CN109284856A - A kind of express delivery packaging material material requirement prediction technique, device and equipment, storage medium - Google Patents
A kind of express delivery packaging material material requirement prediction technique, device and equipment, storage medium Download PDFInfo
- Publication number
- CN109284856A CN109284856A CN201810826691.9A CN201810826691A CN109284856A CN 109284856 A CN109284856 A CN 109284856A CN 201810826691 A CN201810826691 A CN 201810826691A CN 109284856 A CN109284856 A CN 109284856A
- Authority
- CN
- China
- Prior art keywords
- express delivery
- packaging material
- delivery packaging
- data
- history
- 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.)
- Granted
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
- G06Q10/0838—Historical data
-
- 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
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- 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
Abstract
This application discloses a kind of express delivery packaging material material requirement prediction technique, device and equipment, storage medium, it is related to logistics field, due to carrying out the prediction of express delivery packaging material material requirement according to the history consumption data of RDC history quick despatch amount, express delivery packaging material material history delivering amount and site express delivery packaging material material, it accurate can predict the consumption requirements of express delivery packaging material material in a short time, the waste for avoiding express delivery packaging material material also saves the manpower during express delivery packaging material material forecast.
Description
Technical field
The present disclosure relates generally to logistics field more particularly to a kind of express delivery packaging material material requirement prediction technique, device and set
Standby, storage medium.
Background technique
In each site of logistics company, the main packaging material used when daily receipts are sent by special delivery include: waybill, file envelope,
Poly-bag, sealing tape are packed, these packaging materials belong to indispenseble expendables and monthly nearly 300,000,000 of dosage.
Not influence the development that the daily receipts in site send part business, the active predicting of material requirement is realized, to instruct to purchase
The stock of supply chain is produced and is distributed, while being received demand to the daily material of site convenient for goods and materials General Office and being standardized, and is shown
It obtains most important.
Currently, the prediction mode of express delivery packaging material material requirement, reports, estimation results after mainly manually being estimated by site
Dependent on empirical value, objectivity is inadequate, and the acquisition of historical data also relies on artificial collect statistics, and estimation results are by each site storehouse
Pipe responsible person mentions report to MRM system by hand, and whole process is upper inefficient in manpower and time investment, in addition, subsequent goods and materials disappear
Consumption reasonability and cost control are also difficult to meet demand.
Summary of the invention
In view of drawbacks described above in the prior art or deficiency, be intended to provide a kind of express delivery packaging material material requirement prediction technique,
Device and equipment, storage medium, to realize the accurate prediction for carrying out express delivery packaging material material requirement.
In a first aspect, the embodiment of the present invention provides a kind of express delivery packaging material material requirement prediction technique, comprising:
According to regional distribution centre RDC history quick despatch amount and express delivery packaging material material history delivering amount, express delivery packaging material is carried out
Material stock amount tentative prediction；
According to the history consumption data of site express delivery packaging material material, the Demand Forecast of site express delivery packaging material material is carried out；
According to the demand of the express delivery packaging material material stock amount tentative prediction result and the site express delivery packaging material material
Prediction result determines the prediction result of express delivery packaging material material stock amount.
Further, according to RDC history quick despatch amount and express delivery packaging material material history delivering amount, it is standby to carry out express delivery packaging material material
Goods amount tentative prediction, specifically includes:
RDC part amount predicted value is determined according to RDC history quick despatch amount；
Determine that express delivery packaging material material history disappears according to according to RDC history quick despatch amount and express delivery packaging material material history delivering amount
Consumption rate；
Express delivery packaging material supplies consumption rate predicted value is determined according to the express delivery packaging material material historical consumption rate；
According to the RDC part amount predicted value and the express delivery packaging material supplies consumption rate predicted value, express delivery packaging material material is carried out
Stock amount tentative prediction.
Further, the history consumption data according to site express delivery packaging material material carries out site express delivery packaging material material
Demand Forecast specifically includes:
Determine the history consumption data of site express delivery packaging material material；
Data processing is carried out to the history consumption data and determines data characteristics；
Data model is determined according to the data characteristics；
According to the history consumption data and data model, the prediction of site express delivery packaging material material requirement is carried out.
Further, described that data characteristics is determined to history consumption data progress data processing, it specifically includes:
The feature set of prediction model is constructed according to the history consumption data；
According to the feature set tectonic association feature of the prediction model；
According to the assemblage characteristic, Supplementing Data and standardization are carried out；
Feature after standardization is encoded；
Feature after coding is analyzed, determines data characteristics.
Wherein, the history consumption data specifically includes one of following or combination:
Site delivering amount monthly；
Express delivery packaging material material variety and monthly consumption；
Site region；
Site type；
Receive quantity of dispatching officers in site；
Each weight section express mail quantitative proportion in site.
Wherein, the assemblage characteristic specifically includes one of following or combination:
Set the monthly consumption of the quantity moon；
The year-on-year growth rate of each monthly consumption；
The sequential growth rate of each monthly consumption；
When monthly consumption compares the growth rate of the top n moon, N >=2.
Further, described that data model is determined according to the data characteristics, it specifically includes:
Feature is divided into multiple data sets, then training data and test data are divided to multiple data sets；
Modeling and arameter optimization are trained to more parts of training datas with xgboost algorithm；
Determine that data model is the training pattern that RMSE is minimum and result is stable.
Further, further includes:
Expressive ability with test set come training of judgement model on new data set, adjusting training model parameter, so that
RMSE between prediction result and the legitimate reading of test set is minimum.
Preferably, further includes:
According to the prediction result of express delivery packaging material material stock amount, generates supplier's stock production and send plan, Yi Jiqu with charge free
Temporary demand stock meter in domain warehouse is drawn.
Second aspect, the embodiment of the present invention also provide a kind of express delivery packaging material material requirement prediction meanss, comprising:
First predicting unit, for carrying out express delivery according to RDC history quick despatch amount and express delivery packaging material material history delivering amount
Packaging material material stock amount tentative prediction；
Second predicting unit carries out site express delivery packaging material for the history consumption data according to site express delivery packaging material material
The Demand Forecast of material；
Third predicting unit, for according to the express delivery packaging material material stock amount tentative prediction result and the site express delivery
The Demand Forecast of packaging material material is as a result, determine the prediction result of express delivery packaging material material stock amount.
Further, first predicting unit is specifically used for:
RDC part amount predicted value is determined according to RDC history quick despatch amount；
Determine that express delivery packaging material material history disappears according to according to RDC history quick despatch amount and express delivery packaging material material history delivering amount
Consumption rate；
Express delivery packaging material supplies consumption rate predicted value is determined according to the express delivery packaging material material historical consumption rate；
According to the RDC part amount predicted value and the express delivery packaging material supplies consumption rate predicted value, express delivery packaging material material is carried out
Stock amount tentative prediction.
Further, second predicting unit is specifically used for:
Determine the history consumption data of site express delivery packaging material material；
Data processing is carried out to the history consumption data and determines data characteristics；
Data model is determined according to the data characteristics；
According to the history consumption data and data model, the prediction of site express delivery packaging material material requirement is carried out.
Further, second predicting unit carries out data processing to the history consumption data and determines data characteristics,
It specifically includes:
The feature set of prediction model is constructed according to the history consumption data；
According to the feature set tectonic association feature of the prediction model；
According to the assemblage characteristic, Supplementing Data and standardization are carried out；
Feature after standardization is encoded；
Feature after coding is analyzed, determines data characteristics.
Wherein, the history consumption data specifically includes one of following or combination:
Site delivering amount monthly；
Express delivery packaging material material variety and monthly consumption；
Site region；
Site type；
Receive quantity of dispatching officers in site；
Each weight section express mail quantitative proportion in site.
Wherein, the assemblage characteristic specifically includes one of following or combination:
Set the monthly consumption of the quantity moon；
The year-on-year growth rate of each monthly consumption；
The sequential growth rate of each monthly consumption；
When monthly consumption compares the growth rate of the top n moon, N >=2.
Further, second predicting unit determines data model according to the data characteristics, specifically includes:
Feature is divided into multiple data sets, then training data and test data are divided to multiple data sets；
Modeling and arameter optimization are trained to more parts of training datas with xgboost algorithm；
Determine that data model is the training pattern that RMSE is minimum and result is stable.
Further, second predicting unit is also used to:
After determining that data model is RMSE is minimum and result is stable training pattern, with test set come training of judgement model
Expressive ability on new data set, adjusting training model parameter, so that between prediction result and the legitimate reading of test set
RMSE it is minimum.
Preferably, the third predicting unit is also used to:
According to the prediction result of express delivery packaging material material stock amount, generates supplier's stock production and send plan, Yi Jiqu with charge free
Temporary demand stock meter in domain warehouse is drawn.
The third aspect, the embodiment of the present invention also provide a kind of equipment, including processor and memory；
The memory includes can be by instruction that the processor executes so that the processor executes such as first aspect
Described in method.
Fourth aspect, the embodiment of the present invention also provide a kind of computer readable storage medium, are stored thereon with computer journey
Sequence, the computer program is for realizing the method as described in first aspect.
The embodiment of the present invention provides a kind of express delivery packaging material material requirement prediction technique, device and equipment, storage medium, due to
According to the history consumption data of RDC history quick despatch amount, express delivery packaging material material history delivering amount and site express delivery packaging material material
Carry out carry out express delivery packaging material material requirement prediction, can accurate prediction express delivery packaging material material requirement, avoid express delivery packaging material object
The waste of material also saves the manpower during express delivery packaging material material forecast.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is express delivery packaging material material requirement prediction technique flow chart provided in an embodiment of the present invention；
Fig. 2 is provided in an embodiment of the present invention according to history part amount and express delivery packaging material material history delivering amount progress express delivery packet
Material material stock amount tentative prediction schematic diagram；
Fig. 3 is provided in an embodiment of the present invention according to the progress site express delivery of the history consumption data of site express delivery packaging material material
The Demand Forecast schematic diagram of packaging material material；
Fig. 4 is express delivery packaging material material requirement prediction meanss structural schematic diagram provided in an embodiment of the present invention；
Fig. 5 is that express delivery packaging material material requirement provided in an embodiment of the present invention predicts device structure schematic diagram.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Referring to FIG. 1, express delivery packaging material material requirement prediction technique provided in an embodiment of the present invention, comprising:
Step S101, according to RDC (regional distribution center, regional distribution centre) history part amount and
Express delivery packaging material material history delivering amount carries out the stock amount tentative prediction of express delivery packaging material material；
Step S102, according to the history consumption data of site express delivery packaging material material, the need of site express delivery packaging material material are carried out
The amount of asking is predicted；
Step S103, according to the demand of express delivery packaging material material stock amount tentative prediction result and site express delivery packaging material material
Prediction result determines the prediction result of express delivery packaging material material stock amount.
Due to according to RDC history quick despatch amount, express delivery packaging material material history delivering amount and site express delivery packaging material material
History consumption data carry out carry out express delivery packaging material material requirement prediction, can accurate prediction express delivery packaging material material requirement, keep away
The waste for exempting from express delivery packaging material material also saves the manpower during express delivery packaging material material forecast.
Further, it as shown in Fig. 2, in step S101, is delivered according to RDC history quick despatch amount and express delivery packaging material material history
Amount carries out the stock amount tentative prediction of express delivery packaging material material, specifically includes:
RDC part amount predicted value is determined according to RDC history quick despatch amount；
Determine that express delivery packaging material material history disappears according to according to RDC history quick despatch amount and express delivery packaging material material history delivering amount
Consumption rate；
Express delivery packaging material supplies consumption rate predicted value is determined according to express delivery packaging material material historical consumption rate；
According to RDC part amount predicted value and express delivery packaging material supplies consumption rate predicted value, at the beginning of carrying out express delivery packaging material material stock amount
Step prediction.
In general, predetermined period is relatively common as unit of the moon, can also be according to the actual situation single with week certainly
Position, as unit of season, year, or as unit of the defined time cycle.When using the moon as predetermined period, RDC history is fast
Part amount and express delivery packaging material material history delivering amount are passed, each means the monthly history part amount of RDC and the monthly history hair of express delivery packaging material material
Goods amount, RDC part amount predicted value refer to the monthly part amount predicted value of RDC, and express delivery packaging material material historical consumption rate refers to the express delivery packaging material material moon
Historical consumption rate is spent, express delivery packaging material supplies consumption rate predicted value refers to the monthly consumption rate prediction of express delivery packaging material material, express delivery packaging material object
Material stock amount tentative prediction then refers to the monthly stock amount tentative prediction of express delivery packaging material material.
In Fig. 2, SKU group table shows express delivery packaging material material, it is generally the case that every kind of express delivery packaging material material needs individually to carry out demand
Prediction.ASURU and SAP is the database of operation system.
The accuracy rate of usual RDC part amount prediction can reach 90% or more, and prediction switchs to predict on line under line, also larger
Improve forecasting efficiency.
Further, in step S102, according to the history consumption data of site express delivery packaging material material, site express delivery packaging material is carried out
The Demand Forecast of material, specifically includes:
Determine the history consumption data of site express delivery packaging material material；
Data processing is carried out to history consumption data and determines data characteristics；
Data model is determined according to data characteristics；
According to history consumption data and data model, the prediction of site express delivery packaging material material requirement is carried out.
The establishment of data model is carried out according to data characteristics, and then is carried out carrying out site express delivery packet according to the data model
The prediction of material material requirement, can be further improved the accuracy of site express delivery packaging material material requirement prediction.
Further, data processing is carried out to history consumption data and determines data characteristics, specifically included:
The feature set of prediction model is constructed according to history consumption data；
According to the feature set tectonic association feature of prediction model；
According to assemblage characteristic, Supplementing Data and standardization are carried out；
Feature after standardization is encoded；
Feature after coding is analyzed, determines data characteristics.
Wherein, history consumption data specifically includes one of following or combination:
Site delivering amount monthly；
Express delivery packaging material material variety and monthly consumption；
Site region；
Site type；
Receive quantity of dispatching officers in site；
Each weight section express mail quantitative proportion in site.
Assemblage characteristic specifically includes one of following or combination:
Set the monthly consumption of the quantity moon；
The year-on-year growth rate of each monthly consumption；
The sequential growth rate of each monthly consumption；
When monthly consumption compares the growth rate of the top n moon, N >=2.
Generally if desired predict the express delivery packaging material material requirement of the M month, then available following data and feature:
M-2 monthly consumption；
Start 3 months monthly consumptions forward the M-2 month；
Start 6 months monthly consumptions forward the M-2 month；
Start 12 months monthly consumptions forward the M-2 month；
M-2 monthly consumption year-on-year growth rate；
M-2 monthly consumption sequential growth rate；
Growth rate before M-2 monthly consumption is compared first 3 months；
Growth rate before M-2 monthly consumption is compared first 6 months；
Site affiliated area type；Such as residential quarter, shopping centre etc.；
The affiliated urban area in site；Such as Shenzhen, Shanghai etc.；
Express delivery packaging material material type；Such as file envelope, packaging gummed paper, tape, waybill etc.；
Receive quantity of dispatching officers in site；
The monthly part amount in site；
Each weight segment amount accounting in site.
Weight section can divide are as follows: 0-1kg, 1-3kg, 3-5kg, 5-10kg, 10-30kg, 30kg or more.
It according to actual needs and applicable cases, can also include ring ratio between other linear combination features, feature, on year-on-year basis
Or the features such as normal state.
According to assemblage characteristic, when carrying out Supplementing Data and standardization, completion can be carried out to the data of missing, to continuous
Feature be standardized so that mean value is 0, variance 1, in practical application, those skilled in the art can be according to practical need
Specific completion and standardized content are adjusted.
When being encoded to the feature after standardization, it can be encoded using one-hot, those skilled in the art can also root
Other suitable coding modes are used according to actual conditions.
It when analyzing the feature after coding, can specifically include: correlation analysis, feature importance are carried out to feature
Analysis, Monotonicity Analysis.
Further, data model is determined according to data characteristics, specifically included:
Feature is divided into multiple data sets, then training data and test data are divided to multiple data sets；
Modeling and arameter optimization are trained to more parts of training datas with xgboost algorithm；
Determine that data model is the training pattern that RMSE is minimum and result is stable.
Wherein,
XobsIt is predicted value, XmodelIt is true value.
Further, after determining data model, further data model can also be adjusted with test set, thus
More accurate data model is obtained, at this point, this method further include:
Expressive ability with test set come training of judgement model on new data set, adjusting training model parameter, so that
RMSE between prediction result and the legitimate reading of test set is minimum.
The data flow of site express delivery packaging material material requirement prediction is carried out as shown in figure 3, obtaining data from corresponding database
Construction feature collection is modeled by xgboost algorithm, to obtain prediction result.In Fig. 3, SAP, OMS and DVP are pair
The database for the operation system answered.
As shown in Figures 2 and 3, the prediction result of step S101 and step S102 can be aggregated into MRM (operation system)
In, in MRM system, the audit of data can be further carried out by corresponding responsible person；Demand in MRM system after auditing
Data can be pushed to further in SAP system by MRM system, after the warehouse RDC end responsible person checks confirmation, generate supply
Quotient, which gets ready the goods, produces and sends with charge free plan and regional warehouse temporary demand stock meter stroke.
Preferably, after step s 103, supply can also be generated according to the prediction result of express delivery packaging material material stock amount
Quotient, which gets ready the goods, produces and sends with charge free plan and regional warehouse temporary demand stock meter stroke, to further increase working efficiency.
By the express delivery packaging material material requirement prediction technique, big data technology is relied on, the business in conjunction with different demands end is special
Point customizes prediction model, gets through material consumption and predicts relevant business datum interface, realizes and turns under prediction graph on line
Change, and prediction model is docked with operation system MRM, so that prediction process is full-automatic, provides prediction result by MRM system
And the intuitive displaying of related keyword index, meanwhile, machine learning algorithm is introduced, forecasting efficiency is improved, so that the processing time is by 83
Man day foreshortens within 15min, and provides the prediction result based on portfolio and refer to site or portion of area, and site or portion of area are by must
It must submit to be converted to and be confirmed according to reference value or modified, solve site leakage and propose or propose late the influence to whole operation flow, due to
The raising of forecasting accuracy also further reduces site temporary demand and proposes the report frequency, so that area storehouse inventory cost reduces 10%
More than.
It should be noted that although describing the operation of the method for the present invention in the accompanying drawings with particular order, this is not required that
Or hint must execute these operations in this particular order, or have to carry out operation shown in whole and be just able to achieve the phase
The result of prestige.On the contrary, the step of describing in flow chart can change and execute sequence.For example, step S101 and step S102.It is additional
Multiple steps are merged into a step and executed, and/or a step is decomposed by ground or it is alternatively possible to omit certain steps
For execution of multiple steps.For example, step S101 and step S102.
The embodiment of the present invention correspondingly provides a kind of express delivery packaging material material requirement prediction meanss, as shown in Figure 4, comprising:
First predicting unit 401, for carrying out according to RDC history quick despatch amount and express delivery packaging material material history delivering amount
Express delivery packaging material material stock amount tentative prediction；
Second predicting unit 402 carries out site express delivery packet for the history consumption data according to site express delivery packaging material material
The Demand Forecast of material material；
Third predicting unit 403, for according to express delivery packaging material material stock amount tentative prediction result and site express delivery packaging material
The Demand Forecast of material is as a result, determine the prediction result of express delivery packaging material material stock amount.
Further, the first predicting unit 401 is specifically used for:
RDC part amount predicted value is determined according to RDC history quick despatch amount；
Determine that express delivery packaging material material history disappears according to according to RDC history quick despatch amount and express delivery packaging material material history delivering amount
Consumption rate；
Express delivery packaging material supplies consumption rate predicted value is determined according to express delivery packaging material material historical consumption rate；
According to RDC part amount predicted value and express delivery packaging material supplies consumption rate predicted value, at the beginning of carrying out express delivery packaging material material stock amount
Step prediction.
Further, the second predicting unit 402 is specifically used for:
Determine the history consumption data of site express delivery packaging material material；
Data processing is carried out to history consumption data and determines data characteristics；
Data model is determined according to data characteristics；
According to history consumption data and data model, the prediction of site express delivery packaging material material requirement is carried out.
Further, the second predicting unit 402 carries out data processing to history consumption data and determines data characteristics, specific to wrap
It includes:
The feature set of prediction model is constructed according to history consumption data；
According to the feature set tectonic association feature of prediction model；
According to assemblage characteristic, Supplementing Data and standardization are carried out；
Feature after standardization is encoded；
Feature after coding is analyzed, determines data characteristics.
Wherein, history consumption data specifically includes one of following or combination:
Site delivering amount monthly；
Express delivery packaging material material variety and monthly consumption；
Site region；
Site type；
Receive quantity of dispatching officers in site；
Each weight section express mail quantitative proportion in site.
Wherein, assemblage characteristic specifically includes one of following or combination:
Set the monthly consumption of the quantity moon；
The year-on-year growth rate of each monthly consumption；
The sequential growth rate of each monthly consumption；
When monthly consumption compares the growth rate of the top n moon, N >=2.
Further, the second predicting unit 402 determines data model according to data characteristics, specifically includes:
Feature is divided into multiple data sets, then training data and test data are divided to multiple data sets；
Modeling and arameter optimization are trained to more parts of training datas with xgboost algorithm；
Determine that data model is the training pattern that RMSE is minimum and result is stable.
Further, the second predicting unit 402 is also used to:
After determining that data model is RMSE is minimum and result is stable training pattern, with test set come training of judgement model
Expressive ability on new data set, adjusting training model parameter, so that between prediction result and the legitimate reading of test set
RMSE it is minimum.
Preferably, third predicting unit 403 is also used to:
According to the prediction result of express delivery packaging material material stock amount, generates supplier's stock production and send plan, Yi Jiqu with charge free
Temporary demand stock meter in domain warehouse is drawn.
It should be appreciated that all units or module recorded in the device and each step phase in the method with reference to Fig. 1 description
It is corresponding.It is equally applicable to the device and unit wherein included above with respect to the operation and feature of method description as a result, herein not
It repeats again.The device can be realized in advance in the browser of electronic equipment or other security applications, and downloading etc. can also be passed through
Mode and be loaded into the browser or its security application of electronic equipment.Corresponding units in the device can in electronic equipment
Unit cooperate to realize the scheme of the embodiment of the present application.
Below with reference to Fig. 5, it illustrates the calculating of the terminal device or server that are suitable for being used to realize the embodiment of the present application
The structural schematic diagram of machine system.
It, can be according to being stored in read-only storage as shown in figure 5, computer system includes central processing unit (CPU) 501
Program in device (ROM) 502 is executed from the program that storage section 508 is loaded into random access storage device (RAM) 503
Various movements appropriate and processing.In RAM 503, it is also stored with various programs and data needed for system operatio.CPU
501, ROM 502 and RAM 503 is connected with each other by bus 504.Input/output (I/O) interface 505 is also connected to bus
504。
I/O interface 505 is connected to lower component: the importation 506 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 507 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 508 including hard disk etc.；
And the communications portion 509 of the network interface card including LAN card, modem etc..Communications portion 509 via such as because
The network of spy's net executes communication process.Driver 510 is also connected to I/O interface 505 as needed.Detachable media 511, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 510, in order to read from thereon
Computer program be mounted into storage section 508 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer software above with reference to the process of Fig. 1 description
Program.For example, embodiment of the disclosure includes a kind of computer program product comprising be tangibly embodied in machine readable media
On computer program, the computer program includes program code for executing the method for Fig. 1.In such embodiment
In, which can be downloaded and installed from network by communications portion 509, and/or from 511 quilt of detachable media
Installation.
Flow chart and block diagram in attached drawing are illustrated according to the system of various embodiments of the invention, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart, Ke Yiyong
The dedicated hardware based system of defined functions or operations is executed to realize, or can be referred to specialized hardware and computer
The combination of order is realized.
Being described in the embodiment of the present application involved unit or module can be realized by way of software, can also be with
It is realized by way of hardware.Described unit or module also can be set in the processor, for example, can be described as:
A kind of processor includes XX unit, YY unit and ZZ unit.Wherein, the title of these units or module is under certain conditions simultaneously
The restriction to the unit or module itself is not constituted, for example, XX unit is also described as " unit for XX ".
As on the other hand, present invention also provides a kind of computer readable storage medium, the computer-readable storage mediums
Matter can be computer readable storage medium included in device described in above-described embodiment；It is also possible to individualism, not
The computer readable storage medium being fitted into equipment.Computer-readable recording medium storage has one or more than one journey
Sequence, described program are used to execute the formula input method for being described in the application by one or more than one processor.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from the inventive concept, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (20)
1. a kind of express delivery packaging material material requirement prediction technique characterized by comprising
According to regional distribution centre RDC history quick despatch amount and express delivery packaging material material history delivering amount, express delivery packaging material material is carried out
Stock amount tentative prediction；
According to the history consumption data of site express delivery packaging material material, the Demand Forecast of site express delivery packaging material material is carried out；
According to the Demand Forecast of the express delivery packaging material material stock amount tentative prediction result and the site express delivery packaging material material
As a result, determining the prediction result of express delivery packaging material material stock amount.
2. the method as described in claim 1, which is characterized in that according to RDC history quick despatch amount and express delivery packaging material material history
Delivering amount carries out the stock amount tentative prediction of express delivery packaging material material, specifically includes:
RDC part amount predicted value is determined according to RDC history quick despatch amount；
Determine that express delivery packaging material material history consumes according to according to RDC history quick despatch amount and express delivery packaging material material history delivering amount
Rate；
Express delivery packaging material supplies consumption rate predicted value is determined according to the express delivery packaging material material historical consumption rate；
According to the RDC part amount predicted value and the express delivery packaging material supplies consumption rate predicted value, express delivery packaging material material stock is carried out
Measure tentative prediction.
3. the method as described in claim 1, which is characterized in that described to consume number according to the history of site express delivery packaging material material
According to the Demand Forecast of progress site express delivery packaging material material specifically includes:
Determine the history consumption data of site express delivery packaging material material；
Data processing is carried out to the history consumption data and determines data characteristics；
Data model is determined according to the data characteristics；
According to the history consumption data and data model, the prediction of site express delivery packaging material material requirement is carried out.
4. method as claimed in claim 3, which is characterized in that described to be determined to history consumption data progress data processing
Data characteristics specifically includes:
The feature set of prediction model is constructed according to the history consumption data；
According to the feature set tectonic association feature of the prediction model；
According to the assemblage characteristic, Supplementing Data and standardization are carried out；
Feature after standardization is encoded；
Feature after coding is analyzed, determines data characteristics.
5. method as claimed in claim 4, which is characterized in that the history consumption data specifically includes one of following or group
It closes:
Site delivering amount monthly；
Express delivery packaging material material variety and monthly consumption；
Site region；
Site type；
Receive quantity of dispatching officers in site；
Each weight section express mail quantitative proportion in site.
6. method as claimed in claim 4, which is characterized in that the assemblage characteristic specifically includes one of following or combination:
Set the monthly consumption of the quantity moon；
The year-on-year growth rate of each monthly consumption；
The sequential growth rate of each monthly consumption；
When monthly consumption compares the growth rate of the top n moon, N >=2.
7. method as claimed in claim 3, which is characterized in that it is described that data model is determined according to the data characteristics, specifically
Include:
Feature is divided into multiple data sets, then training data and test data are divided to multiple data sets；
Modeling and arameter optimization are trained to more parts of training datas with xgboost algorithm；
Determine that data model is the training pattern that RMSE is minimum and result is stable.
8. the method for claim 7, which is characterized in that further include:
Expressive ability with test set come training of judgement model on new data set, adjusting training model parameter, so that prediction
As a result the RMSE between the legitimate reading of test set is minimum.
9. the method as described in claim 1, which is characterized in that further include:
According to the prediction result of express delivery packaging material material stock amount, generates supplier's stock production and send plan and region storehouse with charge free
Temporary demand stock meter in library is drawn.
10. a kind of express delivery packaging material material requirement prediction meanss characterized by comprising
First predicting unit, for carrying out express delivery packaging material according to RDC history quick despatch amount and express delivery packaging material material history delivering amount
Material stock amount tentative prediction；
Second predicting unit carries out site express delivery packaging material material for the history consumption data according to site express delivery packaging material material
Demand Forecast；
Third predicting unit, for according to the express delivery packaging material material stock amount tentative prediction result and the site express delivery packaging material
The Demand Forecast of material is as a result, determine the prediction result of express delivery packaging material material stock amount.
11. device as claimed in claim 10, which is characterized in that first predicting unit is specifically used for:
RDC part amount predicted value is determined according to RDC history quick despatch amount；
Determine that express delivery packaging material material history consumes according to according to RDC history quick despatch amount and express delivery packaging material material history delivering amount
Rate；
Express delivery packaging material supplies consumption rate predicted value is determined according to the express delivery packaging material material historical consumption rate；
According to the RDC part amount predicted value and the express delivery packaging material supplies consumption rate predicted value, express delivery packaging material material stock is carried out
Measure tentative prediction.
12. device as claimed in claim 10, which is characterized in that second predicting unit is specifically used for:
Determine the history consumption data of site express delivery packaging material material；
Data processing is carried out to the history consumption data and determines data characteristics；
Data model is determined according to the data characteristics；
According to the history consumption data and data model, the prediction of site express delivery packaging material material requirement is carried out.
13. device as claimed in claim 12, which is characterized in that second predicting unit to the history consumption data into
Row data processing determines data characteristics, specifically includes:
The feature set of prediction model is constructed according to the history consumption data；
According to the feature set tectonic association feature of the prediction model；
According to the assemblage characteristic, Supplementing Data and standardization are carried out；
Feature after standardization is encoded；
Feature after coding is analyzed, determines data characteristics.
14. device as claimed in claim 13, which is characterized in that the history consumption data specifically includes one of following or group
It closes:
Site delivering amount monthly；
Express delivery packaging material material variety and monthly consumption；
Site region；
Site type；
Receive quantity of dispatching officers in site；
Each weight section express mail quantitative proportion in site.
15. device as claimed in claim 13, which is characterized in that the assemblage characteristic specifically includes one of following or combination:
Set the monthly consumption of the quantity moon；
The year-on-year growth rate of each monthly consumption；
The sequential growth rate of each monthly consumption；
When monthly consumption compares the growth rate of the top n moon, N >=2.
16. device as claimed in claim 12, which is characterized in that second predicting unit is determined according to the data characteristics
Data model specifically includes:
Feature is divided into multiple data sets, then training data and test data are divided to multiple data sets；
Modeling and arameter optimization are trained to more parts of training datas with xgboost algorithm；
Determine that data model is the training pattern that RMSE is minimum and result is stable.
17. device as claimed in claim 16, which is characterized in that second predicting unit is also used to:
After determining that data model is RMSE is minimum and result is stable training pattern, with test set come training of judgement model new
Data set on expressive ability, adjusting training model parameter, so that between prediction result and the legitimate reading of test set
RMSE is minimum.
18. device as claimed in claim 10, which is characterized in that the third predicting unit is also used to:
According to the prediction result of express delivery packaging material material stock amount, generates supplier's stock production and send plan and region storehouse with charge free
Temporary demand stock meter in library is drawn.
19. a kind of equipment, including processor and memory；It is characterized by:
The memory includes can be by instruction that the processor executes so that the processor executes claim 1-9 such as appoints
Method described in one.
20. a kind of computer readable storage medium is stored thereon with computer program, the computer program is for realizing such as power
Benefit requires any method of 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810826691.9A CN109284856B (en) | 2018-07-25 | 2018-07-25 | Express package material demand prediction method, device and equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810826691.9A CN109284856B (en) | 2018-07-25 | 2018-07-25 | Express package material demand prediction method, device and equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109284856A true CN109284856A (en) | 2019-01-29 |
| CN109284856B CN109284856B (en) | 2022-06-07 |
Family
ID=65183200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810826691.9A Active CN109284856B (en) | 2018-07-25 | 2018-07-25 | Express package material demand prediction method, device and equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109284856B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340278A (en) * | 2020-02-19 | 2020-06-26 | 上海东普信息科技有限公司 | Method for predicting destination cargo volume and storage medium |
| CN112036631A (en) * | 2020-08-25 | 2020-12-04 | 广州视源电子科技股份有限公司 | Purchasing quantity determination method, device, equipment and storage medium |
| CN112258117A (en) * | 2020-10-27 | 2021-01-22 | 上海寻梦信息技术有限公司 | Sending method and device, electronic equipment and storage medium |
| CN112613774A (en) * | 2020-12-28 | 2021-04-06 | 浙江智昌机器人科技有限公司 | MRP algorithm based on data feedback |
| CN112903017A (en) * | 2021-01-26 | 2021-06-04 | 顾远航 | Intelligent logistics state information monitoring system and method |
| CN113283798A (en) * | 2021-06-11 | 2021-08-20 | 杉数科技(北京)有限公司 | Method and device for determining material consumption quantity, electronic equipment and storage medium |
| CN113283924A (en) * | 2020-02-20 | 2021-08-20 | 纬创资通股份有限公司 | Demand forecasting method and demand forecasting device |
| CN113516438A (en) * | 2021-08-06 | 2021-10-19 | 上海中通吉网络技术有限公司 | Express package state judgment method |
| US11526845B2 (en) | 2020-04-07 | 2022-12-13 | Coupang Corp. | Systems and methods for automated outbound profile generation |
| CN116703301A (en) * | 2023-06-15 | 2023-09-05 | 山东盛太锆业资源有限公司 | Zirconia waste material management and control method based on information of multiple recovery warehouses |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020169657A1 (en) * | 2000-10-27 | 2002-11-14 | Manugistics, Inc. | Supply chain demand forecasting and planning |
| JP2003146434A (en) * | 2001-11-14 | 2003-05-21 | Jcb:Kk | Ic card order inventory management system and method |
| US20140337000A1 (en) * | 2013-05-09 | 2014-11-13 | Rockwell Automation Technologies, Inc. | Using cloud-based data for industrial simulation |
| CN105787587A (en) * | 2016-02-26 | 2016-07-20 | 海南电网有限责任公司 | Power system emergency material demand prediction method based on multiple regressions |
| CN106600032A (en) * | 2016-10-28 | 2017-04-26 | 北京国电通网络技术有限公司 | Inventory material demand predicting method and device |
| KR20170102079A (en) * | 2016-02-29 | 2017-09-07 | 주식회사 글로비트 | Enery saving system for marinenursery facilities based on Internet of Things(IoT) |
| CN107292429A (en) * | 2017-06-07 | 2017-10-24 | 上海欧睿供应链管理有限公司 | A kind of Demand Forecast Model system of selection analyzed based on demand characteristics |
| CN107784397A (en) * | 2017-11-09 | 2018-03-09 | 贵州电网有限责任公司 | A kind of power network material requirements forecasting system and its Forecasting Methodology |
-
2018
- 2018-07-25 CN CN201810826691.9A patent/CN109284856B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020169657A1 (en) * | 2000-10-27 | 2002-11-14 | Manugistics, Inc. | Supply chain demand forecasting and planning |
| JP2003146434A (en) * | 2001-11-14 | 2003-05-21 | Jcb:Kk | Ic card order inventory management system and method |
| US20140337000A1 (en) * | 2013-05-09 | 2014-11-13 | Rockwell Automation Technologies, Inc. | Using cloud-based data for industrial simulation |
| CN105787587A (en) * | 2016-02-26 | 2016-07-20 | 海南电网有限责任公司 | Power system emergency material demand prediction method based on multiple regressions |
| KR20170102079A (en) * | 2016-02-29 | 2017-09-07 | 주식회사 글로비트 | Enery saving system for marinenursery facilities based on Internet of Things(IoT) |
| CN106600032A (en) * | 2016-10-28 | 2017-04-26 | 北京国电通网络技术有限公司 | Inventory material demand predicting method and device |
| CN107292429A (en) * | 2017-06-07 | 2017-10-24 | 上海欧睿供应链管理有限公司 | A kind of Demand Forecast Model system of selection analyzed based on demand characteristics |
| CN107784397A (en) * | 2017-11-09 | 2018-03-09 | 贵州电网有限责任公司 | A kind of power network material requirements forecasting system and its Forecasting Methodology |
Non-Patent Citations (2)
| Title |
|---|
| 严冬梅: "城市物流中心选址问题研究", 《中国优秀博硕士学位论文全文数据库 经济与管理科学辑》 * |
| 顾雪景: "我国高铁货运市场需求分析与开行模式研究", 《中国优秀硕士学位论文全文数据库 经济与管理科学辑》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340278A (en) * | 2020-02-19 | 2020-06-26 | 上海东普信息科技有限公司 | Method for predicting destination cargo volume and storage medium |
| CN111340278B (en) * | 2020-02-19 | 2023-10-24 | 上海东普信息科技有限公司 | Destination cargo quantity prediction method and storage medium |
| TWI786376B (en) * | 2020-02-20 | 2022-12-11 | 緯創資通股份有限公司 | Demand forecasting method and demand forecasting apparatus |
| CN113283924A (en) * | 2020-02-20 | 2021-08-20 | 纬创资通股份有限公司 | Demand forecasting method and demand forecasting device |
| US11568429B2 (en) | 2020-02-20 | 2023-01-31 | Wistron Corporation | Demand forecasting method and demand forecasting apparatus |
| CN113283924B (en) * | 2020-02-20 | 2024-05-07 | 纬创资通股份有限公司 | Demand prediction method and demand prediction device |
| US11526845B2 (en) | 2020-04-07 | 2022-12-13 | Coupang Corp. | Systems and methods for automated outbound profile generation |
| CN112036631A (en) * | 2020-08-25 | 2020-12-04 | 广州视源电子科技股份有限公司 | Purchasing quantity determination method, device, equipment and storage medium |
| CN112258117B (en) * | 2020-10-27 | 2021-09-21 | 上海寻梦信息技术有限公司 | Sending method and device, electronic equipment and storage medium |
| CN112258117A (en) * | 2020-10-27 | 2021-01-22 | 上海寻梦信息技术有限公司 | Sending method and device, electronic equipment and storage medium |
| CN112613774A (en) * | 2020-12-28 | 2021-04-06 | 浙江智昌机器人科技有限公司 | MRP algorithm based on data feedback |
| CN112903017A (en) * | 2021-01-26 | 2021-06-04 | 顾远航 | Intelligent logistics state information monitoring system and method |
| CN113283798A (en) * | 2021-06-11 | 2021-08-20 | 杉数科技(北京)有限公司 | Method and device for determining material consumption quantity, electronic equipment and storage medium |
| CN113516438A (en) * | 2021-08-06 | 2021-10-19 | 上海中通吉网络技术有限公司 | Express package state judgment method |
| CN116703301B (en) * | 2023-06-15 | 2023-12-08 | 山东盛太锆业资源有限公司 | Zirconia waste material management and control method based on information of multiple recovery warehouses |
| CN116703301A (en) * | 2023-06-15 | 2023-09-05 | 山东盛太锆业资源有限公司 | Zirconia waste material management and control method based on information of multiple recovery warehouses |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109284856B (en) | 2022-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109284856A (en) | A kind of express delivery packaging material material requirement prediction technique, device and equipment, storage medium | |
| Benjaafar et al. | Carbon footprint and the management of supply chains: Insights from simple models | |
| Acar et al. | A decision support framework for global supply chain modelling: an assessment of the impact of demand, supply and lead-time uncertainties on performance | |
| Pokrovskaya et al. | Assessment of transport and storage systems | |
| Ferreira et al. | Demand response models with correlated price data: A robust optimization approach | |
| Zhong et al. | Optimal trade credit and replenishment policies for supply chain network design | |
| US20090313145A1 (en) | Allocating carbon offsets for printing tasks | |
| US10121120B2 (en) | Information processing system and recording device | |
| WO2008154734A1 (en) | An investment analysis and planning system and method | |
| US8315923B2 (en) | Method of determining safety stock levels | |
| WO2013102932A2 (en) | System and method facilitating forecasting, optimization and visualization of energy data for an industry | |
| Cheong et al. | Understanding the behavior of business groups: A dynamic model and empirical analysis | |
| US20030101062A1 (en) | Large scale procurement of energy efficiency resources | |
| CN110110924A (en) | A kind of power distribution network scale of investment optimization method, device and calculate equipment | |
| Vlckova et al. | Role of demand planning in business process management | |
| Dalle Ave et al. | A non-uniform grid approach for scheduling considering electricity load tracking and future load prediction | |
| Aazami et al. | Benders decomposition algorithm for robust aggregate production planning considering pricing decisions in competitive environment: A case study | |
| Turken et al. | The impact of co-location in emissions regulation clusters on traditional and vendor managed supply chain inventory decisions | |
| Ben Ahmed et al. | Long‐term effects of short planning horizons for inventory routing problems | |
| JP2008021170A (en) | Power plant value evaluation system and its program | |
| Rafke et al. | Simulating fleet procurement in an Indonesian logistics company | |
| Sastry Musti | Multicriteria Decision Analysis for Sustainable Green Financing in Energy Sector | |
| Tian et al. | Simulation-based aggregate planning of batch plant operations | |
| Mou | Nonlinear pricing schemes for mobilizing residential flexibility in power systems. | |
| Busch et al. | Estimation of avoided costs for electric utility demand-side planning |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |