Customer acquisition incentive method and device for logistics industry

Abstract

The invention relates to the technical field of customer data analysis and processing, and discloses a customer acquisition incentive method for a logistics industry. Comprising the following steps: acquiring high-quality waist customer information marked by a system, and extracting customer historical order data, cost data information, peer market data information, competitiveness analysis data information and customer payment record and credit data information in the high-quality waist customer information; performing data processing on the high-quality waist customer data to generate preprocessed data; generating a historical pricing strategy and a company incentive policy over the years according to the preprocessed data, and analyzing the historical pricing strategy and the company incentive policy over the years to design the incentive policy; an incentive policy is optimized by adopting a DDPG policy optimization algorithm, and an optimal customer incentive scheme is generated; the DDPG strategy optimization algorithm is optimized through experience playback, multi-agent learning and reward design optimization; the method has the advantage of improving the customer obtaining efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of customer data analysis and processing, and in particular to a customer acquisition incentive method and device for the logistics industry. Background Art

[0002] Against the backdrop of the current slowdown in the overall growth of the express delivery market, express delivery companies are increasingly competing for mid-tier customers. This is no accident, but rather determined by industry development trends and the market competition landscape. Mid-tier customers (i.e., those with an average daily shipment volume of 50-1000 orders) have become a focus of competition among express delivery companies due to their stable business, considerable profits, and relatively weak bargaining power. Mid-tier customers strike a good balance between profit and stability, and are a key source of profit growth for express delivery companies. With the booming e-commerce industry and the rise of small and medium-sized enterprises, the mid-tier customer base continues to expand, presenting enormous market potential. By competing for these mid-tier customers, express delivery companies can further expand their market share and enhance their competitiveness. Providing higher-quality, more customized services to these mid-tier customers can help express delivery companies improve their service systems and enhance their overall service levels.

[0003] Therefore, a customer acquisition incentive method and device for the logistics industry are provided to solve the above problems. Summary of the Invention

[0004] The main purpose of the present invention is to solve the technical problem in the prior art of lacking a method for automatically generating incentive plans for customers and low efficiency in acquiring customers.

[0005] A first aspect of the present invention provides a customer acquisition incentive method for the logistics industry, the customer acquisition incentive method for the logistics industry comprising: Obtain high-quality mid-range customer information marked by the system, and extract customer historical order data, cost data, peer market data, competitiveness analysis data, as well as customer payment records and credit data from the high-quality mid-range customer information; Process high-quality mid-level customer data to generate pre-processed data; Generate historical pricing strategies and the company's incentive policies over the years based on pre-processed data, analyze historical pricing strategies and the company's incentive policies over the years to design incentive policies; By using the DDPG strategy optimization algorithm to optimize the incentive policy, the optimal customer incentive plan is generated; The DDPG strategy optimization algorithm is optimized through experience replay, real-time effect feedback, multi-agent learning and reward design optimization.

[0006] Optionally, the obtaining of high-quality mid-tier customer information marked by the system and the extraction of customer historical order data, cost data, peer market data, competitiveness analysis data, and customer payment records and credit data from the high-quality mid-tier customer information include: Obtain high-quality waist customer information marked by the system; Extract customer historical order data from high-quality mid-level customer information, extract order quantity data from customer historical order data, extract timeliness requirement data from customer historical order data, and extract order price data from customer historical order data; Extract cost data from high-quality waist-level customer information, extract transportation cost data from cost data, extract warehousing cost data from cost data, and extract service cost data from cost data; Extract peer market data information from high-quality mid-tier customer information, extract peer price data from peer market data, extract peer timeliness data from peer market data, and extract peer service status data from peer market data; Extract competitiveness analysis data from high-quality mid-tier customer information, extract price information for similar customers from competitiveness analysis data, and extract preferential policy information for similar customers from competitiveness analysis data; Extract customer payment records and credit data information from high-quality mid-level customer information, extract customer payment habit data from customer payment records and credit data information, and extract customer credit history data from customer payment records and credit data information.

[0007] Optionally, processing the high-quality waist-level customer data to generate pre-processed data includes: Remove duplicate data from high-quality mid-level customer information, fill in missing values ​​in high-quality mid-level customer information, and modify / delete outliers in high-quality mid-level customer information; Extract the feature values ​​from high-quality waist customer information; Data of different dimensions are standardized using the Z-Score standardization model.

[0008] Optionally, the design incentive policy includes: Set tiered discounts based on order volume, set prices based on timeliness requirements, set prices based on the length of cooperation, provide different payment terms, and provide additional services.

[0009] Optionally, optimizing the incentive policy by adopting the DDPG strategy optimization algorithm to generate the optimal customer incentive plan includes: The market environment information, competitor pricing information, and historical sales data information are input into the DDPG strategy optimization algorithm as the state layer of the DDPG strategy optimization algorithm; Input the incentive policy into the DDPG strategy optimization algorithm as the action layer of the DDPG strategy optimization algorithm; Generate market reaction information through the reward layer in the DDPG strategy optimization algorithm; Select incentive policies as the optimal customer incentive plan based on market response information.

[0010] Optionally, optimizing the DDPG strategy optimization algorithm through experience replay includes: The agent's historical experience is stored in a buffer, from which small batches of experience are randomly sampled for training. The agent's historical experience is a four-tuple consisting of state, action, reward, and next state.

[0011] A second aspect of the present invention provides a customer acquisition incentive device for the logistics industry, the customer acquisition incentive device for the logistics industry comprising: The customer information acquisition module is used to obtain high-quality mid-range customer information marked by the system, and extract customer historical order data, cost data information, peer market data information, competitiveness analysis data information, as well as customer payment records and credit data information from the high-quality mid-range customer information; Data preprocessing module, used to process high-quality waist customer data and generate preprocessed data; The incentive policy design module is used to generate historical pricing strategies and the company's incentive policies over the years based on preprocessed data, and to analyze historical pricing strategies and the company's incentive policies over the years to design incentive policies; The incentive scheme optimization module is used to optimize the incentive policy by using the DDPG strategy optimization algorithm to generate the optimal customer incentive scheme; The algorithm optimization module is used to optimize the DDPG strategy optimization algorithm through experience replay, real-time effect feedback, multi-agent learning, and reward design optimization.

[0012] A third aspect of the present invention provides 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 the various steps of the customer acquisition incentive method for the logistics industry 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 customer acquisition incentive method for the logistics industry as described above.

[0014] In the technical solution of the present invention, by obtaining customer orders, product data information, timeliness requirement cost, service requirement cost, peer competition situation, etc., the DDPG strategy optimization algorithm is used to target the customer's basic information and price cost changes, and reinforcement learning is performed in the continuous action space of selectable strategy solutions to find the optimal customer incentive solution; it can also realize pricing according to market competition conditions to ensure that it can attract customers without being lower than the market average price, realize automatic design of incentive policy solutions, and adopt at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A flowchart of a customer acquisition incentive method for the logistics industry provided by the first embodiment of the present invention; Figure 2 A schematic diagram of the structure of a customer acquisition incentive device for the logistics industry provided by an embodiment of the present invention; Figure 3 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] An embodiment of the present invention provides a customer acquisition incentive method for the logistics industry, including obtaining high-quality mid-level customer information marked by a system, extracting customer historical order data, cost data information, peer market data information, competitiveness analysis data information, and customer payment records and credit data information from the high-quality mid-level customer information; performing data processing on the high-quality mid-level customer data to generate pre-processed data; generating historical pricing strategies and the company's incentive policies over the years based on the pre-processed data, analyzing the historical pricing strategies and the company's incentive policies over the years to design incentive policies; optimizing the incentive policies by adopting a DDPG strategy optimization algorithm to generate an optimal customer incentive plan; optimizing the DDPG strategy optimization algorithm by experience replay, real-time effect feedback, multi-agent learning, and reward design optimization; the present invention solves the technical problems in the prior art of lacking a method for automatically generating incentive plans for customers and low efficiency in acquiring customers.

[0017] The terms "first," "second," "third," "fourth," and so on (if any) in the description and claims of the present invention and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that shown 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 apparatus that includes a series of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, product, or apparatus.

[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 customer acquisition incentive method for the logistics industry in the embodiment of the present invention includes: Obtain high-quality mid-range customer information marked by the system, and extract customer historical order data, cost data, peer market data, competitiveness analysis data, as well as customer payment records and credit data from the high-quality mid-range customer information; Specifically, they include: Obtain high-quality waist customer information marked by the system; Extract customer historical order data from high-quality mid-level customer information, extract order quantity data from customer historical order data, extract timeliness requirement data from customer historical order data, and extract order price data from customer historical order data; Extract cost data from high-quality waist-level customer information, extract transportation cost data from cost data, extract warehousing cost data from cost data, and extract service cost data from cost data; Extract peer market data information from high-quality mid-tier customer information, extract peer price data from peer market data, extract peer timeliness data from peer market data, and extract peer service status data from peer market data; Extract competitiveness analysis data from high-quality mid-tier customer information, extract price information for similar customers from competitiveness analysis data, and extract preferential policy information for similar customers from competitiveness analysis data; Extract customer payment records and credit data information from high-quality mid-level customer information, extract customer payment habit data from customer payment records and credit data information, and extract customer credit history data from customer payment records and credit data information.

[0019] Process high-quality mid-level customer data to generate pre-processed data; Specifically, they include: Remove duplicate data from high-quality mid-level customer information, fill in missing values ​​in high-quality mid-level customer information, and modify / delete outliers in high-quality mid-level customer information; Extract the feature values ​​from high-quality waist customer information; Data of different dimensions are standardized using the Z-Score standardization model; Generate historical pricing strategies and the company's incentive policies over the years based on pre-processed data, analyze historical pricing strategies and the company's incentive policies over the years to design incentive policies; By using the DDPG strategy optimization algorithm to optimize the incentive policy, the optimal customer incentive plan is generated; The DDPG strategy optimization algorithm is optimized through experience replay, real-time effect feedback, multi-agent learning and reward design optimization.

[0020] See also Figure 1 The second embodiment of the customer acquisition incentive method for the logistics industry in the embodiment of the present invention includes: Obtain high-quality mid-range customer information marked by the system, and extract customer historical order data, cost data, peer market data, competitiveness analysis data, as well as customer payment records and credit data from the high-quality mid-range customer information; Specifically, they include: Obtain high-quality waist customer information marked by the system; Extract customer historical order data from high-quality mid-level customer information, extract order quantity data from customer historical order data, extract timeliness requirement data from customer historical order data, and extract order price data from customer historical order data; Extract cost data from high-quality waist-level customer information, extract transportation cost data from cost data, extract warehousing cost data from cost data, and extract service cost data from cost data; Extract peer market data information from high-quality mid-tier customer information, extract peer price data from peer market data, extract peer timeliness data from peer market data, and extract peer service status data from peer market data; Extract competitiveness analysis data from high-quality mid-tier customer information, extract price information for similar customers from competitiveness analysis data, and extract preferential policy information for similar customers from competitiveness analysis data; Extract customer payment records and credit data information from high-quality mid-level customer information, extract customer payment habit data from customer payment records and credit data information, and extract customer credit history data from customer payment records and credit data information.

[0021] Process high-quality mid-level customer data to generate pre-processed data; Specifically, they include: Remove duplicate data from high-quality mid-level customer information, fill in missing values ​​in high-quality mid-level customer information, and modify / delete outliers in high-quality mid-level customer information; Extract the feature values ​​from high-quality waist customer information; Data of different dimensions are standardized using the Z-Score standardization model; Generate historical pricing strategies and the company's incentive policies over the years based on pre-processed data, analyze historical pricing strategies and the company's incentive policies over the years to design incentive policies; Specific incentive policies include: Discounts based on decreasing order volume: Large customers have high order volumes and low unit costs. You can offer tiered discounts to encourage customers to increase their order volume. For example, you can offer a discount for each additional order volume (e.g., a 5% discount for orders of 1,000 pieces, and a 10% discount for orders of 5,000 pieces).

[0022] Time-priority incentives: For customers who demand high-speed delivery, you can set up additional fees based on time requirements. For example, for next-day delivery or express delivery, you can add an expedited fee to the base price, but if the customer accepts standard delivery, you can offer a more competitive price.

[0023] Long-term partnership rewards: For long-term customers, you can provide rewards by establishing a customer loyalty program. For example, signing a contract of one year or longer can enjoy regular price adjustments, or provide more favorable prices during specific periods of time.

[0024] Provide flexible payment terms: Based on the customer's credit status and order volume, more flexible payment terms can be provided, such as extending the payment period, installment payment, etc., to reduce the customer's financial pressure and promote contract signing.

[0025] Additional service packaging: Packaging some additional services (such as insurance, scheduled delivery, etc.) and offering discounts can not only increase the added value but also improve the overall price level. By using the DDPG strategy optimization algorithm to optimize the incentive policy, the optimal customer incentive plan is generated; The DDPG strategy optimization algorithm is optimized through experience replay, real-time effect feedback, multi-agent learning and reward design optimization.

[0026] See also Figure 1 The third embodiment of the customer acquisition incentive method for the logistics industry in the embodiment of the present invention includes: Obtain high-quality mid-range customer information marked by the system, and extract customer historical order data, cost data, peer market data, competitiveness analysis data, as well as customer payment records and credit data from the high-quality mid-range customer information; Specifically, they include: Obtain high-quality waist customer information marked by the system; Extract customer historical order data from high-quality mid-level customer information, extract order quantity data from customer historical order data, extract timeliness requirement data from customer historical order data, and extract order price data from customer historical order data; Extract cost data from high-quality waist-level customer information, extract transportation cost data from cost data, extract warehousing cost data from cost data, and extract service cost data from cost data; Extract peer market data information from high-quality mid-tier customer information, extract peer price data from peer market data, extract peer timeliness data from peer market data, and extract peer service status data from peer market data; Extract competitiveness analysis data from high-quality mid-tier customer information, extract price information for similar customers from competitiveness analysis data, and extract preferential policy information for similar customers from competitiveness analysis data; Extract customer payment records and credit data information from high-quality mid-level customer information, extract customer payment habit data from customer payment records and credit data information, and extract customer credit history data from customer payment records and credit data information.

[0027] Process high-quality mid-level customer data to generate pre-processed data; Specifically, they include: Remove duplicate data from high-quality mid-level customer information, fill in missing values ​​in high-quality mid-level customer information, and modify / delete outliers in high-quality mid-level customer information; Extract the feature values ​​from high-quality waist customer information; Data of different dimensions are standardized using the Z-Score standardization model; Generate historical pricing strategies and the company's incentive policies over the years based on pre-processed data, analyze historical pricing strategies and the company's incentive policies over the years to design incentive policies; Specific incentive policies include: Discounts based on decreasing order volume: Large customers have high order volumes and low unit costs. You can offer tiered discounts to encourage customers to increase their order volume. For example, you can offer a discount for each additional order volume (e.g., a 5% discount for orders of 1,000 pieces, and a 10% discount for orders of 5,000 pieces).

[0028] Time-priority incentives: For customers who demand high-speed delivery, you can set up additional fees based on time requirements. For example, for next-day delivery or express delivery, you can add an expedited fee to the base price, but if the customer accepts standard delivery, you can offer a more competitive price.

[0029] Long-term partnership rewards: For long-term customers, you can provide rewards by establishing a customer loyalty program. For example, signing a contract of one year or longer can enjoy regular price adjustments, or provide more favorable prices during specific periods of time.

[0030] Provide flexible payment terms: Based on the customer's credit status and order volume, more flexible payment terms can be provided, such as extending the payment period, installment payment, etc., to reduce the customer's financial pressure and promote contract signing.

[0031] Additional service packaging: Packaging some additional services (such as insurance, scheduled delivery, etc.) and offering discounts can not only increase the added value but also improve the overall price level. By using the DDPG strategy optimization algorithm to optimize the incentive policy, the optimal customer incentive plan is generated; Specifically include: The market environment information, competitor pricing information, and historical sales data information are input into the DDPG strategy optimization algorithm as the state layer of the DDPG strategy optimization algorithm; Input the incentive policy into the DDPG strategy optimization algorithm as the action layer of the DDPG strategy optimization algorithm; Generate market reaction information through the reward layer in the DDPG strategy optimization algorithm; Select incentive policies as the optimal customer incentive plan based on market response information.

[0032] The pricing decision problem can usually be viewed as a reinforcement learning problem, where: State: includes historical order data, market demand, competitor pricing, customer behavior, inventory status and other information.

[0033] Action: In pricing decisions, the action is typically choosing a price or discount policy. This is a continuous action space because pricing can be a continuous value (e.g., setting a specific price for a product).

[0034] Reward: Reward is the market response to the chosen pricing strategy and is usually directly related to the company's profits (such as sales revenue, profit margin, etc.).

[0035] Specific applications of the DDPG strategy optimization algorithm in pricing decisions include: State representation: For pricing decisions, information such as market conditions, competitor pricing, and historical sales data can be used as state inputs. For example, state could be order volume over the past few days, price elasticity, and market demand changes.

[0036] Action Representation: An action is the selection of a specific pricing strategy or price. This can be a specific number representing the price setting for a product. Since pricing is typically a continuous value, DDPG is well-suited to handling this continuous action space.

[0037] Rewards can be defined based on the profit generated by a set price. For example, pricing strategies may affect sales volume, customer satisfaction, competitor response, etc., which can directly impact a company's profits.

[0038] The DDPG strategy optimization algorithm is optimized through experience replay, multi-agent learning and reward design optimization.

[0039] Specifically include: Experience replay can help improve sample efficiency. In DDPG, the agent's historical experience (i.e., a four-tuple of state, action, reward, and next state) is stored in a buffer, from which small batches of experience are randomly sampled during training. This helps improve training stability and reduce correlation between samples.

[0040] DDPG uses a target network to stabilize the training process. The parameters of the target network gradually converge to those of the main network during each training session, avoiding excessive fluctuations during gradient updates and improving training stability.

[0041] If pricing decisions are not solely determined by the company itself but are also influenced by multiple competitors, we can consider introducing Multi-agent Reinforcement Learning (MARL). In this scenario, each competitor is an independent agent that interacts and influences each other's decisions.

[0042] The design of rewards for pricing decisions is crucial. Beyond traditional profit-maximization rewards, we can incorporate more factors, such as customer satisfaction, brand recognition, and market share, to make the learning process more aligned with actual business needs.

[0043] The above describes the customer acquisition incentive method for the logistics industry in the embodiment of the present invention. The following describes the customer acquisition incentive device for the logistics industry in the embodiment of the present invention. Figure 2 In the embodiment of the present invention, the customer acquisition incentive device for the logistics industry includes the following for the above embodiment: The customer information acquisition module is used to obtain high-quality mid-range customer information marked by the system, and extract customer historical order data, cost data information, peer market data information, competitiveness analysis data information, as well as customer payment records and credit data information from the high-quality mid-range customer information; Data preprocessing module, used to process high-quality waist customer data and generate preprocessed data; The incentive policy design module is used to generate historical pricing strategies and the company's incentive policies over the years based on preprocessed data, and to analyze historical pricing strategies and the company's incentive policies over the years to design incentive policies; The incentive scheme optimization module is used to optimize the incentive policy by using the DDPG strategy optimization algorithm to generate the optimal customer incentive scheme; The algorithm optimization module is used to optimize the DDPG strategy optimization algorithm through experience replay, real-time effect feedback, multi-agent learning, and reward design optimization.

[0044] above Figure 2 The customer acquisition incentive device for the logistics industry in an embodiment of the present invention is described in detail from the perspective of modular functional entities, and the electronic device in an embodiment of the present invention is described in detail from the perspective of hardware processing.

[0045] Figure 3 Figure 7 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. This electronic device 700 may vary significantly due to different configurations or performance characteristics. It may include one or more processors 710 (e.g., one or more processors), memory 720, and one or more storage media 730 (e.g., one or more storage devices, including RAM, FLASH, etc.) that store application programs 733 or data 732. The memory 720 and storage medium 730 may be either transient or persistent storage. The program stored in the storage medium 730 may include one or more modules (not shown), each of which may include a series of instruction operations on the electronic device 700. Furthermore, the processor 710 may be configured to communicate with the storage medium 730 to execute the series of instruction operations stored in the storage medium 730 on the electronic device 700.

[0046] The electronic device 700 may further include one or more power supplies 740, one or more input / output interfaces 750, and / or one or more operating systems 731, such as FreeRTOS, Android, etc. It will be understood by those skilled in the art that Figure 3 The illustrated electronic device structure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain 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. The computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the steps of a customer acquisition incentive method for the logistics industry.

[0048] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0049] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, mobile device, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[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 above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can 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 customer acquisition incentive method for the logistics industry, characterized in that: The customer acquisition incentive methods for the logistics industry include: Obtain high-quality mid-range customer information marked by the system, and extract customer historical order data, cost data, peer market data, competitiveness analysis data, as well as customer payment records and credit data from the high-quality mid-range customer information; Process high-quality mid-level customer data to generate pre-processed data; Generate historical pricing strategies and the company's incentive policies over the years based on pre-processed data, analyze historical pricing strategies and the company's incentive policies over the years to design incentive policies; By using the DDPG strategy optimization algorithm to optimize the incentive policy, the optimal customer incentive plan is generated; The DDPG strategy optimization algorithm is optimized through experience replay, multi-agent learning and reward design optimization.

2. The customer acquisition incentive method for the logistics industry according to claim 1 is characterized in that: The process of obtaining high-quality mid-level customer information marked by the system and extracting customer historical order data, cost data, peer market data, competitiveness analysis data, and customer payment records and credit data from the high-quality mid-level customer information includes: Obtain high-quality waist customer information marked by the system; Extract customer historical order data from high-quality mid-level customer information, extract order quantity data from customer historical order data, extract timeliness requirement data from customer historical order data, and extract order price data from customer historical order data; Extract cost data from high-quality waist-level customer information, extract transportation cost data from cost data, extract warehousing cost data from cost data, and extract service cost data from cost data; Extract peer market data information from high-quality mid-tier customer information, extract peer price data from peer market data, extract peer timeliness data from peer market data, and extract peer service status data from peer market data; Extract competitiveness analysis data from high-quality mid-tier customer information, extract price information for similar customers from competitiveness analysis data, and extract preferential policy information for similar customers from competitiveness analysis data; Extract customer payment records and credit data information from high-quality mid-level customer information, extract customer payment habit data from customer payment records and credit data information, and extract customer credit history data from customer payment records and credit data information.

3. The customer acquisition incentive method for the logistics industry according to claim 1 is characterized in that: The data processing of high-quality mid-level customer data to generate pre-processed data includes: Remove duplicate data from high-quality mid-level customer information, fill in missing values ​​in high-quality mid-level customer information, and modify / delete outliers in high-quality mid-level customer information; Extract the feature values ​​from high-quality waist customer information; Data of different dimensions are standardized using the Z-Score standardization model.

4. The customer acquisition incentive method for the logistics industry according to claim 1 is characterized in that: The design incentive policies include: Set tiered discounts based on order volume, set prices based on timeliness requirements, set prices based on the length of cooperation, provide different payment terms, and provide additional services.

5. The customer acquisition incentive method for the logistics industry according to claim 1 is characterized in that: The above mentioned method of optimizing the incentive policy by using the DDPG strategy optimization algorithm to generate the optimal customer incentive plan includes: The market environment information, competitor pricing information, and historical sales data information are input into the DDPG strategy optimization algorithm as the state layer of the DDPG strategy optimization algorithm; Input the incentive policy into the DDPG strategy optimization algorithm as the action layer of the DDPG strategy optimization algorithm; Generate market reaction information through the reward layer in the DDPG strategy optimization algorithm; Select incentive policies as the optimal customer incentive plan based on market response information.

6. The customer acquisition incentive method for the logistics industry according to claim 1 is characterized in that: The optimization of the DDPG strategy optimization algorithm through experience replay includes: The agent's historical experience is stored in a buffer, from which small batches of experience are randomly sampled for training. The agent's historical experience is a four-tuple consisting of state, action, reward, and next state.

7. A customer acquisition incentive device for the logistics industry, characterized in that: include: The customer information acquisition module is used to obtain high-quality mid-range customer information marked by the system, and extract customer historical order data, cost data information, peer market data information, competitiveness analysis data information, as well as customer payment records and credit data information from the high-quality mid-range customer information; Data preprocessing module, used to process high-quality waist customer data and generate preprocessed data; The incentive policy design module is used to generate historical pricing strategies and the company's incentive policies over the years based on preprocessed data, and to analyze historical pricing strategies and the company's incentive policies over the years to design incentive policies; The incentive scheme optimization module is used to optimize the incentive policy by using the DDPG strategy optimization algorithm to generate the optimal customer incentive scheme; The algorithm optimization module is used to optimize the DDPG strategy optimization algorithm through experience replay, real-time effect feedback, multi-agent learning, and reward design optimization.

8. An electronic device comprising a memory and at least one processor, wherein the memory stores instructions; The at least one processor calls the instructions in the memory so that the electronic device executes each step of the customer acquisition incentive method for the logistics industry 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 customer acquisition incentive method for the logistics industry as described in any one of claims 1 to 6 are implemented.

Images