Logistics express cabinet data analysis method and device, memory and storage medium

Abstract

The invention relates to the technical field of logistics express cabinet management, and discloses a logistics express cabinet data analysis method. Obtaining express cabinet data information of the express cabinet, wherein the express cabinet data information comprises core index information, business volume trend information, yesterday delivery rate ranking information and offline cabinet condition information; performing data processing on the express cabinet data information, wherein the data processing comprises a data cleaning process, a data sorting process and a data classification process; establishing a BP express cabinet data prediction model based on a BP neural network, and optimizing hyper-parameters and weights of the BP express cabinet data prediction model by using a POS particle swarm algorithm; inputting the processed express cabinet data information into the optimized BP express cabinet data prediction model for prediction, and managing the installation number and the use condition of the express cabinets according to a prediction result; the method has the advantage of improving the distribution efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics express cabinet management, and in particular to a logistics express cabinet data analysis method, device, memory and storage medium. Background Art

[0002] In recent years, logistics express lockers have developed rapidly around the world. Especially in China, with the continuous expansion of the e-commerce market, the number and scale of logistics express lockers are also growing continuously. These express lockers not only appear in consumer hotspots such as communities, office buildings, and schools, but also gradually penetrate into rural and remote areas to provide users with more convenient services. However, with the continuous increase in the number of express lockers, traditional manual management methods can no longer meet the needs of the modern logistics industry. How to effectively manage these express lockers has become an urgent problem to be solved.

[0003] Therefore, a logistics express cabinet data analysis method, device, memory and storage medium are provided to solve the above problems. Summary of the invention

[0004] The main purpose of the present invention is to solve the problem in the prior art that as the number of express lockers continues to increase, the traditional manual management method can no longer meet the needs of the modern logistics industry, and how to effectively manage these express lockers.

[0005] A first aspect of the present invention provides a logistics express cabinet data analysis method, the logistics express cabinet data analysis method comprising: Obtaining express cabinet data information of the express cabinet, the express cabinet data information including: core indicator information, business volume trend information, yesterday's delivery rate ranking information and offline cabinet status information; Performing data processing on the express cabinet data information, wherein the data processing includes a data cleaning process, a data sorting process, and a data classification process; A BP express cabinet data prediction model is established based on the BP neural network, and the hyperparameters and weights of the BP express cabinet data prediction model are optimized using the POS particle swarm algorithm; The processed express cabinet data information is input into the optimized BP express cabinet data prediction model for prediction, and the installation quantity and usage of the express cabinets are managed according to the prediction results.

[0006] Optionally, the express cabinet data information of the express cabinet is obtained, and the express cabinet data information includes: core indicator information, business volume trend information, yesterday's delivery rate ranking information and offline cabinet status information including: Obtain core indicator information of express lockers, including delivery volume information, delivery rate information, number of online lockers, number of offline lockers, and number of zero-delivery lockers; Acquire business volume trend information of the express locker, wherein the business volume trend information includes first time range information, first indicator type information, first label selection information, first data display information and first detailed information; Obtain yesterday's delivery rate ranking information of the express lockers, where yesterday's delivery rate ranking information includes second time range information, second label selection information, second data display information, and second detailed information; Obtain offline cabinet status information, wherein the offline cabinet status information includes: third time range information, third indicator type information, third label selection information, third data display information and third detailed information.

[0007] Optionally, the data cleaning process includes: Identify erroneous data information, duplicate data information, incomplete data information and inconsistent data information in express locker data; For erroneous data information, duplicate data information, incomplete data information and inconsistent data information in the express cabinet data, invalid records are removed, erroneous values ​​are corrected, missing values ​​are filled and abnormal values ​​are processed; time series data in the express cabinet data are time-aligned and abnormal fluctuations in the time series are processed.

[0008] Optionally, the data sorting process includes: Organize the cleaned data according to the preset structure; Summarize the data after data cleaning.

[0009] Optionally, the data classification process includes: Obtain analysis purpose information, and divide the express cabinet data that has gone through the data sorting process into training set, validation set, and test set according to the analysis purpose information.

[0010] Optionally, the step of inputting the processed express locker data information into the optimized BP express locker data prediction model for prediction, and managing the installation quantity and usage of the express lockers according to the prediction results includes: Input the processed express cabinet data information into the optimized BP express cabinet data prediction model for prediction, and generate prediction result information, which includes the frequency of use of express cabinets, peak time information and regional demand information; The estimated number of express lockers and the estimated installation locations of express lockers are generated based on the frequency of use of express lockers, peak hours and regional demand information.

[0011] A second aspect of the present invention provides a logistics express cabinet data analysis device, comprising: A data acquisition module is used to acquire the express cabinet data information of the express cabinet, wherein the express cabinet data information includes: core indicator information, business volume trend information, yesterday's delivery rate ranking information and offline cabinet status information; A data processing module is used to process the data information of the express cabinet, and the data processing includes a data cleaning process, a data sorting process and a data classification process; The model building module is used to build a BP express cabinet data prediction model based on the BP neural network, and use the POS particle swarm algorithm to optimize the hyperparameters and weights of the BP express cabinet data prediction model; The prediction management module is used to input the processed express cabinet data information into the optimized BP express cabinet data prediction model for prediction, and manage the installation quantity and usage of the express cabinets according to the prediction results.

[0012] A third aspect of the present invention provides an electronic device, the electronic device comprising a memory and at least one processor, the memory storing instructions; The at least one processor calls the instructions in the memory so that the electronic device executes each step of the logistics express cabinet data analysis method as described above.

[0013] A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed by a processor, implement the various steps of the logistics express cabinet data analysis method described above.

[0014] The technical solution of the present invention provides a logistics express cabinet data analysis method, which can optimize the placement, quantity, opening hours, etc. of the express cabinets to meet the needs of users. Understand the circulation and delivery efficiency of express delivery. Based on these data, we can optimize the delivery route, delivery time, etc. of the express delivery to improve the delivery efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A flow chart of a logistics express cabinet data analysis method provided by the first embodiment of the present invention; Figure 2 A flow chart of a logistics express cabinet data analysis method provided by a second embodiment of the present invention; Figure 3 A flow chart of a logistics express cabinet data analysis method provided by the third embodiment of the present invention; Figure 4 A flow chart of a logistics express cabinet data analysis method provided in a fourth embodiment of the present invention; Figure 5 A schematic diagram of the structure of a logistics express cabinet data analysis device provided by an embodiment of the present invention; Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The embodiment of the present invention provides a method for analyzing logistics express cabinet data, including obtaining express cabinet data information of the express cabinet, the express cabinet data information including: core indicator information, business volume trend information, yesterday's delivery rate ranking information and offline cabinet status information; performing data processing on the express cabinet data information, the data processing including a data cleaning process, a data sorting process and a data classification process; establishing a BP express cabinet data prediction model based on a BP neural network, and optimizing the hyperparameters and weights of the BP express cabinet data prediction model using a POS particle swarm algorithm; inputting the processed express cabinet data information into the optimized BP express cabinet data prediction model for prediction, and managing the installation quantity and usage of the express cabinet according to the prediction results. The present invention solves the problem in the prior art that the traditional manual management method can no longer meet the needs of the modern logistics industry, and how to effectively manage these express cabinets.

[0017] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0018] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 The first embodiment of the logistics express cabinet data analysis method in the embodiment of the present invention includes: Obtaining express cabinet data information of the express cabinet, the express cabinet data information including: core indicator information, business volume trend information, yesterday's delivery rate ranking information and offline cabinet status information; Specifically, they include: Obtain core indicator information of express lockers, including delivery volume information, delivery rate information, number of online lockers, number of offline lockers, and number of zero-delivery lockers; Delivery volume information includes year-on-year data from yesterday and information on packages that have been picked up; The delivery volume information is used to display the number of parcels delivered on the day up to the current system time; The year-on-year data information is used to show the delivery volume at the same time as yesterday, the increase or decrease percentage (today's delivery volume / yesterday's delivery volume at the same time - 1) * 100%; The pickup information is used to display the number of parcels that have been picked up on the day up to the current system time; Delivery rate information includes year-on-year yesterday's data information, subscription information and self-operated information; The delivery rate information is used to display the slot utilization rate (number of parcels in the cabinet / total number of online cabinet slots) from the current day to the current system time. The year-on-year data information is used to show the delivery rate compared with the same time yesterday, the increase or decrease percentage (today's delivery rate - yesterday's delivery rate at the same time) * 100%; Subscription information is used to display the slot utilization rate of the subscription cabinet from the current day to the current system time (number of packages in the cabinet / total number of online cabinet slots); Self-operated information is used to display the slot utilization rate of self-operated lockers from the current day to the current system time (number of parcels in the locker / total number of online locker slots); The number of online cabinets includes year-on-year yesterday's data information, subscription information and self-operated information; The number of online cabinets is used to display the number of online cabinets as of the current system time on that day; The year-on-year data information is used to show the number of online cabinets at the same time as yesterday, and the percentage of increase or decrease is (number of online cabinets / number of online cabinets at the same time yesterday-1)*100%; The subscription information is used to display the number of online subscription cabinets up to the current system time on the day; Self-operated information is used to display the number of online self-operated ATMs up to the current system time on that day; The number of offline cabinets includes year-on-year yesterday's data information, subscription information and self-operated information; The number of offline cabinets is used to display the number of cabinets that are offline as of the current system time. The year-on-year data information is used to show the number of offline cabinets at the same time as yesterday, and the increase or decrease percentage is (number of offline cabinets / number of offline cabinets at the same time yesterday-1)*100%; The subscription information is used to display the number of offline cabinets of subscription cabinets up to the current system time on the day; Self-operated information is used to display the number of online and offline self-operated ATMs as of the current system time on that day; The number of zero-investment cabinets includes year-on-year yesterday's data information, subscription information and self-operated information; The number of zero-drop cabinets is used to display the number of zero-drop cabinets (online) as of the current system time in the current month; The year-on-year data information is used to show the number of zero-drop machines at the same time as yesterday, and the percentage of increase or decrease is (number of zero-drop machines / number of zero-drop machines at the same time yesterday-1)*100%; The subscription information is used to display the number of zero-drop subscription cabinets in the subscription cabinets up to the current system time in the current month; Self-operated information is used to display the number of zero-drop self-operated ATM machines as of the current system time in the current month; Acquire business volume trend information of the express locker, wherein the business volume trend information includes first time range information, first indicator type information, first label selection information, first data display information and first detailed information; The first time range information is used to display the delivery volume data of the past 7 days by default (yesterday is the 7th day). It supports date range filtering, and can filter data within the range of up to 180 days. The longest time span supports 31 days; The first indicator type information is used to count the business volume of each type of ATM according to self-operated, subscribed, and leased ATMs; The first tab selection information is divided into delivery volume, picked up, and waiting for pickup. Click to switch to display the statistics of the corresponding tab; The first data display information is used for bar chart representation. When the mouse hovers over the bar, specific detailed values ​​are displayed, including date, cabinet type identification, and business volume value; The first detailed information is used to jump to the business volume detailed data page; By default, the business volume data for the past 7 days is displayed. Date range filtering is supported. Data within the past 180 days can be filtered at most. The longest time span supported is 31 days, and the most recent date can be yesterday. [Business Volume Details] Data table example, sorted in ascending order by date; Obtain yesterday's delivery rate ranking information of the express lockers, where yesterday's delivery rate ranking information includes second time range information, second label selection information, second data display information, and second detailed information; The second time range information displays the ranking of yesterday's delivery rate by default; The second tab selection information is divided into self-operated, subscription, and rental. Click to switch to display the statistics of the corresponding tab; The second data display information is used to count yesterday's delivery rate by province (taking the average of the cabinet delivery rate within the province), and sorting them in descending order by delivery rate, displaying the ranking, region name, delivery rate, and year-on-year value; The second detailed information is used to jump to the provincial delivery rate detailed data page; By default, yesterday's delivery rate data is displayed. Date selection is supported. The furthest range is 180 days ago, and the latest range is yesterday. [Provincial delivery rate] Data table example, sorted in ascending order according to the first letter of the province; Obtain offline cabinet status information, wherein the offline cabinet status information includes: third time range information, third indicator type information, third label selection information, third data display information and third detailed information.

[0019] The third time range information displays the offline cabinet new data in the past 7 days by default (yesterday is the 7th day), supports date range filtering, and can filter data within the range of up to 180 days, with a maximum time span of 31 days; (here the number of offline cabinets yesterday is defined as Not online 24 hours a day ); The third indicator type information is based on self-operated, subscribed, and leased cabinets, and the newly added / improved offline cabinet values ​​of each type of cabinet are counted; The third tab selection information is divided into new, improved, and total. Click to switch to display the statistical values ​​of the corresponding tab; The third data display information is presented through a bar graph. When the mouse hovers over the bar, the specific detailed values ​​are displayed, including the date, cabinet type identification, and statistical values; The third detailed information is used to jump to the offline cabinet detailed data page; By default, the offline cabinet data for the past 7 days is displayed. Date range filtering is supported. Data within the past 180 days can be filtered at most. The longest time span supported is 31 days. The most recent date can be yesterday. [Offline ATM Details] Data table example, sorted in ascending order by date; Performing data processing on the express cabinet data information, wherein the data processing includes a data cleaning process, a data sorting process, and a data classification process; A BP express cabinet data prediction model is established based on the BP neural network, and the hyperparameters and weights of the BP express cabinet data prediction model are optimized using the POS particle swarm algorithm; BP neural network model construction: BP neural network is suitable for dealing with complex and dynamically changing data prediction problems such as the usage of express lockers due to its powerful nonlinear fitting ability. Key parameters such as the number of network layers, the number of neurons in each layer, and the activation function need to be determined. The input layer nodes correspond to various factors that affect the usage of express lockers (such as time, location, weather conditions, holidays, etc.), and the output layer predicts the usage frequency or demand of express lockers.

[0020] POS particle swarm algorithm optimization: In order to improve the prediction accuracy and generalization ability of BP neural network, the POS algorithm is introduced to automatically find the optimal network hyperparameters (such as learning rate, momentum factor) and weight initialization. POS simulates the foraging behavior of bird flocks. Each particle represents a set of potential solutions, flying in the search space and updating its position, and finally converges to the global optimal solution or the approximate optimal solution. This process reduces the workload of manual parameter adjustment and improves the efficiency and effect of model construction.

[0021] The processed express cabinet data information is input into the optimized BP express cabinet data prediction model for prediction, and the installation quantity and usage of the express cabinets are managed according to the prediction results.

[0022] See also Figure 2 The second embodiment of the logistics express cabinet data analysis method in the embodiment of the present invention includes: Obtaining express cabinet data information of the express cabinet, the express cabinet data information including: core indicator information, business volume trend information, yesterday's delivery rate ranking information and offline cabinet status information; Specifically, they include: Obtain core indicator information of express lockers, including delivery volume information, delivery rate information, number of online lockers, number of offline lockers, and number of zero-delivery lockers; Delivery volume information includes year-on-year data from yesterday and information on packages that have been picked up; The delivery volume information is used to display the number of parcels delivered on the day up to the current system time; The year-on-year data information is used to show the delivery volume at the same time as yesterday, the increase or decrease percentage (today's delivery volume / yesterday's delivery volume at the same time - 1) * 100%; The pickup information is used to display the number of parcels that have been picked up on the day up to the current system time; Delivery rate information includes year-on-year yesterday's data information, subscription information and self-operated information; The delivery rate information is used to display the slot utilization rate (number of parcels in the cabinet / total number of online cabinet slots) from the current day to the current system time. The year-on-year data information is used to show the delivery rate compared with the same time yesterday, the increase or decrease percentage (today's delivery rate - yesterday's delivery rate at the same time) * 100%; Subscription information is used to display the slot utilization rate of the subscription cabinet from the current day to the current system time (number of packages in the cabinet / total number of online cabinet slots); Self-operated information is used to display the slot utilization rate of self-operated lockers from the current day to the current system time (number of parcels in the locker / total number of online locker slots); The number of online cabinets includes year-on-year yesterday's data information, subscription information and self-operated information; The number of online cabinets is used to display the number of online cabinets as of the current system time on that day; The year-on-year data information is used to show the number of online cabinets at the same time as yesterday, and the percentage of increase or decrease is (number of online cabinets / number of online cabinets at the same time yesterday-1)*100%; The subscription information is used to display the number of online subscription cabinets up to the current system time on the day; Self-operated information is used to display the number of online self-operated ATMs up to the current system time on that day; The number of offline cabinets includes year-on-year yesterday's data information, subscription information and self-operated information; The number of offline cabinets is used to display the number of cabinets that are offline as of the current system time. The year-on-year data information is used to show the number of offline cabinets at the same time as yesterday, and the increase or decrease percentage is (number of offline cabinets / number of offline cabinets at the same time yesterday-1)*100%; The subscription information is used to display the number of offline cabinets of subscription cabinets up to the current system time on the day; Self-operated information is used to display the number of online and offline self-operated ATMs as of the current system time on that day; The number of zero-investment cabinets includes year-on-year yesterday's data information, subscription information and self-operated information; The number of zero-drop cabinets is used to display the number of zero-drop cabinets (online) as of the current system time in the current month; The year-on-year data information is used to show the number of zero-drop machines at the same time as yesterday, and the percentage of increase or decrease is (number of zero-drop machines / number of zero-drop machines at the same time yesterday-1)*100%; The subscription information is used to display the number of zero-drop subscription cabinets in the subscription cabinets up to the current system time in the current month; Self-operated information is used to display the number of zero-drop self-operated ATM machines as of the current system time in the current month; Acquire business volume trend information of the express locker, wherein the business volume trend information includes first time range information, first indicator type information, first label selection information, first data display information and first detailed information; The first time range information is used to display the delivery volume data of the past 7 days by default (yesterday is the 7th day). It supports date range filtering, and can filter data within the range of up to 180 days. The longest time span supports 31 days; The first indicator type information is used to count the business volume of each type of ATM according to self-operated, subscribed, and leased ATMs; The first tab selection information is divided into delivery volume, picked up, and waiting for pickup. Click to switch to display the statistics of the corresponding tab; The first data display information is used for bar chart representation. When the mouse hovers over the bar, specific detailed values ​​are displayed, including date, cabinet type identification, and business volume value; The first detailed information is used to jump to the business volume detailed data page; By default, the business volume data for the past 7 days is displayed. Date range filtering is supported. Data within the past 180 days can be filtered at most. The longest time span supported is 31 days, and the most recent date can be yesterday. [Business Volume Details] Data table example, sorted in ascending order by date; Obtain yesterday's delivery rate ranking information of the express lockers, where yesterday's delivery rate ranking information includes second time range information, second label selection information, second data display information, and second detailed information; The second time range information displays the ranking of yesterday's delivery rate by default; The second tab selection information is divided into self-operated, subscription, and rental. Click to switch to display the statistics of the corresponding tab; The second data display information is used to count yesterday's delivery rate by province (taking the average of the cabinet delivery rate within the province), and sorting them in descending order by delivery rate, displaying the ranking, region name, delivery rate, and year-on-year value; The second detailed information is used to jump to the provincial delivery rate detailed data page; By default, yesterday's delivery rate data is displayed. Date selection is supported. The furthest range is 180 days ago, and the latest range is yesterday. [Provincial delivery rate] Data table example, sorted in ascending order according to the first letter of the province; Obtain offline cabinet status information, wherein the offline cabinet status information includes: third time range information, third indicator type information, third label selection information, third data display information and third detailed information.

[0023] The third time range information displays the offline cabinet new data in the past 7 days by default (yesterday is the 7th day), supports date range filtering, and can filter data within the range of up to 180 days, with a maximum time span of 31 days; (here the number of offline cabinets yesterday is defined as Not online 24 hours a day ); The third indicator type information is based on self-operated, subscribed, and leased cabinets, and the newly added / improved offline cabinet values ​​of each type of cabinet are counted; The third tab selection information is divided into new, improved, and total. Click to switch to display the statistical values ​​of the corresponding tab; The third data display information is presented through a bar graph. When the mouse hovers over the bar, the specific detailed values ​​are displayed, including the date, cabinet type identification, and statistical values; The third detailed information is used to jump to the offline cabinet detailed data page; By default, the offline cabinet data for the past 7 days is displayed. Date range filtering is supported. Data within the past 180 days can be filtered at most. The longest time span supported is 31 days. The most recent date can be yesterday. [Offline ATM Details] Data table example, sorted in ascending order by date; Performing data processing on the express cabinet data information, wherein the data processing includes a data cleaning process, a data sorting process, and a data classification process; The data cleaning process includes: Identify erroneous data information, duplicate data information, incomplete data information and inconsistent data information in express locker data; For erroneous data information, duplicate data information, incomplete data information and inconsistent data information in the express cabinet data, invalid records are removed, erroneous values ​​are corrected, missing values ​​are filled and abnormal values ​​are processed; time series data in the express cabinet data are time-aligned and abnormal fluctuations in the time series are processed.

[0024] The entire data cleaning process first needs to identify and process the erroneous, incomplete, duplicate or inconsistent information in the data. This includes removing invalid records (such as blank or incorrectly formatted data), correcting erroneous values, filling missing values ​​(which can be filled by the mean, median or mode, or using more complex data interpolation methods), and processing outliers to ensure the purity of the data. For time series data, time alignment and processing of abnormal fluctuations in the time series are also required.

[0025] A BP express cabinet data prediction model is established based on the BP neural network, and the hyperparameters and weights of the BP express cabinet data prediction model are optimized using the POS particle swarm algorithm; BP neural network model construction: BP neural network is suitable for dealing with complex and dynamically changing data prediction problems such as the usage of express lockers due to its powerful nonlinear fitting ability. Key parameters such as the number of network layers, the number of neurons in each layer, and the activation function need to be determined. The input layer nodes correspond to various factors that affect the usage of express lockers (such as time, location, weather conditions, holidays, etc.), and the output layer predicts the usage frequency or demand of express lockers.

[0026] POS particle swarm algorithm optimization: In order to improve the prediction accuracy and generalization ability of BP neural network, the POS algorithm is introduced to automatically find the optimal network hyperparameters (such as learning rate, momentum factor) and weight initialization. POS simulates the foraging behavior of bird flocks. Each particle represents a set of potential solutions, flying in the search space and updating its position, and finally converges to the global optimal solution or the approximate optimal solution. This process reduces the workload of manual parameter adjustment and improves the efficiency and effect of model construction.

[0027] The processed express cabinet data information is input into the optimized BP express cabinet data prediction model for prediction, and the installation quantity and usage of the express cabinets are managed according to the prediction results.

[0028] See also Figure 3 The third embodiment of the logistics express cabinet data analysis method in the embodiment of the present invention includes: Obtaining express cabinet data information of the express cabinet, the express cabinet data information including: core indicator information, business volume trend information, yesterday's delivery rate ranking information and offline cabinet status information; Specifically, they include: Obtain core indicator information of express lockers, including delivery volume information, delivery rate information, number of online lockers, number of offline lockers, and number of zero-delivery lockers; Delivery volume information includes year-on-year data from yesterday and information on packages that have been picked up; The delivery volume information is used to display the number of parcels delivered on the day up to the current system time; The year-on-year data information is used to show the delivery volume at the same time as yesterday, the increase or decrease percentage (today's delivery volume / yesterday's delivery volume at the same time - 1) * 100%; The pickup information is used to display the number of parcels that have been picked up on the day up to the current system time; Delivery rate information includes year-on-year yesterday's data information, subscription information and self-operated information; The delivery rate information is used to display the slot utilization rate (number of parcels in the cabinet / total number of online cabinet slots) from the current day to the current system time. The year-on-year data information is used to show the delivery rate compared with the same time yesterday, the increase or decrease percentage (today's delivery rate - yesterday's delivery rate at the same time) * 100%; Subscription information is used to display the slot utilization rate of the subscription cabinet from the current day to the current system time (number of packages in the cabinet / total number of online cabinet slots); Self-operated information is used to display the slot utilization rate of self-operated lockers from the current day to the current system time (number of parcels in the locker / total number of online locker slots); The number of online cabinets includes year-on-year yesterday's data information, subscription information and self-operated information; The number of online cabinets is used to display the number of online cabinets as of the current system time on that day; The year-on-year data information is used to show the number of online cabinets at the same time as yesterday, and the percentage of increase or decrease is (number of online cabinets / number of online cabinets at the same time yesterday-1)*100%; The subscription information is used to display the number of online subscription cabinets up to the current system time on the day; Self-operated information is used to display the number of online self-operated ATMs up to the current system time on that day; The number of offline cabinets includes year-on-year yesterday's data information, subscription information and self-operated information; The number of offline cabinets is used to display the number of cabinets that are offline as of the current system time. The year-on-year data information is used to show the number of offline cabinets at the same time as yesterday, and the increase or decrease percentage is (number of offline cabinets / number of offline cabinets at the same time yesterday-1)*100%; The subscription information is used to display the number of offline cabinets of subscription cabinets up to the current system time on the day; Self-operated information is used to display the number of online and offline self-operated ATMs as of the current system time on that day; The number of zero-investment cabinets includes year-on-year yesterday's data information, subscription information and self-operated information; The number of zero-drop cabinets is used to display the number of zero-drop cabinets (online) as of the current system time in the current month; The year-on-year data information is used to show the number of zero-drop machines at the same time as yesterday, and the percentage of increase or decrease is (number of zero-drop machines / number of zero-drop machines at the same time yesterday-1)*100%; The subscription information is used to display the number of zero-drop subscription cabinets in the subscription cabinets up to the current system time in the current month; Self-operated information is used to display the number of zero-drop self-operated ATM machines as of the current system time in the current month; Acquire business volume trend information of the express locker, wherein the business volume trend information includes first time range information, first indicator type information, first label selection information, first data display information and first detailed information; The first time range information is used to display the delivery volume data of the past 7 days by default (yesterday is the 7th day). It supports date range filtering, and can filter data within the range of up to 180 days. The longest time span supports 31 days; The first indicator type information is used to count the business volume of each type of ATM according to self-operated, subscribed, and leased ATMs; The first tab selection information is divided into delivery volume, picked up, and waiting for pickup. Click to switch to display the statistics of the corresponding tab; The first data display information is used for bar chart representation. When the mouse hovers over the bar, specific detailed values ​​are displayed, including date, cabinet type identification, and business volume value; The first detailed information is used to jump to the business volume detailed data page; By default, the business volume data for the past 7 days is displayed. Date range filtering is supported. Data within the past 180 days can be filtered at most. The longest time span supported is 31 days, and the most recent date can be yesterday. [Business Volume Details] Data table example, sorted in ascending order by date; Obtain yesterday's delivery rate ranking information of the express lockers, where yesterday's delivery rate ranking information includes second time range information, second label selection information, second data display information, and second detailed information; The second time range information displays the ranking of yesterday's delivery rate by default; The second tab selection information is divided into self-operated, subscription, and rental. Click to switch to display the statistics of the corresponding tab; The second data display information is used to count yesterday's delivery rate by province (taking the average of the cabinet delivery rate within the province), and sorting them in descending order by delivery rate, displaying the ranking, region name, delivery rate, and year-on-year value; The second detailed information is used to jump to the provincial delivery rate detailed data page; By default, yesterday's delivery rate data is displayed. Date selection is supported. The furthest range is 180 days ago, and the latest range is yesterday. [Provincial delivery rate] Data table example, sorted in ascending order according to the first letter of the province; Obtain offline cabinet status information, wherein the offline cabinet status information includes: third time range information, third indicator type information, third label selection information, third data display information and third detailed information.

[0029] The third time range information displays the offline cabinet new data in the past 7 days by default (yesterday is the 7th day), supports date range filtering, and can filter data within the range of up to 180 days, with a maximum time span of 31 days; (here the number of offline cabinets yesterday is defined as Not online 24 hours a day ); The third indicator type information is based on self-operated, subscribed, and leased cabinets, and the newly added / improved offline cabinet values ​​of each type of cabinet are counted; The third tab selection information is divided into new, improved, and total. Click to switch to display the statistical values ​​of the corresponding tab; The third data display information is presented through a bar graph. When the mouse hovers over the bar, the specific detailed values ​​are displayed, including the date, cabinet type identification, and statistical values; The third detailed information is used to jump to the offline cabinet detailed data page; By default, the offline cabinet data for the past 7 days is displayed. Date range filtering is supported. Data within the past 180 days can be filtered at most. The longest time span supported is 31 days. The most recent date can be yesterday. [Offline ATM Details] Data table example, sorted in ascending order by date; Performing data processing on the express cabinet data information, wherein the data processing includes a data cleaning process, a data sorting process, and a data classification process; The data cleaning process includes: Identify erroneous data information, duplicate data information, incomplete data information and inconsistent data information in express locker data; For erroneous data information, duplicate data information, incomplete data information and inconsistent data information in the express cabinet data, invalid records are removed, erroneous values ​​are corrected, missing values ​​are filled and abnormal values ​​are processed; time series data in the express cabinet data are time-aligned and abnormal fluctuations in the time series are processed.

[0030] The entire data processing process first needs to identify and process erroneous, incomplete, duplicate or inconsistent information in the data. This includes removing invalid records (such as blank or incorrectly formatted data), correcting erroneous values, filling missing values ​​(which can be filled by the mean, median or mode, or using more complex data interpolation methods), and processing outliers to ensure the purity of the data. For time series data, time alignment and processing of abnormal fluctuations in the time series are also required.

[0031] The data sorting process includes: organizing the cleaned data according to a preset structure; summarizing the cleaned data; The entire data sorting process organizes the cleaned data according to a predefined structure, which may include creating new variables, converting variable types (such as encoding categorical variables into numbers), normalizing or standardizing numerical data, etc., to facilitate subsequent analysis. In addition, appropriate summarization or aggregation of data, such as classification and statistics by time period, region or express company, can enhance the readability of data and analysis efficiency.

[0032] A BP express cabinet data prediction model is established based on the BP neural network, and the hyperparameters and weights of the BP express cabinet data prediction model are optimized using the POS particle swarm algorithm; BP neural network model construction: BP neural network is suitable for dealing with complex and dynamically changing data prediction problems such as the usage of express lockers due to its powerful nonlinear fitting ability. Key parameters such as the number of network layers, the number of neurons in each layer, and the activation function need to be determined. The input layer nodes correspond to various factors that affect the usage of express lockers (such as time, location, weather conditions, holidays, etc.), and the output layer predicts the usage frequency or demand of express lockers.

[0033] POS particle swarm algorithm optimization: In order to improve the prediction accuracy and generalization ability of BP neural network, the POS algorithm is introduced to automatically find the optimal network hyperparameters (such as learning rate, momentum factor) and weight initialization. POS simulates the foraging behavior of bird flocks. Each particle represents a set of potential solutions, flying in the search space and updating its position, and finally converges to the global optimal solution or the approximate optimal solution. This process reduces the workload of manual parameter adjustment and improves the efficiency and effect of model construction.

[0034] The processed express cabinet data information is input into the optimized BP express cabinet data prediction model for prediction, and the installation quantity and usage of the express cabinets are managed according to the prediction results.

[0035] See also Figure 4 The fourth embodiment of the logistics express cabinet data analysis method in the embodiment of the present invention includes: Obtaining express cabinet data information of the express cabinet, the express cabinet data information including: core indicator information, business volume trend information, yesterday's delivery rate ranking information and offline cabinet status information; Specifically, they include: Obtain core indicator information of express lockers, including delivery volume information, delivery rate information, number of online lockers, number of offline lockers, and number of zero-delivery lockers; Delivery volume information includes year-on-year data from yesterday and information on packages that have been picked up; The delivery volume information is used to display the number of parcels delivered on the day up to the current system time; The year-on-year data information is used to show the delivery volume at the same time as yesterday, the increase or decrease percentage (today's delivery volume / yesterday's delivery volume at the same time - 1) * 100%; The pickup information is used to display the number of parcels that have been picked up on the day up to the current system time; Delivery rate information includes year-on-year yesterday's data information, subscription information and self-operated information; The delivery rate information is used to display the slot utilization rate (number of parcels in the cabinet / total number of online cabinet slots) from the current day to the current system time. The year-on-year data information is used to show the delivery rate compared with the same time yesterday, the increase or decrease percentage (today's delivery rate - yesterday's delivery rate at the same time) * 100%; Subscription information is used to display the slot utilization rate of the subscription cabinet from the current day to the current system time (number of packages in the cabinet / total number of online cabinet slots); Self-operated information is used to display the slot utilization rate of self-operated lockers from the current day to the current system time (number of parcels in the locker / total number of online locker slots); The number of online cabinets includes year-on-year yesterday's data information, subscription information and self-operated information; The number of online cabinets is used to display the number of online cabinets as of the current system time on that day; The year-on-year data information is used to show the number of online cabinets at the same time as yesterday, and the percentage of increase or decrease is (number of online cabinets / number of online cabinets at the same time yesterday-1)*100%; The subscription information is used to display the number of online subscription cabinets up to the current system time on the day; Self-operated information is used to display the number of online self-operated ATMs up to the current system time on that day; The number of offline cabinets includes year-on-year yesterday's data information, subscription information and self-operated information; The number of offline cabinets is used to display the number of cabinets that are offline as of the current system time. The year-on-year data information is used to show the number of offline cabinets at the same time as yesterday, and the increase or decrease percentage is (number of offline cabinets / number of offline cabinets at the same time yesterday-1)*100%; The subscription information is used to display the number of offline cabinets of subscription cabinets up to the current system time on the day; Self-operated information is used to display the number of online and offline self-operated ATMs as of the current system time on that day; The number of zero-investment cabinets includes year-on-year yesterday's data information, subscription information and self-operated information; The number of zero-drop cabinets is used to display the number of zero-drop cabinets (online) as of the current system time in the current month; The year-on-year data information is used to show the number of zero-drop machines at the same time as yesterday, and the percentage of increase or decrease is (number of zero-drop machines / number of zero-drop machines at the same time yesterday-1)*100%; The subscription information is used to display the number of zero-drop subscription cabinets in the subscription cabinets up to the current system time in the current month; Self-operated information is used to display the number of zero-drop self-operated ATM machines as of the current system time in the current month; Acquire business volume trend information of the express locker, wherein the business volume trend information includes first time range information, first indicator type information, first label selection information, first data display information and first detailed information; The first time range information is used to display the delivery volume data of the past 7 days by default (yesterday is the 7th day). It supports date range filtering, and can filter data within the range of up to 180 days. The longest time span supports 31 days; The first indicator type information is used to count the business volume of each type of ATM according to self-operated, subscribed, and leased ATMs; The first tab selection information is divided into delivery volume, picked up, and waiting for pickup. Click to switch to display the statistics of the corresponding tab; The first data display information is used for bar chart representation. When the mouse hovers over the bar, specific detailed values ​​are displayed, including date, cabinet type identification, and business volume value; The first detailed information is used to jump to the business volume detailed data page; By default, the business volume data for the past 7 days is displayed. Date range filtering is supported. Data within the past 180 days can be filtered at most. The longest time span supported is 31 days, and the most recent date can be yesterday. [Business Volume Details] Data table example, sorted in ascending order by date; Obtain yesterday's delivery rate ranking information of the express lockers, where yesterday's delivery rate ranking information includes second time range information, second label selection information, second data display information, and second detailed information; The second time range information displays the ranking of yesterday's delivery rate by default; The second tab selection information is divided into self-operated, subscription, and rental. Click to switch to display the statistics of the corresponding tab; The second data display information is used to count yesterday's delivery rate by province (taking the average of the cabinet delivery rate within the province), and sorting them in descending order by delivery rate, displaying the ranking, region name, delivery rate, and year-on-year value; The second detailed information is used to jump to the provincial delivery rate detailed data page; By default, yesterday's delivery rate data is displayed. Date selection is supported. The furthest range is 180 days ago, and the latest range is yesterday. [Provincial delivery rate] Data table example, sorted in ascending order according to the first letter of the province; Obtain offline cabinet status information, wherein the offline cabinet status information includes: third time range information, third indicator type information, third label selection information, third data display information and third detailed information.

[0036] The third time range information displays the offline cabinet new data in the past 7 days by default (yesterday is the 7th day), supports date range filtering, and can filter data within the range of up to 180 days, with a maximum time span of 31 days; (here the number of offline cabinets yesterday is defined as Not online 24 hours a day ); The third indicator type information is based on self-operated, subscribed, and leased cabinets, and the newly added / improved offline cabinet values ​​of each type of cabinet are counted; The third tab selection information is divided into new, improved, and total. Click to switch to display the statistical values ​​of the corresponding tab; The third data display information is presented through a bar graph. When the mouse hovers over the bar, the specific detailed values ​​are displayed, including the date, cabinet type identification, and statistical values; The third detailed information is used to jump to the offline cabinet detailed data page; By default, the offline cabinet data for the past 7 days is displayed. Date range filtering is supported. Data within the past 180 days can be filtered at most. The longest time span supported is 31 days. The most recent date can be yesterday. [Offline ATM Details] Data table example, sorted in ascending order by date; Performing data processing on the express cabinet data information, wherein the data processing includes a data cleaning process, a data sorting process, and a data classification process; The data cleaning process includes: Identify erroneous data information, duplicate data information, incomplete data information and inconsistent data information in express locker data; For erroneous data information, duplicate data information, incomplete data information and inconsistent data information in the express cabinet data, invalid records are removed, erroneous values ​​are corrected, missing values ​​are filled and abnormal values ​​are processed; time series data in the express cabinet data are time-aligned and abnormal fluctuations in the time series are processed.

[0037] The entire data processing process first needs to identify and process erroneous, incomplete, duplicate or inconsistent information in the data. This includes removing invalid records (such as blank or incorrectly formatted data), correcting erroneous values, filling missing values ​​(which can be filled by the mean, median or mode, or using more complex data interpolation methods), and processing outliers to ensure the purity of the data. For time series data, time alignment and processing of abnormal fluctuations in the time series are also required.

[0038] The data sorting process includes: organizing the cleaned data according to a preset structure; summarizing the cleaned data; The entire data sorting process organizes the cleaned data according to a predefined structure, which may include creating new variables, converting variable types (such as encoding categorical variables into numbers), normalizing or standardizing numerical data, etc., to facilitate subsequent analysis. In addition, appropriate summarization or aggregation of data, such as classification and statistics by time period, region or express company, can enhance the readability of data and analysis efficiency.

[0039] The data classification process includes: obtaining analysis purpose information, and dividing the express cabinet data that has undergone the data sorting process into a training set, a validation set, and a test set according to the analysis purpose information; The entire data classification process divides the data into training sets, validation sets, and test sets according to the purpose of analysis to ensure the scientific nature of model training, tuning, and evaluation. At the same time, the data is logically classified according to the usage characteristics of express lockers (such as usage frequency, user preferences, geographic location characteristics, etc.) to facilitate the construction of more targeted prediction models.

[0040] A BP express cabinet data prediction model is established based on the BP neural network, and the hyperparameters and weights of the BP express cabinet data prediction model are optimized using the POS particle swarm algorithm; BP neural network model construction: BP neural network is suitable for dealing with complex and dynamically changing data prediction problems such as the usage of express lockers due to its powerful nonlinear fitting ability. Key parameters such as the number of network layers, the number of neurons in each layer, and the activation function need to be determined. The input layer nodes correspond to various factors that affect the usage of express lockers (such as time, location, weather conditions, holidays, etc.), and the output layer predicts the usage frequency or demand of express lockers.

[0041] POS particle swarm algorithm optimization: In order to improve the prediction accuracy and generalization ability of BP neural network, the POS algorithm is introduced to automatically find the optimal network hyperparameters (such as learning rate, momentum factor) and weight initialization. POS simulates the foraging behavior of bird flocks. Each particle represents a set of potential solutions, flying in the search space and updating its position, and finally converges to the global optimal solution or the approximate optimal solution. This process reduces the workload of manual parameter adjustment and improves the efficiency and effect of model construction.

[0042] Input the processed express cabinet data information into the optimized BP express cabinet data prediction model for prediction, and manage the installation quantity and usage of express cabinets according to the prediction results; Specifically, it includes inputting the processed express cabinet data information into the optimized BP express cabinet data prediction model for prediction, and generating prediction result information, wherein the prediction result information includes the frequency of use of the express cabinet, peak time information and regional demand information; The estimated number of express lockers and the estimated installation locations of express lockers are generated based on the frequency of use of express lockers, peak hours and regional demand information.

[0043] The above describes the logistics express cabinet data analysis method in the embodiment of the present invention. The following describes the logistics express cabinet data analysis device in the embodiment of the present invention. Figure 5 , the logistics express cabinet data analysis device in the embodiment of the present invention includes: The data acquisition module 501 is used to acquire the express cabinet data information of the express cabinet, and the express cabinet data information includes: core indicator information, business volume trend information, yesterday's delivery rate ranking information and offline cabinet status information; The data processing module 502 is used to process the data information of the express cabinet, and the data processing includes a data cleaning process, a data sorting process and a data classification process; A model building module 503 is used to build a BP express cabinet data prediction model based on a BP neural network, and optimize the hyperparameters and weights of the BP express cabinet data prediction model using a POS particle swarm algorithm; The prediction management module 504 is used to input the processed express cabinet data information into the optimized BP express cabinet data prediction model for prediction, and manage the installation quantity and usage of the express cabinets according to the prediction results.

[0044] above Figure 5 The logistics express cabinet data analysis device in the embodiment of the present invention is described in detail from the perspective of modular functional entities, and the electronic device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0045] Figure 67 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device 700 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 710 (for example, one or more processors) and a memory 720, and one or more storage media 730 (for example, one or more mass storage devices) storing application programs 733 or data 732. Among them, the memory 720 and the storage medium 730 can be temporary storage or permanent storage. The program stored in the storage medium 730 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the electronic device 700. Furthermore, the processor 710 may be configured to communicate with the storage medium 730 to execute a series of instruction operations in the storage medium 730 on the electronic device 700.

[0046] The electronic device 700 may also include one or more power supplies 740, one or more wired or wireless network interfaces 750, one or more input and output interfaces 750, and / or one or more operating systems 731, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 6 The structure of the electronic device shown does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.

[0047] 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 executed on a computer, the computer executes the steps of the logistics express cabinet data analysis method.

[0048] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device, or unit can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0049] 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 this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole 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, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0050] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A logistics express cabinet data analysis method, characterized in that: The logistics express cabinet data analysis method comprises: Obtaining express cabinet data information of the express cabinet, the express cabinet data information including: core indicator information, business volume trend information, yesterday's delivery rate ranking information and offline cabinet status information; Performing data processing on the express cabinet data information, wherein the data processing includes a data cleaning process, a data sorting process, and a data classification process; A BP express cabinet data prediction model is established based on the BP neural network, and the hyperparameters and weights of the BP express cabinet data prediction model are optimized using the POS particle swarm algorithm; The processed express cabinet data information is input into the optimized BP express cabinet data prediction model for prediction, and the installation quantity and usage of the express cabinets are managed according to the prediction results.

2. The logistics express cabinet data analysis method according to claim 1 is characterized in that: The express cabinet data information of the express cabinet is obtained, and the express cabinet data information includes: core indicator information, business volume trend information, yesterday's delivery rate ranking information and offline cabinet status information including: Obtain core indicator information of express lockers, including delivery volume information, delivery rate information, number of online lockers, number of offline lockers, and number of zero-delivery lockers; Acquire business volume trend information of the express locker, wherein the business volume trend information includes first time range information, first indicator type information, first label selection information, first data display information and first detailed information; Obtain yesterday's delivery rate ranking information of the express lockers, where yesterday's delivery rate ranking information includes second time range information, second label selection information, second data display information, and second detailed information; Obtain offline cabinet status information, wherein the offline cabinet status information includes: third time range information, third indicator type information, third label selection information, third data display information and third detailed information.

3. The logistics express cabinet data analysis method according to claim 1 is characterized in that: The data cleaning process includes: Identify erroneous data information, duplicate data information, incomplete data information and inconsistent data information in express locker data; For erroneous data information, duplicate data information, incomplete data information and inconsistent data information in the express cabinet data, invalid records are removed, erroneous values ​​are corrected, missing values ​​are filled and abnormal values ​​are processed; time series data in the express cabinet data are time-aligned and abnormal fluctuations in the time series are processed.

4. The logistics express cabinet data analysis method according to claim 3 is characterized in that: The data sorting process includes: Organize the cleaned data according to the preset structure; Summarize the data after data cleaning.

5. The logistics express cabinet data analysis method according to claim 4 is characterized in that: The data classification process includes: Obtain analysis purpose information, and divide the express cabinet data that has gone through the data sorting process into training set, validation set, and test set according to the analysis purpose information.

6. The logistics express cabinet data analysis method according to claim 1 is characterized in that: The processing of the express cabinet data information is input into the optimized BP express cabinet data prediction model for prediction, and the installation quantity and usage of the express cabinets are managed according to the prediction results, including: Input the processed express cabinet data information into the optimized BP express cabinet data prediction model for prediction, and generate prediction result information, which includes the frequency of use of express cabinets, peak time information and regional demand information; The estimated number of express lockers and the estimated installation locations of express lockers are generated based on the frequency of use of express lockers, peak hours and regional demand information.

7. A logistics express cabinet data analysis device, characterized in that: include: A data acquisition module is used to acquire the express cabinet data information of the express cabinet, wherein the express cabinet data information includes: core indicator information, business volume trend information, yesterday's delivery rate ranking information and offline cabinet status information; A data processing module is used to process the data information of the express cabinet, and the data processing includes a data cleaning process, a data sorting process and a data classification process; The model building module is used to build a BP express cabinet data prediction model based on the BP neural network, and use the POS particle swarm algorithm to optimize the hyperparameters and weights of the BP express cabinet data prediction model; The prediction management module is used to input the processed express cabinet data information into the optimized BP express cabinet data prediction model for prediction, and manage the installation quantity and usage of the express cabinets according to the prediction results.

8. An electronic device, comprising a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instructions in the memory so that the electronic device executes each step of the logistics express cabinet data analysis method as described in any one of claims 1-6.

9. 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 logistics express cabinet data analysis method as described in any one of claims 1-6 are implemented.

Images