Sales prediction method and device based on logistics center client point mapping

Abstract

The invention provides a sales volume prediction method and device based on logistics center client point location mapping, and belongs to the technical field of sales volume prediction, and the method specifically comprises the steps: a corresponding relation judgment module is responsible for determining a logistics center corresponding to each urban warehouse through employing a mapping table of the logistics centers and the urban warehouses, and determining the corresponding logistics center; the client point location mapping module is responsible for identifying client point locations in charge of each logistics center according to client point location tables of the logistics centers, the performance data analysis module is responsible for acquiring historical performance data of different client point locations in a matched performance table, and the sales prediction module is responsible for predicting the sales of different logistics centers by using a preset algorithm and the historical performance data. The sales volume of the logistics center is trained and predicted, and the accuracy of sales volume prediction processing is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of sales forecasting, and in particular relates to a sales forecasting method and device based on logistics center customer point mapping. Background Art

[0002] Existing sales forecasting methods usually directly count the outbound volume (sales volume) based on the inventory warehouse dimension. However, due to the influence of various human factors such as inventory warehouse switching, inventory scheduling, and new warehouse relocation, the outbound volume data counted by traditional methods cannot accurately reflect the actual needs of users (actual sales volume). This leads to a decrease in prediction accuracy and affects supply chain management and decision-making.

[0003] In order to improve the accuracy of sales forecasts, in the invention patent application CN202311368145.2 "A data processing method, system and storage medium based on a private domain e-commerce platform", through deep data analysis and intelligent prediction, the personalization of product recommendations and the accuracy of sales forecasts will increase user satisfaction, reduce inventory costs, and improve the operating efficiency and profits of merchants. However, there are the following technical problems: The existing technical solutions ignore the sales forecast based on the fulfillment data of users corresponding to the logistics center. There are large differences in the fulfillment data of users in urban warehouses corresponding to different logistics centers, which leads to large differences in the sales data corresponding to the logistics centers. Therefore, if sales forecasts cannot be made based on the fulfillment data of users corresponding to the logistics centers, the accuracy of the forecast results cannot be guaranteed.

[0004] In response to the above technical problems, the present invention provides a sales forecasting method and device based on logistics center customer point mapping. Summary of the invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions: According to one aspect of the present invention, a sales forecasting method and device based on logistics center customer point mapping are provided.

[0006] A sales forecasting device based on customer point mapping of a logistics center, specifically comprising: Correspondence determination module, customer location mapping module, fulfillment data analysis module, sales forecasting module; The corresponding relationship determination module is responsible for determining the logistics center corresponding to each city warehouse by using the mapping table between the logistics center and the city warehouse; The customer point mapping module is responsible for identifying the customer points that each logistics center is responsible for according to the customer point table of the logistics center; The performance data analysis module is responsible for obtaining historical performance data of different customer locations in the matching performance table; The sales forecasting module is responsible for training and forecasting the sales volume of the logistics center using a preset algorithm and the historical fulfillment data.

[0007] A further technical solution is that the preset algorithm adopts the NeuralProphet algorithm.

[0008] On the other hand, the present application provides a sales forecasting method based on logistics center customer point mapping, which is applied to the above-mentioned sales forecasting device based on logistics center customer point mapping, and specifically includes: S1 determines the matching city warehouse of the logistics center based on the correspondence between the logistics center and the city warehouse, and determines the customer change coefficients of different matching city warehouses based on the registered customers of the matching city warehouse of the logistics center within a preset time period. When there is no matching city warehouse whose customer change coefficient does not meet the requirements, proceed to the next step; S2 divides the preset time period into different customer similar time periods according to the customer point data corresponding to different matching city warehouses, and uses the historical delivery data of different customer similar time periods to determine that there are matching city warehouses whose historical delivery data changes do not meet the requirements, and proceeds to the next step; S3 determines the registered customers corresponding to different matching city warehouses based on the mapping relationship of customer locations, and determines the matching user profiles of different registered users based on the analysis results of the historical purchase data and historical browsing data corresponding to different registered customers; S4 predicts the sales data of the logistics center based on the historical purchase data of registered users with different matching user portraits corresponding to the logistics center and the commodity change data corresponding to the matching user portraits.

[0009] The beneficial effects of the present invention are: Based on the analysis results of the historical purchase data and historical browsing data corresponding to different registered customers, the matching user portraits of different registered users are determined, thereby realizing the determination of matching user portraits from both the purchase data and browsing data perspectives, ensuring the accuracy of the evaluation results of the matching user portraits, and laying the foundation for further predicting the sales data of the logistics center based on the matching user portraits of registered users.

[0010] The sales data of the logistics center is predicted and processed based on the historical purchase data of registered users with different matching user portraits corresponding to the logistics center and the commodity change data corresponding to the matching user portraits. This not only takes the historical purchase data of registered users into consideration to realize the prediction and processing of the sales data of the logistics center, but also further combines the commodity change data corresponding to the matching user portraits to realize the consideration of the sales data of the logistics center based on the commodity change situation, thereby ensuring the accuracy of the prediction results of the sales data of the logistics center.

[0011] A further technical solution is that the matching city warehouse of the logistics center is determined according to the city warehouse for which the logistics center is responsible.

[0012] A further technical solution is that the registered customers of the matching city warehouse within a preset time period include registered users of the matching city warehouse on different dates within the preset time period.

[0013] A further technical solution is that the method for determining the customer change coefficient of the matching city warehouse is: Determine the dates corresponding to different registered user intervals based on the registered users of the matching city warehouse of the logistics center within a preset time period; Determine the registered user interval whose number of dates is greater than the preset number of dates based on the number of dates corresponding to different registered user intervals, and use it as the screening user interval; The customer change coefficient of the matching city warehouse is determined according to the number of screened user intervals.

[0014] A further technical solution is that the customer variation coefficient of the matching city warehouse is determined according to a preset variation coefficient corresponding to the number of the screened user intervals.

[0015] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0016] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the accompanying drawings; Figure 1 It is a framework diagram of a sales forecasting device based on customer point mapping in a logistics center; Figure 2 It is a flow chart of a sales forecasting method based on customer point mapping in a logistics center; Figure 3 is a flow chart of a method for determining a customer variation coefficient for matching city warehouses; Figure 4 It is a flow chart of a method for determining a matching user profile of a registered user. DETAILED DESCRIPTION

[0018] The present invention connects an external hardware device through the type-c interface. The device is recognized by the mobile phone as a headset device. The sound of mobile phone calls can be collected through the device and transmitted back to the mobile phone application software. The application software is connected to the cloud AI, and the cloud AI responds to the sound. The response audio is then transmitted back to the external device through the mobile phone application software. The external device provides sound feedback on the mobile phone for the call through the microphone of the headset device.

[0019] To solve the above problems, according to one aspect of the present invention, Figure 1 As shown, a sales forecasting device based on logistics center customer point mapping is provided, which specifically includes: Correspondence determination module, customer location mapping module, fulfillment data analysis module, sales forecasting module; The corresponding relationship determination module is responsible for determining the logistics center corresponding to each city warehouse by using the mapping table between the logistics center and the city warehouse; The customer point mapping module is responsible for identifying the customer points that each logistics center is responsible for according to the customer point table of the logistics center; The performance data analysis module is responsible for obtaining historical performance data of different customer locations in the matching performance table; The sales forecasting module is responsible for training and forecasting the sales volume of the logistics center using a preset algorithm and the historical fulfillment data.

[0020] Furthermore, the preset algorithm adopts the NeuralProphet algorithm.

[0021] In the second aspect, the present application provides a sales forecasting method based on customer location mapping of a logistics center, such as Figure 2 As shown, a sales forecasting device based on logistics center customer point mapping is applied to the above, specifically including: S1 determines the matching city warehouse of the logistics center based on the correspondence between the logistics center and the city warehouse, and determines the customer change coefficients of different matching city warehouses based on the registered customers of the matching city warehouse of the logistics center within a preset time period. When there is no matching city warehouse whose customer change coefficient does not meet the requirements, proceed to the next step; S2 divides the preset time period into different customer similar time periods according to the customer point data corresponding to different matching city warehouses, and uses the historical delivery data of different customer similar time periods to determine that there are matching city warehouses whose historical delivery data changes do not meet the requirements, and proceeds to the next step; S3 determines the registered customers corresponding to different matching city warehouses based on the mapping relationship of customer locations, and determines the matching user profiles of different registered users based on the analysis results of the historical purchase data and historical browsing data corresponding to different registered customers; S4 predicts the sales data of the logistics center based on the historical purchase data of registered users with different matching user portraits corresponding to the logistics center and the commodity change data corresponding to the matching user portraits.

[0022] Furthermore, the matching city warehouse of the logistics center is determined according to the city warehouse for which the logistics center is responsible.

[0023] Specifically, the registered customers of the matching city warehouse within the preset time period include registered users of the matching city warehouse on different dates within the preset time period.

[0024] It should be noted that if Figure 3 As shown, the method for determining the customer change coefficient of the matching city warehouse is: Determine the dates corresponding to different registered user intervals based on the registered users of the matching city warehouse of the logistics center within a preset time period; Determine the registered user interval whose number of dates is greater than the preset number of dates based on the number of dates corresponding to different registered user intervals, and use it as the screening user interval; The customer change coefficient of the matching city warehouse is determined according to the number of screened user intervals.

[0025] Furthermore, the customer variation coefficient of the matching city warehouse is determined according to a preset variation coefficient corresponding to the number of the screened user intervals.

[0026] It can be understood that the value range of the customer change coefficient is between 0 and 1. When the customer change coefficient of the matching city warehouse is greater than the preset coefficient threshold, it is determined that the customer change coefficient of the matching city warehouse does not meet the requirements.

[0027] It should be noted that when there is a matching city warehouse whose customer change coefficient does not meet the requirements, the matching user portrait of the registered user is directly determined.

[0028] Optionally, the method for determining the customer change coefficient of the matching city warehouse is: Determine the number of registered users on different dates based on the registered users of the matching city warehouse of the logistics center within a preset time period; Determine the average of the number of registered users on different dates based on the number of registered users on different dates, and use the average as the number average, and determine the registered user deviation date based on the deviation between the number of registered users and the number average; The customer change coefficient of the matching city warehouse is determined according to the number of deviation dates of registered users.

[0029] Furthermore, the registered user deviation date is a date on which the deviation between the number of registered users and the average number is not within a preset deviation range.

[0030] Optionally, the method for determining the customer change coefficient of the matching city warehouse is: S11 determines the number of registered users on different dates based on the registered users of the matching city warehouse of the logistics center within a preset time period, and divides the different dates into different registered user intervals based on the number of registered users on different dates; Optionally, the above step S11 includes the following contents: S111 determines the number of registered users on different dates based on the registered users of the matching city warehouse of the logistics center within a preset time period, determines the average number of registered users on different dates based on the number of registered users on different dates, and uses the average number as the average number, and determines the registered user deviation date based on the deviation between the number of registered users and the average number; S112: When the number of registered user deviation dates does not meet the requirement, it is determined that the customer change coefficient of the matching city warehouse does not meet the requirement. When the number of registered user deviation dates meets the requirement, the process proceeds to step S113; S113 determines the date quantity deviation coefficient based on the deviation between the number of registered users on different registered user deviation dates and the quantity average value. When the date quantity deviation coefficient does not meet the requirement, it is determined that the customer change coefficient of the matching city warehouse does not meet the requirement. When the date quantity deviation coefficient meets the requirement, the process proceeds to step S114. S114 divides different dates into different registered user intervals according to the number of registered users on different dates.

[0031] S12 determines the date deviation coefficient of different registered user intervals according to the number of dates corresponding to different registered user intervals and the deviation of the number of registered users between different dates; Optionally, the above step S12 includes the following contents: S121: When it is determined that there is no screening user interval based on the number of dates corresponding to different registered user intervals, it is determined that the customer change coefficient of the matching city warehouse does not meet the requirement. If there is a screening user interval, the process proceeds to step S122; S122 obtains the number of screened user intervals. When the number of screened user intervals is greater than the number of preset intervals, it is determined that the customer change coefficient of the matching city warehouse does not meet the requirement. When the number of screened user intervals is not greater than the number of preset intervals, the process proceeds to step S123. S123 determines the date deviation coefficients of different registered user intervals according to the number of dates corresponding to different registered user intervals and the deviation of the number of registered users between different dates. When the date deviation coefficient is greater than the registered user interval with the preset deviation coefficient, the process proceeds to step S124. When there is no registered user interval with the date deviation coefficient greater than the preset deviation coefficient, it is determined that the customer change coefficient of the matching city warehouse does not meet the requirement. S124 When the number of registered user intervals whose date deviation coefficient is greater than the preset deviation coefficient is greater than the preset number of intervals, it is determined that the customer change coefficient of the matching city warehouse does not meet the requirements; when the number of registered user intervals whose date deviation coefficient is greater than the preset deviation coefficient is not greater than the preset number of intervals, proceed to step S13.

[0032] S13 determines the customer change coefficient of the matching city warehouse according to the date deviation coefficients of different registered user intervals.

[0033] Specifically, the preset time period is divided into different customer similar time periods, specifically including: Divide the preset time period into different customer similar time periods based on the customer location data corresponding to different matching city warehouses The number of registered users on different dates in the preset time period is used to divide different dates into different customer similarity time periods.

[0034] It should be noted that the changes in the historical outbound data of the matching city warehouse do not meet the requirements, including: Based on the historical outbound data of customers in similar time periods, determine the historical outbound volume of customers on different dates in similar time periods; Determine the deviation date of the shipment quantity for different customers in a similar time period based on the historical shipment quantity on different dates; The total number of shipment deviation dates is determined based on the shipment deviation dates in similar time periods for different customers, and the total number of shipment deviation dates is used to determine whether changes in the historical shipment data of the matching city warehouse meet the requirements.

[0035] Further, when the total quantity of the shipment deviation date does not meet the requirement, it is determined that the change of the historical shipment data of the matching city warehouse does not meet the requirement.

[0036] In another embodiment, determining that the change in the historical delivery data of the matching city warehouse does not meet the requirements specifically includes: The historical outbound data of the customer in a similar time period is used to determine the historical outbound quantities on different dates in the customer's similar time period. The deviation dates of the outbound quantities in different customer similar time periods are determined based on the historical outbound quantities on different dates. When there is a customer similar time period whose outbound quantity deviation date does not meet the requirements, it is determined that the change in the historical outbound data of the matching city warehouse does not meet the requirements. When the quantity of the deviation date of the outbound quantity of different customers in similar periods is within the preset date quantity range: Determine the total number of shipment deviation dates based on the shipment deviation dates in similar time periods for different customers. When the total number of shipment deviation dates does not meet the requirement, determine that the change in the historical shipment data of the matching city warehouse does not meet the requirement. When the total quantity on the delivery quantity deviation date meets the requirement but is not within the preset quantity range: Determine whether the changes in the historical outbound data of the matching city warehouse meet the requirements; When the total quantity on the delivery quantity deviation date meets the requirement but is within the preset quantity range: When the delivery quantity deviation date in a similar time period of different customers is used to compare the delivery quantity deviation date with the customer's similar time period within the preset date quantity range: The customer similar time period whose delivery quantity deviation date is within the preset date quantity interval is used as the screening time period. When the quantity of the screening time period does not meet the requirement, it is determined that the change of the historical delivery data of the matching city warehouse does not meet the requirement; When the number of screening time periods meets the requirement: Determine the deviation coefficients of different customer similar time periods based on the deviation dates of the shipment quantities in different customer similar time periods and the deviations of the shipment quantities on different dates in the customer similar time periods. When there is a customer similar time period whose deviation coefficient does not meet the requirements, it is determined that the change of the historical shipment data of the matching city warehouse does not meet the requirements. When there is no similar time period for customers whose coefficient of deviation does not meet the requirements: The deviation coefficient of the outbound shipment quantity is determined based on the deviation coefficient of similar time periods for different customers, and the outbound shipment quantity deviation coefficient is used to determine whether the change in the historical outbound shipment data of the matching city warehouse meets the requirements.

[0037] Specifically, Figure 4 As shown, the method for determining the matching user portrait of the registered user is: Determine the number of matches between the purchased goods of the registered user and the goods corresponding to different preset user portraits based on the historical purchase data corresponding to the registered user; Determine the browsed products of the registered user based on the historical browsing data corresponding to the registered user, and determine the matching browsed quantities of products corresponding to different preset user portraits based on the browsed products; The total number of matches is calculated based on the matching browsing number and the matching number, and the matching user portrait of the registered user is determined based on the total number of matches.

[0038] Furthermore, the matched user portrait is a preset user portrait corresponding to the largest total number of matches.

[0039] Optionally, the method for determining the matching user portrait of the registered user is: Determine the number of matches between the purchased goods of the registered user and the goods corresponding to different preset user portraits based on the historical purchase data corresponding to the registered user; Determine the browsed products of the registered user based on the historical browsing data corresponding to the registered user, and determine the matching browsed quantities of products corresponding to different preset user portraits based on the browsed products; A total matching number is calculated based on the matching browsing number and the matching number, and a matching user portrait of the registered user is determined based on the total matching number.

[0040] In another embodiment, the method for determining the matching user portrait of the registered user is: Determine the purchased goods of the registered user by using the historical purchase data corresponding to the registered user, and use the purchase frequency of the purchased goods to screen and determine the purchased goods; Determine the browsed products of the registered user based on the historical browsing data corresponding to the registered user, and filter and determine the browsed products based on the number of views of the browsed products; Matching products are determined based on the matching of the filtered purchased products and the filtered browsed products with the products corresponding to the preset user portrait, and the matching user portrait of the registered user is determined using the number of matching products.

[0041] Furthermore, the preset user portrait with the largest number of matching commodities is used as the matching user portrait of the registered user.

[0042] Optionally, the method for determining the matching user portrait of the registered user is: S31 determines the purchased goods of the registered user based on the historical purchase data corresponding to the registered user, determines the matching purchased goods based on the matching between the purchased goods and the goods corresponding to the preset user portrait, and determines the purchase matching coefficient based on the purchase times of different matching purchased goods; S32 determines the browsed products of the registered user based on the historical browsing data corresponding to the registered user, determines the matching browsed products based on the matching conditions between the browsed products and the products corresponding to the preset user portrait, and determines the browsing matching coefficient based on the browsing times of different matching browsed products; S33 determines a comprehensive matching coefficient based on the purchase matching coefficient and the browsing matching coefficient, and uses the comprehensive matching coefficient to determine a matching user portrait of the registered user.

[0043] Specifically, the forecasting process of the sales volume data of the logistics center specifically includes: According to the historical purchase data of registered users with different matching user portraits corresponding to the logistics center, and combined with the commodity change data corresponding to the matching user portraits, the sales data of the logistics center is predicted and processed. Dividing the registered users into different user profile intervals according to the matching user profiles of different registered users; Using the historical purchase data of registered users corresponding to different user profile intervals, determine the historical purchase volume of registered users corresponding to different user profile intervals, and determine the sales forecast data of different user profile intervals in combination with the change data of matching products corresponding to different user profile intervals; The sales forecast result of the logistics center is determined based on the sales forecast data of different user portrait intervals.

[0044] Optionally, the above step S31 includes the following contents: S311 determines the purchased goods of the registered user based on the historical purchase data corresponding to the registered user, and determines the matching purchased goods based on the matching of the purchased goods with the goods corresponding to the preset user profile. When the number of matching purchased goods is less than the preset number of purchased goods, it is determined that the preset user profile does not belong to the matching user profile. When the number of matching purchased goods is not less than the preset number of purchased goods, the process proceeds to step S312. S312: When the quantity of the matched purchased goods is within the preset purchase goods quantity range, the process proceeds to step S313; when the quantity of the matched purchased goods is not within the preset purchase goods quantity range, the process proceeds to step S314; S313 obtains the purchase times of different matching purchase commodities. When the total purchase times of different matching purchase commodities is less than the preset purchase times threshold, it is determined that the preset user profile does not belong to the matching user profile. When the total purchase times of different matching purchase commodities is not less than the preset purchase times threshold, the process proceeds to step S314. S314 determines a purchase matching coefficient according to the number of purchases of different matching purchase commodities. When the purchase matching coefficient does not meet the requirement, it is determined that the preset user portrait does not belong to the matching user portrait. When the purchase matching coefficient meets the requirement, it proceeds to step S32.

[0045] Optionally, the above step S32 includes the following contents: S321 determines the browsed products of the registered user based on the historical browsing data corresponding to the registered user, and determines the matching browsed products based on the matching between the browsed products and the products corresponding to the preset user portrait. When the purchase matching coefficient is within the preset purchase matching coefficient interval, the process proceeds to step S322; when the purchase matching coefficient is not within the preset purchase matching coefficient interval, the process proceeds to step S324; S322: When the number of matching browsed products is less than the preset number of browsed products, it is determined that the preset user profile does not belong to the matching user profile; when the number of matching browsed products is not less than the preset number of browsed products, the process proceeds to step S323; S323 determines the total number of views based on the number of views of different matching browsed products. When the total number of views is within the preset number of views interval and the number of matching browsed products is within the preset number of products interval, it is determined that the preset user profile does not belong to the matching user profile. When the total number of views is not within the preset number of views interval or the number of matching browsed products is not within the preset number of products interval, the process proceeds to step S324. S324 determines the browsing matching coefficient based on the browsing times of different matching browsing products, and proceeds to step S33.

[0046] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0047] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0048] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A sales forecasting device based on logistics center customer point mapping, characterized in that: Specifically include: Correspondence determination module, customer location mapping module, fulfillment data analysis module, sales volume forecasting module; The corresponding relationship determination module is responsible for determining the logistics center corresponding to each city warehouse by using the mapping table between the logistics center and the city warehouse; The customer point mapping module is responsible for identifying the customer points that each logistics center is responsible for according to the customer point table of the logistics center; The performance data analysis module is responsible for obtaining historical performance data of different customer locations in the matching performance table; The sales forecasting module is responsible for training and forecasting the sales volume of the logistics center using a preset algorithm and the historical fulfillment data.

2. The sales forecasting method based on logistics center customer point mapping as claimed in claim 1, characterized in that: The preset algorithm adopts the NeuralProphet algorithm.

3. A sales forecasting method based on logistics center customer point mapping, applied to a sales forecasting device based on logistics center customer point mapping as claimed in any one of claims 1-2, characterized in that: Specifically include: Based on the correspondence between the logistics center and the city warehouse, the matching city warehouse of the logistics center is determined, and the customer change coefficients of different matching city warehouses are determined based on the registered customers of the matching city warehouse of the logistics center within a preset time period. When there is no matching city warehouse whose customer change coefficient does not meet the requirements, proceed to the next step; The preset time period is divided into different customer similar time periods according to the customer point data corresponding to different matching city warehouses, and when the historical delivery data of different customer similar time periods are used to determine that there are matching city warehouses whose changes in historical delivery data do not meet the requirements, proceed to the next step; Determine the registered customers corresponding to different matching city warehouses based on the mapping relationship of customer locations, and determine the matching user profiles of different registered users based on the analysis results of the historical purchase data and historical browsing data corresponding to different registered customers; The sales volume data of the logistics center is predicted based on the historical purchase data of registered users with different matching user portraits corresponding to the logistics center and the commodity change data corresponding to the matching user portraits.

4. The sales forecasting method based on logistics center customer point mapping as claimed in claim 3 is characterized in that: The matching city warehouse of the logistics center is determined according to the city warehouse that the logistics center is responsible for.

5. The sales forecasting method based on logistics center customer location mapping as claimed in claim 3, characterized in that: The registered customers of the matching city warehouse within the preset time period include registered users of the matching city warehouse on different dates within the preset time period.

6. The sales forecasting method based on logistics center customer point mapping as claimed in claim 3, characterized in that: The method for determining the customer change coefficient of the matching city warehouse is: Determine the dates corresponding to different registered user intervals based on the registered users of the matching city warehouse of the logistics center within a preset time period; Determine the registered user interval whose number of dates is greater than the preset number of dates based on the number of dates corresponding to different registered user intervals, and use it as the screening user interval; The customer change coefficient of the matching city warehouse is determined according to the number of screened user intervals.

7. The sales forecasting method based on logistics center customer point mapping as claimed in claim 6, characterized in that: The customer variation coefficient of the matching city warehouse is determined according to the preset variation coefficient corresponding to the number of the screened user intervals.

8. The sales forecasting method based on logistics center customer location mapping as claimed in claim 3, characterized in that: The method for determining the matching user portrait of the registered user is: Determine the number of matches between the purchased goods of the registered user and the goods corresponding to different preset user portraits based on the historical purchase data corresponding to the registered user; Determine the browsed products of the registered user based on the historical browsing data corresponding to the registered user, and determine the matching browsed quantities of products corresponding to different preset user portraits based on the browsed products; A total matching number is calculated based on the matching browsing number and the matching number, and a matching user portrait of the registered user is determined based on the total matching number.

9. The sales forecasting method based on logistics center customer location mapping as claimed in claim 8, characterized in that: The matching user portrait is the preset user portrait corresponding to the largest total number of matches.

10. The sales forecasting method based on logistics center customer location mapping according to claim 1, characterized in that: The forecasting process of the sales volume data of the logistics center specifically includes: Dividing the registered users into different user profile intervals according to the matching user profiles of different registered users; Using the historical purchase data of registered users corresponding to different user profile intervals, determine the historical purchase volume of registered users corresponding to different user profile intervals, and determine the sales forecast data of different user profile intervals in combination with the change data of matching products corresponding to different user profile intervals; The sales forecast result of the logistics center is determined based on the sales forecast data of different user portrait intervals.

Images