquarters role displays data across the entire network; The regional role displays data for the current region and its subordinate business provinces. The business province role displays the current business province data; The distribution role displays the current distribution data; if it is a district manager, it displays the district manager level information of the next level of distribution. The branch role displays data for the current branch and its subordinate secondary branches; The introduction of role-based access control algorithms combined with dynamic permission decay models specifically includes: A role-based access control model is adopted for basic permission allocation, and a time decay factor is introduced to dynamically downgrade the permissions of data that have not been accessed for a long time. The permission weight is dynamically calculated based on the initial weight, decay coefficient and inaccessibility time.

[0021] Through the above steps, this embodiment achieves refined access control, configuring multi-level data display permissions based on role type to ensure that different roles accurately obtain operational data within their corresponding management scope, thus protecting data security, improving work efficiency, and complying with the logistics data classification and grading management standards.

[0022] Obtain and integrate operational data from multiple data source systems; The data dashboard interface displays core indicator modules, which include: basic account information module, network construction module, data module, outstanding amount module, weight module, ticket module, receipt module, delivery forecast module, quality module, timeliness module, and inventory module. The system performs intelligent calculations on the displayed data, including calculating the cargo volume completion rate, monthly and daily average, daily average month-on-month comparison, real-time receipt rate, average weight per shipment, average weight per piece, and shipment-to-piece ratio; and uses a time series prediction model combining a long short-term memory network and an attention mechanism to predict shipments. The system uses a collaborative filtering algorithm to recommend metrics modules that users are interested in; it also uses a frequency-based sorting algorithm to sort the metrics modules by access frequency, recent access time, and access duration, and arranges them in that order. Data for day T-1 is collected before 5 PM on day T, and data for day T is collected after 5 PM on day T; delivery forecast data is updated hourly; warnings are issued for abnormal situations such as overdue amounts exceeding 2 days, backlog exceeding 72 hours, and delayed delivery.

[0023] Please see Figure 1 The second embodiment of the method for monitoring logistics network operation data based on a multi-level architecture in this invention includes: Based on the role type of the logged-in account, including headquarters role, regional role, business province role, distribution role and branch role, the corresponding data display level is configured, and a role-based access control algorithm combined with a dynamic permission decay model is introduced. The specific data display hierarchy corresponding to the role type is as follows: Headquarters role displays data across the entire network; The regional role displays data for the current region and its subordinate business provinces. The business province role displays the current business province data; The distribution role displays the current distribution data; if it is a district manager, it displays the district manager level information of the next level of distribution. The branch role displays data for the current branch and its subordinate secondary branches; The introduction of role-based access control algorithms combined with dynamic permission decay models specifically includes: A role-based access control model is adopted for basic permission allocation, and a time decay factor is introduced to dynamically downgrade the permissions of data that have not been accessed for a long time. The permission weight is dynamically calculated based on the initial weight, decay coefficient and inaccessibility time.

[0024] Through the above steps, this embodiment achieves refined access control, configuring multi-level data display permissions based on role type to ensure that different roles accurately obtain operational data within their corresponding management scope, thus protecting data security, improving work efficiency, and complying with the logistics data classification and grading management standards.

[0025] Obtain and integrate operational data from multiple data source systems; Specifically, this includes: Obtain data on shipment volume, shipments, receipts, delivery time, and inventory from the reporting platform; Obtain data from the prepayment system; Obtain complaint data from the work order system; Obtain lost or damaged data from the arbitration system; The acquired data is standardized and associated with various mapping processes. A data integrity scoring algorithm is used to calculate the proportion of valid data entries to the total number of data entries. The isolated forest algorithm is used for outlier detection to identify abnormal records in the data source. The K-nearest neighbor interpolation algorithm is used to intelligently fill in missing data, and the filling value is calculated based on the distance weight.

[0026] By integrating data from multiple systems, unified acquisition, standardized processing, and correlation mapping of various data sources are achieved. Combined with data quality assessment algorithms, data missing and anomaly issues are effectively resolved, data integrity and reliability are improved, and solid data support is provided for subsequent analysis and decision-making, which aligns with the industry development needs of open and interconnected logistics data.

[0027] The data dashboard interface displays core indicator modules, which include: basic account information module, network construction module, data module, outstanding amount module, weight module, ticket module, receipt module, delivery forecast module, quality module, timeliness module, and inventory module. The system performs intelligent calculations on the displayed data, including calculating the cargo volume completion rate, monthly and daily average, daily average month-on-month comparison, real-time receipt rate, average weight per shipment, average weight per piece, and shipment-to-piece ratio; and uses a time series prediction model combining a long short-term memory network and an attention mechanism to predict shipments. The system uses a collaborative filtering algorithm to recommend metrics modules that users are interested in; it also uses a frequency-based sorting algorithm to sort the metrics modules by access frequency, recent access time, and access duration, and arranges them in that order. Data for day T-1 is collected before 5 PM on day T, and data for day T is collected after 5 PM on day T; delivery forecast data is updated hourly; warnings are issued for abnormal situations such as overdue amounts exceeding 2 days, backlog exceeding 72 hours, and delayed delivery.

[0028] Please see Figure 1 The third embodiment of the method for monitoring logistics network operation data based on a multi-level architecture in this invention includes: Based on the role type of the logged-in account, including headquarters role, regional role, business province role, distribution role and branch role, the corresponding data display level is configured, and a role-based access control algorithm combined with a dynamic permission decay model is introduced. The specific data display hierarchy corresponding to the role type is as follows: Headquarters role displays data across the entire network; The regional role displays data for the current region and its subordinate business provinces. The business province role displays the current business province data; The distribution role displays the current distribution data; if it is a district manager, it displays the district manager level information of the next level of distribution. The branch role displays data for the current branch and its subordinate secondary branches; The introduction of role-based access control algorithms combined with dynamic permission decay models specifically includes: A role-based access control model is adopted for basic permission allocation, and a time decay factor is introduced to dynamically downgrade the permissions of data that have not been accessed for a long time. The permission weight is dynamically calculated based on the initial weight, decay coefficient and inaccessibility time.

[0029] Through the above steps, this embodiment achieves refined access control, configuring multi-level data display permissions based on role type to ensure that different roles accurately obtain operational data within their corresponding management scope, thus protecting data security, improving work efficiency, and complying with the logistics data classification and grading management standards.

[0030] Obtain and integrate operational data from multiple data source systems; Specifically, this includes: Obtain data on shipment volume, shipments, receipts, delivery time, and inventory from the reporting platform; Obtain data from the prepayment system; Obtain complaint data from the work order system; Obtain lost or damaged data from the arbitration system; The acquired data is standardized and associated with various mapping processes. A data integrity scoring algorithm is used to calculate the proportion of valid data entries to the total number of data entries. The isolated forest algorithm is used for outlier detection to identify abnormal records in the data source. The K-nearest neighbor interpolation algorithm is used to intelligently fill in missing data, and the filling value is calculated based on the distance weight.

[0031] By integrating data from multiple systems, unified acquisition, standardized processing, and correlation mapping of various data sources are achieved. Combined with data quality assessment algorithms, data missing and anomaly issues are effectively resolved, data integrity and reliability are improved, and solid data support is provided for subsequent analysis and decision-making, which aligns with the industry development needs of open and interconnected logistics data.

[0032] The data dashboard interface displays core indicator modules, which include: basic account information module, network construction module, data module, outstanding amount module, weight module, ticket module, receipt module, delivery forecast module, quality module, timeliness module, and inventory module. The module for displaying core indicators on the data dashboard interface specifically includes: The account basic information module displays information such as site structure, name and employee ID, number of outlets, order completion rate, and order ranking. The network construction module displays the number and detailed information of outlets that joined the network last month, joined the network this month, and left the network this month; The data module displays information on the daily number of data outlets, daily data revenue, monthly number of data outlets, and monthly data revenue. The "Amount in Debt" module displays the number of branches with outstanding amounts, the amount owed, data on amounts owed for more than 2 days, and information on changes compared to yesterday. The weight module displays today's / yesterday's cargo volume, the current / previous month's cumulative volume, the current / previous month's daily average, and the month-on-month comparison of the daily average. The ticket module displays the number of tickets and items for today / yesterday, cumulative for the current month / last month, daily average for the current month / last month, and daily average month-on-month comparison, as well as the average weight of tickets, average weight of items, and ticket-to-item ratio analysis information; The signing module displays the actual signing rate, number of unsigned tickets, number of overdue unsigned tickets, number of tickets that should be signed, number of signed tickets, data that does not meet the standards, and real-time signing rate information. The delivery forecast module displays the estimated weight, volume, number of tickets, and number of packages to be delivered over the next three days. The quality module displays daily and monthly data on complaints, lost items, and damages. The timeliness module displays daily and monthly data on delayed delivery and delayed receipt. The inventory module displays information on the number of items in stock, the number of originating shipments, the number of non-originating shipments, the number of items backlogged for more than 72 hours, the amount of loans received, and the amount of cash on delivery for the past seven days.

[0033] Enhance the effectiveness of visual monitoring; multi-dimensional core indicator modules comprehensively cover the entire logistics operation process, intuitively presenting key information such as cargo volume, timeliness, and quality.

[0034] The system performs intelligent calculations on the displayed data, including calculating the cargo volume completion rate, monthly and daily average, daily average month-on-month comparison, real-time receipt rate, average weight per shipment, average weight per piece, and shipment-to-piece ratio; and uses a time series prediction model combining a long short-term memory network and an attention mechanism to predict shipments. The specific calculation formulas used in intelligent calculation of the displayed data include: Cargo volume completion rate = (Actual cargo volume completed in the current month / Target value for the current month) × 100%; Monthly average daily volume = Monthly cumulative cargo volume / (Working day coefficient 1 + Working day coefficient 2 + ... + Working day coefficient n); Daily average month-on-month change = (This month's daily average - Last month's daily average) / Last month's daily average × 100%; Real-time acceptance rate = (Number of tickets accepted in real time / Number of tickets that should be accepted in real time) × 100%; Average ticket weight = Total weight of tickets issued in the current month / Total number of tickets issued in the current month; Average weight per piece = Total weight of orders placed in the current month / Total number of orders placed in the current month; Ticket-to-item ratio = Total number of tickets issued in the current month / Total number of items issued in the current month.

[0035] The training process for a time-series prediction model that combines a long short-term memory network with an attention mechanism specifically includes: Feature engineering: Extracting historical seven-day cargo volume features, date features, holiday features, weather features, and promotional activity features; Data standardization: Standardizing data to eliminate differences in units of measurement; Model training: An adaptive moment estimation optimizer is used, with appropriate learning rate and batch size set; Forecast output: Outputs the estimated weight, volume, number of tickets, and number of packages for delivery over the next three days; Model updates: Incremental training is performed every hour to keep the model up-to-date.

[0036] Prediction principle: Multi-step prediction based on historical sequence data and contextual features.

[0037] The system employs a collaborative filtering algorithm to recommend user-focused indicator modules; it also uses a frequency-based sorting algorithm to rank the indicator modules by access frequency, recent access time, and access duration. In this step, the embodiment supports the following interactive operations: pull-down to refresh interface data; swipe left and right to switch pages; click on an indicator module to jump to the detailed information interface; click the indicator description button to display a pop-up window with explanatory content; and click the banner to display a pop-up window showing network entry / exit details.

[0038] Data for day T-1 is collected before 5 PM on day T, and data for day T is collected after 5 PM on day T; delivery forecast data is updated hourly; warnings are issued for abnormal situations such as overdue amounts exceeding 2 days, backlog exceeding 72 hours, and delayed delivery.

[0039] The above describes the logistics network operation data monitoring method based on a multi-level architecture in the embodiments of the present invention. The following describes the logistics network operation data monitoring device based on a multi-level architecture in the embodiments of the present invention. Please refer to [link / reference]. Figure 2 The logistics network operation data monitoring device based on a multi-level architecture in this embodiment of the invention includes, for the above embodiments: The permission configuration module 201 is used to configure the corresponding data display level according to the role type of the login account, which includes headquarters role, regional role, business province role, distribution role and branch role, and introduces a role-based access control algorithm combined with a dynamic permission decay model. The data acquisition and integration module 202 is used to acquire and integrate operational data from multiple data source systems. The indicator display module 203 is used to display core indicator modules on the data dashboard interface. The core modules include: basic account information module, network construction module, data module, outstanding amount module, weight module, ticket module, receipt module, delivery forecast module, quality module, timeliness module, and inventory module. The data calculation module 204 is used to perform intelligent calculations on the displayed data, including calculating the cargo volume completion rate, monthly and daily average, daily average month-on-month comparison, real-time receipt rate, average weight of each shipment, average weight of each piece, and shipment-to-piece ratio; and uses a time series prediction model combining a long short-term memory network and an attention mechanism to predict the delivery of goods. The recommendation interaction module 205 is used to recommend indicator modules that users are interested in using a collaborative filtering algorithm; it uses a sorting algorithm based on usage frequency to sort the access frequency, recent access time, and access duration, and arranges the indicator modules in order. Update the early warning module 206 to collect data for day T-1 before 5 PM on day T and data for day T after 5 PM on day T; update the delivery forecast data hourly; and provide early warnings for abnormal situations such as overdue amounts exceeding 2 days, backlog exceeding 72 hours, and delayed receipt.

[0040] above Figure 2 The logistics network operation data monitoring device based on a multi-level architecture in this embodiment of the invention will be described in detail from the perspective of modular functional entities. The electronic equipment in this embodiment of the invention will be described in detail from the perspective of hardware processing.

[0041] Figure 3 This is a schematic diagram of the structure of an electronic device 700 provided in an embodiment of the present invention. The electronic device 700 can vary significantly due to differences in configuration or performance. It may include one or more processors 710 (e.g., one or more processors) and a memory 720, and one or more storage media 730 (e.g., one or more storage devices, including RAM, FLASH, etc.) for storing application programs 733 or data 732. The memory 720 and storage media 730 can be temporary or persistent storage. The program stored in the storage media 730 may include one or more modules (not shown in the diagram), each module including a series of instruction operations on the electronic device 700. Furthermore, the processor 710 may be configured to communicate with the storage media 730 and execute the series of instruction operations in the storage media 730 on the electronic device 700.

[0042] The electronic device 700 may also include one or more power supplies 740, one or more input / output interfaces 750, and / or one or more operating systems 731, such as FreeRTOS, Android, etc. Those skilled in the art will understand that... Figure 3The illustrated electronic device structure does not constitute a limitation on electronic devices and may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0043] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the steps of a logistics network operation data monitoring method based on a multi-level architecture.

[0044] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system, device, or unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0045] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, mobile device, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0046] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring logistics network operation data based on a multi-level architecture, characterized in that, The multi-level architecture logistics network operation data monitoring method includes: Based on the role type of the logged-in account, including headquarters role, regional role, business province role, distribution role and branch role, the corresponding data display level is configured, and a role-based access control algorithm combined with a dynamic permission decay model is introduced. Obtain and integrate operational data from multiple data source systems; The data dashboard interface displays core indicator modules, which include: basic account information module, network construction module, data module, outstanding amount module, weight module, ticket module, receipt module, delivery forecast module, quality module, timeliness module, and inventory module. The system performs intelligent calculations on the displayed data, including calculating the cargo volume completion rate, monthly and daily average, daily average month-on-month comparison, real-time receipt rate, average weight per shipment, average weight per piece, and shipment-to-piece ratio; and uses a time series prediction model combining a long short-term memory network and an attention mechanism to predict shipments. The system uses a collaborative filtering algorithm to recommend metrics modules that users are interested in; it also uses a frequency-based sorting algorithm to sort the metrics modules by access frequency, recent access time, and access duration, and arranges them in that order. Data for day T-1 is collected before 5 PM on day T, and data for day T is collected after 5 PM on day T; delivery forecast data is updated hourly; warnings are issued for abnormal situations such as overdue amounts exceeding 2 days, backlog exceeding 72 hours, and delayed delivery.

2. The method for monitoring logistics network operation data based on a multi-level architecture according to claim 1, characterized in that, The specific data display hierarchy corresponding to the role type in the phrase "based on the role type of the login account, including headquarters role, regional role, business province role, distribution role, and branch role, configure corresponding data display levels, and introduce a role-based access control algorithm combined with a dynamic permission decay model" is as follows: Headquarters role displays data across the entire network; The regional role displays data for the current region and its subordinate business provinces. The business province role displays the current business province data; The distribution role displays the current distribution data; if it is a district manager, it displays the district manager level information of the next level of distribution. The branch role displays data for the current branch and its subordinate secondary branches.

3. The method for monitoring logistics network operation data based on a multi-level architecture according to claim 1, characterized in that, The process of acquiring and integrating operational data from multiple data source systems specifically includes: Obtain data on shipment volume, shipments, receipts, delivery time, and inventory from the reporting platform; Obtain data from the prepayment system; Obtain complaint data from the work order system; Obtain lost or damaged data from the arbitration system; The acquired data is standardized and associated with various mapping processes. A data integrity scoring algorithm is used to calculate the proportion of valid data entries to the total number of data entries. The isolated forest algorithm is used for outlier detection to identify abnormal records in the data source. The K-nearest neighbor interpolation algorithm is used to intelligently fill in missing data, and the filling value is calculated based on the distance weight.

4. The method for monitoring logistics network operation data based on a multi-level architecture according to claim 1, characterized in that, The module for displaying core indicators on the data dashboard interface specifically includes: The account basic information module displays information such as site structure, name and employee ID, number of outlets, order completion rate, and order ranking. The network construction module displays the number and detailed information of outlets that joined the network last month, joined the network this month, and left the network this month; The data module displays information on the daily number of data outlets, daily data revenue, monthly number of data outlets, and monthly data revenue. The "Amount in Debt" module displays the number of branches with outstanding amounts, the amount owed, data on amounts owed for more than 2 days, and information on the change compared to yesterday. The weight module displays today's / yesterday's cargo volume, the current / previous month's cumulative volume, the current / previous month's daily average, and the month-on-month comparison of the daily average. The ticket module displays the number of tickets and items for today / yesterday, cumulative for the current month / last month, daily average for the current month / last month, and daily average month-on-month comparison, as well as the average weight of tickets, average weight of items, and ticket-to-item ratio analysis information; The signing module displays the actual signing rate, number of unsigned tickets, number of overdue unsigned tickets, number of tickets that should be signed, number of signed tickets, data that does not meet the standards, and real-time signing rate information. The delivery forecast module displays the estimated weight, volume, number of tickets, and number of packages to be delivered over the next three days. The quality module displays daily and monthly data on complaints, lost items, and damages. The timeliness module displays daily and monthly data on delayed delivery and delayed receipt. The inventory module displays information on the number of items in stock, the number of originating shipments, the number of non-originating shipments, the number of items backlogged for more than 72 hours, the amount of loans received, and the amount of cash on delivery for the past seven days.

5. The method for monitoring logistics network operation data based on a multi-level architecture according to claim 1, characterized in that, The calculation formulas used in the intelligent calculation of the displayed data specifically include: Cargo volume completion rate = (Actual cargo volume completed in the current month / Target value for the current month) × 100%; Monthly average daily volume = Monthly cumulative cargo volume / (Working day coefficient 1 + Working day coefficient 2 + ... + Working day coefficient n); Daily average month-on-month change = (This month's daily average - Last month's daily average) / Last month's daily average × 100%; Real-time acceptance rate = (Number of tickets accepted in real time / Number of tickets that should be accepted in real time) × 100%; Average ticket weight = Total weight of tickets issued in the current month / Total number of tickets issued in the current month; Average weight per piece = Total weight of orders placed in the current month / Total number of orders placed in the current month; Ticket-to-item ratio = Total number of tickets issued in the current month / Total number of items issued in the current month.

6. The method for monitoring logistics network operation data based on a multi-level architecture according to claim 1, characterized in that, The training process of the time series prediction model using a long short-term memory network combined with an attention mechanism for delivery forecasting specifically includes: Feature engineering: Extracting historical seven-day cargo volume features, date features, holiday features, weather features, and promotional activity features; Data standardization: Standardizing data to eliminate differences in units of measurement; Model training: An adaptive moment estimation optimizer is used, with appropriate learning rate and batch size set; Forecast output: Outputs the estimated weight, volume, number of tickets, and number of packages for delivery over the next three days; Model updates: Incremental training is performed every hour to keep the model up-to-date. Prediction principle: Multi-step prediction based on historical sequence data and contextual features.

7. The method for monitoring logistics network operation data based on a multi-level architecture according to claim 1, characterized in that, The introduction of a role-based access control algorithm combined with a dynamic permission decay model specifically includes: A role-based access control model is adopted for basic permission allocation, and a time decay factor is introduced to dynamically downgrade the permissions of data that have not been accessed for a long time. The permission weight is dynamically calculated based on the initial weight, decay coefficient and inaccessibility time.

8. A logistics network operation data monitoring device based on a multi-level architecture, used in the logistics network operation data monitoring method based on a multi-level architecture as described in any one of claims 1-7, characterized in that, include: The permission configuration module is used to configure the corresponding data display level according to the role type of the logged-in account, which includes headquarters role, regional role, business province role, distribution role and branch role. It introduces a role-based access control algorithm combined with a dynamic permission decay model. The data acquisition and integration module is used to acquire and integrate operational data from multiple data source systems. The indicator display module is used to display core indicator modules on the data dashboard interface. The core modules include: basic account information module, network construction module, data module, outstanding amount module, weight module, ticket module, receipt module, delivery forecast module, quality module, timeliness module, and inventory module. The data calculation module is used to perform intelligent calculations on the displayed data, including calculating the cargo volume completion rate, monthly and daily average, daily average month-on-month comparison, real-time receipt rate, average weight of each shipment, average weight of each piece, and shipment-to-piece ratio; and it uses a time series prediction model that combines a long short-term memory network with an attention mechanism to predict the delivery schedule. The recommendation interaction module uses a collaborative filtering algorithm to recommend indicator modules that users are interested in; it uses a frequency-based sorting algorithm to sort the indicator modules by access frequency, recent access time, and access duration, and arranges them in order. Update the early warning module to collect data for day T-1 before 5 PM on day T and data for day T after 5 PM on day T; update delivery forecast data hourly; and provide early warnings for abnormal situations such as overdue amounts exceeding 2 days, backlog exceeding 72 hours, and delayed receipt.

9. An electronic device comprising a memory and at least one processor, wherein the memory stores instructions; characterized in that, The at least one processor invokes the instructions in the memory to cause the electronic device to perform the steps of the multi-level architecture-based logistics network operation data monitoring method as described in any one of claims 1-7.

10. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement the various steps of the logistics network operation data monitoring method based on a multi-level architecture as described in any one of claims 1-7.

Images