Logistics express delivery pick-up mode correction system

Abstract

The invention relates to a logistics express delivery pickup mode correction system, which comprises a data mapping component and a data processing component, the method is used for adopting a deep neural network model to set various associated information of an e-commerce APP in a current city block. The set e-commerce APP intelligently predicts the corresponding return number of the set e-commerce APP in the current time interval relative to the current city block according to a plurality of return related data corresponding to a set number of a plurality of historical time intervals before the current time interval relative to the current city block and the types of sold goods of the set e-commerce APP; and the dynamic correction assembly is used for determining a corresponding return strategy based on the intelligent prediction data. According to the invention, the deep neural network model can be obtained to execute intelligent prediction of the number of returned goods corresponding to the current time interval of the current city block by the set e-commerce APP, and a corresponding goods return strategy is formulated, so that two different requirements of full use and rapid goods return and retrieval of personnel are considered.

Description

Technical Field

[0001] The present invention relates to the field of logistics management, and in particular to a logistics express pickup mode correction system. Background Art

[0002] E-commerce refers to business activities conducted on the Internet. It is a business activity centered on commodity exchange using information network technology as a means; in the macro sense, e-commerce is the second revolution of computer networks, and is a new economic order established through electronic means, involving not only electronic technology and business transactions themselves, but also other social aspects such as finance, taxation, and education. In the micro sense, e-commerce refers to various commercial trade activities conducted by entities with commercial activities using the Internet and advanced digital communication technologies.

[0003] E-commerce companies usually sell all kinds of goods through their own applications, namely APPs. In the sales process, returns due to various reasons are inevitable. When there are fewer returns, e-commerce companies will have delivery personnel take away the returned goods. Only when there are more returns will they arrange fixed return personnel to take back a large number of returned goods. However, the number of returns from e-commerce companies in the future time period cannot be accurately predicted, resulting in the inability of e-commerce companies to implement corresponding return strategies according to local conditions, which can easily lead to delayed returns of returned goods or excessive deployment of return personnel. Summary of the invention

[0004] In order to solve the technical problems in the prior art, the present invention provides a logistics express pickup mode correction system, which can obtain a deep neural network model to perform intelligent prediction of the number of returns corresponding to the current city block in the current time interval of the set e-commerce APP, and when the number of returns corresponding to the current city block in the current time interval of the intelligently predicted set e-commerce APP is greater than the set number limit, a special door-to-door pickup personnel is allocated for the current city block in the current time interval; otherwise, a special door-to-door pickup personnel is not allocated for the current city block in the current time interval, and the delivery personnel of the current city block in the current time interval are set to pick up the goods on the way to the door, thereby taking into account the return needs while realizing full utilization of the limited logistics personnel of the set e-commerce APP.

[0005] The present invention has at least the following main inventive features: Firstly: a dynamic correction component is introduced to allocate special door-to-door pickup personnel for the current city block in the current time interval when the number of returns corresponding to the current city block in the current time interval predicted by the intelligent e-commerce APP is greater than the set number limit; otherwise, no special door-to-door pickup personnel are allocated for the current city block in the current time interval, so that the delivery personnel of the current city block in the current time interval are set to pick up the goods on the way to the door, wherein the number of special door-to-door pickup personnel allocated for the current city block in the current time interval is positively correlated with the number of returns corresponding to the current city block in the current time interval predicted by the intelligent e-commerce APP, thereby taking into account the return demand and making full use of the limited logistics personnel of the set e-commerce APP; Secondly: obtaining a deep neural network model to perform intelligent prediction of the number of returns corresponding to the current city block in the current time interval of the set e-commerce APP, in which the deep neural network is trained continuously for each time to obtain a deep neural network after each training, and the deep neural network after each training is used as the deep neural network model, and the number of times the deep neural network is trained is proportional to the number of types of goods sold by the set e-commerce APP, so as to customize artificial intelligence models with different structures for different set e-commerce APPs; Again: In order to set the intelligent prediction of the number of returns of the e-commerce APP relative to the current city block in the current time interval, a number of sufficient and comprehensive basic data are referenced, including setting various related information of the e-commerce APP in the current city block, setting multiple return-related data corresponding to multiple historical time intervals set before the current time interval of the e-commerce APP relative to the current city block, and setting the types of goods sold by the e-commerce APP, thereby ensuring the reliability and stability of the intelligent prediction results.

[0006] According to the present invention, a logistics express pickup mode correction system is provided, the system comprising: The first parsing mechanism is used to obtain various related information of the set e-commerce APP in the current city block, and the various related information of the set e-commerce APP in the current city block is the number of registered customers of the set e-commerce APP in the current city block, the proportion of young customers, and the geographical area occupied by the current city block; The second parsing mechanism is used to obtain a plurality of return-related data corresponding to a set number of historical time intervals before the current time interval of the set e-commerce APP relative to the current city block, and set the single return-related data corresponding to each historical time interval before the current time interval of the e-commerce APP relative to the current city block as the number of returns and the number of purchases on the set e-commerce APP in the current city block within the said historical time interval; A sequential training mechanism, used to obtain a deep neural network model, in which the deep neural network is trained continuously for each time to obtain a deep neural network after each training, and the deep neural network after each training is used as the deep neural network model, and the number of times the deep neural network is trained is proportional to the number of types of goods sold by the set e-commerce APP; a data mapping component, connected to the first parsing mechanism, the second parsing mechanism and the sequential training mechanism respectively, for using the deep neural network model to intelligently predict the number of returns corresponding to the set e-commerce APP in the current time interval relative to the current city block based on various associated information of the set e-commerce APP in the current city block, multiple sets of return-related data corresponding to multiple historical time intervals of a set number before the current time interval relative to the set e-commerce APP, and the types of goods sold by the set e-commerce APP; A dynamic correction component, connected to the data mapping component, is used to allocate a special door-to-door pickup person for the current city block in the current time interval when the number of returns corresponding to the set e-commerce APP in the current city block in the current time interval predicted by the intelligence is greater than the set number limit; Wherein, when the number of returns corresponding to the current city block in the current time interval of the set e-commerce APP predicted by the intelligent prediction is greater than the set number limit, a special door-to-door pickup personnel is deployed for the current city block in the current time interval, including: the number of special door-to-door pickup personnel deployed for the current city block in the current time interval is positively correlated with the number of returns corresponding to the set e-commerce APP predicted by the intelligent prediction in the current city block in the current time interval; Among them, the dynamic correction component is also used to set up delivery personnel in the current city block within the current time interval to pick up the goods on the way to the door instead of allocating special door-to-door pickup personnel for the current city block in the current time interval when the number of returns corresponding to the set e-commerce APP in the current time interval relative to the current city block is less than or equal to the set number limit. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein: Figure 1 It is a structural block diagram of a logistics express pickup mode correction system according to implementation scheme A of the present invention.

[0008] Figure 2 It is a structural block diagram of the logistics express pickup mode correction system according to implementation scheme B of the present invention.

[0009] Figure 3It is a structural block diagram of the logistics express pickup mode correction system according to the C implementation scheme of the present invention. DETAILED DESCRIPTION

[0010] The implementation scheme of the logistics express pickup mode correction system of the present invention will be described in detail below with reference to the accompanying drawings.

[0011] Figure 1 The structural block diagram of the logistics express pickup mode correction system according to the A embodiment of the present invention is shown, and the system includes: The first parsing mechanism is used to obtain various related information of the set e-commerce APP in the current city block, and the various related information of the set e-commerce APP in the current city block is the number of registered customers of the set e-commerce APP in the current city block, the proportion of young customers, and the geographical area occupied by the current city block; The second parsing mechanism is used to obtain a plurality of return-related data corresponding to a set number of historical time intervals before the current time interval of the set e-commerce APP relative to the current city block, and set the single return-related data corresponding to each historical time interval before the current time interval of the e-commerce APP relative to the current city block as the number of returns and the number of purchases on the set e-commerce APP in the current city block within the said historical time interval; A sequential training mechanism, used to obtain a deep neural network model, in which the deep neural network is trained continuously for each time to obtain a deep neural network after each training, and the deep neural network after each training is used as the deep neural network model, and the number of times the deep neural network is trained is proportional to the number of types of goods sold by the set e-commerce APP; Specifically, a sequential training mechanism is used to obtain a deep neural network model, in which the deep neural network is trained continuously for each time to obtain a deep neural network after each training, and the deep neural network after each training is used as the deep neural network model, and the number of times the deep neural network is trained is proportional to the number of types of goods sold by the set e-commerce APP. The acquisition of the deep neural network model can be completed by using a numerical simulation mode; a data mapping component, connected to the first parsing mechanism, the second parsing mechanism and the sequential training mechanism respectively, for using the deep neural network model to intelligently predict the number of returns corresponding to the set e-commerce APP in the current time interval relative to the current city block based on various associated information of the set e-commerce APP in the current city block, multiple sets of return-related data corresponding to multiple historical time intervals of a set number before the current time interval relative to the set e-commerce APP, and the types of goods sold by the set e-commerce APP; A dynamic correction component, connected to the data mapping component, is used to allocate a special door-to-door pickup person for the current city block in the current time interval when the number of returns corresponding to the set e-commerce APP in the current city block in the current time interval predicted by the intelligence is greater than the set number limit; Wherein, when the number of returns corresponding to the current city block in the current time interval of the set e-commerce APP predicted by the intelligent prediction is greater than the set number limit, a special door-to-door pickup personnel is deployed for the current city block in the current time interval, including: the number of special door-to-door pickup personnel deployed for the current city block in the current time interval is positively correlated with the number of returns corresponding to the set e-commerce APP predicted by the intelligent prediction in the current city block in the current time interval; The dynamic correction component is also used to set the delivery personnel of the current city block in the current time interval to pick up the goods on the way to the door instead of allocating a special door-to-door pickup personnel for the current city block in the current time interval when the number of returns corresponding to the set e-commerce APP in the current city block in the current time interval is less than or equal to the set number limit; Among them, multiple return-related data corresponding to a set number of historical time intervals before the current time interval of the set e-commerce APP relative to the current city block are obtained, and a single return-related data corresponding to each historical time interval before the current time interval of the e-commerce APP relative to the current city block is set as the number of returns and the number of purchases on the set e-commerce APP in the current city block within the said historical time interval, including: the value of the said set number is monotonically positively correlated with the geographical area occupied by the said current city block.

[0012] Figure 2 It is a structural block diagram of the logistics express pickup mode correction system according to implementation scheme B of the present invention.

[0013] Compared with the implementation scheme A, the logistics express pickup mode correction system shown in the implementation scheme B of the present invention may also include: an electric quantity measuring mechanism, connected to the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism, respectively, and used to measure the current electric quantity used by the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism respectively; Wherein, the power measurement mechanism is respectively connected with the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism, and is used to respectively measure the current power usage of the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism, including: the power measurement mechanism includes a plurality of power measurement units, which are respectively connected with the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism, so as to complete the respective measurement of the current power usage of the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism; Wherein, the power measurement mechanism includes a plurality of power measurement units, which are respectively connected to the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism to complete the respective measurement of the current power usage of the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism, including: the plurality of power measurement units are a plurality of power sensing circuits, which are respectively connected to the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism to complete the respective measurement of the current power usage of the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism; Wherein, the plurality of power measurement units are a plurality of power sensing circuits, which are used to be connected to the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism respectively, so as to complete the respective measurement of the current power usage of the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism respectively, including: the structures of the plurality of power sensing circuits are the same; And wherein, the multiple power measurement units are multiple power sensing circuits, which are used to connect to the data mapping component, the first analysis mechanism, the second analysis mechanism and the sequential training mechanism respectively to complete the separate measurement of the current power usage of the data mapping component, the first analysis mechanism, the second analysis mechanism and the sequential training mechanism respectively, and also include: the multiple power sensing circuits have the same power measurement upper limit value and power measurement lower limit value.

[0014] Figure 3 It is a structural block diagram of the logistics express pickup mode correction system according to the C implementation scheme of the present invention.

[0015] Compared with implementation scheme A, the logistics express pickup mode correction system shown in implementation scheme C of the present invention may also include: A fan heat dissipation mechanism is arranged near the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism, and is used to provide the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism with the heat dissipation services they need respectively; Wherein, the fan heat dissipation mechanism is arranged near the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism, and is used to provide the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism with the heat dissipation services required by each of them, including: the fan heat dissipation mechanism includes a plurality of fan heat dissipation units, which are respectively arranged near the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism to provide the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism with the heat dissipation services required by each of them; And wherein, the fan cooling mechanism includes multiple fan cooling units, which are respectively arranged near the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism to provide the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism with their respective required cooling services, including: the rated output power of the multiple fan cooling units is equal.

[0016] In addition, in the logistics express pickup mode correction system, the deep neural network model is used to intelligently predict the number of returns corresponding to the set e-commerce APP relative to the current city block in the current time interval based on various related information of the set e-commerce APP in the current city block, multiple return-related data corresponding to multiple historical time intervals set number before the current time interval relative to the current city block, and the types of goods sold by the set e-commerce APP. The method includes: inputting various related information of the set e-commerce APP in the current city block, multiple return-related data corresponding to multiple historical time intervals set number before the current time interval relative to the current city block, and the types of goods sold by the set e-commerce APP into the deep neural network model in parallel, and executing the deep neural network model to obtain the number of returns corresponding to the set e-commerce APP relative to the current city block in the current time interval output by the deep neural network model.

[0017] The logistics express pickup mode correction system of the present invention is used to address the technical problem in the prior art that e-commerce companies are unable to formulate targeted return personnel arrangement strategies for future time intervals. By acquiring a deep neural network model to execute intelligent prediction of the number of returns corresponding to the current city block in the current time interval of the e-commerce APP, a corresponding return strategy is formulated, thereby taking into account the two different needs of full use of personnel and rapid return and retrieval, thereby solving the above technical problem.

[0018] Those skilled in the art should understand that various improvements can be made to the device disclosed in the above invention without departing from the content of the invention. Therefore, the protection scope of the present invention should be determined by the content of the attached claims.

Claims

1. A logistics express pickup mode correction system, characterized in that: The system comprises: The first parsing mechanism is used to obtain various related information of the set e-commerce APP in the current city block, and the various related information of the set e-commerce APP in the current city block is the number of registered customers of the set e-commerce APP in the current city block, the proportion of young customers, and the geographical area occupied by the current city block; The second parsing mechanism is used to obtain a plurality of return-related data corresponding to a set number of historical time intervals before the current time interval of the set e-commerce APP relative to the current city block, and set the single return-related data corresponding to each historical time interval before the current time interval of the e-commerce APP relative to the current city block as the number of returns and the number of purchases on the set e-commerce APP in the current city block within the said historical time interval; A sequential training mechanism, used to obtain a deep neural network model, in which the deep neural network is trained continuously for each time to obtain a deep neural network after each training, and the deep neural network after each training is used as the deep neural network model, and the number of times the deep neural network is trained is proportional to the number of types of goods sold by the set e-commerce APP; a data mapping component, connected to the first parsing mechanism, the second parsing mechanism and the sequential training mechanism respectively, for using the deep neural network model to intelligently predict the number of returns corresponding to the set e-commerce APP in the current time interval relative to the current city block based on various associated information of the set e-commerce APP in the current city block, multiple sets of return-related data corresponding to multiple historical time intervals of a set number before the current time interval relative to the set e-commerce APP, and the types of goods sold by the set e-commerce APP; A dynamic correction component, connected to the data mapping component, is used to allocate a special door-to-door pickup person for the current city block in the current time interval when the number of returns corresponding to the set e-commerce APP in the current city block in the current time interval predicted by the intelligence is greater than the set number limit; Wherein, when the number of returns corresponding to the current city block in the current time interval of the set e-commerce APP predicted by the intelligent prediction is greater than the set number limit, a special door-to-door pickup personnel is deployed for the current city block in the current time interval, including: the number of special door-to-door pickup personnel deployed for the current city block in the current time interval is positively correlated with the number of returns corresponding to the set e-commerce APP predicted by the intelligent prediction in the current city block in the current time interval; Among them, the dynamic correction component is also used to set up delivery personnel in the current city block within the current time interval to pick up the goods on the way to the door instead of allocating special door-to-door pickup personnel for the current city block in the current time interval when the number of returns corresponding to the set e-commerce APP in the current time interval relative to the current city block is less than or equal to the set number limit.

2. The logistics express pickup mode correction system according to claim 1, characterized in that: Acquire multiple sets of return-related data corresponding to a set number of historical time intervals before the current time interval relative to the current city block of the set e-commerce APP, and set a single set of return-related data corresponding to each historical time interval before the current time interval relative to the current city block of the set e-commerce APP as the number of returns and the number of purchases on the set e-commerce APP of the current city block within the said historical time interval, including: the value of the said set number is monotonically positively correlated with the geographical area occupied by the said current city block.

3. The logistics express pickup mode correction system as claimed in claim 2, characterized in that: The system further comprises: an electric quantity measuring mechanism, connected to the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism, respectively, and used to measure the current electric quantity used by the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism respectively; Among them, the power measurement mechanism is respectively connected to the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism, and is used to respectively measure the current power usage of the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism. The power measurement mechanism includes multiple power measurement units, which are respectively connected to the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism to complete the respective measurements of the current power usage of the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism.

4. The logistics express pickup mode correction system according to claim 3, characterized in that: The power measurement mechanism includes multiple power measurement units, which are used to connect with the data mapping component, the first analysis mechanism, the second analysis mechanism and the sequential training mechanism respectively to complete the separate measurement of the current power usage of the data mapping component, the first analysis mechanism, the second analysis mechanism and the sequential training mechanism respectively. The multiple power measurement units are multiple power sensing circuits, which are used to connect with the data mapping component, the first analysis mechanism, the second analysis mechanism and the sequential training mechanism respectively to complete the separate measurement of the current power usage of the data mapping component, the first analysis mechanism, the second analysis mechanism and the sequential training mechanism respectively.

5. The logistics express pickup mode correction system according to claim 4, characterized in that: The multiple power measurement units are multiple power sensing circuits, which are used to connect to the data mapping component, the first analysis mechanism, the second analysis mechanism and the sequential training mechanism respectively, so as to complete the respective measurements of the current power usage of the data mapping component, the first analysis mechanism, the second analysis mechanism and the sequential training mechanism, including: the structures of the multiple power sensing circuits are the same.

6. The logistics express pickup mode correction system according to claim 5, characterized in that: The multiple power measurement units are multiple power sensing circuits, which are used to connect to the data mapping component, the first analysis mechanism, the second analysis mechanism and the sequential training mechanism respectively to complete the separate measurement of the current power usage of the data mapping component, the first analysis mechanism, the second analysis mechanism and the sequential training mechanism respectively, and also include: the multiple power sensing circuits have the same power measurement upper limit value and power measurement lower limit value.

7. The logistics express pickup mode correction system as claimed in claim 2, characterized in that: The system further comprises: A fan heat dissipation mechanism is arranged near the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism, and is used to provide the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism with the heat dissipation services they need respectively.

8. The logistics express pickup mode correction system according to claim 7, characterized in that: A fan cooling mechanism is arranged near the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism, and is used to provide the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism with the required cooling services respectively. The fan cooling mechanism includes multiple fan cooling units, which are respectively arranged near the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism to provide the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism with the required cooling services respectively.

9. The logistics express pickup mode correction system according to claim 8, characterized in that: The fan cooling mechanism includes multiple fan cooling units, which are respectively arranged near the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism to provide the data mapping component, the first parsing mechanism, the second parsing mechanism and the sequential training mechanism with their respective required cooling services, including: the rated output power of the multiple fan cooling units is equal.

Images