Intelligent bulk order freight management method and device, medium and equipment

Abstract

The invention provides an intelligent bulk order freight management method and device, a medium and equipment. The intelligent bulk order freight management method comprises the following steps: identifying and marking a bulk order by using an identification model; determining a bulk order quotation model, wherein the bulk order quotation model comprises a headquarter bulk order quotation model and a website bulk order quotation model; for the bulk order, determining the bulk order freight by using the selected bulk order quotation model, and determining the bulk order quotation model according to the customer selection, or calculating the bulk order freight based on the headquarter bulk order quotation model and the website bulk order quotation model, and selecting the optimal quotation based on the calculated bulk order freight; and predicting the floating rate by adopting the dynamic floating rate calculation model, and updating the bulk bill cost based on the floating rate. The intelligent quotation model is adopted, so that manual intervention is reduced, the working efficiency is improved, and quotation errors caused by human factors are reduced.

Description

Technical Field

[0001] The present invention relates to the field of logistics technology, and in particular to an intelligent bulk freight management method, device, medium and equipment. Background Art

[0002] In the logistics industry, the management of scattered orders has always been a major challenge for enterprises. Especially in the context of the rapid development of e-commerce, the number of scattered orders has increased dramatically, and its processing efficiency and cost control have become key factors in the core competitiveness of enterprises. Traditional scattered order quotations rely on manual experience, which is not only inefficient, but also easily affected by subjective factors, making it difficult to achieve accurate pricing. At the same time, with the continuous changes in market demand, fixed freight rates often cannot flexibly respond to seasonal fluctuations, regional differences and emergencies, resulting in limited corporate profit margins or damaged customer experience. Summary of the invention

[0003] The main purpose of the present invention is to solve the technical problems that the traditional individual order quotation in the prior art is too dependent on manual experience and judgment, which is not only inefficient, but also easily affected by subjective factors, making it difficult to achieve accurate pricing; at the same time, the fixed freight standard cannot flexibly respond to seasonal fluctuations, regional differences and emergencies.

[0004] The first aspect of the present invention provides an intelligent bulk freight management method, comprising: Determine a single order quotation model, wherein the single order quotation model includes a headquarters single order quotation model and a branch single order quotation model; For bulk orders, use the selected bulk quotation model to determine the bulk freight; A dynamic floating fee calculation model is used to predict floating rates, and individual order fees are updated based on the floating rates.

[0005] Optionally, in a first implementation of the first aspect of the present invention, the determining of the individual order quotation model, wherein the individual order quotation model includes a headquarters individual order quotation model and an outlet individual order quotation model, includes: Determine the individual order quotation model based on the customer's choice, or calculate the individual order freight based on the headquarters individual order quotation model and the branch individual order quotation model respectively, and select the best quotation based on the individually calculated individual order freight.

[0006] Optionally, in a second implementation of the first aspect of the present invention, the method further includes: Obtain historical order data, mark individual orders in the historical orders, and construct a data set; Divide the data set into training set, validation set and test set; Build recognition models based on machine learning algorithms; Use the training set to train the recognition model, and use the validation set and test set to verify and test the trained model respectively; Use the trained recognition model to identify and mark individual orders.

[0007] Optionally, in a third implementation of the first aspect of the present invention, the headquarters single order quotation model includes: Build headquarters' individual order quotation model based on machine learning model; Obtaining historical order data, including order quantity, transportation distance, package weight, delivery area, and demand fluctuation factors caused by seasonal changes; Preprocessing the acquired historical individual order data to obtain the preprocessed historical individual order data; The preprocessed historical individual order data is used to train the headquarters individual order quotation model to obtain the trained headquarters individual order quotation model.

[0008] Optionally, in a fourth implementation of the first aspect of the present invention, the preprocessing of the acquired historical scattered order data includes: Performing data cleaning on the acquired historical order data, wherein the data cleaning includes missing value processing and duplicate data processing; obtaining the cleaned historical order data; The cleaned historical scattered order data is standardized to obtain the standardized historical scattered order data.

[0009] Optionally, in a fifth implementation of the first aspect of the present invention, the network point scattered order quotation model includes: in, ; Indicates the recharge rate.

[0010] Optionally, in a sixth implementation of the first aspect of the present invention, the adopting a dynamic floating fee calculation model to predict a floating rate includes: Construct a dynamic floating fee calculation model based on a time series analysis model or a regression analysis model; The floating fee calculation model is used to monitor factors including market supply and demand conditions, fuel price changes, and holiday impacts, and the time series analysis model or regression analysis model is used to predict the optimal floating rate.

[0011] The second aspect of the present invention provides an intelligent single-order freight management device, characterized in that it includes: A model selection module, used to determine a single order quotation model, wherein the single order quotation model includes a headquarters single order quotation model and a branch single order quotation model; The module for calculating the bulk freight is used to determine the bulk freight for bulk orders by using the selected bulk quotation model; The single-order freight update module is used to predict the floating rate using a dynamic floating rate calculation model and update the single-order fees based on the floating rate.

[0012] Optionally, in a first implementation of the second aspect of the present invention, the model selection module includes: Determine the individual order quotation model based on the customer's choice, or calculate the individual order freight based on the headquarters individual order quotation model and the branch individual order quotation model respectively, and select the best quotation based on the individually calculated individual order freight.

[0013] Optionally, in a second implementation of the second aspect of the present invention, the device further includes: an order identification and marking module; the order identification and marking module includes: Obtain historical order data, mark individual orders in the historical orders, and construct a data set; Divide the data set into training set, validation set and test set; Build recognition models based on machine learning algorithms; Use the training set to train the recognition model, and use the validation set and test set to verify and test the trained model respectively; Use the trained recognition model to identify and mark individual orders.

[0014] Optionally, in a third implementation of the second aspect of the present invention, the headquarters single order quotation model includes: Build headquarters' individual order quotation model based on machine learning model; Obtaining historical order data, including order quantity, transportation distance, package weight, delivery area, and demand fluctuation factors caused by seasonal changes; Preprocessing the acquired historical individual order data to obtain the preprocessed historical individual order data; The preprocessed historical individual order data is used to train the headquarters individual order quotation model to obtain the trained headquarters individual order quotation model.

[0015] Optionally, in a fourth implementation of the second aspect of the present invention, the preprocessing of the acquired historical scattered order data includes: Performing data cleaning on the acquired historical order data, wherein the data cleaning includes missing value processing and duplicate data processing; obtaining the cleaned historical order data; The cleaned historical scattered order data is standardized to obtain the standardized historical scattered order data.

[0016] Optionally, in a fifth implementation of the second aspect of the present invention, the network point scattered order quotation model includes: in, ; Indicates the recharge rate.

[0017] Optionally, in a sixth implementation of the second aspect of the present invention, the single-order freight update module includes: Construct a dynamic floating fee calculation model based on a time series analysis model or a regression analysis model; The floating fee calculation model is used to monitor factors including market supply and demand conditions, fuel price changes, and holiday impacts, and the time series analysis model or regression analysis model is used to predict the optimal floating rate.

[0018] The third aspect of the present invention provides a computer-readable storage medium storing a computer program, characterized in that when the computer program is executed by a processor, the steps of the above-mentioned intelligent individual order freight management method are implemented.

[0019] The fourth aspect of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the above-mentioned intelligent individual order freight management method when executed by the processor.

[0020] Compared with the prior art, the present invention has the following beneficial effects: 1. The use of intelligent quotation models reduces manual intervention, improves work efficiency, and reduces quotation errors caused by human factors; 2. The present invention provides a headquarters single order quotation model and a branch single order quotation model, which can be selected according to local conditions and has greater flexibility; 3. The present invention can adjust freight rates in a timely manner according to market changes through a dynamic floating fee calculation model, thereby reducing the risk of losses caused by price fluctuations; 4. The automated identification, calculation and update processes have significantly reduced the manpower costs of enterprises in the management of individual freight rates, improved operational efficiency, and reduced errors and uncertainties caused by human factors through decision-making methods based on algorithms and data, thus improving the efficiency of the entire freight management process. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 A first flow chart of the intelligent bulk freight management method provided in an embodiment of the present invention.

[0022] Figure 2A second flow chart of the intelligent bulk freight management method provided in an embodiment of the present invention.

[0023] Figure 3 A third flow chart of the intelligent bulk freight management method provided in an embodiment of the present invention.

[0024] Figure 4 A fourth flow chart of the intelligent bulk freight management method provided in an embodiment of the present invention.

[0025] Figure 5 A structural schematic diagram of an intelligent single-order freight management device provided in an embodiment of the present invention.

[0026] Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The embodiments of the present invention provide an intelligent single-order freight management method, device, medium and equipment, which can automatically identify and mark single orders, enable users to quickly locate and process single orders, determine fees according to a single-order quotation model, and automatically adjust the floating fees of single orders using a dynamic floating fee calculation model; this solves the problem that single-order quotations in the prior art are too dependent on manual experience and judgment, which is not only inefficient, but also easily affected by subjective factors, making it difficult to achieve accurate pricing; and the fixed freight standards cannot flexibly respond to seasonal fluctuations, regional differences and emergencies.

[0028] 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.

[0029] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 The first embodiment of the intelligent bulk freight management method in the embodiment of the present invention includes: 101. Determine a single order quotation model according to customer demand, wherein the single order quotation model includes a headquarters single order quotation model and a branch single order quotation model; In this embodiment, the individual order quotation model is determined according to the customer's selection; when the individual order is quoted according to the total price, the headquarters individual order quotation model is selected; when the branch customized freight quotation is selected, the branch individual order quotation model is selected.

[0030] 102. For bulk orders, use the selected bulk quotation model to determine the bulk freight; In this embodiment, the headquarters single order quotation model includes: Build headquarters' individual order quotation model based on machine learning model; Obtaining historical order data, including order quantity, transportation distance, package weight, delivery area, and demand fluctuation factors caused by seasonal changes; Preprocessing the acquired historical order data to obtain preprocessed historical order data; wherein, performing data cleaning processing on the acquired historical order data, the data cleaning processing includes missing value processing and duplicate data processing; obtaining cleaned historical order data; performing standardization processing on the cleaned historical order data to obtain standardized historical order data.

[0031] The preprocessed historical individual order data is used to train the headquarters individual order quotation model to obtain the trained headquarters individual order quotation model.

[0032] The quotation model for point-of-sale orders includes: in, ; Indicates the recharge rate.

[0033] 103. Use a dynamic floating fee calculation model to predict floating rates and update individual order fees based on the floating rates.

[0034] In this embodiment, a dynamic floating fee calculation model is constructed based on a time series analysis model or a regression analysis model; The floating fee calculation model is used to monitor factors including market supply and demand conditions, fuel price changes, and holiday impacts, and the time series analysis model or regression analysis model is used to predict the optimal floating rate.

[0035] This embodiment makes reasonable use of data, dynamically adjusts pricing and automates quotation, which not only improves the accuracy of freight management and efficiency, but also enables flexible response to market fluctuations, thereby improving overall operational efficiency.

[0036] See also Figure 2 The second embodiment of the intelligent bulk freight management method in the embodiment of the present invention includes: 201. Determine a single order quotation model based on the optimal quotation principle, wherein the single order quotation model includes a headquarters single order quotation model and a branch single order quotation model; In this embodiment, the individual order freight is calculated based on the headquarters individual order quotation model and the network point individual order quotation model, and the optimal quotation is selected based on the individual order freight calculated respectively.

[0037] 202. For the bulk order, determine the bulk freight by using the selected bulk quotation model; In this embodiment, the headquarters single order quotation model includes: Collect and organize detailed data of historical single orders, including but not limited to order quantity, transportation distance, package weight, delivery area, demand fluctuations caused by seasonal changes, and other factors. Use big data analysis technology to clean and preprocess these data to ensure data quality. Subsequently, apply machine learning algorithms (such as decision trees, random forests, neural networks, etc.) to conduct deep learning on the data to identify the complex correlation between various factors and freight quotes. Through iterative training, optimize model parameters, and finally form a quotation model that can accurately predict single-order freight. This model can automatically output reasonable freight quotation suggestions based on the input order characteristics, providing a scientific basis for subsequent automatic quotations.

[0038] The network point scattered order quotation model includes: Calculation formula for bulk order fees ={first weight*first weight rate+first weight operation fee}+{settlement weight-first weight)*renewal weight rate+renewal weight operation fee = first weight * first weight rate + first weight operation fee + settlement weight * additional weight rate - first weight * additional weight rate + additional weight operation fee = first weight handling fee + additional weight handling fee + first weight * first weight rate + additional weight rate * settlement weight - first weight * additional weight rate = first weight operation fee + additional weight operation fee + first weight * first weight rate + additional weight rate * (settlement weight - first weight) ={first weight operation fee + additional weight operation fee + first weight * first weight rate} + additional weight rate * (settlement weight - first weight) =A+B*(settlement weight-first weight) Therefore, the calculation formula for calculating the fee = A + B * (settlement weight - first weight), the fee can be calculated by directly substituting the settlement weight into the formula A: First weight handling fee + additional weight handling fee + first weight * first weight rate B: Recharge rate After collecting the corresponding quotation from the salesperson's customer freight (distribution fee) invoice, the fee is calculated based on the destination and settlement weight according to the weight range in which the settlement weight is located. The formula is: distribution fee = first weight rate + (settlement weight - first weight) x additional weight rate + first weight operation fee + additional weight operation fee.

[0039] 203. Use a dynamic floating fee calculation model to predict floating rates and update individual order fees based on the floating rates; In this embodiment, a floating fee calculation model that dynamically responds to market changes is constructed. The model can automatically adjust the floating fees of individual orders based on external factors such as market supply and demand conditions, fuel price changes, and holiday impacts. In specific implementation, the model will monitor the above variables and use time series analysis, regression analysis and other methods to predict the optimal floating rate. Outlets or salesmen can flexibly set the floating surcharge ratio on top of the basic quotation based on actual operating conditions. The system automatically calculates and applies it to the individual freight rates, thereby achieving dynamic adaptability and competitiveness of the quotation.

[0040] This embodiment calculates the optimal quotation based on two models respectively, and provides quotations that better meet customer needs, making quotations more flexible and accurate, which helps to improve customer satisfaction and business profitability; at the same time, the automated identification, calculation and update processes greatly reduce the company's labor costs in the management of individual freight rates, improve operational efficiency, and the decision-making method based on algorithms and data reduces errors and uncertainties caused by human factors, thereby improving the efficiency of the entire freight management process.

[0041] See also Figure 3 The third embodiment of the intelligent bulk freight management method in the embodiment of the present invention includes: 301. Using the recognition model to identify and mark individual orders; In this embodiment, historical order data is obtained, and individual orders in the historical orders are marked to construct a data set; Divide the data set into training set, validation set and test set; Build recognition models based on machine learning algorithms; Use the training set to train the recognition model, and use the validation set and test set to verify and test the trained model respectively; Use the trained recognition model to identify and mark individual orders.

[0042] This embodiment implements intelligent recognition and marking through a mail recognition model, improves order processing efficiency, and facilitates batch screening and batch processing.

[0043] 302. Determine a single order quotation model based on the single order, where the single order quotation model includes a headquarters single order quotation model and a branch single order quotation model; In this embodiment, a single order quotation model is selected and determined according to customer demand, or single order freight is calculated based on the headquarters single order quotation model and the branch single order quotation model respectively, and the optimal quotation is selected based on the separately calculated single order freight.

[0044] 303. For the bulk order, determine the bulk freight by using the selected bulk quotation model; In this embodiment, the headquarters batch order quotation model is used to determine the batch order freight, wherein the headquarters batch order quotation model includes: Build headquarters' individual order quotation model based on machine learning model; Obtaining historical order data, including order quantity, transportation distance, package weight, delivery area, and demand fluctuation factors caused by seasonal changes; Preprocessing the acquired historical individual order data to obtain the preprocessed historical individual order data; The preprocessed historical individual order data is used to train the headquarters individual order quotation model to obtain the trained headquarters individual order quotation model.

[0045] The point-to-point bulk order quotation model is used to determine the bulk order freight, where the point-to-point bulk order quotation model includes: in, ; Indicates the recharge rate.

[0046] 304. Use a dynamic floating fee calculation model to predict floating rates, and update individual order fees based on the floating rates.

[0047] In this embodiment, a dynamic floating fee calculation model is constructed based on a time series analysis model or a regression analysis model; The floating fee calculation model is used to monitor factors including market supply and demand conditions, fuel price changes, and holiday impacts, and the time series analysis model or regression analysis model is used to predict the optimal floating rate.

[0048] This embodiment can provide customers with more personalized and flexible quotation options through accurate models and real-time data updates, thereby improving customer satisfaction and loyalty.

[0049] See also Figure 4 The fourth embodiment of the intelligent bulk freight management method in the embodiment of the present invention includes: 401. Introduce machine learning algorithms to analyze the relationship between historical single-order data and freight quotes, and generate single-order quote models; In this embodiment, the historical scattered order data includes factors such as order quantity, distance, weight, seasonal changes, etc., dynamically adjusts the scattered order quotation, and automatically recommends the optimal floating rate for the outlets based on the headquarters quotation to balance costs and benefits, so as to achieve intelligent recommendation of personalized quotation strategies. Collect and organize detailed data of historical scattered orders, including but not limited to factors such as order quantity, transportation distance, package weight, delivery area, and demand fluctuations caused by seasonal changes. Use big data analysis technology to clean and preprocess these data to ensure data quality. Subsequently, apply machine learning algorithms (such as decision trees, random forests, neural networks, etc.) to conduct deep learning on the data to identify the complex correlation between various factors and freight quotations. Through iterative training, optimize model parameters, and finally form a quotation model that can accurately predict the freight of scattered orders. This model can automatically output reasonable freight quotation suggestions based on the input order characteristics, providing a scientific basis for subsequent automatic quotations.

[0050] 402. Automatically identify and mark bulk orders, and automatically determine fees based on settlement weight and weight range according to the bulk order quotation model; In this embodiment, based on the order label (such as Cainiao GOGO, single piece, etc.) and the identification rules configured by the system, it is automatically determined whether the order belongs to the single order category. Once confirmed as a single order, the system immediately decides whether to use the previously established single order quotation model based on the switch status of "single orders are quoted according to headquarters". If it is on, the system immediately queries and applies the single order quotation calculated by the model; if it is off, the freight quotation customized by the outlet is used. In addition, multi-dimensional filtering functions are provided, such as single order type, origin, destination, weight range, etc., so that users can dynamically filter and display the corresponding single order quotation list according to specific needs, thereby improving query efficiency and accuracy.

[0051] Calculation formula for bulk order fees ={first weight*first weight rate+first weight operation fee}+{settlement weight-first weight)*renewal weight rate+renewal weight operation fee = first weight * first weight rate + first weight operation fee + settlement weight * additional weight rate - first weight * additional weight rate + additional weight operation fee = first weight handling fee + additional weight handling fee + first weight * first weight rate + additional weight rate * settlement weight - first weight * additional weight rate = first weight operation fee + additional weight operation fee + first weight * first weight rate + additional weight rate * (settlement weight - first weight) ={first weight operation fee + additional weight operation fee + first weight * first weight rate} + additional weight rate * (settlement weight - first weight) =A+B*(settlement weight-first weight) Therefore, the calculation formula for calculating the fee = A + B * (settlement weight - first weight), the fee can be calculated by directly substituting the settlement weight into the formula A: First weight handling fee + additional weight handling fee + first weight * first weight rate B: Recharge rate After collecting the corresponding quotation from the salesperson's customer freight (distribution fee) invoice, the fee is calculated based on the destination and settlement weight according to the weight range in which the settlement weight is located. The formula is: distribution fee = first weight rate + (settlement weight - first weight) x additional weight rate + first weight operation fee + additional weight operation fee.

[0052] 403. Use dynamic floating fee calculation model to automatically adjust floating fees for individual orders; In this embodiment, a floating fee calculation model that dynamically responds to market changes is constructed. The model can automatically adjust the floating fees of individual orders based on external factors such as market supply and demand conditions, fuel price changes, and holiday impacts. In specific implementation, the model will monitor the above variables and use time series analysis, regression analysis and other methods to predict the optimal floating rate. Outlets or salesmen can flexibly set the floating surcharge ratio on top of the basic quotation based on actual operating conditions. The system automatically calculates and applies it to the individual freight rates, thereby achieving dynamic adaptability and competitiveness of the quotation.

[0053] 404. Users can quickly locate and process individual orders, identify and prioritize key tags such as "Cainiao Guoguo" and "Individual Orders", and select specific tags for order screening and batch processing as needed; In this embodiment, detailed instructions are added for special order number types (such as handover code, Fengchao, electronic reverse, and scattered order direct purchase). Through interactive question mark prompts, instant help information is provided, which enhances the user's understanding and application of system rules. A highly intelligent tag screening tool is integrated into the system, allowing users to quickly locate and process scattered orders. Through algorithm optimization, the system can identify and prioritize key tags, such as "Cainiao Guoguo" and "scattered orders", and support users to select specific tags for order screening and batch processing as needed. In addition, combined with the automated processes of the order processing system, such as automatic matching of the best quotation, one-click bill generation, and quick response to customer inquiries, manual intervention is greatly reduced, the workflow is simplified, and the processing speed is improved. This not only improves internal management efficiency, but also enhances customer satisfaction and loyalty through fast and accurate service responses.

[0054] The above describes the intelligent bulk freight management method in the embodiment of the present invention. The following describes the intelligent bulk freight management device in the embodiment of the present invention. Figure 5 In one embodiment of the present invention, an intelligent single-order freight management device includes: The order recognition and marking module 501 is used to recognize and mark individual orders using a recognition model; In this embodiment, the order identification and labeling module 501 includes: obtaining historical order data, and labeling individual orders in the historical orders to construct a data set; Divide the data set into training set, validation set and test set; Build recognition models based on machine learning algorithms; Use the training set to train the recognition model, and use the validation set and test set to verify and test the trained model respectively; Use the trained recognition model to identify and mark individual orders.

[0055] A model selection module 502 is used to determine a single order quotation model based on the single order, wherein the single order quotation model includes a headquarters single order quotation model and a branch single order quotation model; In this embodiment, the model selection module 502 includes: selecting and determining a single order quotation model according to customer demand, or calculating single order freight rates based on the headquarters single order quotation model and the branch single order quotation model respectively, and selecting the optimal quotation based on the separately calculated single order freight rates.

[0056] This embodiment utilizes a dual-model selection mechanism to select a suitable individual order quotation model based on customer demand, and combines the quotation mechanisms of the headquarters and outlets to ensure that freight calculation is more flexible and adaptable.

[0057] The bulk freight calculation module 503 is used to determine the bulk freight for bulk orders by using the selected bulk quotation model; In this embodiment, the bulk order freight calculation module 503 includes: determining the bulk order freight using the headquarters bulk order quotation model or determining the bulk order freight using the outlet bulk order quotation model; Among them, the headquarters' individual order quotation model includes: Collect and organize detailed data of historical single orders, including but not limited to order quantity, transportation distance, package weight, delivery area, demand fluctuations caused by seasonal changes, and other factors. Use big data analysis technology to clean and preprocess these data to ensure data quality. Subsequently, apply machine learning algorithms (such as decision trees, random forests, neural networks, etc.) to conduct deep learning on the data to identify the complex correlation between various factors and freight quotes. Through iterative training, optimize model parameters, and finally form a quotation model that can accurately predict single-order freight. This model can automatically output reasonable freight quotation suggestions based on the input order characteristics, providing a scientific basis for subsequent automatic quotations.

[0058] Among them, the network point scattered order quotation model includes: Calculation formula for bulk order fees ={first weight*first weight rate+first weight operation fee}+{settlement weight-first weight)*renewal weight rate+renewal weight operation fee = first weight * first weight rate + first weight operation fee + settlement weight * additional weight rate - first weight * additional weight rate + additional weight operation fee = first weight handling fee + additional weight handling fee + first weight * first weight rate + additional weight rate * settlement weight - first weight * additional weight rate = first weight operation fee + additional weight operation fee + first weight * first weight rate + additional weight rate * (settlement weight - first weight) ={first weight operation fee + additional weight operation fee + first weight * first weight rate} + additional weight rate * (settlement weight - first weight) =A+B*(settlement weight-first weight) Therefore, the calculation formula for calculating the fee = A + B * (settlement weight - first weight), the fee can be calculated by directly substituting the settlement weight into the formula A: First weight handling fee + additional weight handling fee + first weight * first weight rate B: Recharge rate After collecting the corresponding quotation from the salesperson's customer freight (distribution fee) invoice, the fee is calculated based on the destination and settlement weight according to the weight range in which the settlement weight is located. The formula is: distribution fee = first weight rate + (settlement weight - first weight) x additional weight rate + first weight operation fee + additional weight operation fee.

[0059] The single-order freight update module 504 is used to predict the floating rate using a dynamic floating rate calculation model and update the single-order fee based on the floating rate.

[0060] In this embodiment, the bulk freight update module 504 includes: constructing a floating fee calculation model that dynamically responds to market changes, which can automatically adjust the floating fees of bulk orders according to external factors such as market supply and demand conditions, fuel price changes, and holiday impacts. In specific implementation, the model will monitor the above variables and use time series analysis, regression analysis and other methods to predict the optimal floating rate. The outlets or salesmen can flexibly set the floating surcharge ratio on top of the basic quotation according to the actual operating conditions, and the system automatically calculates and applies it to the bulk freight, thereby achieving dynamic adaptability and competitiveness of the quotation.

[0061] This embodiment responds to market changes in real time through a dynamic floating fee calculation model, automatically adjusts freight rates, and ensures pricing competitiveness and market applicability. Specifically, the model can monitor market supply and demand, fuel prices, holiday impacts and other factors in real time, providing a dynamic, data-driven update mechanism for quotations.

[0062] In this embodiment, the efficiency and effectiveness of freight management are significantly improved through efficient data processing, accurate quotation model, flexible freight calculation and improvement of user experience. It can not only meet market demand, but also enhance corporate competitiveness, reduce operating costs, and bring significant technical advantages to enterprises in the modern logistics industry.

[0063] above Figure 5 The intelligent individual order freight management 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.

[0064] Figure 6 7 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.

[0065] 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.

[0066] 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 intelligent single-order freight management method.

[0067] 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.

[0068] 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.

[0069] 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. An intelligent method for managing the freight costs of individual orders, characterized in that: include: Determine a single order quotation model, wherein the single order quotation model includes a headquarters single order quotation model and a branch single order quotation model; For bulk orders, use the selected bulk quotation model to determine the bulk freight; A dynamic floating fee calculation model is used to predict floating rates, and individual order fees are updated based on the floating rates.

2. The intelligent single-order freight management method according to claim 1 is characterized in that: The determining of the individual order quotation model, wherein the individual order quotation model includes a headquarters individual order quotation model and a branch individual order quotation model, includes: Determine the individual order quotation model based on the customer's choice, or calculate the individual order freight based on the headquarters individual order quotation model and the branch individual order quotation model respectively, and select the best quotation based on the individually calculated individual order freight.

3. The intelligent single-order freight management method according to claim 1 is characterized in that: The method further comprises: Obtain historical order data, mark individual orders in the historical orders, and construct a data set; Divide the data set into training set, validation set and test set; Build recognition models based on machine learning algorithms; Use the training set to train the recognition model, and use the validation set and test set to verify and test the trained model respectively; Use the trained recognition model to identify and mark individual orders.

4. The intelligent single-order freight management method according to claim 1 is characterized in that: The headquarters single order quotation model includes: Build headquarters' individual order quotation model based on machine learning model; Obtaining historical order data, including order quantity, transportation distance, package weight, delivery area, and demand fluctuation factors caused by seasonal changes; Preprocessing the acquired historical individual order data to obtain the preprocessed historical individual order data; The preprocessed historical individual order data is used to train the headquarters individual order quotation model to obtain the trained headquarters individual order quotation model.

5. The intelligent single-order freight management method according to claim 3 is characterized in that: The preprocessing of the acquired historical scattered order data includes: Performing data cleaning on the acquired historical order data, wherein the data cleaning includes missing value processing and duplicate data processing; obtaining the cleaned historical order data; The cleaned historical scattered order data is standardized to obtain the standardized historical scattered order data.

6. The intelligent single-order freight management method according to claim 1 is characterized in that: The network point scattered order quotation model includes: in, ; Indicates the recharge rate.

7. The intelligent single-order freight management method according to claim 1 is characterized in that: The method of using a dynamic floating fee calculation model to predict the floating rate includes: Construct a dynamic floating fee calculation model based on a time series analysis model or a regression analysis model; The floating fee calculation model is used to monitor factors including market supply and demand conditions, fuel price changes, and holiday impacts, and the time series analysis model or regression analysis model is used to predict the optimal floating rate.

8. An intelligent single-order freight management device, characterized in that: include: A model selection module, used to determine a single order quotation model, wherein the single order quotation model includes a headquarters single order quotation model and a branch single order quotation model; The module for calculating the bulk freight is used to determine the bulk freight for bulk orders by using the selected bulk quotation model; The single-order freight update module is used to predict the floating rate using a dynamic floating rate calculation model and update the single-order fees based on the floating rate.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the intelligent single-order freight management method described in any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer program is executed by a processor, the steps of the intelligent single-order freight management method described in any one of claims 1 to 7 are implemented.

Images