Efficient logistics booking management method and system based on big data

Abstract

The invention relates to the technical field of logistics management, in particular to an efficient logistics cabin booking management method and system based on big data. An efficient logistics cabin booking management method based on big data comprises the following steps: S1, obtaining client cabin-out data of logistics, and obtaining client portrait data according to the client cabin-out data; s2, obtaining a logistics adjustment priority level and a protection adjustment priority level according to the customer check-out type and the customer portrait data, and carrying out preliminary compensation adjustment on the customer according to the logistics adjustment priority level and the protection adjustment priority level; and S3, obtaining a space compensation value according to the logistics adjustment priority, the protection adjustment priority and the target customer booking space data. According to the method, active cabin retreating and passive cabin retreating of the clients are distinguished, and the multi-dimensional client portraits are generated, so that differential priority calculation and compensation strategies can be realized, and efficient optimization management when the clients resume cabins is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics management, and particularly to an efficient logistics booking management method and system based on big data. Background Art

[0002] With the continuous expansion of the global trade scale and the rapid growth of e-commerce business, the booking demand for sea transportation has risen sharply. However, traditional booking management systems are mostly based on manual or simple rule scheduling and cannot make full use of massive historical data. There are the following main deficiencies: insufficient analysis of booking cancellation behavior. Existing systems often treat customers' active booking cancellations and passive booking cancellations equally, lacking refined differentiation of booking cancellation types and frequencies, making it difficult to implement differential compensation and priority management for different customer groups, resulting in unfair resource allocation and decreased customer satisfaction; most platforms only use simple timeliness or cargo value indicators to measure the priority of cabin allocation, ignoring the deep influencing factors such as the time difference of customers' historical booking cancellations and the number of booking cancellation segments, and it is difficult to objectively reflect the true degree of influence on customers due to their own adjustments or insufficient transport capacity. Summary of the Invention

[0003] In order to overcome the shortcoming that existing systems often treat customers' active booking cancellations and passive booking cancellations equally, the present invention provides an efficient logistics booking management method and system based on big data.

[0004] The technical implementation solution of the present invention is: an efficient logistics booking management method based on big data, including the following steps: S1: Obtain the customer booking cancellation data of the logistics, and obtain customer portrait data according to the customer booking cancellation data; S2: Obtain the logistics adjustment priority and the protection adjustment priority according to the customer booking cancellation types and the customer portrait data, and perform preliminary compensation adjustments on customers according to the logistics adjustment priority and the protection adjustment priority; S3: Obtain a space compensation value according to the logistics adjustment priority, the protection adjustment priority, and the target customer's booking space data; S4: Perform final compensation adjustments on the target customer according to the space compensation value.

[0005] Preferably, obtaining the customer's cabin return data of the logistics and obtaining the customer portrait data according to the customer's cabin return data includes: obtaining the customer's cabin return data of the logistics, where the customer's cabin return data includes the number of customer cabin returns and the types of customer cabin returns. The types of customer cabin returns include active cabin returns and passive cabin returns. The active cabin return is the behavior of the customer actively returning the cabin; the passive cabin return is the behavior of the customer being forced to return the cabin due to overbooking; obtaining the customer portrait data according to the types of customer cabin returns and the number of customer cabin returns. The customer portrait data includes the logistics departure time, the customer's logistics arrangement time, the importance of the customer's goods, the number of passive cabin returns of the customer within a preset time period, and the time of passive cabin returns.

[0006] Preferably, before obtaining the customer portrait data according to the types of customer cabin returns and the number of customer cabin returns, it includes: performing data preprocessing on the customer portrait data, such as removing outliers, filling in missing values, and removing duplicate values.

[0007] Preferably, obtaining the logistics adjustment priority and the protection adjustment priority according to the types of customer cabin returns and the customer portrait data, and performing preliminary compensation adjustment on the customer according to the logistics adjustment priority and the protection adjustment priority includes: If the type of customer cabin return is an active cabin return, obtain the logistics adjustment priority according to the customer portrait data using the logistics adjustment formula, and adjust the customer's logistics arrangement time according to the logistics adjustment priority; If the type of customer cabin return is a passive cabin return, obtain the protection adjustment priority according to the customer portrait data using the protection adjustment formula, and then adjust the order of customers with overbooked cabin returns according to the protection adjustment priority.

[0008] Preferably, if the type of customer cabin return is an active cabin return, obtaining the logistics adjustment priority according to the customer portrait data using the logistics adjustment formula includes: The logistics adjustment formula is: ; In the formula, is the logistics adjustment priority; is the nth logistics departure time; is the ith customer's logistics arrangement time; im is the importance of the customer's goods; is the adjustment coefficient; is the weight adjustment factor.

[0009] Preferably, if the type of customer cabin return is a passive cabin return, obtaining the protection adjustment priority according to the customer portrait data using the protection adjustment formula includes: The protection adjustment formula is: ; Wherein, P is the protection adjustment priority; N is the number of times the customer has a passive flight cancellation within a preset time period; m is the number of segments of the customer's passive flight cancellation within a preset time period; is the length of the j-th segment of operation; , is an adjustment parameter; , are the weight adjustment parameters of the protection adjustment formula; im is the importance degree of the customer's goods.

[0010] Preferably, the m is the number of segments of the customer's passive flight cancellation within a preset time period, including: mapping the customer's passive flight cancellation situation within the preset time period into a binary sequence, taking the situation of passive flight cancellation as the first data; otherwise as the second data, and taking all adjacent first data in the binary sequence as a continuous running segment, finally obtaining the number of segments of the customer's passive flight cancellation within the preset time period, and obtaining the length of each segment of operation according to the number of segments of the customer's passive flight cancellation within the preset time period.

[0011] Preferably, the obtaining the space compensation value according to the logistics adjustment priority, the protection adjustment priority and the target customer's booking space data includes: using a space compensation formula to obtain the space compensation value according to the logistics adjustment priority, the protection adjustment priority and the target customer's booking space data, wherein the target customer's booking space data is the size of the warehouse space reserved by the target customer, and the space compensation formula is: ; Wherein, F is the space compensation value; S is the size of the warehouse space reserved by the target customer; is the logistics adjustment priority of the target customer; P is the protection adjustment priority of the target customer; , are the weight adjustment coefficients of the space compensation formula.

[0012] Preferably, the final compensation adjustment of the target customer according to the space compensation value includes: setting a virtual cabin roaming facility for the cabin space, obtaining the adjustable compensation space of the target customer according to the space compensation value, displaying the layout of the space inside the cabin and the effect of cargo placement to the target customer according to the adjustable compensation space, and accepting the layout adjustment and placement adjustment of the adjustable compensation space by the target customer.

[0013] Preferably, an efficient logistics booking management system based on big data includes: A data acquisition module, configured to acquire the customer flight cancellation data of the logistics, and acquire the customer portrait data according to the customer flight cancellation data; A preliminary adjustment module, configured to obtain the logistics adjustment priority and the protection adjustment priority according to the customer flight cancellation type and the customer portrait data, and perform a preliminary compensation adjustment on the customer according to the logistics adjustment priority and the protection adjustment priority; The first adjustment acquisition module is configured to obtain the logistics adjustment priority according to the customer portrait data using the logistics adjustment formula; The second adjustment acquisition module is configured to obtain the protection adjustment priority according to the customer portrait data using the protection adjustment formula; The segmented acquisition module is configured to obtain the number of segments of the customer's passive cabin cancellation within a preset time period; The compensation value acquisition module is configured to obtain the space compensation value according to the logistics adjustment priority, the protection adjustment priority, and the target customer's booking space data; The final adjustment module is configured to perform the final compensation adjustment on the target customer according to the space compensation value.

[0014] The beneficial effects are as follows:

[0015] 1. By distinguishing between the customer's active and passive cabin cancellations, and counting the customer's cabin cancellation times and types of cabin cancellations to generate a multi-dimensional customer portrait, the present invention can implement differential priority calculation and compensation strategies, and improve the accuracy of classification management; 2. By using the logistics adjustment formula and the protection adjustment formula, the present invention scientifically quantifies the comprehensive impact of the customer portrait data on the customer experience, and ensures that the priority evaluation is more objective and reasonable; 3. By introducing the virtual cabin roaming facility and using the space compensation formula to obtain the space compensation value, and improving the interpretability and user participation of the compensation plan according to the space compensation value, the present invention further enhances the customer satisfaction. Description of the Drawings

[0016] Figure 1 It is a flowchart of an efficient logistics booking management method based on big data according to the present invention; Figure 2 It is a schematic structural diagram of an efficient logistics booking management system based on big data according to the present invention. Detailed Embodiments

[0017] The following further describes the above solution with specific embodiments. It should be understood that these embodiments are for illustrating the present application and not for limiting the scope of the present application. The implementation conditions adopted in the embodiments can be further adjusted according to the conditions of specific manufacturers, and the implementation conditions not specified are usually the conditions in conventional experiments.

[0018] Embodiment 1: An efficient logistics booking management method based on big data, as Figure 1 shown, includes the following steps: S1: Obtain the customer cabin cancellation data of the logistics, and obtain the customer portrait data according to the customer cabin cancellation data; The logistics customer check-in data is obtained, and the customer check-in data includes the number of customer check-ins and the types of customer check-ins, wherein the types of customer check-ins include active check-ins and passive check-ins, and the active check-in refers to the behavior of customers actively checking in; the passive check-in refers to the behavior of customers passively checking in due to overbooking; the customer portrait data is obtained according to the customer check-in types and the number of customer check-ins, and the customer portrait data includes the logistics departure time, the customer's logistics arrangement time, the customer's cargo importance, the number of passive check-ins by the customer within a preset time period, and the time of passive check-ins.

[0019] It should be explained that the customer de-shipping data of the target customers is obtained through real-time synchronization with the interface of the freight forwarder or shipping company reservation system. The customer de-shipping data includes the number of customer de-shipping: the total number of de-shipping operations submitted by customers within the predetermined time window (for example, within the past three months); the types of customer de-shipping include active de-shipping and passive de-shipping; active de-shipping: refers to the behavior of customers actively initiating de-shipping applications due to their own business adjustments or cancellation needs; passive de-shipping: refers to the behavior of the operator or the scheduling system forcibly canceling the original space due to overbooking of routes, insufficient space or automatic downgrade; logistics departure time: that is, the time point of each actual loading or shipment; customer logistics arrangement time: the requirements for the arrival time and loading time of the goods arranged by the customer; the importance of the customer's goods: the goods priority field filled in by the customer when placing an order or scored according to the historical default cost and complaint rate indicators; the number of passive de-shipping within a preset time period: the total number of passive de-shipping that occurred to the customer, for example, in the past three months or the past 5 orders; the time of passive de-shipping: specifically refers to the time point of each passive de-shipping, which is used for subsequent continuous segment analysis.

[0020] Data preprocessing is performed on customer portrait data to remove outliers, fill in missing values, and remove duplicate values.

[0021] It needs to be explained that: removing outliers: eliminating outliers in the number of cancellations caused by erroneous or repeated orders, such as the cancellation events of an order being recorded repeatedly; filling missing values: for missing cancellation timestamps or cancellation type identifiers, nearest neighbor interpolation or business rules (such as default marking as active cancellation) are used to complete them; removing duplicate values: for multiple records of the same customer, the same order number and the same cancellation time, only one valid record is retained to prevent redundant statistics.

[0022] S2: Obtaining the logistics adjustment priority and the protection adjustment priority according to the type of customer cancellation and customer profile data, and making preliminary compensation adjustments to the customer according to the logistics adjustment priority and the protection adjustment priority; If the type of the customer's cancellation is active cancellation, the logistics adjustment priority is obtained using the logistics adjustment formula based on the customer profile data, and the logistics arrangement time of the customer is adjusted according to the logistics adjustment priority; If the type of the customer's cabin return is passive cabin return, the protection adjustment priority is obtained by using the protection adjustment formula according to the customer portrait data, and then the order of the customers with overbooked cabin returns is adjusted according to the protection adjustment priority.

[0023] It should be noted that for customers with active cabin returns, the logistics adjustment formula is called according to their customer portrait data to calculate the logistics adjustment priority, and the logistics arrangement time of the customer is compensatorily adjusted according to the logistics adjustment priority, advancing the logistics arrangement time of the customer to indirectly improve the safety of the customer's goods and reduce the risk caused by congestion when loading near the departure time; for customers with passive cabin returns, the protection adjustment formula is also called according to their customer portrait data to calculate the protection adjustment priority, and when reallocating subsequent resources for the customers who return the cabin due to overbooking, the cabin space requirements of the customers with the highest protection adjustment priority are first met.

[0024] The logistics adjustment formula is as follows: ; In the formula, is the logistics adjustment priority; is the i-th logistics departure time; is the i-th customer's logistics arrangement time; im is the importance of the customer's goods; is the adjustment coefficient; is the weight adjustment factor.

[0025] It should be noted that the active cabin return behavior of the customer near the shipment time is analyzed. For the active cabin return behavior caused by the customer's temporary demand change or temporary accidental increase near the shipment time, the logistics arrangement time of such customers is changed to increase the error tolerance space of such customers when booking the next cabin.

[0026] The protection adjustment formula is as follows: ; In the formula, P is the protection adjustment priority; N is the number of times the customer has a passive cabin return within the preset time period; m is the number of segments of the customer's passive cabin return within the preset time period; is the length of the j-th segment of operation; 、 are the adjustment parameters; 、 are the weight adjustment parameters of the protection adjustment formula; im is the importance of the customer's goods.

[0027] It should be noted that N is the number of times a customer has a passive flight cancellation within a preset time period, which is the total number of times the customer has a passive flight cancellation due to overbooking and insufficient cabin space within the preset time period (e.g., the past three months or the last five order cycles); through the protection adjustment formula, customers with a large number of passive flight cancellations and customers with continuous passive flight cancellations are taken seriously, where , mapping business: when two or more flight cancellations occur adjacent to each other, it indicates a series of setbacks encountered by the customer; , mapping business: the negative impacts brought by multiple consecutive flight cancellations often accumulate exponentially. For example, if there are three consecutive flight cancellations, the customer's trust will collapse rapidly.

[0028] Map the passive flight cancellation situation of the customer within the preset time period into a binary sequence, take the situation of passive flight cancellation as the first data; otherwise as the second data, and take all adjacent first data in the binary sequence as a continuously running segment, and finally obtain the number of segments of the customer's passive flight cancellation within the preset time period, and obtain the length of each segment of operation according to the number of segments of the customer's passive flight cancellation within the preset time period.

[0029] It should be noted that the passive flight cancellation situation in a period of time (or several orders) is mapped into a binary sequence, ; In the above binary sequence, regard all adjacent "1"s as a continuously running segment. For example, the sequence: ; can be divided into three continuously running segments, where the first segment is: 1, 1, 1 (length is 3); the second segment is: a single 1 (length is 1); the third segment is: two 1s (length is 2); therefore, the number of segments of the customer's passive flight cancellation within the preset time period is 3, and the length of each segment of operation can be obtained.

[0030] S3: Obtain the space compensation value according to the logistics adjustment priority, the protection adjustment priority and the target customer's booking space data; According to the logistics adjustment priority, the protection adjustment priority and the target customer's booking space data, use the space compensation formula to obtain the space compensation value, where the target customer's booking space data is the size of the warehouse space reserved by the target customer, and the space compensation formula is: ; In the formula, F is the space compensation value; S is the size of the warehouse space reserved by the target customer; is the logistics adjustment priority of the target customer; P is the protection adjustment priority of the target customer; , is the weight adjustment coefficient for the space compensation formula.

[0031] It should be noted that the size of the warehouse space reserved by the customer this time is extracted from the customer order system for setting the subsequent compensation space upper limit; the logistics adjustment priority and the protection adjustment priority are obtained, and the two types of priorities are combined according to the weight as the input of the exponential function to obtain the space compensation value, and the space compensation value is the size of the space that the target customer can view and adjust according to the virtual cabin roaming facility.

[0032] S4: Perform final compensation adjustment on the target customer according to the space compensation value.

[0033] Set up a virtual cabin roaming facility for the cabin space, obtain the adjustable compensation space of the target customer according to the space compensation value, display the space layout and cargo placement effect in the cabin to the target customer according to the adjustable compensation space, and accept the layout adjustment and placement adjustment of the adjustable compensation space by the target customer.

[0034] It should be noted that the customer enters the virtual cabin roaming interface through the web page or the client, and is automatically positioned to the compensable area, where the compensable area is the space displayed according to the size of the space compensation value, and the corridor, brackets and cargo placement positions in the cabin are displayed from a dynamic roaming perspective; an initial placement plan is automatically generated according to the original cargo specifications and quantities of the customer, the 3D model of the cargo is rendered and displayed in the compensable area; the customer can perform operations such as dragging, rotating and stacking the cargo in the compensable space through the mouse or touch screen, and the space occupancy and remaining available space after loading are fed back in real time; when the customer is satisfied with the layout, click the confirm compensation layout button to write the final cabin layout plan (including the adjusted cargo position and size data) into the scheduling management module for actual booking and container loading execution. After the customer confirms, score and leave a message for the virtual roaming experience and compensation effect, and this feedback will be used as the basis for optimizing the subsequent priority model and interaction interface.

[0035] Embodiment 2: On the basis of Embodiment 1, an efficient logistics booking management system based on big data, as Figure 2 shown, includes: A data acquisition module, which is used to acquire the customer cabin return data of the logistics and obtain the customer portrait data according to the customer cabin return data; A preliminary adjustment module, which is used to obtain the logistics adjustment priority and the protection adjustment priority according to the customer cabin return type and the customer portrait data, and perform preliminary compensation adjustment on the customer according to the logistics adjustment priority and the protection adjustment priority; A first adjustment acquisition module, which is used to obtain the logistics adjustment priority by using the logistics adjustment formula according to the customer portrait data; A second adjustment obtaining module, configured to obtain a protection adjustment priority according to customer portrait data by using a protection adjustment formula; A segmented obtaining module, configured to obtain the number of segments of a customer's passive flight cancellation within a preset time period; A compensation value obtaining module, configured to obtain a space compensation value according to a logistics adjustment priority, a protection adjustment priority, and target customer booking space data; A final adjustment module, configured to perform a final compensation adjustment on a target customer according to the space compensation value.

[0036] As described above, the foregoing is only a specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An efficient logistics booking management method based on big data, characterized in that, It includes the following steps: S1: Obtain the customer's cabin return data of the logistics, and obtain the customer portrait data according to the customer's cabin return data; S2: Obtain the logistics adjustment priority and the protection adjustment priority according to the customer's cabin return type and the customer portrait data, and perform a preliminary compensation adjustment on the customer according to the logistics adjustment priority and the protection adjustment priority; S3: Obtain the space compensation value according to the logistics adjustment priority, the protection adjustment priority and the target customer's booking space data; S4: Perform a final compensation adjustment on the target customer according to the space compensation value.

2. The efficient logistics booking management method based on big data according to claim 1, characterized in that The obtaining of the customer's cabin return data of the logistics and the obtaining of the customer portrait data according to the customer's cabin return data include: obtaining the customer's cabin return data of the logistics, where the customer's cabin return data includes the customer's cabin return times and the customer's cabin return type, and the customer's cabin return type includes active cabin return and passive cabin return, and the active cabin return is the behavior of the customer taking the initiative to return the cabin; the passive cabin return is the behavior of the customer being forced to return the cabin due to overbooking; obtaining the customer portrait data according to the customer's cabin return type and the customer's cabin return times, and the customer portrait data includes the logistics departure time, the customer's logistics arrangement time, the importance of the customer's goods, the number of times the customer has been forced to return the cabin within a preset time period, and the time of the forced cabin return.

3. The efficient logistics booking management method based on big data according to claim 2, characterized in that, Before obtaining the customer portrait data according to the customer's cabin return type and the customer's cabin return times, it includes: performing data preprocessing on the customer portrait data to remove outliers, fill in missing values, and remove duplicate values.

4. The efficient logistics booking management method based on big data according to claim 1, characterized in that The obtaining of the logistics adjustment priority and the protection adjustment priority according to the customer's cabin return type and the customer portrait data, and the performing of a preliminary compensation adjustment on the customer according to the logistics adjustment priority and the protection adjustment priority include: If the customer's cabin return type is active cabin return, obtain the logistics adjustment priority according to the customer portrait data using the logistics adjustment formula, and adjust the customer's logistics arrangement time according to the logistics adjustment priority; If the customer's cabin return type is passive cabin return, obtain the protection adjustment priority according to the customer portrait data using the protection adjustment formula, and adjust the order of the customers who have been forced to return the cabin due to overbooking according to the protection adjustment priority.

5. The efficient logistics booking management method based on big data according to claim 4, characterized in that The obtaining of the logistics adjustment priority according to the customer portrait data using the logistics adjustment formula when the customer's cabin return type is active cabin return includes: where the logistics adjustment formula is: ； In the formula, is the logistics adjustment priority; is the logistics departure time for the is the logistics arrangement time for the i-th customer; im is the importance degree of the customer's goods; is the adjustment coefficient; is the weight adjustment factor.

6. The efficient logistics booking management method based on big data according to claim 4, characterized in that The obtaining of the protection adjustment priority according to the customer portrait data using the protection adjustment formula when the customer's cabin return type is passive cabin return includes: where the protection adjustment formula is: ； Wherein, P is the protection adjustment priority; N is the number of times the customer has a passive cabin withdrawal within a preset time period; m is the number of segments of the customer's passive cabin withdrawal within a preset time period; is the length of the j-th segment of operation; , are adjustment parameters; , are the weight adjustment parameters of the protection adjustment formula; is the importance degree of the customer's goods.

7. The efficient logistics booking management method based on big data according to claim 6, characterized in that The m is the number of segments of the customer's forced cabin return within a preset time period, including: mapping the customer's forced cabin return situation within the preset time period into a binary sequence, taking the situation of forced cabin return as the first data; otherwise as the second data, and taking all adjacent first data in the binary sequence as a continuous running segment, finally obtaining the number of segments of the customer's forced cabin return within the preset time period, and obtaining the length of each segment's operation according to the number of segments of the customer's forced cabin return within the preset time period.

8. The efficient logistics booking management method based on big data according to claim 1, characterized in that Adjusting the priority according to logistics, the protection adjustment priority, and the target customer's space booking data to obtain a space compensation value, including: using a space compensation formula to obtain a space compensation value according to the logistics adjustment priority, the protection adjustment priority, and the target customer's space booking data, where the target customer's space booking data is the size of the warehouse space reserved by the target customer, and the space compensation formula is: ； In the formula, F is the space compensation value; S is the warehouse space size reserved by the target customer; Adjust the priority for logistics of target customers;PAdjust the priority for protection of target customers; , It is the weight adjustment coefficient of the space compensation formula.

9. The efficient logistics booking management method based on big data according to claim 8, wherein, Making a final compensation adjustment to the target customer according to the space compensation value, including: setting virtual cabin roaming facilities for the cabin space, obtaining the adjustable compensation space for the target customer according to the space compensation value, displaying the space layout and cargo placement effect in the cabin to the target customer according to the adjustable compensation space, and accepting the layout adjustment and placement adjustment of the adjustable compensation space by the target customer.

10. An efficient logistics booking management system based on big data, a method for efficient logistics booking management based on big data according to any one of claims 1-9, characterized in that, It also includes: A data acquisition module, configured to acquire the customer's cabin return data of the logistics and obtain customer portrait data according to the customer's cabin return data; A preliminary adjustment module, configured to obtain a logistics adjustment priority and a protection adjustment priority according to the customer's cabin return type and the customer portrait data, and make a preliminary compensation adjustment to the customer according to the logistics adjustment priority and the protection adjustment priority; A first adjustment acquisition module, configured to obtain a logistics adjustment priority using a logistics adjustment formula according to the customer portrait data; A second adjustment acquisition module, configured to obtain a protection adjustment priority using a protection adjustment formula according to the customer portrait data; A segment acquisition module, configured to acquire the number of segments of the customer's passive cabin return within a preset time period; A compensation value acquisition module, configured to obtain a space compensation value according to the logistics adjustment priority, the protection adjustment priority, and the target customer's space booking data; A final adjustment module, configured to make a final compensation adjustment to the target customer according to the space compensation value.

Images