CN116205315A - Method and device for predicting arrival time of shipping bill - Google Patents
Method and device for predicting arrival time of shipping bill Download PDFInfo
- Publication number
- CN116205315A CN116205315A CN202111442553.9A CN202111442553A CN116205315A CN 116205315 A CN116205315 A CN 116205315A CN 202111442553 A CN202111442553 A CN 202111442553A CN 116205315 A CN116205315 A CN 116205315A
- Authority
- CN
- China
- Prior art keywords
- waybill
- predicted
- stage
- determining
- quantile
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a method and a device for predicting the arrival time of a shipping bill, wherein the shipping process of the shipping bill comprises a first stage and a second stage, and the method for predicting the arrival time of the shipping bill comprises the following steps: acquiring a first to-be-predicted waybill; determining a first-stage predicted arrival time of the first to-be-predicted waybill according to the first to-be-predicted waybill and a plurality of first historical waybill samples; updating the first to-be-predicted waybill according to the first stage predicted delivery time to obtain a second to-be-predicted waybill; determining second-stage prediction delivery time of the second to-be-predicted waybill according to the second to-be-predicted waybill and a plurality of second historical waybill samples; and determining the predicted arrival time of the target waybill according to the predicted arrival time of the second stage. The method and the device can improve the accuracy of the method for predicting the delivery time of the delivery bill.
Description
Technical Field
The application mainly relates to the technical field of big data, in particular to a method and a device for predicting delivery time of a delivery bill.
Background
When a user places an order, a general logistics company supports promise of a predicted delivery time to the user, namely promise aging. The achievement rate of the promised time of the product and the overlarge difference between the promised time and the actual dispatch time can cause customer complaints and reduce user experience. The existing promised aging is promised aging based on 80% of the historical achievement rate of coarse granularity of administrative areas, and the administrative areas are too large to reflect aging differences among sites. Problems in the existing mode: the promised aging of the granularity of the administrative area ensures the achievement rate of 80 percent, but the administrative area is too large to embody the aging difference among finer granularity (such as network points); in the general scheme, the process from the start of user order to the end of user hand delivery is used as a whole blurring process, and an intermediate link cannot be embodied, so that the delivery time accuracy is low.
That is, the accuracy of the method for predicting the arrival time of the delivery bill in the prior art is not high.
Disclosure of Invention
The application provides a method and a device for predicting delivery time of a delivery bill, and aims to solve the problem that the accuracy of the method for predicting delivery time of the delivery bill is low in the prior art.
In a first aspect, the present application provides a method for predicting a delivery time of a waybill, where a delivery process of the waybill includes a first stage and a second stage, and the method for predicting the delivery time of the waybill includes:
acquiring a first to-be-predicted waybill;
determining a first-stage predicted arrival time of the first to-be-predicted waybill according to the first to-be-predicted waybill and a plurality of first historical waybill samples;
updating the first to-be-predicted waybill according to the first stage predicted arrival time to obtain a second to-be-predicted waybill;
determining second-stage predicted delivery time of the second to-be-predicted waybill according to the second to-be-predicted waybill and a plurality of second historical waybill samples;
and determining the predicted arrival time of the target waybill according to the predicted arrival time of the second stage.
Optionally, the determining the first stage predicted arrival time of the first to-be-predicted waybill according to the first to-be-predicted waybill and the plurality of first historical waybill samples includes:
Acquiring a first stage starting time of the first to-be-predicted waybill;
acquiring the plurality of first historical waybill samples matched with the first stage start time;
and determining a first-stage predicted delivery time of the first to-be-predicted waybill according to the first to-be-predicted waybill and the plurality of first historical waybill samples.
Optionally, the determining the first stage predicted arrival time of the first to-be-predicted waybill according to the first to-be-predicted waybill and the plurality of first historical waybill samples includes:
obtaining a preset target achievement rate;
determining a first quantile parameter and a second quantile parameter according to the preset target achievement rate;
determining a first-stage predicted arrival time of the first to-be-predicted waybill according to the first quantile parameter, the first to-be-predicted waybill and a plurality of first historical waybill samples;
the determining the second stage prediction arrival time of the second to-be-predicted waybill according to the second to-be-predicted waybill and a plurality of second historical waybill samples comprises:
and determining second-stage predicted delivery time of the second to-be-predicted waybill according to the second quantile parameter, the second to-be-predicted waybill and a plurality of second historical waybill samples.
Optionally, the determining the first stage predicted arrival time of the first to-be-predicted waybill according to the first quantile parameter, the first to-be-predicted waybill and the plurality of first historical waybill samples includes:
calculating the waybill similarity of the first to-be-predicted waybill and the plurality of first historical waybill samples respectively;
placing a first historical waybill sample with the similarity to the first to-be-predicted waybill higher than the preset similarity into a waybill set;
acquiring a target waybill sample from the waybill set according to the first quantile parameter;
and determining the first-stage real-time delivery time of the target waybill sample as the first-stage predicted delivery time of the first to-be-predicted waybill.
Optionally, the calculating the waybill similarity of the first to-be-predicted waybill and the plurality of first historical waybill samples respectively includes:
acquiring a waybill feature vector of the first to-be-predicted waybill and a waybill feature vector of the first historical waybill sample, wherein the waybill feature vector comprises a waybill space feature, a waybill time feature and a waybill attribute feature;
and carrying out vector similarity calculation according to the waybill feature vector of the first to-be-predicted waybill and the waybill feature vector of the first historical waybill sample to obtain the waybill similarity.
Optionally, the determining the first quantile parameter and the second quantile parameter according to the preset target achievement rate includes:
obtaining a plurality of candidate quantile parameter combinations and a training set according to the preset target achievement rate, wherein each candidate quantile parameter combination comprises a first-stage candidate quantile parameter and a second-stage candidate quantile parameter, and the training set comprises a plurality of training samples and the real time of arrival of the waybill of each training sample;
carrying out delivery time prediction on each training sample in the training set according to the candidate quantile parameter combinations to obtain the waybill prediction delivery time of each training sample;
determining a plurality of prediction effect index values corresponding to a plurality of candidate quantile parameter combinations according to the waybill prediction delivery time of each training sample and the waybill real delivery time of each training sample;
and determining the candidate quantile parameter combination corresponding to the predictive effect index value meeting the preset condition as the first quantile parameter and the second quantile parameter.
Optionally, the obtaining a plurality of candidate quantile parameter combinations and training sets according to the preset target achievement rate includes:
Determining quantile reference parameters according to the preset target achievement rate and the stage number of the conveying process;
determining a quantile value range according to the quantile reference parameter, wherein the value of the quantile value range is not larger than the quantile reference parameter;
and obtaining a plurality of quantile parameters from the quantile value range according to a preset step length, and combining to obtain a plurality of candidate quantile parameter combinations.
In a second aspect, the present application provides a device for predicting a delivery time of a waybill, a delivery process of the waybill includes a first stage and a second stage, and the device for predicting the delivery time of the waybill includes:
the system comprises an acquisition unit, a prediction unit and a prediction unit, wherein the acquisition unit is used for acquiring a first to-be-predicted waybill;
the first determining unit is used for determining a first stage prediction delivery time of the first to-be-predicted waybill according to the first to-be-predicted waybill and a plurality of first historical waybill samples;
the updating unit is used for updating the first to-be-predicted freight list according to the first-stage predicted delivery time to obtain a second to-be-predicted freight list;
the second determining unit is used for determining second-stage predicted delivery time of the second to-be-predicted waybill according to the second to-be-predicted waybill and a plurality of second historical waybill samples;
And the third determining unit is used for determining the predicted delivery time of the target waybill according to the predicted delivery time of the second stage.
Optionally, the first determining unit is configured to:
acquiring a first stage starting time of the first to-be-predicted waybill;
acquiring the plurality of first historical waybill samples matched with the first stage start time;
and determining a first-stage predicted delivery time of the first to-be-predicted waybill according to the first to-be-predicted waybill and the plurality of first historical waybill samples.
Optionally, the first determining unit is configured to:
obtaining a preset target achievement rate;
determining a first quantile parameter and a second quantile parameter according to the preset target achievement rate;
determining a first-stage predicted arrival time of the first to-be-predicted waybill according to the first quantile parameter, the first to-be-predicted waybill and a plurality of first historical waybill samples;
the second determining unit is configured to:
and determining second-stage predicted delivery time of the second to-be-predicted waybill according to the second quantile parameter, the second to-be-predicted waybill and a plurality of second historical waybill samples.
Optionally, the first determining unit is configured to:
Calculating the waybill similarity of the first to-be-predicted waybill and the plurality of first historical waybill samples respectively;
placing a first historical waybill sample with the similarity to the first to-be-predicted waybill higher than the preset similarity into a waybill set;
acquiring a target waybill sample from the waybill set according to the first quantile parameter;
and determining the first-stage real-time delivery time of the target waybill sample as the first-stage predicted delivery time of the first to-be-predicted waybill.
Optionally, the first determining unit is configured to:
acquiring a waybill feature vector of the first to-be-predicted waybill and a waybill feature vector of the first historical waybill sample, wherein the waybill feature vector comprises a waybill space feature, a waybill time feature and a waybill attribute feature;
and carrying out vector similarity calculation according to the waybill feature vector of the first to-be-predicted waybill and the waybill feature vector of the first historical waybill sample to obtain the waybill similarity.
Optionally, the first determining unit is configured to:
obtaining a plurality of candidate quantile parameter combinations and a training set according to the preset target achievement rate, wherein each candidate quantile parameter combination comprises a first-stage candidate quantile parameter and a second-stage candidate quantile parameter, and the training set comprises a plurality of training samples and the real time of arrival of the waybill of each training sample;
Carrying out delivery time prediction on each training sample in the training set according to the candidate quantile parameter combinations to obtain the waybill prediction delivery time of each training sample;
determining a plurality of prediction effect index values corresponding to a plurality of candidate quantile parameter combinations according to the waybill prediction delivery time of each training sample and the waybill real delivery time of each training sample;
and determining the candidate quantile parameter combination corresponding to the predictive effect index value meeting the preset condition as the first quantile parameter and the second quantile parameter.
Optionally, the first determining unit is configured to:
determining quantile reference parameters according to the preset target achievement rate and the stage number of the conveying process;
determining a quantile value range according to the quantile reference parameter, wherein the value of the quantile value range is not larger than the quantile reference parameter;
and obtaining a plurality of quantile parameters from the quantile value range according to a preset step length, and combining to obtain a plurality of candidate quantile parameter combinations.
In a third aspect, the present application provides a computer device comprising:
one or more processors;
A memory; and
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the method of predicting a delivery arrival time of a manifest of any one of the first aspects.
In a fourth aspect, the present application provides a computer readable storage medium storing a plurality of instructions adapted to be loaded by a processor to perform the steps in the method of predicting a waybill delivery time of any one of the first aspects.
The application provides a method and a device for predicting the arrival time of a shipping bill, wherein the shipping process of the shipping bill comprises a first stage and a second stage, and the method for predicting the arrival time of the shipping bill comprises the following steps: acquiring a first to-be-predicted waybill; determining a first-stage predicted arrival time of the first to-be-predicted waybill according to the first to-be-predicted waybill and a plurality of first historical waybill samples; updating the first to-be-predicted waybill according to the first stage predicted delivery time to obtain a second to-be-predicted waybill; determining second-stage prediction delivery time of the second to-be-predicted waybill according to the second to-be-predicted waybill and a plurality of second historical waybill samples; and determining the predicted arrival time of the target waybill according to the predicted arrival time of the second stage. According to the method, the transportation process of the bill is divided into at least two stages, namely the first stage and the second stage, the first stage prediction arrival time is predicted according to the first to-be-predicted bill and the historical data, the first to-be-predicted bill is updated according to the predicted first stage prediction arrival time, the second to-be-predicted bill is obtained, and the second stage prediction arrival time is predicted according to the second to-be-predicted bill and the historical data.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic view of a scenario of a system for predicting delivery time of a bill according to an embodiment of the present application;
FIG. 2 is a flow chart of one embodiment of a method for predicting a delivery time of a manifest provided in an embodiment of the present application;
FIG. 3 is a flowchart of another embodiment of a method for predicting a delivery time of a bill provided in an embodiment of the present application;
FIG. 4 is a schematic structural diagram of an embodiment of a device for predicting arrival time of a bill provided in an embodiment of the present application;
fig. 5 is a schematic structural diagram of one embodiment of a computer device provided in an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
In the description of the present application, it should be understood that the terms "center," "longitudinal," "transverse," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate an orientation or positional relationship based on that shown in the drawings, merely for convenience of description and to simplify the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be configured and operated in a particular orientation, and thus should not be construed as limiting the present application. Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more features. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In this application, the term "exemplary" is used to mean "serving as an example, instance, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the application. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present application may be practiced without these specific details. In other instances, well-known structures and processes have not been shown in detail to avoid obscuring the description of the present application with unnecessary detail. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
The embodiment of the application provides a method and a device for predicting the arrival time of a delivery bill, which are respectively described in detail below.
Referring to fig. 1, fig. 1 is a schematic view of a scenario of a system for predicting a delivery time of a bill according to an embodiment of the present application, where the system for predicting a delivery time of a bill may include a computer device 100, and a device for predicting a delivery time of a bill is integrated in the computer device 100.
In the embodiment of the present application, the computer device 100 may be an independent server, or may be a server network or a server cluster formed by servers, for example, the computer device 100 described in the embodiment of the present application includes, but is not limited to, a computer, a network host, a single network server, a plurality of network server sets, or a cloud server formed by a plurality of servers. Wherein the Cloud server is composed of a large number of computers or web servers based on Cloud Computing (Cloud Computing).
In the embodiment of the present application, the computer device 100 may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device 100 may be a desktop, a portable computer, a network server, a palm computer (Personal Digital Assistant, PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, an embedded device, etc., and the embodiment is not limited to the type of the computer device 100.
It will be appreciated by those skilled in the art that the application environment shown in fig. 1 is only one application scenario of the present application scenario, and is not limited to the application scenario of the present application scenario, and other application environments may also include more or fewer computer devices than those shown in fig. 1, for example, only 1 computer device is shown in fig. 1, and it will be appreciated that the delivery order delivery time prediction system may also include one or more other computer devices capable of processing data, which is not limited herein.
In addition, as shown in fig. 1, the system for predicting the arrival time of a bill may further include a memory 200 for storing data.
It should be noted that, the schematic view of the scenario of the system for predicting the arrival time of the delivery order shown in fig. 1 is only an example, and the system for predicting the arrival time of the delivery order and the scenario described in the embodiments of the present application are for more clearly describing the technical solutions of the embodiments of the present application, and do not constitute a limitation to the technical solutions provided in the embodiments of the present application, and as a person of ordinary skill in the art can know that the technical solutions provided in the embodiments of the present application are equally applicable to similar technical problems with the evolution of the system for predicting the arrival time of the delivery order and the occurrence of new service scenarios.
Firstly, in the embodiment of the present application, a method for predicting a delivery time of a manifest is provided, where a delivery process of the manifest includes a first stage and a second stage, and the method for predicting a delivery time of the manifest includes: acquiring a first to-be-predicted waybill; determining a first-stage predicted arrival time of the first to-be-predicted waybill according to the first to-be-predicted waybill and a plurality of first historical waybill samples; updating the first to-be-predicted waybill according to the first stage predicted delivery time to obtain a second to-be-predicted waybill; determining second-stage prediction delivery time of the second to-be-predicted waybill according to the second to-be-predicted waybill and a plurality of second historical waybill samples; and determining the predicted arrival time of the target waybill according to the predicted arrival time of the second stage.
As shown in fig. 2, fig. 2 is a flowchart of one embodiment of a method for predicting a delivery time of a bill provided in an embodiment of the present application, where the method for predicting a delivery time of a bill includes steps S201 to S205 as follows:
s201, a first to-be-predicted waybill is obtained.
In the embodiment of the application, the waybill feature vector of the first to-be-predicted waybill is obtained. The waybill feature vector may include a waybill spatial feature, a waybill temporal feature, and a waybill attribute feature, among others. The time characteristics of the waybill mainly comprise address receiving and sending information; the time characteristics of the waybill mainly comprise the time of ordering, the work order receiving and the like; the waybill attribute features mainly comprise express mail receiver information, product type, aging type, cost, weight, towing object and the like.
S202, determining a first-stage predicted arrival time of the first to-be-predicted waybill according to the first to-be-predicted waybill and a plurality of first historical waybill samples.
In the embodiment of the application, the shipping process of the manifest includes a first stage and a second stage. In other embodiments, the shipping process of the manifest includes a first stage, a second stage, and a third stage, where the first stage is a receiving stage, and the receiving stage starts from when the user places the manifest to when the manifest arrives at the origin transfer station; the second stage is a transfer stage, wherein the transfer stage starts from the arrival of a waybill at an origin transfer station to the arrival of the waybill at a destination transfer station; the third stage is a dispatch stage, which starts from the arrival of the waybill at the destination transfer station to the end of the user sign. Of course, the conveying process can be divided into more stages according to specific situations.
In this embodiment of the present application, determining the first-stage predicted arrival time of the first to-be-predicted waybill according to the first to-be-predicted waybill and the plurality of first historical waybill samples may include:
(1) And acquiring the first stage starting time of the first to-be-predicted waybill.
In this embodiment, the first stage is a receiving stage, and the first stage start time of the first to-be-predicted waybill may be a time for ordering the waybill, for example, the user orders at 5 points, and the first stage start time is 5 points.
(2) A plurality of first historical waybill samples matching the first stage start time are obtained.
In the embodiment of the application, a plurality of initial historical waybill samples in a preset historical time period are obtained, and a plurality of first historical waybill samples matched with the initial time of the first stage are obtained from the plurality of initial historical waybill samples. The preset historical time period can be 2 months, 3 months and the like, and the preset historical time period is only needed according to specific settings. For example, there are 1000 initial historical waybill samples within 3 months of the history. The waybill feature vector of the initial historical waybill sample may include a waybill space feature, a waybill time feature and a waybill attribute feature, and the initial historical waybill sample is labeled with a label (label), and the label (label) of the initial historical waybill sample is the first-stage real time delivery time of the initial historical waybill sample. The waybill feature vector of the initial historical waybill sample includes a first stage historical starting time, which is typically the order time.
In a specific embodiment, obtaining a plurality of first historical waybill samples from a plurality of initial historical waybill samples that match a first stage start time comprises: and determining a preset time range according to the first stage starting time, wherein the preset time range comprises the first stage starting time, and determining the initial historical waybill samples of which the first stage historical starting time belongs to the preset time range as a plurality of first historical waybill samples matched with the first stage starting time. The preset time range may be set according to specific situations, for example, the starting time of the first stage is 5 points, and the preset time range is 4:50-5:10. Preferably, the midpoint of the preset time range is the first stage start time. The first historical waybill sample and the first to-be-predicted waybill have similar time, and the waybill prediction delivery time of the first to-be-predicted waybill is predicted according to the first historical waybill sample, so that the method can be more accurate. Of course, in other embodiments, an initial historical waybill sample having a first stage historical start time equal to the first stage start time may also be determined as a plurality of first historical waybill samples that match the first stage start time.
(3) And determining the first-stage predicted delivery time of the first to-be-predicted waybill according to the first to-be-predicted waybill and the plurality of first historical waybill samples.
In this embodiment of the present application, determining the first-stage predicted arrival time of the first to-be-predicted waybill according to the first to-be-predicted waybill and the plurality of first historical waybill samples may include: obtaining a preset target achievement rate; determining a first quantile parameter and a second quantile parameter according to a preset target achievement rate; and determining the first-stage predicted delivery time of the first to-be-predicted waybill according to the first quantile parameter, the first to-be-predicted waybill and the plurality of first historical waybill samples. The Quantile (Quantile), also called Quantile, refers to a numerical point that divides the probability distribution range of a random variable into several equal parts, and there are usually median (i.e., bipartite), quartile, percentile, etc.
In this embodiment, the preset target achievement rate is a preset index, for example, 0.85, which indicates that the predicted result of the first to-be-predicted waybill has a probability of 85% that the arrival can be completed before the predetermined arrival time, that is, that 85% of the waybills in the group of waybills are required to be completed before the predetermined arrival time.
In this embodiment of the present application, determining the second stage predicted arrival time of the second to-be-predicted waybill according to the second to-be-predicted waybill and the plurality of second historical waybill samples may include: and determining the second-stage predicted delivery time of the second to-be-predicted waybill according to the second quantile parameter, the second to-be-predicted waybill and the plurality of second historical waybill samples.
In this embodiment of the present application, the first quantile parameter p1 may represent a probability of delivering in time in the first stage, and the second quantile parameter p2 may represent a probability of delivering in time in the second stage, which is used to adjust accuracy of delivering time prediction. Of course, if the shipping process of the bill includes the first stage, the second stage and the third stage, the third quantile parameter p3 is also obtained.
In a specific embodiment, determining the first quantile parameter and the second quantile parameter according to the preset target achievement rate may include: and determining quantile reference parameters according to the preset target achievement rate and the stage number of the conveying process, and determining the quantile reference parameters as a first quantile parameter p1 and a second quantile parameter p2. If the transporting process of the waybill includes a first stage, a second stage and a third stage, the quantile reference parameter is determined as a first quantile parameter p1 and a second quantile parameter p2 to obtain a third quantile parameter p3. For example, the preset target achievement rate is 0.85, and if the number of stages of the conveying process is two, the quantile reference parameter is
If the number of stages of the transportation process is 3, the quantile reference parameter is +.>
First quantile parameter p1=second quantile parameter p2=third quantile parameter +. >
That is, by considering each stage as an independent process and performing prediction, calculation can be simplified.
In this embodiment of the present application, determining the first stage predicted arrival time of the first to-be-predicted waybill according to the first quantile parameter, the first to-be-predicted waybill and the plurality of first historical waybill samples may include:
(1) And calculating the waybill similarity of the first to-be-predicted waybill and the plurality of first historical waybill samples respectively.
Specifically, a waybill feature vector of a first to-be-predicted waybill and a waybill feature vector of a first historical waybill sample are obtained, wherein the waybill feature vector comprises a waybill space feature, a waybill time feature and a waybill attribute feature; and carrying out vector similarity calculation according to the waybill feature vector of the first to-be-predicted waybill and the waybill feature vector of the first historical waybill sample to obtain the waybill similarity.
In the embodiment of the present application, the set of the plurality of first historical waybill samples is m= { g1, g2, …, gm }, and the waybill similarity between the first to-be-predicted waybill and the first historical waybill sample is calculated according to the formula (1). Taking a waybill feature vector of a first to-be-predicted waybill sample as f j Wherein j=1, 2 …, n; taking the waybill feature vector of the first historical waybill sample as g i Wherein i=1, 2 …, m, substituting formula (1) to obtain the waybill similarity S (f j ,g i )。g i = (x 1, x2, …, xn), x1 being the individual features. f (f) j = (y 1, y2, …, yn), y1 being the respective feature.
(2) And placing the first historical waybill sample with the similarity to the first to-be-predicted waybill higher than the preset similarity into the waybill set.
In the embodiment of the application, after the waybill similarity of the first to-be-predicted waybill and the plurality of first historical waybill samples is obtained, the first historical waybill samples with the similarity higher than the preset similarity with the first to-be-predicted waybill are placed into the waybill set. The preset similarity may be set according to specific situations, for example, the preset similarity is 60%. In other embodiments, after the waybill similarity between the first to-be-predicted waybill and the plurality of first historical waybill samples is obtained, the plurality of first historical waybill samples are sorted according to the waybill similarity from small to small, and the first historical waybill samples with the preset number k after the waybill similarity is sorted are put into the waybill set H1. For example, h1=l { w1< w2< … < wk }.
(3) And acquiring a target waybill sample from the waybill set according to the first quantile parameter.
In the embodiment of the application, a first historical waybill sample corresponding to a first quantile parameter in a waybill set is used as a target waybill sample. For example, if the first quantile parameter p1 is 95%, the 95% of the first historical waybill samples arranged in the waybill set are determined to be target waybill samples.
(4) The first-stage real-time delivery time of the target waybill sample is determined as the first-stage predicted delivery time of the first waybill to be predicted.
The first-stage predicted delivery time T1 is based on the first quantile parameter p1, and the first quantile parameter p1 is determined according to the preset target achievement rate, so that the first-stage predicted delivery time is the smallest of the predicted times that satisfy the preset target achievement rate, and the first-stage predicted delivery time is the smallest of the predicted times that satisfy the preset target achievement rate. The first quantile parameter p1 is 95%, indicating that the probability of 95% of the time that the waybill ends in the first stage is the first stage predicted arrival time.
And S203, updating the first to-be-predicted waybill according to the first stage predicted arrival time to obtain a second to-be-predicted waybill.
In the embodiment of the present application, the second stage start time of the first to-be-predicted waybill is updated to the first stage predicted arrival time T1. That is, the waybill predicts the arrival time T1 to arrive at the starting transfer station in the first stage, and starts the second stage. After the arrival time is obtained through prediction in each section, the freight note is updated, then prediction in the next stage is carried out, the predictions in each stage are linked, and the prediction accuracy is improved.
S204, determining second-stage prediction delivery time of the second to-be-predicted waybill according to the second to-be-predicted waybill and the plurality of second historical waybill samples.
In this embodiment of the present application, determining the second stage predicted arrival time T2 of the second to-be-predicted waybill according to the second to-be-predicted waybill and the plurality of second historical waybill samples includes: acquiring the starting time of a second stage of a second to-be-predicted waybill; acquiring a plurality of second historical waybill samples matched with the second stage starting time; and determining a second-stage predicted delivery time T2 of the second to-be-predicted waybill according to the second to-be-predicted waybill and the plurality of second historical waybill samples.
Further, determining a second-stage predicted delivery time T2 of the second to-be-predicted waybill according to the second to-be-predicted waybill and the plurality of second historical waybill samples comprises determining the second-stage predicted delivery time T2 of the second to-be-predicted waybill according to the second quantile parameter, the second to-be-predicted waybill and the plurality of second historical waybill samples.
Further, determining a second stage predicted arrival time T2 of the second to-be-predicted waybill according to the second quantile parameter, the second to-be-predicted waybill, and the plurality of second historical waybill samples, including: calculating the waybill similarity of the second waybill to be predicted and a plurality of second historical waybill samples respectively; placing a second historical waybill sample with the similarity to the second to-be-predicted waybill higher than the preset similarity into a waybill set H2; acquiring a target waybill sample from the waybill set H2 according to the second quantile parameter; and determining the second-stage actual delivery time of the target waybill sample as the second-stage predicted delivery time T2 of the second waybill to be predicted.
S205, determining the predicted delivery time of the target waybill according to the predicted delivery time of the second stage.
Specifically, if the bill conveying process is composed of only the first stage and the second stage, the second stage predicted arrival time T2 is determined as the bill predicted arrival time T.
If the bill is transported, the bill is transported by the first stage, the second stage and the third stage. Updating the second to-be-predicted waybill according to the second stage predicted delivery time T2 to obtain a third to-be-predicted waybill; and determining a third-stage predicted delivery time T3 of the third to-be-predicted waybill according to the third to-be-predicted waybill and the plurality of third historical waybill samples, and determining the third-stage predicted delivery time T3 as the waybill predicted delivery time T.
In the above embodiment, the stages of the bill delivery process are regarded as independent stages for calculation, however, in actual situations, the stages are related to each other, so in order to improve the prediction accuracy, the present application provides another embodiment, referring to fig. 3, fig. 3 is a flowchart of another example of a method for predicting the delivery time of a bill provided in the embodiment of the present application, in a specific example, the method for predicting the delivery time of a bill may include S301 to S310:
S301, acquiring a first to-be-predicted waybill.
S302, obtaining a preset target achievement rate.
S303, acquiring a plurality of candidate quantile parameter combinations and training sets according to a preset target achievement rate.
Wherein each candidate quantile parameter combination comprises a first-stage candidate quantile parameter and a second-stage candidate quantile parameter, and the training set comprises a plurality of training samples and the real time delivery time of the waybill of each training sample.
In a specific embodiment, obtaining a plurality of candidate quantile parameter combinations and training sets according to a preset target achievement rate may include:
(1) And determining quantile reference parameters according to the preset target achievement rate and the stage number of the conveying process.
In the embodiment of the present application, the quantile reference parameter is
Wherein Z is a preset target achievement rate, and the stage number of the conveying process is b. For example, the preset target achievement rate is 0.85, and if the number of stages of the transportation process is two, the quantile reference parameter is +.>
If the number of stages of the transportation process is 3, the quantile reference parameter is +.>
(2) And determining a quantile value range according to the quantile reference parameter, wherein the value of the quantile value range is not larger than the quantile reference parameter.
In a specific embodiment, the quantile reference parameter is 0.95 and the quantile value ranges from [0.5-0.85] or [0.5-0.95]. The quantile value range can be set according to specific situations.
(3) And obtaining a plurality of quantile parameters from the quantile value range according to a preset step length, and combining to obtain a plurality of candidate quantile parameter combinations.
In a specific embodiment, the preset step size may be 0.05, which may be set according to the specific situation. For example, the plurality of candidate quantile parameter combinations are (0.85), (0.8,0.85), (0.75,0.0.7), (0.7,0.85), (0.85,0.7), respectively.
S304, carrying out delivery time prediction on each training sample in the training set according to the combination of a plurality of candidate quantile parameters to obtain the waybill prediction delivery time of each training sample.
In this embodiment of the present application, each training sample may be used as the first to-be-predicted waybill in S201, and the waybill prediction arrival time of each training sample may be calculated according to the steps of S201 to S205.
S305, determining a plurality of prediction effect index values corresponding to the candidate fractional parameter combinations according to the waybill prediction delivery time of each training sample and the waybill real delivery time of each training sample.
In the embodiment of the present application, the prediction effect index may be the achievement rate Y and the mean square error (MSE, mean Square Error), or may be the achievement rate Y and the mean absolute error (MAE, mean Absolute Error). Wherein, the mean square error L is shown in the formula (2),
where yi is the real time of arrival of the manifest for each training sample,
the delivery time is predicted for the waybill of each training sample, n being the total number of training samples.
Wherein the achievement rate Y is shown in the formula (3),
Y＝m/n＞＝0.85 (3)
wherein n is the total number of training samples, and the m predicted waybill real time is later than the number of training samples of the predicted waybill time.
Wherein, the average absolute error MAE is shown in the formula (4),
where yi is the real time of arrival of the manifest for each training sample,
the delivery time is predicted for the waybill of each training sample, n being the total number of training samples.
S306, determining candidate quantile parameter combinations corresponding to the predictive effect index values meeting the preset conditions as a first quantile parameter and a second quantile parameter.
In this embodiment of the present application, the preset condition may be that the mean square error is the smallest in the predicted effect index value in which the achievement rate Y is not smaller than the preset target achievement rate. The preset condition may be that the average absolute error is the smallest among the predictive effect index values whose achievement rate Y is not smaller than the preset target achievement rate. For example, the plurality of candidate quantile parameter combinations are respectively: (0.85), (0.8,0.85), (0.75,0.0.7), (0.7,0.85), (0.85,0.7). The corresponding multiple prediction effect index values are y=0.9 and mae=0.5 respectively; y=0.86, mae=0.2; y=0.91, mae=0.1; y=0.7, mae=0.05; y=0.6, mae=0.5. Firstly, obtaining a predicted effect index value of which the achievement rate Y is not smaller than a preset target achievement rate to be Y=0.9, wherein MAE=0.5; y=0.86, mae=0.2; y=0.91, mae=0.1, from which the mean square error is least selected, i.e. y=0.91, mae=0.1. The smaller the MAE, the higher the prediction accuracy. That is, when the achievement rate is 85% or more, the smaller the MAE, the better the parameter. Thus, the quantile parameter combination (0.75,0.0.7) corresponding to y=0.91 and mae=0.1 is determined as the first quantile parameter and the second quantile parameter.
When the shipping stage of the bill comprises three stages, the first quantile parameter p1=0.54, the second quantile parameter p2=0.74 and the third quantile parameter p3=0.82, and under the condition that the achievement rate is ensured to be more than 85%, the prediction result error of the product is reduced by 38% compared with the default parameter and is reduced by 55% compared with the old scheme error.
S307, determining a first stage prediction delivery time of the first to-be-predicted waybill according to the first quantile parameter, the first to-be-predicted waybill and the plurality of first historical waybill samples.
In this embodiment, the specific implementation of S307 may refer to the previous embodiment, and will not be described herein.
And S308, updating the first to-be-predicted waybill according to the predicted delivery time of the first stage to obtain a second to-be-predicted waybill.
In this embodiment, the specific implementation of S308 may refer to the previous embodiment, and will not be described herein.
S309, determining a second-stage predicted arrival time of the second to-be-predicted waybill according to the second quantile parameter, the second to-be-predicted waybill and the plurality of second historical waybill samples.
In this embodiment, the specific implementation of S309 may refer to the previous embodiment, and will not be described herein.
S310, determining the predicted delivery time of the target waybill according to the predicted delivery time of the second stage.
In this embodiment, the specific implementation of S310 may refer to the previous embodiment, and will not be described herein.
In order to better implement the method for predicting the arrival time of a delivery bill in the embodiment of the present application, on the basis of the method for predicting the arrival time of a delivery bill, the embodiment of the present application further provides a device for predicting the arrival time of a delivery bill, as shown in fig. 4, where the device 400 for predicting the arrival time of a delivery bill includes:
an obtaining unit 401, configured to obtain a first to-be-predicted waybill;
a first determining unit 402, configured to determine a first stage predicted arrival time of the first to-be-predicted waybill according to the first to-be-predicted waybill and the plurality of first historical waybill samples;
an updating unit 403, configured to update the first to-be-predicted waybill according to the first stage predicted arrival time, to obtain a second to-be-predicted waybill;
a second determining unit 404, configured to determine a second-stage predicted arrival time of the second to-be-predicted waybill according to the second to-be-predicted waybill and the plurality of second historical waybill samples;
and a third determining unit 405, configured to determine a predicted arrival time of the destination waybill according to the predicted arrival time of the second stage.
Optionally, the first determining unit 402 is configured to:
acquiring a first stage starting time of a first to-be-predicted waybill;
Acquiring a plurality of first historical waybill samples matched with the first stage starting time;
and determining the first-stage predicted delivery time of the first to-be-predicted waybill according to the first to-be-predicted waybill and the plurality of first historical waybill samples.
Optionally, the first determining unit 402 is configured to:
obtaining a preset target achievement rate;
determining a first quantile parameter and a second quantile parameter according to a preset target achievement rate;
determining a first-stage predicted arrival time of the first to-be-predicted waybill according to the first quantile parameter, the first to-be-predicted waybill and the plurality of first historical waybill samples;
a second determining unit 404, configured to:
and determining the second-stage predicted delivery time of the second to-be-predicted waybill according to the second quantile parameter, the second to-be-predicted waybill and the plurality of second historical waybill samples.
Optionally, the first determining unit 402 is configured to:
calculating the waybill similarity of the first to-be-predicted waybill and a plurality of first historical waybill samples respectively;
placing a first historical waybill sample with the similarity to the first to-be-predicted waybill higher than the preset similarity into a waybill set;
acquiring a target waybill sample from the waybill set according to the first quantile parameter;
the first-stage real-time delivery time of the target waybill sample is determined as the first-stage predicted delivery time of the first waybill to be predicted.
Optionally, the first determining unit 402 is configured to:
acquiring a waybill feature vector of a first to-be-predicted waybill and a waybill feature vector of a first historical waybill sample, wherein the waybill feature vector comprises a waybill space feature, a waybill time feature and a waybill attribute feature;
and carrying out vector similarity calculation according to the waybill feature vector of the first to-be-predicted waybill and the waybill feature vector of the first historical waybill sample to obtain the waybill similarity.
Optionally, the first determining unit 402 is configured to:
obtaining a plurality of candidate quantile parameter combinations and a training set according to a preset target achievement rate, wherein each candidate quantile parameter combination comprises a first-stage candidate quantile parameter and a second-stage candidate quantile parameter, and the training set comprises a plurality of training samples and a waybill real time delivery time of each training sample;
carrying out delivery time prediction on each training sample in the training set according to the combination of the candidate quantile parameters to obtain the waybill prediction delivery time of each training sample;
determining a plurality of prediction effect index values corresponding to a plurality of candidate quantile parameter combinations according to the waybill prediction delivery time of each training sample and the waybill real delivery time of each training sample;
And determining the candidate quantile parameter combination corresponding to the predictive effect index value meeting the preset condition as a first quantile parameter and a second quantile parameter.
Optionally, the first determining unit 402 is configured to:
determining quantile reference parameters according to a preset target achievement rate and the stage number of the conveying process;
determining a quantile value range according to the quantile reference parameter, wherein the value of the quantile value range is not larger than the quantile reference parameter;
and obtaining a plurality of quantile parameters from the quantile value range according to a preset step length, and combining to obtain a plurality of candidate quantile parameter combinations.
The embodiment of the application also provides a computer device, which integrates any of the prediction devices of the delivery time of the delivery list provided by the embodiment of the application, and the computer device comprises:
one or more processors;
a memory; and
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to perform the steps of the method for predicting a pick-up time in any of the embodiments of the method for predicting a pick-up time described above.
As shown in fig. 5, a schematic structural diagram of a computer device according to an embodiment of the present application is shown, specifically:
The computer device may include one or more processing cores 'processors 501, one or more computer-readable storage media's memory 502, a power supply 503, and an input unit 504, among other components. It will be appreciated by those skilled in the art that the computer device structure shown in the figures is not limiting of the computer device and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components. Wherein:
the processor 501 is the control center of the computer device and uses various interfaces and lines to connect the various parts of the overall computer device, and by running or executing software programs and/or modules stored in the memory 502, and invoking data stored in the memory 502, performs various functions of the computer device and processes the data, thereby performing overall monitoring of the computer device. Optionally, processor 501 may include one or more processing cores; the processor 501 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, and preferably the processor 501 may integrate an application processor that primarily handles operating systems, user interfaces, applications, etc. with a modem processor that primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 501.
The memory 502 may be used to store software programs and modules, and the processor 501 executes various functional applications and data processing by executing the software programs and modules stored in the memory 502. The memory 502 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the computer device, etc. In addition, memory 502 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 502 may also include a memory controller to provide access to the memory 502 by the processor 501.
The computer device further includes a power supply 503 for powering the various components, and preferably the power supply 503 may be logically coupled to the processor 501 via a power management system such that functions such as charge, discharge, and power consumption management are performed by the power management system. The power supply 503 may also include one or more of any of a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.
The computer device may also include an input unit 504, which input unit 504 may be used to receive input numeric or character information and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
Although not shown, the computer device may further include a display unit or the like, which is not described herein. In particular, in this embodiment, the processor 501 in the computer device loads executable files corresponding to the processes of one or more application programs into the memory 502 according to the following instructions, and the processor 501 executes the application programs stored in the memory 502, so as to implement various functions as follows:
acquiring a first to-be-predicted waybill; determining a first-stage predicted arrival time of the first to-be-predicted waybill according to the first to-be-predicted waybill and a plurality of first historical waybill samples; updating the first to-be-predicted waybill according to the first stage predicted delivery time to obtain a second to-be-predicted waybill; determining second-stage prediction delivery time of the second to-be-predicted waybill according to the second to-be-predicted waybill and a plurality of second historical waybill samples; and determining the predicted arrival time of the target waybill according to the predicted arrival time of the second stage.
Those of ordinary skill in the art will appreciate that all or a portion of the steps of the various methods of the above embodiments may be performed by instructions, or by instructions controlling associated hardware, which may be stored in a computer-readable storage medium and loaded and executed by a processor.
To this end, embodiments of the present application provide a computer readable storage medium, which may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like. On which a computer program is stored, the computer program being loaded by a processor to perform the steps of any of the methods for predicting delivery time of a manifest provided by embodiments of the present application. For example, the loading of the computer program by the processor may perform the steps of:
acquiring a first to-be-predicted waybill; determining a first-stage predicted arrival time of the first to-be-predicted waybill according to the first to-be-predicted waybill and a plurality of first historical waybill samples; updating the first to-be-predicted waybill according to the first stage predicted delivery time to obtain a second to-be-predicted waybill; determining second-stage prediction delivery time of the second to-be-predicted waybill according to the second to-be-predicted waybill and a plurality of second historical waybill samples; and determining the predicted arrival time of the target waybill according to the predicted arrival time of the second stage.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and the portions of one embodiment that are not described in detail in the foregoing embodiments may be referred to in the foregoing detailed description of other embodiments, which are not described herein again.
In the implementation, each unit or structure may be implemented as an independent entity, or may be implemented as the same entity or several entities in any combination, and the implementation of each unit or structure may be referred to the foregoing method embodiments and will not be repeated herein.
The specific implementation of each operation above may be referred to the previous embodiments, and will not be described herein.
The foregoing describes in detail a method and apparatus for predicting delivery time of a delivery bill provided in the embodiments of the present application, and specific examples are applied herein to illustrate principles and embodiments of the present application, where the foregoing examples are only for helping to understand the method and core ideas of the present application; meanwhile, as those skilled in the art will vary in the specific embodiments and application scope according to the ideas of the present application, the contents of the present specification should not be construed as limiting the present application in summary.
Claims (10)
1. A method for predicting a delivery time of a waybill, wherein a delivery process of the waybill includes a first stage and a second stage, the method for predicting the delivery time of the waybill comprising:
Acquiring a first to-be-predicted waybill;
determining a first-stage predicted arrival time of the first to-be-predicted waybill according to the first to-be-predicted waybill and a plurality of first historical waybill samples;
updating the first to-be-predicted waybill according to the first stage predicted arrival time to obtain a second to-be-predicted waybill;
determining second-stage predicted delivery time of the second to-be-predicted waybill according to the second to-be-predicted waybill and a plurality of second historical waybill samples;
and determining the predicted arrival time of the target waybill according to the predicted arrival time of the second stage.
2. The method of claim 1, wherein determining the first stage predicted arrival time of the first to-be-predicted waybill based on the first to-be-predicted waybill and a plurality of first historical waybill samples comprises:
acquiring a first stage starting time of the first to-be-predicted waybill;
acquiring the plurality of first historical waybill samples matched with the first stage start time;
and determining a first-stage predicted delivery time of the first to-be-predicted waybill according to the first to-be-predicted waybill and the plurality of first historical waybill samples.
3. The method of claim 1, wherein determining the first stage predicted arrival time of the first to-be-predicted waybill based on the first to-be-predicted waybill and a plurality of first historical waybill samples comprises:
Obtaining a preset target achievement rate;
determining a first quantile parameter and a second quantile parameter according to the preset target achievement rate;
determining a first-stage predicted arrival time of the first to-be-predicted waybill according to the first quantile parameter, the first to-be-predicted waybill and a plurality of first historical waybill samples;
the determining the second stage prediction arrival time of the second to-be-predicted waybill according to the second to-be-predicted waybill and a plurality of second historical waybill samples comprises:
and determining second-stage predicted delivery time of the second to-be-predicted waybill according to the second quantile parameter, the second to-be-predicted waybill and a plurality of second historical waybill samples.
4. The method of claim 3, wherein determining the first stage predicted arrival time of the first to-be-predicted waybill based on the first quantile parameter, the first to-be-predicted waybill, and a plurality of first historical waybill samples comprises:
calculating the waybill similarity of the first to-be-predicted waybill and the plurality of first historical waybill samples respectively;
placing a first historical waybill sample with the similarity to the first to-be-predicted waybill higher than the preset similarity into a waybill set;
Acquiring a target waybill sample from the waybill set according to the first quantile parameter;
and determining the first-stage real-time delivery time of the target waybill sample as the first-stage predicted delivery time of the first to-be-predicted waybill.
5. The method of claim 4, wherein calculating the waybill similarity for the first to-be-predicted waybill and the plurality of first historical waybill samples, respectively, comprises:
acquiring a waybill feature vector of the first to-be-predicted waybill and a waybill feature vector of the first historical waybill sample, wherein the waybill feature vector comprises a waybill space feature, a waybill time feature and a waybill attribute feature;
and carrying out vector similarity calculation according to the waybill feature vector of the first to-be-predicted waybill and the waybill feature vector of the first historical waybill sample to obtain the waybill similarity.
6. The method for predicting a delivery order arrival time according to claim 3, wherein determining the first quantile parameter and the second quantile parameter according to the preset target achievement rate comprises:
obtaining a plurality of candidate quantile parameter combinations and a training set according to the preset target achievement rate, wherein each candidate quantile parameter combination comprises a first-stage candidate quantile parameter and a second-stage candidate quantile parameter, and the training set comprises a plurality of training samples and the real time of arrival of the waybill of each training sample;
Carrying out delivery time prediction on each training sample in the training set according to the candidate quantile parameter combinations to obtain the waybill prediction delivery time of each training sample;
determining a plurality of prediction effect index values corresponding to a plurality of candidate quantile parameter combinations according to the waybill prediction delivery time of each training sample and the waybill real delivery time of each training sample;
and determining the candidate quantile parameter combination corresponding to the predictive effect index value meeting the preset condition as the first quantile parameter and the second quantile parameter.
7. The method for predicting a delivery order arrival time according to claim 6, wherein the obtaining a plurality of candidate quantile parameter combinations and training sets according to the preset target achievement rate comprises:
determining quantile reference parameters according to the preset target achievement rate and the stage number of the conveying process;
determining a quantile value range according to the quantile reference parameter, wherein the value of the quantile value range is not larger than the quantile reference parameter;
and obtaining a plurality of quantile parameters from the quantile value range according to a preset step length, and combining to obtain a plurality of candidate quantile parameter combinations.
8. A bill arrival time prediction apparatus, wherein a delivery process of the bill includes a first stage and a second stage, the bill arrival time prediction apparatus comprising:
the system comprises an acquisition unit, a prediction unit and a prediction unit, wherein the acquisition unit is used for acquiring a first to-be-predicted waybill;
the first determining unit is used for determining a first stage prediction delivery time of the first to-be-predicted waybill according to the first to-be-predicted waybill and a plurality of first historical waybill samples;
the updating unit is used for updating the first to-be-predicted freight list according to the first-stage predicted delivery time to obtain a second to-be-predicted freight list;
the second determining unit is used for determining second-stage predicted delivery time of the second to-be-predicted waybill according to the second to-be-predicted waybill and a plurality of second historical waybill samples;
and the third determining unit is used for determining the predicted delivery time of the target waybill according to the predicted delivery time of the second stage.
9. A computer device, the computer device comprising:
one or more processors;
a memory; and
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the method of predicting a waybill delivery time of any one of claims 1 to 7.
10. A computer-readable storage medium, having stored thereon a computer program, the computer program being loaded by a processor to perform the steps of the method of predicting a delivery order arrival time of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111442553.9A CN116205315A (en) | 2021-11-30 | 2021-11-30 | Method and device for predicting arrival time of shipping bill |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111442553.9A CN116205315A (en) | 2021-11-30 | 2021-11-30 | Method and device for predicting arrival time of shipping bill |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116205315A true CN116205315A (en) | 2023-06-02 |
Family
ID=86513385
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111442553.9A Pending CN116205315A (en) | 2021-11-30 | 2021-11-30 | Method and device for predicting arrival time of shipping bill |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116205315A (en) |
-
2021
- 2021-11-30 CN CN202111442553.9A patent/CN116205315A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rivera et al. | Anticipatory freight selection in intermodal long-haul round-trips | |
| CN111553626A (en) | Path planning method and device, electronic equipment and storage medium thereof | |
| US20200082487A1 (en) | Inventory deployment planning device and inventory deployment planning method | |
| CN110689159B (en) | Method and device for supplementing commodity | |
| CN111178810B (en) | Method and device for generating information | |
| CN113592282A (en) | Article distribution method and device | |
| CN108197825B (en) | System scheduling method and device | |
| CN107563530A (en) | Removal of home vehicle call request method for pushing and system based on fence | |
| CN116586312B (en) | Goods sorting method, device, electronic equipment and readable storage medium | |
| CN114444751A (en) | Material demand prediction method and device, computer equipment and storage medium | |
| CN116205315A (en) | Method and device for predicting arrival time of shipping bill | |
| CN113065274B (en) | Vehicle path planning method, device, terminal and readable storage medium | |
| CN115689454A (en) | Method and device for determining service site, electronic equipment and storage medium | |
| CN111105176A (en) | Data processing method, device, equipment and storage medium | |
| CN114707820A (en) | Cargo transportation method and device, terminal equipment and readable storage medium | |
| CN112837001A (en) | Logistics network planning method and device and computer readable storage medium | |
| CN112801567B (en) | Express delivery mode selection method and device, computer equipment and storage medium | |
| CN113807753B (en) | Distribution route planning method, distribution route planning device, server and storage medium | |
| CN114418645B (en) | Information delivery method and device, terminal equipment and storage medium | |
| CN118095993B (en) | Method, device, computer equipment and storage medium for determining transportation scheme | |
| CN113822612B (en) | Method and device for controlling a transport device | |
| CN116362637A (en) | Method and device for predicting dispatch time consumption, server and readable storage medium | |
| WO2024139785A1 (en) | Method and apparatus for acquiring waybill information of cargo without waybill, electronic device, and storage medium | |
| US20220383254A1 (en) | Determining pick pallet build operations and pick sequencing | |
| CN113077072B (en) | Method and device for predicting cargo quantity |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |