CN109840730A - Method and device for data prediction - Google Patents
Method and device for data prediction Download PDFInfo
- Publication number
- CN109840730A CN109840730A CN201711222407.9A CN201711222407A CN109840730A CN 109840730 A CN109840730 A CN 109840730A CN 201711222407 A CN201711222407 A CN 201711222407A CN 109840730 A CN109840730 A CN 109840730A
- Authority
- CN
- China
- Prior art keywords
- data
- commodity
- history
- order data
- scoring
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a kind of method and device for data prediction.It is related to computer information processing field, this method comprises: obtaining the order data in the predetermined time, the order data includes the relevant information of commodity;The order data is subjected to polymerization processing to extract polymerization achievement data;The polymerization achievement data input prediction model is obtained to the scoring of the commodity;And the sales volume of the commodity is predicted by the scoring.Method and device disclosed in the present application for data prediction, can predict and control commodity amount and inventory cost in warehouse, and maximizes improve commodity distribution timeliness on this basis, improve customer satisfaction.
Description
Technical field
The present invention relates to computer information processing fields, in particular to a kind of method and dress for data prediction
It sets.
Background technique
It is to meet that supply chain management, which covers various aspects, the targets such as product flowing, information flow and Capital Flow,
Under the premise of customer need, maximizing reduces logistics and inventory cost.In e-commerce industry, the key of customer satisfaction is improved
One of be to reduce delivery duration, therefore electric business company can all select in the warehouse for establishing oneself apart from the closer position of customer,
To have shortest delivery distance and most fast actual effect after customer places an order.And in realistic problem, apart from the closer position of customer
Only seldom geographical space is set, causes the warehouse capacity opened up smaller, is unable to store all SKU (Stock keeping
Unit, commodity minimum unit), so the SKU for how selecting a part that can accommodate is stored in the warehouse closer apart from customer,
It is that this item patent solves the problems, such as to achieve the purpose that maximization meets customer demand under the premise of guaranteeing inventory cost.
In the prior art, generally according to the sales volume for polymerizeing each SKU in History Order, according to the descending sequence of sales volume,
Select part SKU in the top as white list.But practical business is more complicated, is retouched according to above-mentioned to the prior art
It states, it can be found that the prior art can have a following four aspects disadvantage: first, customer often buys multiple simultaneously when lower single
SKU, it may occur that while the case where the purchase amount of countervailing SKU and high sales volume SKU, the order of the customer still cannot in this case
It is delivered completely by the warehouse for closing on customer, leads to actual effect increase of honouring an agreement.Second, the big SKU of some sales volumes are by some or certain
Several customer's purchases, if such SKU is placed on warehouse, the satisfaction of fraction customer can only be also promoted, it can be for example, having
Two SKU, SKU1 buy 50 parts there are two user respectively, sell 100 parts altogether;SKU2 has 60 clients to buy one respectively
Part, purchase has sold 60 parts altogether.If entering the rule of white list according to high sales volume SKU, SKU1 can be white into what is finally determined
List, and SKU2 then will not, but in this case, the order of two customers can only be met, and have lost 60 customers'
Satisfaction.Third, the prior art are based on a hypothesis: the history sales volume sequence of each SKU is consistent with the following sales volume sequence, that is, goes through
The larger SKU in the top of sales volume in history, sales volume is also bigger in following order.But in practical situations, due to promoting
The reasons such as pin and season, history and following situation are not fully consistent, so there are relatively large deviations for the prior art.4th, base
It is different from following hypothesis in history, it is believed that many because being known as of each SKU future order volume are influenced, and the prior art is only
Consider the information of SKU history sales volume.
Therefore, it is necessary to a kind of new method and devices for data prediction.
Above- mentioned information are only used for reinforcing the understanding to background of the invention, therefore it disclosed in the background technology part
It may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
In view of this, the present invention provides a kind of method and device for data prediction, it can predict and control in warehouse
Commodity amount and inventory cost, and maximize improve commodity distribution timeliness on this basis, improve customer satisfaction.
Other characteristics and advantages of the invention will be apparent from by the following detailed description, or partially by the present invention
Practice and acquistion.
According to an aspect of the invention, it is proposed that a kind of method for data prediction, this method comprises: obtaining the predetermined time
Interior order data, the order data include the relevant information of commodity;The order data is subjected to polymerization processing to extract
It polymerize achievement data;The polymerization achievement data input prediction model is obtained to the scoring of the commodity;And by described
The sales volume of the commodity is predicted in scoring.
In a kind of exemplary embodiment of the disclosure, further includes: by the scoring of the commodity, adjust commodity in warehouse
Quantity and type.
In a kind of exemplary embodiment of the disclosure, the scoring by the commodity adjusts commodity in warehouse
Quantity and type, comprising: the commodity in warehouse successively sort according to the scoring;And predetermined is chosen according to the sequence
Inventory of the commodity of quantity as warehouse.
In a kind of exemplary embodiment of the disclosure, further includes: built by History Order data and history inventory data
Found the prediction model.
It is described that institute is established by History Order data and history inventory data in a kind of exemplary embodiment of the disclosure
State prediction model, comprising: using History Order data as the input feature vector of machine learning algorithm;Using history inventory data as machine
The mark value of device learning algorithm;And the prediction model is generated by the machine learning algorithm.
It is described that the prediction mould is generated by the machine learning algorithm in a kind of exemplary embodiment of the disclosure
Type, comprising: decision Tree algorithms are promoted by gradient and generate the prediction model.
It is described that institute is established by History Order data and history inventory data in a kind of exemplary embodiment of the disclosure
State prediction model, further includes: obtain the order data in the first historical time;And by the order in first historical time
Data carry out polymerization processing to generate the History Order data.
It is described that institute is established by History Order data and history inventory data in a kind of exemplary embodiment of the disclosure
State prediction model, further includes: obtain the inventory data in the second historical time;Calculate the inventory in second historical time
According to optimal solution;And the history inventory data is generated by the optimal solution.
In a kind of exemplary embodiment of the disclosure, the inventory data calculated in second historical time is most
Excellent solution, including it is following at least one: pass through Zero-one integer programming algorithm and obtain the optimal solution;And it is resolved by near-optimization
Method obtains the optimal solution.
In a kind of exemplary embodiment of the disclosure, comprising:
Objective function:
Constraint condition:
xj,ξi∈{0,1};
Wherein, xj=1, which represents j-th of commodity, is selected, aij=1, which represents i-th of order, includes j-th of commodity, ξi=1 generation
I-th of order of table is satisfied, and α is fill rate, and M is blanket order amount.
According to an aspect of the invention, it is proposed that a kind of device for data prediction, which includes: data module, is used
In obtaining the order data in the predetermined time, the order data includes the relevant information of commodity;Aggregation module, being used for will be described
Order data carries out polymerization processing to extract polymerization achievement data;Grading module, it is pre- for inputting the polymerization achievement data
Model is surveyed to obtain the scoring of the commodity;And prediction module, for being carried out by sales volume of the scoring to the commodity
Prediction.
In a kind of exemplary embodiment of the disclosure, further includes: processing module, for the scoring by the commodity,
Adjust the quantity and type of commodity in warehouse.
According to an aspect of the invention, it is proposed that a kind of electronic equipment, which includes: one or more processors;
Storage device, for storing one or more programs;When one or more programs are executed by one or more processors, so that one
A or multiple processors realize such as methodology above.
According to an aspect of the invention, it is proposed that a kind of computer-readable medium, is stored thereon with computer program, feature
It is, method as mentioned in the above is realized when program is executed by processor.
Method and device according to the present invention for data prediction, can predict and control commodity amount and library in warehouse
It is saved as this, and maximizes improve commodity distribution timeliness on this basis, improves customer satisfaction.
It should be understood that the above general description and the following detailed description are merely exemplary, this can not be limited
Invention.
Detailed description of the invention
Its example embodiment is described in detail by referring to accompanying drawing, above and other target of the invention, feature and advantage will
It becomes more fully apparent.Drawings discussed below is only some embodiments of the present invention, for the ordinary skill of this field
For personnel, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of system block diagram of method for data prediction shown according to an exemplary embodiment.
Fig. 2 is a kind of flow chart of method for data prediction shown according to an exemplary embodiment.
Fig. 3 is a kind of flow chart of the method for data prediction shown according to another exemplary embodiment.
Fig. 4 is a kind of block diagram of device for data prediction shown according to an exemplary embodiment.
Fig. 5 is a kind of block diagram of the device for data prediction shown according to another exemplary embodiment.
Fig. 6 is the block diagram of a kind of electronic equipment shown according to an exemplary embodiment.
Fig. 7 schematically shows a kind of computer readable storage medium schematic diagram in disclosure exemplary embodiment.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be real in a variety of forms
It applies, and is not understood as limited to embodiment set forth herein;On the contrary, thesing embodiments are provided so that the present invention will be comprehensively and complete
It is whole, and the design of example embodiment is comprehensively communicated to those skilled in the art.Identical appended drawing reference indicates in figure
Same or similar part, thus repetition thereof will be omitted.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In example.In the following description, many details are provided to provide and fully understand to the embodiment of the present invention.However,
It will be appreciated by persons skilled in the art that technical solution of the present invention can be practiced without one or more in specific detail,
Or it can be using other methods, constituent element, device, step etc..In other cases, it is not shown in detail or describes known side
Method, device, realization or operation are to avoid fuzzy each aspect of the present invention.
Block diagram shown in the drawings is only functional entity, not necessarily must be corresponding with physically separate entity.
I.e., it is possible to realize these functional entitys using software form, or realized in one or more hardware modules or integrated circuit
These functional entitys, or these functional entitys are realized in heterogeneous networks and/or processor device and/or microcontroller device.
Flow chart shown in the drawings is merely illustrative, it is not necessary to including all content and operation/step,
It is not required to execute by described sequence.For example, some operation/steps can also decompose, and some operation/steps can close
And or part merge, therefore the sequence actually executed is possible to change according to the actual situation.
It should be understood that although herein various assemblies may be described using term first, second, third, etc., these groups
Part should not be limited by these terms.These terms are to distinguish a component and another component.Therefore, first group be discussed herein below
Part can be described as the second component without departing from the teaching of disclosure concept.As used herein, term " and/or " include associated
All combinations for listing any of project and one or more.
It will be understood by those skilled in the art that attached drawing is the schematic diagram of example embodiment, module or process in attached drawing
Necessary to not necessarily implementing the present invention, therefore it cannot be used for limiting the scope of the invention.
Fig. 1 is a kind of system block diagram of method for data prediction shown according to an exemplary embodiment.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications, such as the application of shopping class, net can be installed on terminal device 101,102,103
The application of page browsing device, searching class application, instant messaging tools, mailbox client, social platform software etc..
Terminal device 101,102,103 can be the various electronic equipments with display screen and supported web page browsing, packet
Include but be not limited to smart phone, tablet computer, pocket computer on knee and desktop computer etc..
Server 105 can be to provide the server of various services, such as utilize terminal device 101,102,103 to user
The shopping class website browsed provides the back-end data storage server supported.Background server can purchase the commodity received
The relevant information bought analyze etc. processing, and by processing result (such as article sales data, merchandise sales prediction data etc.)
Feed back to terminal device.
It should be noted that method for generating message provided by the embodiment of the present application is generally executed by server 105, accordingly
Ground, auto-building html files device are generally positioned in client 101.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
Fig. 2 is a kind of flow chart of method for data prediction shown according to an exemplary embodiment.
As shown in Fig. 2, obtaining the order data in the predetermined time, the order data includes the phase of commodity in S202
Close information.It can be for example, obtaining trimestral History Order data forward with current time to refer to.It include using in order data
The merchandise news of family purchase can be bought product name (SKU title), type for example including the time buying.Buy the quantity of commodity
Etc. details.
History Order detailed data can be for example shown in following table:
Wherein, order_id represents the unique encodings of each order, and each order_id represents a different order, phase
With order to have identical order_id user_id representative to place an order subscriber-coded, each user_id represent one it is different
Customer, identical customer have identical user_id.
Sale_qtty represents the quantity that the customer buys a certain SKU in the order;
Sale_ord_dt represents single date under customer;
The dispatching warehouse that the place of acceptance that delv_center_num represents the customer is belonged to;
Sku_id represents the unique encodings for the SKU that the customer buys in the order.
In S204, the order data is subjected to polymerization processing to extract polymerization achievement data.Order data is carried out
Valuable information in data is extracted in polymerization processing, and the information mainly extracted can be for example as shown in the table:
In S206, the polymerization achievement data input prediction model is obtained to the scoring of the commodity.Machine learning
Theory mainly design and analyze it is some allow computer can automatic " study " algorithm.Machine learning algorithm is a kind of from data
In automatically analyze acquisition rule, and the algorithm that assimilated equations predict unknown data.It can be for example, passing through machine learning algorithm
In gradient promote decision Tree algorithms and generate the prediction model.
Gradient promotes decision tree (Gradient Boosting Decision Tree, GBDT), is a kind of decision of iteration
Tree algorithm, the algorithm are made of more decision trees, and the conclusion of all trees, which adds up, does final result.It at the beginning of being suggested just
It is together considered as the stronger algorithm of generalization ability with SVM.Tree in GBDT is regression tree (not being classification tree), and GBDT is used to do
Regression forecasting can be used for classifying after adjustment.In GBDT, by M iteration, each iteration generates a regression tree mould
Type, in each iteration by so that loss function is smaller and smaller, thus may be used to the negative gradient direction of loss function is mobile
To obtain more and more accurate model.
The aggregate index data above obtained input is promoted into decision Tree algorithms by gradient and generates the prediction model
In, input the scoring of the commodity.
In S208, the sales volume of the commodity is predicted by the scoring.Scoring may be, for example, the form of probability
Output, the probability the big, indicates, within following one period, a possibility which is sold is higher.
Method according to the present invention for data prediction, establishes prediction model using gradient decision Tree algorithms, and will go through
History order data inputs the model, and then obtains the mode of the following Sales Volume of Commodity prediction, can predict and control commodity in warehouse
Quantity and inventory cost, and maximize improve commodity distribution timeliness on this basis, improve customer satisfaction.
It will be clearly understood that the present disclosure describe how being formed and using particular example, but the principle of the present invention is not limited to
These exemplary any details.On the contrary, the introduction based on present disclosure, these principles can be applied to many other
Embodiment.
Fig. 3 is a kind of flow chart of the method for data prediction shown according to another exemplary embodiment.Fig. 3 is to build
Found the exemplary description of the process of the prediction model.
In S302, using History Order data as the input feature vector of machine learning algorithm.Wherein, when obtaining the first history
Interior order data;And the order data in first historical time is subjected to polymerization processing and is ordered with generating the history
Forms data.The polymerization processing of History Order data can step in exemplary reference S202, details are not described herein.
In S304, using history inventory data as the mark value of machine learning algorithm.Wherein, the second historical time is obtained
Interior inventory data;Calculate the optimal solution of the inventory data in second historical time;And it is generated by the optimal solution
The history inventory data.
Inventory record detailed data can be for example as shown in the table:
sku_id | delv_center_num | stock_qtty | dt |
4879844 | 4 | 20 | 2017-09-27 |
4609868 | 4 | 100 | 2017-09-27 |
4510588 | 2 | 1099 | 2017-09-27 |
3510478 | 2 | 321 | 2017-09-27 |
4461494 | 4 | 1089 | 2017-09-27 |
3510478 | 2 | 222 | 2017-09-27 |
2600248 | 4 | 20 | 2017-09-27 |
4371862 | 10 | 0 | 2017-09-27 |
4507940 | 10 | 10 | 2017-09-27 |
4507940 | 4 | 19 | 2017-09-27 |
Wherein, delv_center_num represents the warehouse where the SKU;
Sku_id represents the unique encodings of SKU;
Stock_qtty represents the SKU in the existing stockpile number in the warehouse;
Dt represents the stockpile number record date.
Upper and lower cabinet state detailed data can be for example as shown in the table:
sku_id | delv_center_num | dt | status |
4879844 | 4 | 2017-09-27 | 0 |
4609868 | 4 | 2017-09-27 | 1 |
4510588 | 2 | 2017-09-27 | 2 |
3510478 | 2 | 2017-09-27 | 2 |
4461494 | 4 | 2017-09-27 | 1 |
3510478 | 2 | 2017-09-27 | 1 |
2600248 | 4 | 2017-09-27 | 1 |
4371862 | 10 | 2017-09-27 | 1 |
4507940 | 10 | 2017-09-27 | 0 |
4507940 | 4 | 2017-09-27 | 0 |
Wherein, delv_center_num represents the warehouse where the SKU;
Sku_id represents the unique encodings of SKU;
Dt represents the stockpile number record date;
Status represents the SKU in the cabinet state encoding up and down in the warehouse: cabinet under 0, and cabinet on 1,2 to upper cabinet.
Because the order of history belongs to Given information, can calculate for example using the order data of each SKU to reach one
The quantity of minimum SKU required for fixed fill rate, i.e., if these SKU are in the white list of history, history
Fill rate is up to maximum.It, can be for example using the Zero-one integer programming method for optimizing field of planning strategies for solve this problem.
Operational research: operational research is an important specialized core course of Modern administrology.It is early 1930s development
The new branch of science got up, main purpose are to provide scientific basis in decision for administrative staff, be realize effectively management,
One of correct decisions and the important method of modern management.The subject is the cross-cutting research of applied mathematics and formal science, benefit
With the methods of statistics, mathematical model and algorithm, best or near optimal the answer in challenge is looked for.
Linear programming: linear programming (Linear programming, abbreviation LP) be studied in operational research relatively early, development compared with
Fastly, it is widely used, the important branch that method is more mature, it is a kind of mathematical method for assisting people to carry out scientific management.
Study the mathematical theory and method of the extreme-value problem of Linear Constraints lower linear objective function.
Integer programming: integer programming refers to that the variable (all or part) in planning is limited to integer, if in linear model
In, variable is limited to integer, then referred to as integral linear programming.
Decision variable: be policymaker be realize the object of planning take scheme, measure, be problem Chinese medicine determine it is unknown
Amount.
In the embodiment of the present application, according to the above, objective function and constraint condition can for example be set as following form:
Objective function:
Constraint condition:All i are set up;
xj,ξi∈{0,1};
Wherein, xj=1, which represents j-th of commodity, is selected, aij=1, which represents i-th of order, includes j-th of commodity, ξi=1 generation
I-th of order of table is satisfied, and α is fill rate, and M is blanket order amount.
Objective function: refer to problem purpose requirement to be achieved, be expressed as the function of decision variable.In above formula, examine
Consider the condition of capacity and SKU quantity, the objective function of the present embodiment is the quantity for minimizing SKU in white list.
Constraint condition: when decision variable value by various available resources limited, be expressed as containing decision variable
Equation or inequality.In the present embodiment, constraint condition is respectively as follows:
To each order, if the order can be satisfied (ξi=1), then all SKU in order all in white list
In, otherwise the order cannot be satisfied (ξ i=0);
Theoretical Service Efficiency is more than or equal to fill rate to be achieved (α);
Whether commodity selected and order is all that (0- is 0-1 variable whether it is satisfied;1- is no) by above method, it can be with
Determine whether each SKU should theoretically appear in the white list of history.
In S306, the prediction model is generated by the machine learning algorithm.Using History Order data as machine
The input feature vector of learning algorithm passes through machine learning algorithm pair using history inventory data as the mark value of machine learning algorithm
Data are trained, and then generate the prediction model.
In a kind of exemplary embodiment of the disclosure, further includes: by the scoring of the commodity, adjust commodity in warehouse
Quantity and type.Commodity in warehouse are successively sorted according to the scoring;And predetermined number is chosen according to the sequence
Inventory of the commodity of amount as warehouse.Scoring may be, for example, the form output of probability, and the bigger expression SKU of probability is more possible to out
In the present following white list namely the SKU is possible larger in following order volume.In the present embodiment, white list can be such as
Refer to that the SKU stored in the warehouse for closing on customer gathers.
It, can be for example, policymaker needs according to warehouse capacity size or the storehouse in a kind of exemplary embodiment of the disclosure
Library overlay area demand size determines the SKU quantity that the warehouse may accommodate, and is denoted as A.Model exports each SKU and will order in future
It is single to measure biggish probability, by the descending sequence of probability value, preceding A SKU in the top is exported as following white list.
It will be appreciated by those skilled in the art that realizing that all or part of the steps of above-described embodiment is implemented as being executed by CPU
Computer program.When the computer program is executed by CPU, above-mentioned function defined by the above method provided by the invention is executed
Energy.The program can store in a kind of computer readable storage medium, which can be read-only memory, magnetic
Disk or CD etc..
Further, it should be noted that above-mentioned attached drawing is only place included by method according to an exemplary embodiment of the present invention
Reason schematically illustrates, rather than limits purpose.It can be readily appreciated that above-mentioned processing shown in the drawings is not indicated or is limited at these
The time sequencing of reason.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Following is apparatus of the present invention embodiment, can be used for executing embodiment of the present invention method.For apparatus of the present invention reality
Undisclosed details in example is applied, embodiment of the present invention method is please referred to.
Fig. 4 is a kind of block diagram of device for data prediction shown according to an exemplary embodiment.As shown in figure 4,
Device 40 for data prediction includes: data module 402, aggregation module 404, grading module 406 and prediction module 408.
Data module 402 is used to obtain the order data in the predetermined time, and the order data includes the related letter of commodity
Breath.The order data includes the relevant information of commodity.It can be for example, being reference with current time, acquisition is trimestral forward to go through
History order data.Include the merchandise news of user's purchase in order data, product name can be bought for example including the time buying
(SKU title), type.Buy the details such as the quantity of commodity.
Aggregation module 404 is used to carry out the order data polymerization processing to extract polymerization achievement data.By order numbers
According to polymerization processing is carried out, valuable information in data is extracted.
Grading module 406 is used to obtain on the polymerization achievement data input prediction model scoring of the commodity.Machine
The device theories of learning be mainly design and analyze it is some allow computer can automatic " study " algorithm.Machine learning algorithm is a kind of
It is automatically analyzed from data and obtains rule, and the algorithm that assimilated equations predict unknown data.It can be for example, passing through engineering
It practises the gradient in algorithm and promotes the decision Tree algorithms generation prediction model.
Prediction module 408 is used to predict the sales volume of the commodity by the scoring.Scoring may be, for example, probability
Form output, the probability the big, indicates, within following one period, a possibility which is sold is higher.
Device 40 in a kind of exemplary embodiment of the disclosure, for data prediction further include: processing module is (in figure
It is not shown) for the scoring by the commodity, adjust the quantity and type of commodity in warehouse.By the scoring of the commodity,
Adjust the quantity and type of commodity in warehouse.Commodity in warehouse are successively sorted according to the scoring;And according to the row
Sequence chooses inventory of the commodity of predetermined number amount as warehouse.
Fig. 5 is a kind of block diagram of the device for data prediction shown according to another exemplary embodiment.For data
The device 50 of prediction includes: data acquisition module 502, data processing module 504, history optimal solution computing module 506, training mould
Pattern block 508 and output model module 510.
Wherein, data acquisition module 502 is used to obtain the order data in the predetermined time.Data processing module 504 is used for
The order data is subjected to polymerization processing to extract polymerization achievement data.History optimal solution computing module 506, because history
Order belongs to Given information, and the order data of each SKU can be used in we, calculates to reach certain fill rate institute
The quantity of the minimum SKU needed, i.e., if these SKU are in the white list of history, the fill rate of history is up to
It is maximum.To solve this problem, for example optimal solution can be sought by usage history optimal solution computing module 506.Training pattern module
508, using History Order data as the input feature vector of machine learning algorithm, using history inventory data as machine learning algorithm
Mark value is trained data by training pattern module 508, and output model module 510 exports last training pattern.
Fig. 6 is the block diagram of a kind of electronic equipment shown according to an exemplary embodiment.
The electronic equipment 600 of this embodiment according to the present invention is described referring to Fig. 6.The electronics that Fig. 6 is shown
Equipment 600 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in fig. 6, electronic equipment 600 is showed in the form of universal computing device.The component of electronic equipment 600 can wrap
It includes but is not limited to: at least one processing unit 610, at least one storage unit 620, (including the storage of the different system components of connection
Unit 620 and processing unit 610) bus 630, display unit 640 etc..
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 610
Row, so that the processing unit 610 executes described in this specification above-mentioned electronic prescription circulation processing method part according to this
The step of inventing various illustrative embodiments.For example, the processing unit 610 can execute step as shown in Figure 2.
The storage unit 620 may include the readable medium of volatile memory cell form, such as random access memory
Unit (RAM) 6201 and/or cache memory unit 6202 can further include read-only memory unit (ROM) 6203.
The storage unit 620 can also include program/practical work with one group of (at least one) program module 6205
Tool 6204, such program module 6205 includes but is not limited to: operating system, one or more application program, other programs
It may include the realization of network environment in module and program data, each of these examples or certain combination.
Bus 630 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 600 can also be with one or more external equipments 300 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 600 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 600 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 650.Also, electronic equipment 600 can be with
By network adapter 660 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.Network adapter 660 can be communicated by bus 630 with other modules of electronic equipment 600.It should
Understand, although not shown in the drawings, other hardware and/or software module can be used in conjunction with electronic equipment 600, including but unlimited
In: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and number
According to backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server or network equipment etc.) executes the above-mentioned electronics according to disclosure embodiment
Prescription circulation processing method.
Fig. 7 schematically shows a kind of computer readable storage medium schematic diagram in disclosure exemplary embodiment.
Refering to what is shown in Fig. 7, describing the program product for realizing the above method of embodiment according to the present invention
700, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The computer readable storage medium may include in a base band or the data as the propagation of carrier wave a part are believed
Number, wherein carrying readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetism
Signal, optical signal or above-mentioned any appropriate combination.Readable storage medium storing program for executing can also be any other than readable storage medium storing program for executing
Readable medium, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or
Person's program in connection.The program code for including on readable storage medium storing program for executing can transmit with any suitable medium, packet
Include but be not limited to wireless, wired, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
Above-mentioned computer-readable medium carries one or more program, when said one or multiple programs are by one
When the equipment executes, so that the computer-readable medium implements function such as: the order data in the predetermined time is obtained, it is described to order
Forms data includes the relevant information of commodity;The order data is subjected to polymerization processing to extract polymerization achievement data;It will be described
It polymerize achievement data input prediction model to obtain the scoring of the commodity;And by the scoring to the sales volume of the commodity
It is predicted.
It will be appreciated by those skilled in the art that above-mentioned each module can be distributed in device according to the description of embodiment, it can also
Uniquely it is different from one or more devices of the present embodiment with carrying out corresponding change.The module of above-described embodiment can be merged into
One module, can also be further split into multiple submodule.
By the description of above embodiment, those skilled in the art is it can be readily appreciated that example embodiment described herein
It can also be realized in such a way that software is in conjunction with necessary hardware by software realization.Therefore, implement according to the present invention
The technical solution of example can be embodied in the form of software products, which can store in a non-volatile memories
In medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) or on network, including some instructions are so that a calculating equipment (can
To be personal computer, server, mobile terminal or network equipment etc.) it executes according to the method for the embodiment of the present invention.
It is particularly shown and described exemplary embodiment of the present invention above.It should be appreciated that the present invention is not limited to
Detailed construction, set-up mode or implementation method described herein;On the contrary, it is intended to cover included in appended claims
Various modifications and equivalence setting in spirit and scope.
In addition, structure shown by this specification Figure of description, ratio, size etc., only to cooperate specification institute
Disclosure, for skilled in the art realises that be not limited to the enforceable qualifications of the disclosure with reading, therefore
Do not have technical essential meaning, the modification of any structure, the change of proportionate relationship or the adjustment of size are not influencing the disclosure
Under the technical effect and achieved purpose that can be generated, it should all still fall in technology contents disclosed in the disclosure and obtain and can cover
In the range of.Meanwhile cited such as "upper" in this specification, " first ", " second " and " one " term, be also only and be convenient for
Narration is illustrated, rather than to limit the enforceable range of the disclosure, relativeness is altered or modified, without substantive change
Under technology contents, when being also considered as the enforceable scope of the present invention.
Claims (14)
1. a kind of method for data prediction characterized by comprising
The order data in the predetermined time is obtained, the order data includes the relevant information of commodity;
The order data is subjected to polymerization processing to extract polymerization achievement data;
The polymerization achievement data input prediction model is obtained to the scoring of the commodity;And
The sales volume of the commodity is predicted by the scoring.
2. the method as described in claim 1, which is characterized in that further include:
By the scoring of the commodity, the quantity and type of commodity in warehouse are adjusted.
3. method according to claim 2, which is characterized in that the scoring by the commodity adjusts commodity in warehouse
Quantity and type, comprising:
Commodity in warehouse are successively sorted according to the scoring;And
Inventory of the commodity of predetermined number amount as warehouse is chosen according to the sequence.
4. the method as described in claim 1, which is characterized in that further include:
The prediction model is established by History Order data and history inventory data.
5. method as claimed in claim 4, which is characterized in that described to be established by History Order data and history inventory data
The prediction model, comprising:
Using History Order data as the input feature vector of machine learning algorithm;
Using history inventory data as the mark value of machine learning algorithm;And
The prediction model is generated by the machine learning algorithm.
6. method as claimed in claim 5, which is characterized in that described to generate the prediction mould by the machine learning algorithm
Type, comprising:
Decision Tree algorithms, which are promoted, by gradient generates the prediction model.
7. method as claimed in claim 5, which is characterized in that described to be established by History Order data and history inventory data
The prediction model, further includes:
Obtain the order data in the first historical time;And
Order data in first historical time is subjected to polymerization processing to generate the History Order data.
8. method as claimed in claim 5, which is characterized in that described to be established by History Order data and history inventory data
The prediction model, further includes:
Obtain the inventory data in the second historical time;
Calculate the optimal solution of the inventory data in second historical time;And
The history inventory data is generated by the optimal solution.
9. method according to claim 8, which is characterized in that described to calculate inventory data in second historical time
Optimal solution, including it is following at least one:
The optimal solution is obtained by Zero-one integer programming algorithm;And
The optimal solution is obtained by near-optimization resolving Algorithm.
10. method as claimed in claim 9 characterized by comprising
Objective function:
Constraint condition:All i are set up;
xj,ξi∈{0,1};
Wherein, xj=1, which represents j-th of commodity, is selected, aij=1, which represents i-th of order, includes j-th of commodity, ξi=1 represents i-th
A order is satisfied, and α is fill rate, and M is blanket order amount.
11. a kind of device for data prediction characterized by comprising
Data module, for obtaining the order data in the predetermined time, the order data includes the relevant information of commodity;
Aggregation module, for the order data to be carried out polymerization processing to extract polymerization achievement data;
Grading module, for the polymerization achievement data input prediction model to be obtained to the scoring of the commodity;And
Prediction module, for being predicted by the scoring the sales volume of the commodity.
12. device as claimed in claim 11, which is characterized in that further include:
Processing module adjusts the quantity and type of commodity in warehouse for the scoring by the commodity.
13. a kind of electronic equipment characterized by comprising
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1-10.
14. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that described program is held by processor
The method as described in any in claim 1-10 is realized when row.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711222407.9A CN109840730B (en) | 2017-11-29 | 2017-11-29 | Method and device for data prediction |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711222407.9A CN109840730B (en) | 2017-11-29 | 2017-11-29 | Method and device for data prediction |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109840730A true CN109840730A (en) | 2019-06-04 |
CN109840730B CN109840730B (en) | 2021-06-29 |
Family
ID=66881756
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711222407.9A Active CN109840730B (en) | 2017-11-29 | 2017-11-29 | Method and device for data prediction |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109840730B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111310977A (en) * | 2020-01-20 | 2020-06-19 | 重庆亚德科技股份有限公司 | Big data-based drug inventory prediction system and method |
CN111831675A (en) * | 2020-07-07 | 2020-10-27 | 平安科技(深圳)有限公司 | Storage model training method and device, computer equipment and storage medium |
CN112183969A (en) * | 2020-09-15 | 2021-01-05 | 北京每日优鲜电子商务有限公司 | Payment equipment operation control method and device for supply order and electronic equipment |
WO2021004169A1 (en) * | 2019-07-10 | 2021-01-14 | 江苏博子岛智能科技有限公司 | System and method for logistics control and having artificial intelligence |
CN112396365A (en) * | 2019-08-14 | 2021-02-23 | 顺丰科技有限公司 | Inventory item prediction method and device, computer equipment and storage medium |
CN113379173A (en) * | 2020-03-09 | 2021-09-10 | 北京京东振世信息技术有限公司 | Method and apparatus for labeling warehouse goods |
CN113554457A (en) * | 2021-07-04 | 2021-10-26 | 杭州拼便宜网络科技有限公司 | Intelligent poster generation method and device suitable for e-commerce platform and storage medium |
CN114186903A (en) * | 2020-09-14 | 2022-03-15 | 上海顺如丰来技术有限公司 | Warehouse product selection method and device, computer equipment and storage medium |
CN115130858A (en) * | 2022-06-27 | 2022-09-30 | 上海聚水潭网络科技有限公司 | Order aggregation method and system based on multi-target heuristic method |
CN112396365B (en) * | 2019-08-14 | 2024-07-02 | 顺丰科技有限公司 | Stock item prediction method, device, computer equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105825354A (en) * | 2016-03-11 | 2016-08-03 | 北京小米移动软件有限公司 | Storage scheduling method and apparatus |
CN106156880A (en) * | 2015-04-22 | 2016-11-23 | 阿里巴巴集团控股有限公司 | A kind of predict the method for inventory allocation ratio, device and electronic equipment |
CN106504067A (en) * | 2016-11-03 | 2017-03-15 | 北京挖玖电子商务有限公司 | Commodity intelligent sorting device |
CN107230035A (en) * | 2017-06-29 | 2017-10-03 | 北京京东尚科信息技术有限公司 | Information-pushing method and device |
-
2017
- 2017-11-29 CN CN201711222407.9A patent/CN109840730B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106156880A (en) * | 2015-04-22 | 2016-11-23 | 阿里巴巴集团控股有限公司 | A kind of predict the method for inventory allocation ratio, device and electronic equipment |
CN105825354A (en) * | 2016-03-11 | 2016-08-03 | 北京小米移动软件有限公司 | Storage scheduling method and apparatus |
CN106504067A (en) * | 2016-11-03 | 2017-03-15 | 北京挖玖电子商务有限公司 | Commodity intelligent sorting device |
CN107230035A (en) * | 2017-06-29 | 2017-10-03 | 北京京东尚科信息技术有限公司 | Information-pushing method and device |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021004169A1 (en) * | 2019-07-10 | 2021-01-14 | 江苏博子岛智能科技有限公司 | System and method for logistics control and having artificial intelligence |
CN112396365A (en) * | 2019-08-14 | 2021-02-23 | 顺丰科技有限公司 | Inventory item prediction method and device, computer equipment and storage medium |
CN112396365B (en) * | 2019-08-14 | 2024-07-02 | 顺丰科技有限公司 | Stock item prediction method, device, computer equipment and storage medium |
CN111310977A (en) * | 2020-01-20 | 2020-06-19 | 重庆亚德科技股份有限公司 | Big data-based drug inventory prediction system and method |
CN113379173A (en) * | 2020-03-09 | 2021-09-10 | 北京京东振世信息技术有限公司 | Method and apparatus for labeling warehouse goods |
CN113379173B (en) * | 2020-03-09 | 2023-11-07 | 北京京东振世信息技术有限公司 | Method and device for marking warehouse goods with labels |
CN111831675A (en) * | 2020-07-07 | 2020-10-27 | 平安科技(深圳)有限公司 | Storage model training method and device, computer equipment and storage medium |
CN114186903A (en) * | 2020-09-14 | 2022-03-15 | 上海顺如丰来技术有限公司 | Warehouse product selection method and device, computer equipment and storage medium |
CN112183969A (en) * | 2020-09-15 | 2021-01-05 | 北京每日优鲜电子商务有限公司 | Payment equipment operation control method and device for supply order and electronic equipment |
CN113554457A (en) * | 2021-07-04 | 2021-10-26 | 杭州拼便宜网络科技有限公司 | Intelligent poster generation method and device suitable for e-commerce platform and storage medium |
CN115130858A (en) * | 2022-06-27 | 2022-09-30 | 上海聚水潭网络科技有限公司 | Order aggregation method and system based on multi-target heuristic method |
CN115130858B (en) * | 2022-06-27 | 2024-01-26 | 上海聚水潭网络科技有限公司 | Order aggregation method and system based on multi-objective heuristic |
Also Published As
Publication number | Publication date |
---|---|
CN109840730B (en) | 2021-06-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109840730A (en) | Method and device for data prediction | |
Jabbarzadeh et al. | Designing a supply chain network under the risk of disruptions | |
CN107729937A (en) | For determining the method and device of user interest label | |
CN110135876A (en) | The method and device of Method for Sales Forecast | |
CN110110012A (en) | User's expectancy appraisal procedure, device, electronic equipment and readable medium | |
Mousavi et al. | The capacitated multi-facility location–allocation problem with probabilistic customer location and demand: two hybrid meta-heuristic algorithms | |
Liu et al. | A Pseudo‐Parallel Genetic Algorithm Integrating Simulated Annealing for Stochastic Location‐Inventory‐Routing Problem with Consideration of Returns in E‐Commerce | |
CN113643103B (en) | Product recommendation method, device, equipment and storage medium based on user similarity | |
CN109934369A (en) | Method and device for information push | |
Defersha et al. | Machine cell formation using a mathematical model and a genetic-algorithm-based heuristic | |
CN109697641A (en) | The method and apparatus for calculating commodity similarity | |
CN110110226A (en) | A kind of proposed algorithm, recommender system and terminal device | |
CN109658033A (en) | Source of goods route similarity calculating method, system, equipment and storage medium | |
CN110135878A (en) | Method and device for firm sale price | |
CN109087138A (en) | Data processing method and system, computer system and readable storage medium storing program for executing | |
CN110378545A (en) | Trade company's credit estimation method and device, storage medium, electronic equipment | |
CN108197298A (en) | A kind of smart shopper exchange method and system based on natural language processing | |
CN110020154A (en) | For determining the method and device of user force | |
CN109977316A (en) | A kind of parallel type article recommended method, device, equipment and storage medium | |
Riaz et al. | [Retracted] Pythagorean m‐Polar Fuzzy Weighted Aggregation Operators and Algorithm for the Investment Strategic Decision Making | |
CN110503520A (en) | Information recommendation method, device, electronic equipment and computer-readable medium | |
CN110866625A (en) | Promotion index information generation method and device | |
CN110309142A (en) | The method and apparatus of regulation management | |
Singh et al. | Robust strategies for mitigating operational and disruption risks: a fuzzy AHP approach | |
CN109902980A (en) | Method and device for business processing |
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 |