Intelligent logistics route cost prediction system

Abstract

The present invention relates to an intelligent logistics route cost prediction system, comprising: a model application device, which intelligently predicts the number of logistics pieces and the total logistics cost of the current logistics route in the future time segment of the day based on the route mileage of the current logistics route, the number of each adjacent logistics route and each past simultaneous information; an information transmission device, which wirelessly transmits the intelligent prediction result together with the future time segment of the day to a logistics management server. The intelligent logistics route cost prediction system of the present invention is intelligent in operation and widely used. Since a feedforward neural network model can be used to intelligently predict the number of logistics pieces and the total logistics cost of the current logistics route in the future time segment of the day based on the logistics cost information of each past time segment of the past days that is simultaneous with the future time segment of the day, the route mileage of the current logistics route and the number of each adjacent logistics route, reliable resource allocation information is provided for the management of logistics operators.

Description

Technical Field

[0001] The present invention relates to the field of logistics management, and in particular to an intelligent logistics route cost prediction system. Background Art

[0002] The "object" in logistics refers to the part of the material world that has the characteristics of a material entity and can be physically displaced. "Flow" is physical movement, which has a limited meaning. It is the physical movement relative to the earth with the earth as the reference system, which is called "displacement". The scope of flow can be a large geographical range, or it can be a microscopic movement and small-scale displacement in the same region and environment. The combination of "object" and "flow" is a high-level form of movement based on natural movement. The mutual connection is to find the law of movement between economic purposes and physical objects, between military purposes and physical objects, and even between certain social purposes and physical objects.

[0003] However, when it comes to each logistics route, it is impossible to predict the number of logistics pieces and the total logistics costs of the logistics route in the future time segments of the day, and thus it is impossible to provide valuable reference information in advance for the operation management and resource allocation of the logistics operator. For example, the logistics operator cannot determine how many transport vehicles and logistics personnel will be needed to match the number of logistics pieces and the total logistics costs in the future time segments of the day for the logistics route. Summary of the invention

[0004] In order to overcome the technical problems in the prior art, the present invention proposes an intelligent logistics route cost prediction system, which can determine the adjacent logistics routes that intersect with the current logistics route based on the positioning data of various locations along the current logistics route, and adopt a feedforward neural network model with targeted structural design to intelligently predict the number of logistics pieces and the total logistics cost of the current logistics route in the future time segment of the day based on the logistics cost information of each past time segment of the past days that is simultaneous with the future time segment of the day, the route mileage of the current logistics route and the number of adjacent logistics routes, thereby providing valuable reference information in advance for the operation management and resource allocation of logistics operators.

[0005] According to the present invention, an intelligent logistics route cost prediction system is provided, the system comprising:

[0006] A geographic analysis device, used to obtain positioning data of various locations along the current logistics route, and determine various neighboring logistics routes that intersect with the current logistics route based on the positioning data of various locations along the current logistics route;

[0007] The simultaneous detection device is used to take the future time segment of the current day as the target time segment, and output the past logistics information corresponding to the past time segments of the current logistics route in the same time segment as the target time segment on the days before the current day as the past simultaneous information;

[0008] A multiple learning device, used for performing multiple learning actions on the feedforward neural network to obtain the feedforward neural network after multiple learning actions and output it as a feedforward neural network model, wherein the number of learning actions of the feedforward neural network is proportional to the number of adjacent logistics routes;

[0009] A model application device, connected to the multiple learning device, the simultaneous detection device and the geographic analysis device, respectively, for synchronously inputting the route mileage of the current logistics route, the number of each adjacent logistics route and each piece of past simultaneous information into the feedforward neural network model, and executing the feedforward neural network model to obtain the number of logistics pieces and the total logistics cost of the current logistics route in the future time segment of the day output by the feedforward neural network model;

[0010] An information transmission device, connected to the model application device, for wirelessly transmitting the number of logistics pieces and the total logistics cost of the current logistics route in the future time segment of the day output by the feedforward neural network model together with the future time segment of the day to a remote logistics management server;

[0011] The future time segment of the day is taken as the target time segment, and the past logistics information corresponding to the past time segments of the current logistics route on the days before the day that are in the same time segment as the target time segment is output as the past simultaneous information, including: the past logistics information corresponding to the past time segment of the current logistics route on a certain day before the day that is in the same time segment as the target time segment is the number of logistics pieces and the total amount of logistics costs in the past time segment of the current logistics route on a certain day before the day that is in the same time segment as the target time segment;

[0012] The future time segment of the day is taken as the target time segment, and the past logistics information corresponding to each past time segment of the current logistics route in the same time segment as the target time segment on each day before the day is output as each past simultaneous information, including: the number of days before the day is positively correlated with the route mileage of the current logistics route;

[0013] Among them, obtaining the positioning data of various points along the current logistics route, and determining the adjacent logistics routes that intersect with the current logistics route based on the positioning data of various points along the current logistics route includes: when the positioning data of various points along a certain logistics route has numerical matching positioning data with the positioning data of various points along the current logistics route, judging that the certain logistics route belongs to a single adjacent logistics route that intersects with the current logistics route.

[0014] It can be seen that the present invention has at least the following important invention points:

[0015] Important invention point 1: Based on the positioning data of various locations along the current logistics route, each adjacent logistics route that intersects with the current logistics route is determined. Specifically, when the positioning data of various locations along a certain logistics route has numerical matching positioning data with the positioning data of various locations along the current logistics route, it is determined that the certain logistics route belongs to a single adjacent logistics route that intersects with the current logistics route.

[0016] The second important invention point: performing multiple learning actions on the feedforward neural network to obtain a feedforward neural network after multiple learning actions and outputting it as a feedforward neural network model, wherein the number of learning actions of the feedforward neural network is proportional to the number of adjacent logistics routes, thereby designing feedforward neural network models with different structures for different current logistics routes;

[0017] Important invention point three: A feedforward neural network model with targeted structural design intelligently predicts the number of logistics pieces and the total logistics costs of the current logistics route in the future time segment of the day based on the logistics cost information of each past time segment of the past days that is simultaneous with the future time segment of the day, the route mileage of the current logistics route, and the number of adjacent logistics routes, thereby providing valuable reference information in advance for the operation management and resource allocation of logistics operators.

[0018] The intelligent logistics route cost prediction system of the present invention is intelligent in operation and widely used. Since it can adopt a feedforward neural network model to intelligently predict the number of logistics pieces and the total logistics cost of the current logistics route in the future time segment of the day based on the logistics cost information of each past time segment of the past days that is simultaneous with the future time segment of the day, the route mileage of the current logistics route and the number of each adjacent logistics route, it can provide reliable resource allocation information for the management of logistics operators. DETAILED DESCRIPTION

[0019] The implementation scheme of the intelligent logistics route cost prediction system of the present invention will be described in detail below.

[0020] The intelligent logistics route cost prediction system shown in Embodiment 1 of the present invention includes:

[0021] A geographic analysis device, used to obtain positioning data of various locations along the current logistics route, and determine various neighboring logistics routes that intersect with the current logistics route based on the positioning data of various locations along the current logistics route;

[0022] Specifically, the geographic analysis device is used to obtain the positioning data of various locations along the current logistics route, and determine various neighboring logistics routes that intersect with the current logistics route based on the positioning data of various locations along the current logistics route, including: the positioning data of various locations along the current logistics route is Galileo navigation data or Beidou navigation data;

[0023] The simultaneous detection device is used to take the future time segment of the current day as the target time segment, and output the past logistics information corresponding to the past time segments of the current logistics route in the same time segment as the target time segment on the days before the current day as the past simultaneous information;

[0024] A multiple learning device, used for performing multiple learning actions on the feedforward neural network to obtain the feedforward neural network after multiple learning actions and output it as a feedforward neural network model, wherein the number of learning actions of the feedforward neural network is proportional to the number of adjacent logistics routes;

[0025] A model application device, connected to the multiple learning device, the simultaneous detection device and the geographic analysis device, respectively, for synchronously inputting the route mileage of the current logistics route, the number of each adjacent logistics route and each piece of past simultaneous information into the feedforward neural network model, and executing the feedforward neural network model to obtain the number of logistics pieces and the total logistics cost of the current logistics route in the future time segment of the day output by the feedforward neural network model;

[0026] An information transmission device, connected to the model application device, for wirelessly transmitting the number of logistics pieces and the total logistics cost of the current logistics route in the future time segment of the day output by the feedforward neural network model together with the future time segment of the day to a remote logistics management server;

[0027] The future time segment of the day is taken as the target time segment, and the past logistics information corresponding to the past time segments of the current logistics route on the days before the day that are in the same time segment as the target time segment is output as the past simultaneous information, including: the past logistics information corresponding to the past time segment of the current logistics route on a certain day before the day that is in the same time segment as the target time segment is the number of logistics pieces and the total amount of logistics costs in the past time segment of the current logistics route on a certain day before the day that is in the same time segment as the target time segment;

[0028] The future time segment of the day is taken as the target time segment, and the past logistics information corresponding to each past time segment of the current logistics route in the same time segment as the target time segment on each day before the day is output as each past simultaneous information, including: the number of days before the day is positively correlated with the route mileage of the current logistics route;

[0029] Wherein, obtaining the positioning data of various locations along the current logistics route, and determining various adjacent logistics routes that intersect with the current logistics route based on the positioning data of various locations along the current logistics route includes: when there is positioning data with numerical matching between the positioning data of various locations along a certain logistics route and the positioning data of various locations along the current logistics route, judging that the certain logistics route belongs to a single adjacent logistics route that intersects with the current logistics route;

[0030] Among them, obtaining the positioning data of various points along the current logistics route, and determining the adjacent logistics routes that intersect with the current logistics route based on the positioning data of various points along the current logistics route also includes: the positioning data of various points along the current logistics route is the navigation positioning data of various points along the current logistics route.

[0031] Compared with the first embodiment of the present invention, the intelligent logistics route cost prediction system shown in the second embodiment of the present invention may also include the following components:

[0032] A synchronous driving device, which is arranged near the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device and is connected to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively;

[0033] Among them, the synchronous driving device is arranged near the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device and is respectively connected to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device, including: the synchronous driving device is used to respectively realize the synchronous driving control of each of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device.

[0034] Compared with the first embodiment of the present invention, the intelligent logistics route cost prediction system shown in the third embodiment of the present invention may also include the following components:

[0035] A circuit supply device is arranged near the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device and is connected to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively;

[0036] Among them, the circuit supply device is arranged near the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device and is respectively connected to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device, including: the circuit supply device is used to provide the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device with the required working voltage values ​​respectively.

[0037] Next, the specific structure of the intelligent logistics route cost prediction system of the present invention will be further described.

[0038] In the intelligent logistics route cost prediction system according to any embodiment of the present invention:

[0039] An ASIC chip is used to perform image data processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively.

[0040] In the intelligent logistics route cost prediction system according to any embodiment of the present invention:

[0041] Using an ASIC chip to perform image data processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain the output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively includes: performing maximum value filtering processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain the output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively.

[0042] In the intelligent logistics route cost prediction system according to any embodiment of the present invention:

[0043] Using an ASIC chip to perform image data processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain the output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively includes: performing minimum value filtering processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain the output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively.

[0044] In the intelligent logistics route cost prediction system according to any embodiment of the present invention:

[0045] Using an ASIC chip to perform image data processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain the output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively includes: performing median filtering processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain the output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively.

[0046] And in the intelligent logistics route cost prediction system according to any embodiment of the present invention:

[0047] Using an ASIC chip to perform image data processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain the output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively includes: performing edge sharpening processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain the output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively.

[0048] In addition, in the intelligent logistics route cost prediction system, the future time segment of the day is taken as the target time segment, and the past logistics information corresponding to each past time segment of the current logistics route in the same time segment as the target time segment on the days before the day is taken as each past simultaneous information output also includes: using a numerical mapping formula to represent the numerical mapping relationship of the positive correlation between the number of days before the day and the route mileage of the current logistics route.

[0049] The above embodiments are merely examples for implementing the present invention, and the present invention is not limited thereto. Various modifications to these embodiments are within the scope of the present invention. It can be understood from the above contents that various other embodiments are possible within the scope of the present invention.

Claims

1. An intelligent logistics route cost prediction system, characterized in that: The system comprises: A geographic analysis device, used to obtain positioning data of various locations along the current logistics route, and determine various neighboring logistics routes that intersect with the current logistics route based on the positioning data of various locations along the current logistics route; The simultaneous detection device is used to take the future time segment of the current day as the target time segment, and output the past logistics information corresponding to the past time segments of the current logistics route in the same time segment as the target time segment on the days before the current day as the past simultaneous information; A multiple learning device, used for performing multiple learning actions on the feedforward neural network to obtain the feedforward neural network after multiple learning actions and output it as a feedforward neural network model, wherein the number of learning actions of the feedforward neural network is proportional to the number of adjacent logistics routes; A model application device, connected to the multiple learning device, the simultaneous detection device and the geographic analysis device, respectively, for synchronously inputting the route mileage of the current logistics route, the number of each adjacent logistics route and each piece of past simultaneous information into the feedforward neural network model, and executing the feedforward neural network model to obtain the number of logistics pieces and the total logistics cost of the current logistics route in the future time segment of the day output by the feedforward neural network model; An information transmission device, connected to the model application device, for wirelessly transmitting the number of logistics pieces and the total logistics cost of the current logistics route in the future time segment of the day output by the feedforward neural network model together with the future time segment of the day to a remote logistics management server; The future time segment of the day is taken as the target time segment, and the past logistics information corresponding to the past time segments of the current logistics route on the days before the day that are in the same time segment as the target time segment is output as the past simultaneous information, including: the past logistics information corresponding to the past time segment of the current logistics route on a certain day before the day that is in the same time segment as the target time segment is the number of logistics pieces and the total amount of logistics costs in the past time segment of the current logistics route on a certain day before the day that is in the same time segment as the target time segment; The future time segment of the day is taken as the target time segment, and the past logistics information corresponding to each past time segment of the current logistics route in the same time segment as the target time segment on each day before the day is output as each past simultaneous information, including: the number of days before the day is positively correlated with the route mileage of the current logistics route; Wherein, a numerical mapping formula is used to represent a numerical mapping relationship of the number of days before the current day and the route mileage of the current logistics route in a positive correlation; Wherein, obtaining the positioning data of various locations along the current logistics route, and determining various adjacent logistics routes that intersect with the current logistics route based on the positioning data of various locations along the current logistics route includes: when there is positioning data with numerical matching between the positioning data of various locations along a certain logistics route and the positioning data of various locations along the current logistics route, judging that the certain logistics route belongs to a single adjacent logistics route that intersects with the current logistics route; Acquiring the positioning data of various points along the current logistics route, and determining the adjacent logistics routes that intersect with the current logistics route based on the positioning data of various points along the current logistics route also includes: the positioning data of various points along the current logistics route is the navigation positioning data of various points along the current logistics route.

2. The intelligent logistics route cost prediction system according to claim 1, characterized in that: The system further comprises: A synchronous driving device, which is arranged near the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device and is connected to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively; Among them, the synchronous driving device is arranged near the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device and is respectively connected to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device, including: the synchronous driving device is used to respectively realize the synchronous driving control of each of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device.

3. The intelligent logistics route cost prediction system according to claim 1, characterized in that: The system further comprises: A circuit supply device is arranged near the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device and is connected to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively; Among them, the circuit supply device is arranged near the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device and is respectively connected to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device, including: the circuit supply device is used to provide the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device with the required working voltage values ​​respectively.

4. The intelligent logistics route cost prediction system according to any one of claims 1 to 3, characterized in that: An ASIC chip is used to perform image data processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively.

5. The intelligent logistics route cost prediction system according to claim 4, characterized in that: Using an ASIC chip to perform image data processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain the output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively includes: performing maximum value filtering processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain the output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively.

6. The intelligent logistics route cost prediction system according to claim 4, characterized in that: Using an ASIC chip to perform image data processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain the output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively includes: performing minimum value filtering processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain the output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively.

7. The intelligent logistics route cost prediction system according to claim 4, characterized in that: Using an ASIC chip to perform image data processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain the output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively includes: performing median filtering processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain the output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively.

8. The intelligent logistics route cost prediction system according to claim 4, characterized in that: Using an ASIC chip to perform image data processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain the output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively includes: performing edge sharpening processing on the output data of the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device to obtain the output processing data corresponding to the model application device, the multiple learning device, the simultaneous detection device and the geographic analysis device respectively.