CN108596399A - Method, apparatus, electronic equipment and the storage medium of express delivery amount prediction - Google Patents
Method, apparatus, electronic equipment and the storage medium of express delivery amount prediction Download PDFInfo
- Publication number
- CN108596399A CN108596399A CN201810421169.2A CN201810421169A CN108596399A CN 108596399 A CN108596399 A CN 108596399A CN 201810421169 A CN201810421169 A CN 201810421169A CN 108596399 A CN108596399 A CN 108596399A
- Authority
- CN
- China
- Prior art keywords
- express delivery
- information
- delivery amount
- amount information
- portfolio
- 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
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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (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
An embodiment of the present invention provides method, apparatus, electronic equipment and the storage mediums of a kind of prediction of express delivery amount, belong to field of computer technology.The above method includes：Obtain the express delivery amount information and portfolio influence information preset in historical period, it includes weather information and/or date feature information that portfolio, which influences information, information and express delivery amount information are influenced according to portfolio, preset initial model is trained, obtain Traffic prediction model, according to the express delivery amount information and Traffic prediction model in preset time step-length, output prediction express delivery amount information.The method predicted using the express delivery amount of the embodiment of the present invention, can improve the accuracy of express delivery amount information prediction.
Description
Technical field
This application involves field of computer technology, method, apparatus, electronic equipment more particularly to the prediction of express delivery amount
And storage medium.
Background technology
Postal industry is the key industries of modern service industry, is the modern industry for pushing circulation transition, promoting consumption upgrading, is
The guiding industry of logistics field.During the nearly last ten years, express mail service industry sustained and rapid development, working scale constantly extend, postal industry
Business amount grows at top speed, and makes tremendous contribution for national economy, wherein 2012-2017 express delivery amount total amounts and increases by a year-on-year basis
Amount is as shown in table 1.
Table 1
During the annual express delivery busy season is concentrated mainly on electric business activity, such as " double 11 ", " double 12 ", the Spring Festival, 618 activities
Period.Accurate Traffic prediction information produces businessman storage in advance, Express firm business scale personnel prepare and to state
Supervision department of post office of family determines that guarantee plan all has especially important meaning in advance.
In the prior art use ARIMA (Autoregressive Integrated Moving Average Model, from
Regression-Integral moving average model) prediction model predicts express delivery amount.ARIMA models are based on the pre- of time series
Survey method.The model is by express delivery amount daily in the date section of acquisition, to predict next day express delivery amount.For example, as it is known that 1
Month No. 1 to daily express delivery amount data on May 10, after being trained to ARIMA models with these data, which can be pre-
Measure the express delivery amount data after May 10.
Based on existing technical solution, ARIMA models are to be instructed using the relationship of simple date and express delivery amount
Practice, therefore forecasting accuracy is low.
Invention content
The method, apparatus for being designed to provide the prediction of express delivery amount, electronic equipment and storage of the embodiment of the present application are situated between
Matter, to realize the accuracy for improving express delivery amount information prediction.Specific technical solution is as follows：
In a first aspect, an embodiment of the present invention provides a kind of method of express delivery amount prediction, the method includes：
Obtain the express delivery amount information and portfolio influence information preset in historical period, the portfolio influence information
Including weather information and/or date feature information；
Information and the express delivery amount information are influenced according to the portfolio, preset initial model is trained,
Obtain Traffic prediction model；
According in preset time step-length express delivery amount information and the Traffic prediction model, output prediction express delivery industry
Business amount information.
Optionally, described that information and the express delivery amount information are influenced according to the portfolio, to preset introductory die
Type is trained, and obtains Traffic prediction model, including：
The portfolio is influenced into information and the express delivery amount information, according to preset time step-length to preset initial
Model is trained, and determines Traffic prediction model.
Optionally, the express delivery amount information according in preset time step-length and the Traffic prediction model, it is defeated
Go out to predict express delivery amount information, including：
By the express delivery amount information in target date foregoing description preset time step-length, the Traffic prediction mould is inputted
Type；
Export the prediction express delivery amount information of the target date.
Optionally, the preset initial model is shot and long term memory network LSTM models.
Optionally, the preset time step-length is less than the duration of the default historical period.
Second aspect, an embodiment of the present invention provides a kind of device of express delivery amount prediction, described device includes：
Acquisition module obtains the express delivery amount information and portfolio influence information preset in historical period, the business
It includes weather information and/or date feature information that amount, which influences information,；
Training module influences information and the express delivery amount information, to preset initial model according to the portfolio
It is trained, obtains Traffic prediction model；
Output module, according in preset time step-length express delivery amount information and the Traffic prediction model, output
Predict express delivery amount information.
Optionally, the training module, including：
The portfolio is influenced information and the express delivery amount information, according to preset time step-length by training submodule
Preset initial model is trained, determines Traffic prediction model.
Optionally, the output module, including：
Input submodule, by the express delivery amount information in target date foregoing description preset time step-length, described in input
Traffic prediction model；
Output sub-module exports the prediction express delivery amount information of the target date.
Optionally, the preset initial model is shot and long term memory network LSTM models.
Optionally, the preset time step-length is less than the duration of the default historical period.
The third aspect, an embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Dielectric memory contains computer program, and the computer program realizes that above-mentioned first aspect is any described when being executed by processor
The method of express delivery amount prediction.
Fourth aspect, an embodiment of the present invention provides a kind of electronic equipment, including processor, communication interface, memory and
Communication bus, wherein the processor, the communication interface, the memory complete mutual communication by communication bus；
The memory, for storing computer program；The processor, when for executing the program stored on the memory,
The method for realizing any express delivery amount prediction of above-mentioned first aspect.
Method, apparatus, electronic equipment and the storage medium of express delivery amount prediction provided in an embodiment of the present invention, can obtain
Express delivery amount information and portfolio in default historical period is taken to influence information, it includes weather information that portfolio, which influences information,
And/or date feature information, information and express delivery amount information are influenced according to portfolio, preset initial model is instructed
Practice, obtain Traffic prediction model, according to the express delivery amount information and Traffic prediction model in preset time step-length, output
Predict express delivery amount information.The embodiment of the present invention considers Multiple factors, such as weather information and/or date feature information.
Therefore the accuracy of express delivery amount information prediction can be improved.Certainly, it implements any of the products of the present invention or method and differs
It is fixed to need while reaching all the above advantage.
Description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of application for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of flow chart for the method that the express delivery amount of the embodiment of the present invention is predicted；
Fig. 2 is the first curve graph of the express delivery amount of the embodiment of the present invention；
Fig. 3 is second of curve graph of the express delivery amount of the embodiment of the present invention；
Fig. 4 is a kind of schematic diagram for the device that the express delivery amount of the embodiment of the present invention is predicted；
Fig. 5 is a kind of schematic diagram of the electronic equipment of the embodiment of the present invention.
Specific implementation mode
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
An embodiment of the present invention provides a kind of methods of express delivery amount prediction, it is contemplated that Multiple factors, such as meteorological letter
Breath and/or date feature information.Therefore, this method can improve the accuracy of express delivery amount information prediction.This method is held
Row theme can be terminal, and terminal can be mobile phone or computer.
As shown in Figure 1, the processing procedure of this method is as follows：
Step 101, the express delivery amount information and portfolio influence information preset in historical period are obtained.
Wherein, it includes weather information and/or date feature information that portfolio, which influences information,.
Weather information is the information for characterizing the meteorological condition in preset duration, such as the highest gas in preset duration
The warm, lowest temperature and the rain or shine information such as sleet.Date feature information is the letter for characterizing the feature of period residing for preset duration
Breath, such as the period is in all several, period at corresponding exact dates and whether the period is in the adjacent time interval in special red-letter day
(such as before and after double 11) etc..Preset duration is arbitrary duration, is set according to actual demand, such as preset duration is 1 small
When, 12 hours, 1 day or 7 days etc..In inventive embodiments for 1 day, because in actual conditions, each express delivery operator is usually with 1
It is unit, and statistics pulls the information such as part amount, can facilitate calculating.Optionally, date feature information includes special festival information, example
Such as double 11, double 12 or the period in the Spring Festival portfolio.
In the present invention is implemented, terminal can prestore the express delivery amount information in historical period and portfolio influence
Information, terminal can influence information from the express delivery amount information and portfolio being locally stored in middle acquisition historical period；Alternatively,
Terminal can also obtain express delivery amount information and portfolio influence information in historical period by network.For example, terminal is logical
It crosses application program and obtains weather information on the net from weather, and obtain postal express delivery amount information from national post system general bureau, soon
It includes pulling the information such as number of packages amount to pass traffic information.
Step 102, information and express delivery amount information are influenced according to portfolio, preset initial model are trained,
Obtain Traffic prediction model.
In force, terminal can prestore initial model.Terminal can influence information and express delivery industry by portfolio
Initial model is trained to Traffic prediction model by business amount information.Specifically, the initial model can be ARIMA, HMM
(Hidden Markov Model, hidden Markov model), SVR (support) vector regression, supporting vector are returned
Return) model or LSTM (Long Short-Term Memory) model etc..For convenience of description, the present embodiment is with LSTM models
Initial model illustrates, other situations are similar therewith.
Optionally, above-mentioned that information and above-mentioned express delivery amount information are influenced according to above-mentioned portfolio, to preset introductory die
Type is trained, and obtains Traffic prediction model, including：
Above-mentioned portfolio is influenced into information and above-mentioned express delivery amount information, according to preset time step-length to preset initial
Model is trained, and determines Traffic prediction model.
Preset time step-length N is obtained, N is arbitrary duration, can be set according to actual demand, such as N is 7 days, 22
It, 30 days or 40 days etc..
In order to which daily portfolio is influenced information and is converted to dimensional information by training pattern, terminal more quickly, for example, it is special
Levy vector etc., the physical meaning of the dimension of dimensional information and each dimension can be with sets itself, in the embodiment of the present invention by taking table 2 as an example
It illustrates.
Table 2
For terminal in training pattern, the date is simultaneously not involved in training, and the date is only used as the mark of each training data, with one
It is unit, portfolio influence information is converted to the feature vector of 27 dimensions, wherein the highest temperature, the lowest temperature and wind-force value
The numerical value of corresponding dimension is respectively the actual numerical value when daily maximum temperature, the lowest temperature and wind-force value.Except the highest temperature, minimum gas
Outside mild wind-force value, other dimensions indicate to meet respectively according to same day actual conditions by 0 or 1 assignment, 1, and 0 indicates not meeting.Example
If the same day is Friday, then the value of Monday, Tuesday, Wednesday, Thursday, Saturday and Sunday corresponding dimension is 0, Friday corresponding dimension
Value be 1.
Portfolio influences in information to include weather and week information factor, and in addition to ordinary day feature, is additionally added consideration
Special red-letter day factor has been arrived, double 11 features are added.Improve the precision of express delivery amount prediction.
For each date, by the feature vector on the date and express delivery amount information input to default LSTM models,
Default LSTM models are trained according to preset time step-length, to obtain Traffic prediction model.
Traffic prediction model includes input layer, hidden layer and output layer.The network node number M of input layer can be arranged
It is 28, is the dimension according to feature vector, in addition what a bias node obtained.Letter is activated using tanh functions as each node
Number.Hidden layer is LSTM structures, and node in hidden layer J could be provided as 9 (including a bias nodes).Output layer number of nodes can
To be set as 1.
In the training process, using the method for cross validation come adjustment parameter, by the data in a preset time step-length
Card set is surveyed as one, and optimizes Traffic prediction model using stochastic gradient descent algorithm.To obtain final portfolio
Prediction model.
Step 103, according to the express delivery amount information and Traffic prediction model in preset time step-length, output prediction is fast
Pass traffic information.
In the present invention is implemented, after terminal obtains trained Traffic prediction model, so that it may to start to predict portfolio
Influence information.Terminal is according to historical data, to predict following express delivery amount.The embodiment of the present invention considers Multiple factors,
Such as weather information and/or date feature information.Therefore the accuracy of express delivery amount information prediction can be improved.
Optionally, the above-mentioned express delivery amount information according in preset time step-length and above-mentioned Traffic prediction model, it is defeated
Go out to predict express delivery amount information, including：
Express delivery amount information before target date in preset time step-length it is pre- to be inputted the portfolio by step 1
Survey model.
In the present invention is implemented, after terminal chooses target date to be predicted, by preset time step-length before target date
History express delivery amount data as input sample, be input in trained Traffic prediction model.
Step 2 exports the prediction express delivery amount information of the target date.
In the present invention is implemented, terminal is by trained Traffic prediction model, to pre- before the target date of input
If the express delivery amount information in time step is analyzed, the prediction express delivery amount information of target date is obtained.Terminal is defeated
The prediction express delivery amount information of the target date gone out.For example, terminal obtains the express delivery amount letter of the target date
After breath, the prediction express delivery amount information is shown on a terminal screen.
Optionally, above-mentioned preset time step-length is less than the duration of above-mentioned default historical period.
When preset time step-length is less than the duration of default historical period, can preferably by default historical period,
Express delivery amount information beyond preset time step-length part, to determine the prediction express delivery amount information of target date.And
Default historical period is more than preset time step-length, and it is default can to ensure that the time span of the feature vector of preset time step-length is less than
The time span of the feature vector of historical period, to ensure effective analysis to the time continuity of feature vector, Ke Yiti
The accuracy of the survey express delivery amount information of heavy traffic prediction model output.
In embodiments of the present invention, preset time step-length is less than default historical period, can improve Traffic prediction model
The accuracy of the survey express delivery amount information of output.
Optionally, the preset initial model in the embodiment of the present invention is shot and long term memory network LSTM models.
Referring to Fig. 2, Fig. 2 is the first curve graph of express delivery amount, and horizontal axis represents the date, and the longitudinal axis represents express delivery
Amount.Curve 201 is obtained express delivery industry when applying LSTM models in the method predicted of express delivery amount of the embodiment of the present invention
Business amount；Curve 202 is the express delivery amount obtained in the prior art using ARIMA prediction models；Curve 203 is actual express delivery
Portfolio.
Referring to Fig. 3, Fig. 3 is second of curve graph of express delivery amount, and horizontal axis represents the date, and the longitudinal axis represents express delivery
Amount, wherein be the express delivery amount curve before and after double 11 in box.Curve 301 is the express delivery in the embodiment of the present invention
It measures when applying LSTM models in the method for prediction, obtained express delivery amount；Curve 302 is to use ARIMA pre- in the prior art
Survey the express delivery amount that model obtains；Curve 303 is actual express delivery amount.
When applying LSTM models in the method that the express delivery amount of the embodiment of the present invention is predicted, obtained express delivery amount
With the error of practical express delivery amount, and in the prior art use ARIMA prediction models when, obtained express delivery amount and reality
The error of express delivery amount, as shown in table 3 and table 4, wherein table 3 is the application condition table in non-double 11 periods, and table 4 is double ten
The application condition table in one period.
Table 3
| ARIMA models | LSTM models | |
| MSE/E11 | 4.27 | 0.9 |
| MAE/E5 | 5.40 | 1.72 |
| RMSE/E5 | 6.54 | 3.00 |
| R-Square | 0.569557974 | 0.72730548 |
Table 4
| ARIMA models | LSTM models | |
| MSE/E11 | 68.8 | 1.99585 |
| MAE/E5 | 22.266 | 3.1765 |
| RMSE/E5 | 26.225 | 4.46749 |
| R-Square | -1.85358 | 0.914952044 |
Wherein, MSE (Mean Square Error, mean square error), MAE (Mean Absolute Error, average absolute
Error) and the closer actual value of the smaller expression of RMSE (Root Mean Square Error, root-mean-square error) value.R-Square
Value is bigger to be indicated closer to actual value.
It can be seen that when applying LSTM models in the method for the express delivery amount prediction of the embodiment of the present invention, obtained express delivery
Amount, compared to the express delivery amount for using ARIMA prediction models to obtain, closer to practical express delivery amount, especially double ten
Before and after one.
The embodiment of the present invention additionally provides a kind of device of express delivery amount prediction, and referring to Fig. 4, which includes：
Acquisition module 401 obtains the express delivery amount information and portfolio influence information preset in historical period, above-mentioned industry
It includes weather information and/or date feature information that business amount, which influences information,；
Training module 402 influences information and above-mentioned express delivery amount information, to preset introductory die according to above-mentioned portfolio
Type is trained, and obtains Traffic prediction model；
Output module 403, according in preset time step-length express delivery amount information and above-mentioned Traffic prediction model, it is defeated
Go out to predict express delivery amount information.
Optionally, above-mentioned training module 402, including：
Above-mentioned portfolio is influenced information and above-mentioned express delivery amount information, according to preset time step by training submodule
Length is trained preset initial model, determines Traffic prediction model.
Optionally, above-mentioned output module 403, including：
Input submodule, by the express delivery amount information before target date in above-mentioned preset time step-length, input is above-mentioned
Traffic prediction model；
Output sub-module exports the prediction express delivery amount information of above-mentioned target date.
Optionally, in the device of the express delivery amount of embodiment of the present invention prediction, above-mentioned preset initial model is length
Short-term memory network LSTM models.
Optionally, in the device of the express delivery amount of embodiment of the present invention prediction, above-mentioned preset time step is less than
The duration of above-mentioned default historical period.
The embodiment of the present invention additionally provides a kind of electronic equipment, as shown in figure 5, including processor 501, communication interface 502,
Memory 503 and communication bus 504, wherein processor 501, communication interface 502, memory 503 are complete by communication bus 504
At mutual communication,
Memory 503, for storing computer program；
Processor 501 executes following steps when for executing the program stored on memory 503：
Obtain the express delivery amount information and portfolio influence information preset in historical period, the portfolio influence information
Including weather information and/or date feature information；
Information and the express delivery amount information are influenced according to the portfolio, preset initial model is trained,
Obtain Traffic prediction model；
According in preset time step-length express delivery amount information and the Traffic prediction model, output prediction express delivery industry
Business amount information.
The embodiment of the present invention considers Multiple factors, such as weather information and/or date feature information.Therefore it can improve
The accuracy of express delivery amount information prediction.
Optionally, above-mentioned processor 501 is for when executing the program stored on memory 503, additionally it is possible to realize above-mentioned
The method of any express delivery amount prediction.
A kind of device of express delivery amount prediction provided in an embodiment of the present invention, can obtain fast in default historical period
Passing traffic information and portfolio influences information, and it includes weather information and/or date feature information that portfolio, which influences information, according to
Portfolio influences information and express delivery amount information, is trained to preset initial model, obtains Traffic prediction model, root
According to the express delivery amount information and Traffic prediction model in preset time step-length, output prediction express delivery amount information.This hair
Bright embodiment considers daily Multiple factors, such as weather information and/or date feature information.Therefore express delivery industry can be improved
The accuracy of business amount information prediction.Certainly, it implements any of the products of the present invention or method must be not necessarily required to reach above simultaneously
All advantages.
Machine readable storage medium may include RAM (Random Access Memory, random access memory), also may be used
To include NVM (Non-Volatile Memory, nonvolatile memory), for example, at least a magnetic disk storage.In addition, machine
Device readable storage medium storing program for executing can also be at least one storage device for being located remotely from aforementioned processor.
Above-mentioned processor can be general processor, including CPU (Central Processing Unit, central processing
Device), NP (Network Processor, network processing unit) etc.；Can also be DSP (Digital Signal Processing,
Digital signal processor), ASIC (Application Specific Integrated Circuit, application-specific integrated circuit),
FPGA (Field-Programmable Gate Array, field programmable gate array) or other programmable logic device are divided
Vertical door or transistor logic, discrete hardware components.
The embodiment of the present invention additionally provides a kind of computer readable storage medium, above computer readable storage medium storing program for executing memory
Computer program is contained, which realizes following steps when being executed by processor：
Obtain the express delivery amount information and portfolio influence information preset in historical period, the portfolio influence information
Including weather information and/or date feature information；
Information and the express delivery amount information are influenced according to the portfolio, preset initial model is trained,
Obtain Traffic prediction model；
According in preset time step-length express delivery amount information and the Traffic prediction model, output prediction express delivery industry
Business amount information.
The embodiment of the present invention considers Multiple factors, such as weather information and/or date feature information.Therefore it can improve
The accuracy of express delivery amount information prediction.
Optionally, when above computer program is executed by processor, additionally it is possible to realize any of the above-described express delivery amount prediction
Method.
It should be noted that herein, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also include other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
Each embodiment in this specification is all made of relevant mode and describes, identical similar portion between each embodiment
Point just to refer each other, and each embodiment focuses on the differences from other embodiments.Especially for device,
For electronic equipment and storage medium embodiment, since it is substantially similar to the method embodiment, so fairly simple, the phase of description
Place is closed referring to the part of embodiment of the method to illustrate.
The foregoing is merely the preferred embodiments of the application, are not intended to limit the protection domain of the application.It is all
Any modification, equivalent replacement, improvement and so within spirit herein and principle are all contained in the protection domain of the application
It is interior.
Claims (10)
1. a kind of method of express delivery amount prediction, which is characterized in that the method includes：
The express delivery amount information and portfolio influence information preset in historical period are obtained, the portfolio influence information includes
Weather information and/or date feature information；
Information and the express delivery amount information are influenced according to the portfolio, preset initial model is trained, is obtained
Traffic prediction model；
According in preset time step-length express delivery amount information and the Traffic prediction model, output prediction express delivery amount
Information.
2. according to the method described in claim 1, it is characterized in that, described influence information and the express delivery according to the portfolio
Traffic information is trained preset initial model, obtains Traffic prediction model, including：
The portfolio is influenced into information and the express delivery amount information, according to preset time step-length to preset initial model
It is trained, determines Traffic prediction model.
3. according to the method described in claim 1, it is characterized in that, the express delivery amount according in preset time step-length is believed
Breath and the Traffic prediction model, output prediction express delivery amount information, including：
By the express delivery amount information in target date foregoing description preset time step-length, the Traffic prediction model is inputted；
Export the prediction express delivery amount information of the target date.
4. according to the method described in claim 1, it is characterized in that, the preset initial model is shot and long term memory network
LSTM models.
5. according to the method described in claim 1, it is characterized in that, the preset time step-length is less than the default historical period
Duration.
6. a kind of device of express delivery amount prediction, which is characterized in that described device includes：
Acquisition module obtains the express delivery amount information and portfolio influence information preset in historical period, the portfolio shadow
It includes weather information and/or date feature information to ring information；
Training module influences information and the express delivery amount information according to the portfolio, is carried out to preset initial model
Training, obtains Traffic prediction model；
Output module, according in preset time step-length express delivery amount information and the Traffic prediction model, output prediction
Express delivery amount information.
7. device according to claim 6, which is characterized in that the training module, including：
The portfolio is influenced information and the express delivery amount information, according to preset time step-length to pre- by training submodule
If initial model be trained, determine Traffic prediction model.
8. device according to claim 6, which is characterized in that the output module, including：
Express delivery amount information in target date foregoing description preset time step-length is inputted the business by input submodule
Measure prediction model；
Output sub-module exports the prediction express delivery amount information of the target date.
9. a kind of electronic equipment, which is characterized in that including processor, communication interface, memory and communication bus, wherein described
Processor, the communication interface, the memory complete mutual communication by communication bus；The memory, for depositing
Put computer program；The processor when for executing the program stored on the memory, is realized in claim 1-5
Any one of them method and step.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer in the computer readable storage medium
Program realizes the method and step described in any one of claim 1-5 when the computer program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810421169.2A CN108596399A (en) | 2018-05-04 | 2018-05-04 | Method, apparatus, electronic equipment and the storage medium of express delivery amount prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810421169.2A CN108596399A (en) | 2018-05-04 | 2018-05-04 | Method, apparatus, electronic equipment and the storage medium of express delivery amount prediction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108596399A true CN108596399A (en) | 2018-09-28 |
Family
ID=63619874
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810421169.2A Pending CN108596399A (en) | 2018-05-04 | 2018-05-04 | Method, apparatus, electronic equipment and the storage medium of express delivery amount prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108596399A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109360625A (en) * | 2018-11-12 | 2019-02-19 | 四川骏逸富顿科技有限公司 | Forecasting system and prediction technique for internet middle or short term medical consultation portfolio |
| CN109816442A (en) * | 2019-01-16 | 2019-05-28 | 四川驹马科技有限公司 | A kind of various dimensions freight charges prediction technique and its system based on feature tag |
| CN109934385A (en) * | 2019-01-29 | 2019-06-25 | 跨越速运集团有限公司 | Goods amount prediction technique and system based on length Memory Neural Networks |
| CN110175695A (en) * | 2019-04-19 | 2019-08-27 | 跨越速运集团有限公司 | For the goods amount prediction technique and system during the Spring Festival |
| CN110889560A (en) * | 2019-12-06 | 2020-03-17 | 西北工业大学 | Express delivery sequence prediction method with deep interpretability |
| CN111401960A (en) * | 2020-03-19 | 2020-07-10 | 深圳市丰巢科技有限公司 | Intelligent cabinet specification recommendation method and device, server and storage medium |
| CN111415044A (en) * | 2020-03-24 | 2020-07-14 | 狄永杰 | Logistics distribution vehicle scheduling system and method based on big data |
| WO2020164275A1 (en) * | 2019-02-15 | 2020-08-20 | 平安科技（深圳）有限公司 | Processing result prediction method and apparatus based on prediction model, and server |
| CN111861006A (en) * | 2020-07-23 | 2020-10-30 | 上海中通吉网络技术有限公司 | Express delivery traffic prediction method, device and equipment based on cubic regression curve |
| CN111950781A (en) * | 2020-07-31 | 2020-11-17 | 上海中通吉网络技术有限公司 | Order arrival quantity prediction method and equipment |
| CN112183832A (en) * | 2020-09-17 | 2021-01-05 | 上海东普信息科技有限公司 | Express pickup quantity prediction method, device, equipment and storage medium |
| CN112312411A (en) * | 2019-07-29 | 2021-02-02 | 中国移动通信集团广东有限公司 | Traffic prediction method of VoLTE service and terminal equipment |
| CN112418534A (en) * | 2020-11-26 | 2021-02-26 | 上海东普信息科技有限公司 | Method and device for predicting collection quantity, electronic equipment and computer readable storage medium |
| CN112560325A (en) * | 2019-09-25 | 2021-03-26 | 奥动新能源汽车科技有限公司 | Prediction method, system, equipment and storage medium for battery swapping service |
| CN112990826A (en) * | 2021-04-15 | 2021-06-18 | 西南交通大学 | Short-time logistics demand prediction method, device, equipment and readable storage medium |
| CN113222057A (en) * | 2021-05-28 | 2021-08-06 | 中邮信息科技(北京)有限公司 | Data prediction model training method, data prediction device, data prediction equipment and data prediction medium |
| CN114579643A (en) * | 2022-05-05 | 2022-06-03 | 国家邮政局邮政业安全中心 | Express delivery traffic prediction method and device and electronic equipment |
| CN112560325B (en) * | 2019-09-25 | 2024-06-07 | 奥动新能源汽车科技有限公司 | Prediction method, system, equipment and storage medium for electricity conversion service |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090106033A1 (en) * | 2007-10-18 | 2009-04-23 | Ashok Thangavelu | System and Method for Estimating a Shipment Delivery Date |
| CN103617459A (en) * | 2013-12-06 | 2014-03-05 | 李敬泉 | Commodity demand information prediction method under multiple influence factors |
| WO2015040791A1 (en) * | 2013-09-20 | 2015-03-26 | 日本電気株式会社 | Order-volume determination device, order-volume determination method, recording medium, and order-volume determination system |
| CN105404945A (en) * | 2015-12-29 | 2016-03-16 | 中冶南方工程技术有限公司 | Harbor transportation volume prediction method and system |
| CN107403296A (en) * | 2017-06-29 | 2017-11-28 | 北京小度信息科技有限公司 | Conveyance equilibrium method and device |
| CN107678803A (en) * | 2017-09-30 | 2018-02-09 | 广东欧珀移动通信有限公司 | Using management-control method, device, storage medium and electronic equipment |
-
2018
- 2018-05-04 CN CN201810421169.2A patent/CN108596399A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090106033A1 (en) * | 2007-10-18 | 2009-04-23 | Ashok Thangavelu | System and Method for Estimating a Shipment Delivery Date |
| WO2015040791A1 (en) * | 2013-09-20 | 2015-03-26 | 日本電気株式会社 | Order-volume determination device, order-volume determination method, recording medium, and order-volume determination system |
| CN103617459A (en) * | 2013-12-06 | 2014-03-05 | 李敬泉 | Commodity demand information prediction method under multiple influence factors |
| CN105404945A (en) * | 2015-12-29 | 2016-03-16 | 中冶南方工程技术有限公司 | Harbor transportation volume prediction method and system |
| CN107403296A (en) * | 2017-06-29 | 2017-11-28 | 北京小度信息科技有限公司 | Conveyance equilibrium method and device |
| CN107678803A (en) * | 2017-09-30 | 2018-02-09 | 广东欧珀移动通信有限公司 | Using management-control method, device, storage medium and electronic equipment |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109360625B (en) * | 2018-11-12 | 2021-11-23 | 四川骏逸富顿科技有限公司 | Prediction system and prediction method for Internet medium-short term medication consultation business volume |
| CN109360625A (en) * | 2018-11-12 | 2019-02-19 | 四川骏逸富顿科技有限公司 | Forecasting system and prediction technique for internet middle or short term medical consultation portfolio |
| CN109816442A (en) * | 2019-01-16 | 2019-05-28 | 四川驹马科技有限公司 | A kind of various dimensions freight charges prediction technique and its system based on feature tag |
| CN109934385A (en) * | 2019-01-29 | 2019-06-25 | 跨越速运集团有限公司 | Goods amount prediction technique and system based on length Memory Neural Networks |
| WO2020164275A1 (en) * | 2019-02-15 | 2020-08-20 | 平安科技（深圳）有限公司 | Processing result prediction method and apparatus based on prediction model, and server |
| CN110175695A (en) * | 2019-04-19 | 2019-08-27 | 跨越速运集团有限公司 | For the goods amount prediction technique and system during the Spring Festival |
| CN110175695B (en) * | 2019-04-19 | 2022-06-17 | 跨越速运集团有限公司 | Method and system for predicting cargo volume during spring festival |
| CN112312411A (en) * | 2019-07-29 | 2021-02-02 | 中国移动通信集团广东有限公司 | Traffic prediction method of VoLTE service and terminal equipment |
| CN112560325B (en) * | 2019-09-25 | 2024-06-07 | 奥动新能源汽车科技有限公司 | Prediction method, system, equipment and storage medium for electricity conversion service |
| CN112560325A (en) * | 2019-09-25 | 2021-03-26 | 奥动新能源汽车科技有限公司 | Prediction method, system, equipment and storage medium for battery swapping service |
| CN110889560A (en) * | 2019-12-06 | 2020-03-17 | 西北工业大学 | Express delivery sequence prediction method with deep interpretability |
| CN111401960A (en) * | 2020-03-19 | 2020-07-10 | 深圳市丰巢科技有限公司 | Intelligent cabinet specification recommendation method and device, server and storage medium |
| CN111415044A (en) * | 2020-03-24 | 2020-07-14 | 狄永杰 | Logistics distribution vehicle scheduling system and method based on big data |
| CN111861006A (en) * | 2020-07-23 | 2020-10-30 | 上海中通吉网络技术有限公司 | Express delivery traffic prediction method, device and equipment based on cubic regression curve |
| CN111950781A (en) * | 2020-07-31 | 2020-11-17 | 上海中通吉网络技术有限公司 | Order arrival quantity prediction method and equipment |
| CN112183832A (en) * | 2020-09-17 | 2021-01-05 | 上海东普信息科技有限公司 | Express pickup quantity prediction method, device, equipment and storage medium |
| CN112418534B (en) * | 2020-11-26 | 2022-10-14 | 上海东普信息科技有限公司 | Method and device for predicting quantity of collected parts, electronic equipment and computer readable storage medium |
| CN112418534A (en) * | 2020-11-26 | 2021-02-26 | 上海东普信息科技有限公司 | Method and device for predicting collection quantity, electronic equipment and computer readable storage medium |
| CN112990826B (en) * | 2021-04-15 | 2021-11-02 | 西南交通大学 | Short-time logistics demand prediction method, device, equipment and readable storage medium |
| CN112990826A (en) * | 2021-04-15 | 2021-06-18 | 西南交通大学 | Short-time logistics demand prediction method, device, equipment and readable storage medium |
| CN113222057A (en) * | 2021-05-28 | 2021-08-06 | 中邮信息科技(北京)有限公司 | Data prediction model training method, data prediction device, data prediction equipment and data prediction medium |
| CN114579643A (en) * | 2022-05-05 | 2022-06-03 | 国家邮政局邮政业安全中心 | Express delivery traffic prediction method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108596399A (en) | Method, apparatus, electronic equipment and the storage medium of express delivery amount prediction | |
| US20210223434A1 (en) | Weather-driven multi-category infrastructure impact forecasting | |
| CN109615226B (en) | Operation index abnormity monitoring method | |
| Kisi et al. | Evaporation modelling by heuristic regression approaches using only temperature data | |
| CN108345958A (en) | A kind of order goes out to eat time prediction model construction, prediction technique, model and device | |
| CN106126391A (en) | System monitoring method and apparatus | |
| US8588821B1 (en) | Techniques for automatically outputting severe weather notifications at a user's mobile computing device | |
| CN105678398A (en) | Power load forecasting method based on big data technology, and research and application system based on method | |
| CN109583625A (en) | One kind pulling part amount prediction technique, system, equipment and storage medium | |
| Elsner et al. | Comparison of hurricane return levels using historical and geological records | |
| Sonnadara et al. | A Markov chain probability model to describe wet and dry patterns of weather at Colombo | |
| Liu et al. | Imputation of missing traffic data during holiday periods | |
| CN108446795A (en) | Power system load fluction analysis method, apparatus and readable storage medium storing program for executing | |
| CN111476441A (en) | Load prediction method for electric vehicle charging equipment and related device | |
| CN111260151A (en) | Multi-frequency dispatch duration prediction method, device, equipment and storage medium | |
| Liu et al. | Daily tourism demand forecasting: The impact of complex seasonal patterns and holiday effects | |
| Stemkovski et al. | Disorder or a new order: how climate change affects phenological variability | |
| US20190378406A1 (en) | Method of predicting a traffic behaviour in a road system | |
| CN108154259B (en) | Load prediction method and device for heat pump, storage medium, and processor | |
| CN116030617A (en) | Method and device for predicting traffic flow based on road OD data | |
| CN107704942A (en) | Distribution path determines method, apparatus and equipment | |
| Singh et al. | Load forecasting at distribution transformer using IoT based smart meter data from 6000 Irish homes | |
| CN107544785A (en) | A kind of application program update method and device | |
| Mandal et al. | Forecasting several-hours-ahead electricity demand using neural network | |
| CN115169731A (en) | Smart campus energy consumption prediction method, device, equipment and medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180928 |
|
| RJ01 | Rejection of invention patent application after publication |