CN109376929A - Dispense determination method for parameter, determining device, storage medium and electronic equipment - Google Patents
Dispense determination method for parameter, determining device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN109376929A CN109376929A CN201811247116.XA CN201811247116A CN109376929A CN 109376929 A CN109376929 A CN 109376929A CN 201811247116 A CN201811247116 A CN 201811247116A CN 109376929 A CN109376929 A CN 109376929A
- Authority
- CN
- China
- Prior art keywords
- parameter
- dispatching
- conversion ratio
- trade company
- sensitivity
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Disclose a kind of dispatching determination method for parameter, determining device, storage medium and electronic equipment.The embodiment of the present invention determines that the prediction of trade company dispenses parameter according to the dispatching Parameter sensitivity of history allocation data acquisition trade company, and then according to dispatching Parameter sensitivity by obtaining the history allocation data of same trade company or same class trade company.Thus, it is possible to make the determination for dispensing parameter more rationally and accurate, while improving the user satisfaction of trade company.
Description
Technical field
The present invention, which discloses, is related to technical field of data processing, and in particular to a kind of dispatching determination method for parameter determines dress
It sets, storage medium and electronic equipment.
Background technique
With the development of internet, O2O (Online To Offline, under line on line) transaction becomes increasingly prevalent.
For O2O platform or logistics company, how to determine that the dispatching parameter of commodity is an extremely complex problem.Usually dispatching
The determination of parameter needs to consider distance, path planning, transport power cost, weather and peak period between trade company and client etc..
But for the trade company of part, problem still unreasonable or inaccurate there may be dispatching parameter.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of dispatching determination method for parameter, determining device, storage medium and
Electronic equipment can predict the dispatching parameter of target date according to the history allocation data of trade company, so that the determination of dispatching parameter
It is more rationally and accurate, improve the user satisfaction of trade company.
In a first aspect, the embodiment of the invention provides a kind of dispatching determination method for parameter, which comprises
Obtain the history allocation data of same trade company or same class trade company, wherein the history allocation data includes history
Dispatching parameter and corresponding conversion ratio, the conversion ratio characterize the order quantity performed of the trade company and the ratio of accessed quantity
Value；
The dispatching Parameter sensitivity of the trade company is obtained according to the history allocation data, wherein the dispatching parameter is quick
Sensitivity be used for characterize dispatching parameter variation to do business parameter variation influence degree；
Determine that the prediction of the trade company dispenses parameter according to the dispatching Parameter sensitivity.
Preferably, the history allocation data further includes the corresponding date parameter of the history dispatching parameter；
The dispatching Parameter sensitivity of the trade company is obtained according to the history allocation data specifically: match according to the history
Send the dispatching Parameter sensitivity of trade company described in data acquisition on a predetermined date；
Determine that the prediction of the trade company dispenses parameter according to the dispatching Parameter sensitivity specifically: according to the pre- settled date
The dispatching Parameter sensitivity of phase determines that prediction of the trade company in the target date dispenses parameter.
Preferably, include: according to the dispatching Parameter sensitivity that the history allocation data obtains user
Conversion ratio prediction model is obtained according to the history allocation data；
Determine that first dispenses parameter with reference to dispatching parameter and the second reference according to scheduled dispatching parameter area；
Described first is obtained respectively with reference to the corresponding conversion ratio of dispatching parameter and described according to the conversion ratio prediction model
Second with reference to the corresponding conversion ratio of dispatching parameter；
The dispatching Parameter sensitivity is calculated according to the conversion ratio.
Preferably, obtaining conversion ratio prediction model according to the history allocation data includes:
Linear regression is carried out to history dispatching parameter, obtains original conversion ratio prediction model；
The optimization of L2 canonical is carried out to the original conversion ratio prediction model, obtains the conversion ratio prediction model.
Preferably, calculating the dispatching Parameter sensitivity according to the conversion ratio includes:
The first business parameter is obtained with reference to dispatching parameter and corresponding conversion ratio according to described first, wherein described first
The product for the first reference match parameter and corresponding conversion ratio described in parameter characterization of doing business；
The second business parameter is obtained with reference to dispatching parameter and corresponding conversion ratio according to described second, wherein described second
The product for the second reference match parameter and corresponding conversion ratio described in parameter characterization of doing business；
Joined with the difference of the second dispatching parameter and the first business parameter with the second business according to the first dispatching parameter
Several differences calculates the dispatching Parameter sensitivity.
Preferably, described first is the scheduled upper limit for dispensing parameter area, second ginseng with reference to dispatching parameter
Examine the lower limit that dispatching parameter is the scheduled dispatching parameter area.
Preferably, the dispatching Parameter sensitivity are as follows:
The difference of the first business parameter and the second business parameter is matched with the first dispatching parameter with described second
Send the absolute value of the ratio of the difference of parameter；Or
Function comprising the absolute value.
Second aspect, the embodiment of the invention provides a kind of determining device for dispensing parameter, described device includes:
Historical data acquiring unit, for obtaining the history allocation data of same trade company or same class trade company, wherein described
History allocation data includes history dispatching parameter and corresponding conversion ratio, and the order that the conversion ratio characterizes the trade company completes number
The ratio of amount and accessed quantity；
Susceptibility acquiring unit, for obtaining the dispatching Parameter sensitivity of the trade company according to the history allocation data,
Wherein, it is described dispatching Parameter sensitivity be used for characterize dispatching parameter variation to do business parameter variation influence degree；
Parameter prediction unit is dispensed, for determining the prediction dispatching ginseng of the trade company according to the dispatching Parameter sensitivity
Number.
The third aspect, the embodiment of the invention provides a kind of computer readable storage mediums, store computer program thereon
Instruction, wherein the computer program instructions realize the method as described in any one of first aspect when being executed by processor.
Fourth aspect, the embodiment of the invention provides a kind of electronic equipment, including memory and processor, wherein described
Memory is for storing one or more computer program instructions, wherein one or more computer program instructions are by institute
Processor is stated to execute to realize the method as described in any one of first aspect.
The embodiment of the present invention is dispensed by obtaining the history allocation data of same trade company or same class trade company according to history
The dispatching Parameter sensitivity of data acquisition trade company, and then determine that the prediction of trade company dispenses parameter according to dispatching Parameter sensitivity.By
This, can make the determination for dispensing parameter more rationally and accurate, while improving the user satisfaction of trade company.
Detailed description of the invention
By referring to the drawings to the description of the embodiment of the present invention, the above and other purposes of the present invention, feature and
Advantage will be apparent from, in the accompanying drawings:
Fig. 1 is the flow chart of the dispatching determination method for parameter of first embodiment of the invention；
Fig. 2 is to be obtained to dispense according to history allocation data in another optional implementation of first embodiment of the invention
The flow chart of Parameter sensitivity；
Fig. 3 is the signal that L2 regularization coefficient is determined in another optional implementation of first embodiment of the invention
Figure；
Fig. 4 is quick according to conversion ratio calculating dispatching parameter in another optional implementation of first embodiment of the invention
The flow chart of sensitivity；
Fig. 5 is the schematic diagram of the determining device of the dispatching parameter of second embodiment of the invention；
Fig. 6 is the data flowchart of the dispatching determination method for parameter of the embodiment of the present invention；
Fig. 7 is the number that the method for the embodiment of the present invention obtains the dispatching Parameter sensitivity of trade company according to conversion ratio prediction model
According to flow chart；
Fig. 8 is the application scenarios interface schematic diagram of the embodiment of the present invention；
Fig. 9 is the schematic diagram of the electronic equipment of the embodiment of the present invention.
Specific embodiment
The present invention is disclosed below based on embodiment and is described, but the present invention discloses and is not restricted to these implementations
Example.It is detailed to describe some specific detail sections below in datail description disclosed by the invention.To those skilled in the art
Of the invention disclose can also be understood completely in the description of part without these details for member.It is disclosed by the invention in order to avoid obscuring
Essence, there is no narrations in detail for well known method, process, process, element and circuit.
In addition, it should be understood by one skilled in the art that provided herein attached drawing be provided to explanation purpose, and
What attached drawing was not necessarily drawn to scale.
Unless the context clearly requires otherwise, "include", "comprise" otherwise throughout the specification and claims etc. are similar
Word should be construed as the meaning for including rather than exclusive or exhaustive meaning；That is, be " including but not limited to " contains
Justice.
In description disclosed by the invention, it is to be understood that term " first ", " second " etc. are used for description purposes only,
It is not understood to indicate or imply relative importance.In addition, in description disclosed by the invention, it is unless otherwise indicated, " more
It is a " it is meant that two or more.
For O2O platform or logistics company, need to consider to dispense the determination problem of parameter.The usually determination of dispatching parameter
It needs to consider distance, path planning, transport power cost, weather and the peak period etc. between trade company and client, and passes through training
Model prediction dispenses parameter.But the dispatching parameter of part trade company is still it is possible that the true problem of forecasting inaccuracy.Also, by institute
There is the dispatching parameter of trade company to determine using the same model, in some instances it may even be possible to will appear the dispatching parameter prediction exception of part trade company
Problem influences trade company's normal work.Below in an example, it is illustrated for dispensing parameter as dispatching expense, still,
It should be readily apparent to one skilled in the art that the scheme of the embodiment of the present invention can also be applied in other dispatching parameters relevant to dispatching.
Fig. 1 is the flow chart of the dispatching determination method for parameter of first embodiment of the invention.In the present embodiment, to quotient
It is illustrated for the determination process of the dispatching parameter at family.As shown in Figure 1, the method for the present embodiment includes the following steps:
Step S100 obtains the history allocation data of same trade company or same class trade company, wherein history allocation data includes
History dispenses parameter and corresponding conversion ratio.
In the present embodiment, conversion ratio can calculate according to the following formula:
Conversion ratio=order quantity performed/accessed quantity
Specifically, conversion ratio is that the order quantity performed of same date and the same day be not accessed in history allocation data for trade company
The ratio of quantity.In the present embodiment, the multiple groups history allocation data of available same trade company or similar same class trade company,
Thus, it is possible in the subsequent conversion ratio prediction model for obtaining same trade company or same class trade company, so as to same trade company or same
For class trade company, the prediction of conversion ratio is more accurate.It should be understood that can history allocation data determine according to actual needs number
Amount.
History allocation data is other than including history dispatching parameter (that is, dispatching expense of the not same date recorded), also
May include other parameters, such as the corresponding date parameter of history dispatching parameter, specially the date, in one week number of days (that is,
What day), whether be winter and summer vacation, whether be working day etc..There are different influences to conversion ratio for above-mentioned history dispatching parameter.Phase
It hopes to choose and maximum relevant parameter is influenced for conversion ratio to assist determining prediction dispatching parameter (that is, prediction is reasonably matched
Send expense).In an optional implementation, the phase relation of the other parameters in conversion ratio and history allocation data can be calculated
Number.Related coefficient is bigger, and other parameters and the correlation of conversion ratio are higher, therefore the influence to conversion ratio is bigger.Pass through selection
The absolute value of related coefficient comes the input that the other parameters of maximum top N are calculated as subsequent transformation rate, wherein N is big
In the predetermined integers for being equal to 1.
Related coefficient can calculate according to the following formula:
Wherein, x is conversion ratio, yiFor the other parameters in history allocation data, ρ (x, yi) it is conversion ratio x and other parameters
yiRelated coefficient, cov (x, yi) it is conversion ratio and other parameters yiCovariance, Dx be conversion ratio variance, DyiFor other
The variance of parameter, n are the quantity of other parameters.
Other parameters y in conversion ratio x and history allocation dataiCovariance cov (x, yi) can count according to the following formula
It calculates:
cov(x,yi)=E (x-Ex) (yi-Eyi)
Wherein, Ex is the expectation (that is, mean value) of conversion ratio x, EyiFor other parameters yiExpectation.
In the present embodiment, history dispatching parameter, corresponding exact date, what day, whether be the dates phase such as working day
It closes parameter and the correlation of conversion ratio is higher.Therefore, in an optional implementation of the present embodiment, history can be matched
Send parameter corresponding exact date, what day, whether be to bring on working day in history allocation data.Thus, it is possible to turn
Subsequent calculation amount is reduced in the lesser situation of the predicted impact of rate.
It should be understood that the other parameters that can also be calculated in history allocation data using other modes are similar to conversion ratio
Degree.
Step S200 obtains the dispatching Parameter sensitivity of trade company according to history allocation data.
In the present embodiment, dispatching Parameter sensitivity be used for characterize dispatching parameter variation to do business parameter variation shadow
The degree of sound.The dispatching Parameter sensitivity of trade company on a predetermined date can be obtained according to history allocation data.Fig. 2 is the present invention first
The flow chart of dispatching Parameter sensitivity is obtained in another optional implementation of embodiment according to history allocation data.Such as figure
Shown in 2, in another optional implementation of the present embodiment, step S200 be may include steps of:
Step S210 obtains conversion ratio prediction model according to history allocation data.
Conversion ratio prediction model is really a conversion ratio anticipation function, for predicting that same trade company or same class trade company exist
The conversion ratio of target date.In this step, linear regression can be carried out by the history allocation data to trade company and obtains conversion
Rate anticipation function.Sample set of the history allocation data of trade company as conversion ratio prediction model, sample set are randomly drawn
It is divided into training sample set and test sample set.Each sample in sample set includes its in one group of history allocation data
His parameter (in embodiments of the present invention, that is, history dispatching parameter, corresponding exact date, what day and whether be work
Day) and corresponding conversion ratio.Specifically, in the training process of model, the input of model is other in history allocation data
Parameter exports as corresponding conversion ratio.That is, in the conversion ratio anticipation function obtained by linear regression, independent variable
For the other parameters in history allocation data, dependent variable is corresponding conversion ratio.For example, history dispatching parameter is 3, corresponding tool
The body date is August 17th, Friday, and on working day, corresponding conversion ratio is 0.6.Accordingly, the input of model can be 3,
8.17 5,1, output can be 0.6.Wherein, working day can be indicated with 1, and nonworkdays (that is, day off) can use 0 table
Show.It should be understood that the parameter inputted during parameter and prediction that conversion ratio prediction model inputs in the training process is corresponding.
That is, the input of model in the training process be history dispatching parameter, corresponding exact date, what day, whether be working day,
Input during prediction be then dispatching parameter, corresponding exact date, what day, whether be working day.
In the present embodiment, such as artificial neural network, SVM (support vector machines, Support Vector can also be used
Machines), logistic regression, naive Bayesian, decision tree, K-NN (K- closes on, K-nearest neighbor analysis)
Conversion ratio prediction model is established etc. various existing modeling patterns.
Preferably, conversion ratio anticipation function can be optimized using the methods of L1 canonical, L2 canonical.In the present embodiment
In, conversion ratio anticipation function is optimized using the method for L2 canonical.Specifically, the formula of L2 canonical is as follows:
J=J0+cΣwj 2, j=1 ... m
Wherein, J0For original conversion ratio anticipation function, J is the conversion ratio anticipation function after optimization, and c is L2 regularization system
Number, wj 2For square of the coefficient of other allocation datas, m is the quantity for other allocation datas finally chosen.Specifically, L2 canonical
Changing coefficient c can be determined by learning curve.Fig. 3 is determined in another optional implementation of first embodiment of the invention
The schematic diagram of L2 regularization coefficient c.As shown in figure 3, l1For the change curve of the test error under the different values of c, l2For in c
Different values under training error change curve.When test error and smaller simultaneously training error (that is, y-axis coordinate),
It can determine that corresponding x-axis coordinate co is the value of c.Using the conversion ratio anticipation function J after optimization as the conversion ratio of the present embodiment
The classification function of prediction model.
If should be understood that the determination that the method for the embodiment of the present invention is applied to the dispatching parameter on non-predetermined date, at this
It does not include history dispatching parameter corresponding exact date in step, in history allocation data.
Step S220 determines that first joins with reference to dispatching parameter and second with reference to dispatching according to scheduled dispatching parameter area
Number.
In the present embodiment, it first is used in subsequent calculating trade company with reference to dispatching parameter pre- with reference to dispatching parameter and second
The dispatching Parameter sensitivity fixed the date.It should be understood that first is unequal with reference to dispatching parameter with second with reference to dispatching parameter.It is preferred that
Ground, first with reference to the upper limit that parameter can be scheduled dispatching parameter area is dispensed, and the second reference dispatching parameter can be predetermined
Dispatching parameter area lower limit.It is more accurate in the subsequent dispatching Parameter sensitivity for calculating acquisition as a result,.
Step S230 obtains first with reference to the corresponding conversion ratio of dispatching parameter and second according to conversion ratio prediction model respectively
With reference to the corresponding conversion ratio of dispatching parameter.
In the present embodiment, first on a predetermined date is with reference to the corresponding conversion ratio of dispatching parameter and of even date the
Two are equally used for the dispatching Parameter sensitivity in subsequent calculating trade company on a predetermined date with reference to the corresponding conversion ratio of dispatching parameter.?
When obtaining conversion ratio on a predetermined date according to conversion ratio prediction model, the input of model is same trade company or same class trade company
Dispatching parameter, the corresponding target date parameter of dispatching parameter (in the present embodiment, that is, target date, what day and whether be
Working day), it exports as corresponding conversion ratio.Preferably, if can be automatic with what day according to the date of input for working day
It determines.For example, the date of input is September 14th, it is then working day that the number of days in one week, which is Friday, and the date of input is 9
The moon 30, it is then working day that the number of days in one week, which is Sunday,.Specifically, the dispatching parameter of input is respectively the first reference
Parameter and second is dispensed with reference to dispatching parameter.
Step S240 calculates dispatching Parameter sensitivity according to conversion ratio.
After first is obtained with reference to dispatching parameter, the second reference dispatching parameter and corresponding conversion ratio, it can be obtained by calculating
Obtain the dispatching Parameter sensitivity of trade company on a predetermined date.Fig. 4 is another optional implementation of first embodiment of the invention
The middle flow chart that dispatching Parameter sensitivity is calculated according to conversion ratio.As shown in figure 4, in another optional realization of the present embodiment
In mode, step S240 be may include steps of:
Step S241 obtains the first business parameter with reference to dispatching parameter and corresponding conversion ratio according to first.
Step S242 obtains the second business parameter with reference to dispatching parameter and corresponding conversion ratio according to second.
In the present embodiment, business parameter can calculate according to the following formula:
Business parameter=dispatching parameter * conversion ratio
Specifically, product of the first business parameter characterization first with reference to match parameter and corresponding conversion ratio, the second business
Product of the parameter characterization second with reference to match parameter and corresponding conversion ratio.Obtain the first business parameter and the second business parameter
Afterwards, acquisition dispatching Parameter sensitivity can be calculated.It should be understood that step S241 and step S242 is without apparent sequencing.
Step S243 joins with the difference of the second dispatching parameter and the first business parameter with the second business according to the first dispatching parameter
Several differences calculates the dispatching Parameter sensitivity.
In the present embodiment, Parameter sensitivity and the first dispatching parameter difference and the first business with the second dispatching parameter are dispensed
Parameter is related with the second business difference of parameter.Specifically, the dispatching Parameter sensitivity of trade company on a predetermined date can be according to as follows
Formula calculates:
ROI=| Δ business parameter/Δ dispenses parameter |
Wherein, ROI is the dispatching Parameter sensitivity of trade company on a predetermined date, and Δ parameter of doing business is the first business parameter and the
The difference of two business parameters, Δ dispense the difference that parameter is the first dispatching parameter with the second dispatching parameter.It should be understood that dispatching parameter sensitivity
The function of the absolute value of degree or the ratio comprising Δ business parameter and Δ dispatching parameter.
Step S300 determines that the prediction of trade company dispenses parameter according to dispatching Parameter sensitivity.
In embodiment, the prediction dispatching ginseng on the same day can be determined according to the dispatching Parameter sensitivity of trade company on a predetermined date
Number.Specifically, trade company's same day can be determined according to dispatching Parameter sensitivity, scheduled dispatching parameter area on a predetermined date
Prediction dispatching parameter.More specifically, the prediction dispatching parameter of trade company can calculate according to the following formula:
ui=L+si t(H-L)
Wherein, uiParameter is dispensed for the prediction of same trade company or same class trade company on a predetermined date, L is scheduled dispatching ginseng
The lower limit of number range, H are the lower limit of scheduled dispatching parameter area, siFor normalized dispatching parameter sensitivity on a predetermined date
Degree, t are the predetermined real number greater than 0.Preferably, t can be adjusted according to actual needs, it is possible thereby to obtain accurately
Prediction dispatching parameter.
The embodiment of the present invention is dispensed by obtaining the history allocation data of same trade company or same class trade company according to history
The dispatching Parameter sensitivity of data acquisition trade company, and then determine that the prediction of trade company dispenses parameter according to dispatching Parameter sensitivity.By
This, can make the determination for dispensing parameter more rationally and accurate, while improving the user satisfaction of trade company.
Fig. 5 is the schematic diagram of the determining device of the dispatching parameter of second embodiment of the invention.As shown in figure 5, the present embodiment
Dispatching parameter determining device 5 include historical data acquiring unit 51, susceptibility acquiring unit 52 and dispatching parameter prediction list
Member 53.
Wherein, historical data acquiring unit 51 is used to obtain the history allocation data of same trade company or same class trade company,
In, the history allocation data includes that history dispatching parameter and corresponding conversion ratio, the conversion ratio characterize ordering for the trade company
The ratio of single quantity performed and accessed quantity.Susceptibility acquiring unit 52 is used for according to history allocation data acquisition
The dispatching Parameter sensitivity of trade company, wherein the dispatching Parameter sensitivity is used to characterize the variation of dispatching parameter to business parameter
Variation influence degree.Dispatching parameter prediction unit 53 is used to determine the pre- of the trade company according to the dispatching Parameter sensitivity
It is measured and send parameter.
Further, the history allocation data further includes the corresponding date parameter of the history dispatching parameter.It is described quick
Sensitivity acquiring unit 52 is used to obtain the dispatching Parameter sensitivity of the trade company on a predetermined date according to the history allocation data.
The dispatching parameter prediction unit 53 is used to determine the trade company described according to the dispatching Parameter sensitivity of the target date
The prediction of target date dispenses parameter.
Further, the susceptibility acquiring unit 52 includes the first subelement 521, the second subelement 522, third son list
Member 523 and the 4th subelement 524.
Wherein, the first subelement 521 is used to obtain conversion ratio prediction model according to the history allocation data.Second son is single
Member 522 according to scheduled dispatching parameter area for determining the first reference dispatching parameter and second with reference to dispatching parameter.Third
Unit 523 is used to obtain described first respectively according to the conversion ratio prediction model with reference to the corresponding conversion ratio of dispatching parameter and institute
Second is stated with reference to the corresponding conversion ratio of dispatching parameter.4th subelement 524, which is used to calculate the dispatching according to the conversion ratio, joins
Number susceptibility.
Further, first subelement 521 includes that model obtains module 5211 and model optimization module 5212.
Wherein, model obtains module 5211 and is used to carry out linear regression to history dispatching parameter, obtains original turn
Rate prediction model.Model optimization module 5212 is used to carry out the optimization of L2 canonical to the original conversion ratio prediction model, obtains
Take the conversion ratio prediction model.
Further, the 4th subelement 524 includes business parameter acquisition module 5241 and susceptibility computing module
5242。
Wherein, business parameter acquisition module 5241 is used to obtain according to described first with reference to dispatching parameter and corresponding conversion ratio
The first business parameter is taken, obtains the second business parameter with reference to dispatching parameter and corresponding conversion ratio according to described second, wherein institute
State the product of the first reference match parameter and corresponding conversion ratio described in the first business parameter characterization, the second business parameter list
Levy the described second product with reference to match parameter and corresponding conversion ratio.
Susceptibility computing module 5242 is used for the difference and described the according to the first dispatching parameter and the second dispatching parameter
The difference of one business parameter and the second business parameter calculates the dispatching Parameter sensitivity.
Further, it is described first with reference to dispatching parameter be it is described it is scheduled dispatching parameter area the upper limit, described second
It is the lower limit of the scheduled dispatching parameter area with reference to dispatching parameter.
Further, the dispatching Parameter sensitivity are as follows:
The difference of the first business parameter and the second business parameter is matched with the first dispatching parameter with described second
Send the absolute value of the ratio of the difference of parameter；Or
Function comprising the absolute value.
Further, the dispatching parameter prediction unit 53 is used for according to the dispatching Parameter sensitivity and scheduled dispatching
Parameter area determines the prediction dispatching parameter of the trade company.
Further, the prediction dispatching parameter of the trade company calculates according to the following formula:
ui=L+si t(H-L)
Wherein, uiParameter is dispensed for the prediction of the trade company, L is the lower limit of the scheduled dispatching parameter area, and H is institute
State the upper limit of scheduled dispatching parameter area, siFor the normalized dispatching Parameter sensitivity, t is the predetermined real number greater than 0.
The embodiment of the present invention is dispensed by obtaining the history allocation data of same trade company or same class trade company according to history
The dispatching Parameter sensitivity of data acquisition trade company, and then determine that the prediction of trade company dispenses parameter according to dispatching Parameter sensitivity.By
This, can make the determination for dispensing parameter more rationally and accurate, while improving the user satisfaction of trade company.
Fig. 6 is the data flowchart of the dispatching determination method for parameter of the embodiment of the present invention.As shown in fig. 6, the change of data
Change as follows:
Step S1000 obtains nearly 60 days history allocation datas of same trade company or same class trade company, wherein history dispatching
Data include history dispatching expense (that is, history dispatching parameter) and corresponding conversion ratio.
Step S2000 screens history allocation data.
Specifically, the related coefficient that the other parameters in conversion ratio and history allocation data can be calculated, in related coefficient
Corresponding other parameters are brought into the history allocation data after screening when meeting predetermined condition.In the present embodiment, it screens
History allocation data afterwards includes history dispatching expense, corresponding exact date, the number of days (that is, what day) in one week, is
No is working day and corresponding conversion ratio.
Step S3000 obtains conversion ratio prediction model according to history allocation data.
It specifically, can be using nearly 60 days history allocation datas after screening as the sample set of conversion ratio prediction model
It closes.Wherein, daily history allocation data is as a sample in sample set.Sample set is divided into training sample set
It closes and test sample set, wherein training sample set is shared in training conversion ratio prediction model, may include history allocation data
In preceding 59 days data, test sample collection share in test conversion ratio prediction model accuracy, may include history dispatching number
Last 1 day data in.History in sample set is dispensed into expense, corresponding exact date, the number of days in one week and is
No is input of the working day as conversion ratio prediction model, using corresponding conversion ratio as the output of model.
Step S4000 obtains dispatching expense (that is, dispatching parameter) susceptibility of trade company according to conversion ratio prediction model.
Fig. 7 is the number that the method for the embodiment of the present invention obtains the dispatching Parameter sensitivity of trade company according to conversion ratio prediction model
According to flow chart.Trade company is determined on a predetermined date as shown in fig. 7, taking in range (that is, dispatching parameter area) in scheduled dispatching
First with reference to dispatching take and second refer to dispatching expense, according to conversion ratio prediction model obtain trade company on a predetermined date first join
It examines dispatching and takes corresponding first conversion ratio and second with reference to corresponding second conversion ratio of dispatching expense.According to first with reference to dispatching take with
First conversion ratio obtains first turnover (that is, business parameter), take with reference to dispatching and the second conversion ratio acquisition the according to second
Two turnovers take with reference to dispatching according to first and second obtain Δ dispatching expense with reference to dispatching expense, according to first turnover and second
The turnover obtains the Δ turnover, is taken according to Δ dispatching and the Δ turnover obtains the dispatching expense susceptibility ROI of trade company on a predetermined date.
The calculation of above-mentioned parameter is identical as first embodiment of the invention, and details are not described herein.
Step S5000 obtains trade company on a predetermined date pre- according to the dispatching expense susceptibility of trade company on a predetermined date and is measured
Send expense.
Specifically, the dispatching expense susceptibility of range and trade company on a predetermined date is taken according to scheduled dispatching and obtains trade company pre-
The prediction dispatching expense fixed the date.The calculation that prediction dispatching takes is identical as first embodiment of the invention, and details are not described herein.
Fig. 8 is the application scenarios interface schematic diagram of the embodiment of the present invention.As shown in figure 8, the application 8 of the present embodiment includes matching
Send Data-entry windows 81 and prediction dispatching parameter display window 82.Specifically, it can be inputted in allocation data input window 81
Prediction dispatching parameter corresponding date, such as September 30th, what day, such as Sunday, if for working day according to the date of input and
Number of days in one week automatically determines.It should be understood that can also be manually entered.It can be 7 and 3.5 with reference to dispatching parameter.Preferably,
Can also to it is scheduled with reference to dispatching parameter area prompt, such as " note that input reference dispense parameter must 1-10 it
Between ".After the completion of input, target date, corresponding prediction dispatching parameter can be shown in prediction dispatching parameter display window 82.Such as, 9
The prediction dispatching parameter on the moon 30 is 5.
Fig. 9 is the schematic diagram of the electronic equipment of the embodiment of the present invention.Electronic equipment shown in Fig. 9 is general data processing dress
It sets comprising general computer hardware structure includes at least processor 91 and memory 92.Processor 91 and memory 92
It is connected by bus 93.Memory 92 is suitable for the instruction or program that storage processor 91 can be performed.Processor 91 can be independence
Microprocessor, be also possible to one or more microprocessor set.Processor 91 is deposited by executing memory 92 as a result,
The order of storage is realized thereby executing the method flow of embodiment present invention as described above for the processing of data and for other
The control of device.Bus 93 links together above-mentioned multiple components, while said modules are connected to 94 He of display controller
Display device and input/output (I/O) device 95.Input/output (I/O) device 95 can be mouse, keyboard, modulation /demodulation
Device, network interface, touch-control input device, body-sensing input unit, printer and other devices well known in the art.Typically,
Input/output (I/O) device 95 is connected by input/output (I/O) controller 96 with system.
Wherein, memory 92 can store component software, such as operating system, communication module, interactive module and application
Program.Above-described each module and application program are both corresponded to complete one or more functions and be retouched in inventive embodiments
One group of executable program instructions of the method stated.
It is above-mentioned according to the method for the embodiment of the present invention, the flow chart and/or frame of equipment (system) and computer program product
Figure describes various aspects disclosed by the invention.It should be understood that each of flowchart and or block diagram piece and flow chart legend and/
Or the combination of the block in block diagram can be realized by computer program instructions.These computer program instructions can be provided to logical
With the processor of computer, special purpose computer or other programmable data processing devices, to generate machine, so that (via calculating
What machine or the processor of other programmable data processing devices executed) instruction creation for realizing flowchart and or block diagram block or
The device for the function action specified in block.
Meanwhile as skilled in the art will be aware of, the various aspects of the embodiment of the present invention may be implemented as be
System, method or computer program product.Therefore, the various aspects of the embodiment of the present invention can take following form: complete hardware
Implementation, complete software implementation (including firmware, resident software, microcode etc.) usually can all claim herein
For the implementation for combining software aspects with hardware aspect of circuit, " module " or " system ".In addition, the present invention discloses
Aspect can take following form: the computer program product realized in one or more computer-readable medium, calculate
Machine readable medium has the computer readable program code realized on it.
It can use any combination of one or more computer-readable mediums.Computer-readable medium can be computer
Readable signal medium or computer readable storage medium.Computer readable storage medium can be such as (but not limited to) electronics,
Magnetic, optical, electromagnetism, infrared or semiconductor system, device or any suitable combination above-mentioned.Meter
The more specific example (exhaustive to enumerate) of calculation machine readable storage medium storing program for executing will include the following terms: with one or more electric wire
Electrical connection, hard disk, random access memory (RAM), read-only memory (ROM), erasable is compiled portable computer diskette
Journey read-only memory (EPROM or flash memory), optical fiber, portable optic disk read-only storage (CD-ROM), light storage device,
Magnetic memory apparatus or any suitable combination above-mentioned.In the context of the embodiment of the present invention, computer readable storage medium
It can be that can include or store the program used by instruction execution system, device or combine instruction execution system, set
Any tangible medium for the program that standby or device uses.
Computer-readable signal media may include the data-signal propagated, and the data-signal of the propagation has wherein
The computer readable program code realized such as a part in a base band or as carrier wave.The signal of such propagation can use
Any form in diversified forms, including but not limited to: electromagnetism, optical or its any combination appropriate.It is computer-readable
Signal media can be following any computer-readable medium: not be computer readable storage medium, and can be to by instructing
Program that is that execution system, device use or combining instruction execution system, device to use is communicated, is propagated
Or transmission.
Computer program code for executing the operation for disclosing various aspects for the present invention can be with one or more volumes
Any combination of Cheng Yuyan is write, and the programming language includes: programming language such as Java, Smalltalk, C+ of object-oriented
+, PHP, Python etc.；And conventional process programming language such as " C " programming language or similar programming language.Program code can be with
It fully on the user computer, is partly executed on the user computer as independent software package；Partly calculated in user
On machine and partly execute on the remote computer；Or it fully executes on a remote computer or server.In latter
In the case of, can by remote computer by include any type of network connection of local area network (LAN) or wide area network (WAN) extremely
Subscriber computer, or can be attached with outer computer (such as the Yin Te by using ISP
Net).
The embodiment of the invention discloses A1, a kind of dispatching determination method for parameter, which comprises
Obtain the history allocation data of same trade company or same class trade company, wherein the history allocation data includes history
Dispatching parameter and corresponding conversion ratio, the conversion ratio characterize the order quantity performed of the trade company and the ratio of accessed quantity
Value；
The dispatching Parameter sensitivity of the trade company is obtained according to the history allocation data, wherein the dispatching parameter is quick
Sensitivity be used for characterize dispatching parameter variation to do business parameter variation influence degree；
Determine that the prediction of the trade company dispenses parameter according to the dispatching Parameter sensitivity.
In A2, method as described in a1, the history allocation data further includes the history dispatching parameter corresponding date
Parameter；
The dispatching Parameter sensitivity of the trade company is obtained according to the history allocation data specifically: match according to the history
Send the dispatching Parameter sensitivity of trade company described in data acquisition on a predetermined date；
Determine that the prediction of the trade company dispenses parameter according to the dispatching Parameter sensitivity specifically: according to the pre- settled date
The dispatching Parameter sensitivity of phase determines that prediction of the trade company in the target date dispenses parameter.
In A3, method as described in a1 or a2, the dispatching Parameter sensitivity of user is obtained according to the history allocation data
Include:
Conversion ratio prediction model is obtained according to the history allocation data；
Determine that first dispenses parameter with reference to dispatching parameter and the second reference according to scheduled dispatching parameter area；
Described first is obtained respectively with reference to the corresponding conversion ratio of dispatching parameter and described according to the conversion ratio prediction model
Second with reference to the corresponding conversion ratio of dispatching parameter；
The dispatching Parameter sensitivity is calculated according to the conversion ratio.
In A4, the method as described in A3, obtaining conversion ratio prediction model according to the history allocation data includes:
Linear regression is carried out to history dispatching parameter, obtains original conversion ratio prediction model；
The optimization of L2 canonical is carried out to the original conversion ratio prediction model, obtains the conversion ratio prediction model.
In A5, the method as described in A3, calculating the dispatching Parameter sensitivity according to the conversion ratio includes:
The first business parameter is obtained with reference to dispatching parameter and corresponding conversion ratio according to described first, wherein described first
The product for the first reference match parameter and corresponding conversion ratio described in parameter characterization of doing business；
The second business parameter is obtained with reference to dispatching parameter and corresponding conversion ratio according to described second, wherein described second
The product for the second reference match parameter and corresponding conversion ratio described in parameter characterization of doing business；
Joined with the difference of the second dispatching parameter and the first business parameter with the second business according to the first dispatching parameter
Several differences calculates the dispatching Parameter sensitivity.
In A6, the method as described in A3, the first reference dispatching parameter is the upper of the scheduled dispatching parameter area
Limit, the second reference dispatching parameter are the lower limit of the scheduled dispatching parameter area.
In A7, the method as described in A3, the dispatching Parameter sensitivity are as follows:
The difference of the first business parameter and the second business parameter is matched with the first dispatching parameter with described second
Send the absolute value of the ratio of the difference of parameter；Or
Function comprising the absolute value.
In A8, method as described in a1 or a2, determine that the prediction of the trade company dispenses according to the dispatching Parameter sensitivity
Parameter includes:
Determine that the prediction of the trade company dispenses parameter according to the dispatching Parameter sensitivity and scheduled dispatching parameter area.
In A9, the method as described in A8, the prediction dispatching parameter of the trade company calculates according to the following formula:
ui=L+si t(H-L)
Wherein, uiParameter is dispensed for the prediction of the trade company, L is the lower limit of the scheduled dispatching parameter area, and H is institute
State the upper limit of scheduled dispatching parameter area, siFor the normalized dispatching Parameter sensitivity, t is the predetermined real number greater than 0.
The embodiment of the invention also discloses B1, a kind of determining device for dispensing parameter, described device includes:
Historical data acquiring unit, for obtaining the history allocation data of same trade company or same class trade company, wherein described
History allocation data includes history dispatching parameter and corresponding conversion ratio, and the order that the conversion ratio characterizes the trade company completes number
The ratio of amount and accessed quantity；
Susceptibility acquiring unit, for obtaining the dispatching Parameter sensitivity of the trade company according to the history allocation data,
Wherein, it is described dispatching Parameter sensitivity be used for characterize dispatching parameter variation to do business parameter variation influence degree；
Parameter prediction unit is dispensed, for determining the prediction dispatching ginseng of the trade company according to the dispatching Parameter sensitivity
Number.
In B2, the device as described in B1, the history allocation data further includes the history dispatching parameter corresponding date
Parameter；
The susceptibility acquiring unit is used to obtain the trade company matching on a predetermined date according to the history allocation data
Send Parameter sensitivity；
The dispatching parameter prediction unit is used to determine the trade company according to the dispatching Parameter sensitivity of the target date
Parameter is dispensed in the prediction of the target date.
In B3, the device as described in B1 or B2, the susceptibility acquiring unit includes:
First subelement, for obtaining conversion ratio prediction model according to the history allocation data；
Second subelement, for determining that first matches with reference to dispatching parameter and the second reference according to scheduled dispatching parameter area
Send parameter；
Third subelement, it is corresponding with reference to dispatching parameter for obtaining described first respectively according to the conversion ratio prediction model
Conversion ratio and described second with reference to the corresponding conversion ratio of dispatching parameter；
4th subelement, for calculating the dispatching Parameter sensitivity according to the conversion ratio.
In B4, the device as described in B3, first subelement includes:
Model obtains module, for carrying out linear regression to history dispatching parameter, obtains original conversion ratio prediction
Model；
Model optimization module obtains described turn for carrying out the optimization of L2 canonical to the original conversion ratio prediction model
Rate prediction model.
In B5, the device as described in B3, the 4th subelement includes:
Business parameter acquisition module is sought for obtaining first with reference to dispatching parameter and corresponding conversion ratio according to described first
Industry parameter, wherein the product of the first reference match parameter and corresponding conversion ratio described in the first business parameter characterization；
Business parameter acquisition module is sought for obtaining second with reference to dispatching parameter and corresponding conversion ratio according to described second
Industry parameter, wherein the product of the second reference match parameter and corresponding conversion ratio described in the second business parameter characterization；
Susceptibility computing module, for being sought according to the difference and described first of the first dispatching parameter and the second dispatching parameter
Industry parameter and the difference of the second business parameter calculate the dispatching Parameter sensitivity.
In B6, the device as described in B3, the first reference dispatching parameter is the upper of the scheduled dispatching parameter area
Limit, the second reference dispatching parameter are the lower limit of the scheduled dispatching parameter area.
In B7, the device as described in B3, the dispatching Parameter sensitivity are as follows:
The difference of the first business parameter and the second business parameter is matched with the first dispatching parameter with described second
Send the absolute value of the ratio of the difference of parameter；Or
Function comprising the absolute value.
In B8, the device as described in B1 or B2, the dispatching parameter prediction unit is used for according to the dispatching parameter sensitivity
Degree and scheduled dispatching parameter area determine the prediction dispatching parameter of the trade company.
In B9, the device as described in B8, the prediction dispatching parameter of the trade company calculates according to the following formula:
ui=L+si t(H-L)
Wherein, uiParameter is dispensed for the prediction of the trade company, L is the lower limit of the scheduled dispatching parameter area, and H is institute
State the upper limit of scheduled dispatching parameter area, siFor the normalized dispatching Parameter sensitivity, t is the predetermined real number greater than 0.
The embodiment of the invention also discloses C1, a kind of computer readable storage medium, store computer program instructions thereon,
Wherein, the computer program instructions realize the method as described in any one of A1-A9 when being executed by processor.
The embodiment of the invention also discloses D1, a kind of electronic equipment, including memory and processor, wherein the storage
Device is for storing one or more computer program instructions, wherein one or more computer program instructions are by the place
Device is managed to execute to realize the method as described in any one of A1-A9.
The foregoing is merely preferred embodiments disclosed by the invention, disclosure are not intended to restrict the invention, for this field
For technical staff, the present invention, which discloses, can various modifications and changes.All institutes within spirit disclosed by the invention and principle
Any modification, equivalent substitution, improvement and etc. of work should be included within protection scope disclosed by the invention.
Claims (10)
1. a kind of dispatching determination method for parameter, which is characterized in that the described method includes:
Obtain the history allocation data of same trade company or same class trade company, wherein the history allocation data includes history dispatching
Parameter and corresponding conversion ratio, the conversion ratio characterize the order quantity performed of the trade company and the ratio of accessed quantity；
The dispatching Parameter sensitivity of the trade company is obtained according to the history allocation data, wherein the dispatching Parameter sensitivity
For characterize dispatching parameter variation to business parameter variation influence degree；
Determine that the prediction of the trade company dispenses parameter according to the dispatching Parameter sensitivity.
2. dispatching determination method for parameter according to claim 1, which is characterized in that the history allocation data further includes
The history dispenses the corresponding date parameter of parameter；
The dispatching Parameter sensitivity of the trade company is obtained according to the history allocation data specifically: number is dispensed according to the history
According to the dispatching Parameter sensitivity of the acquisition trade company on a predetermined date；
Determine that the prediction of the trade company dispenses parameter according to the dispatching Parameter sensitivity specifically: according to the target date
Dispatching Parameter sensitivity determines that prediction of the trade company in the target date dispenses parameter.
3. dispatching determination method for parameter according to claim 1 or 2, which is characterized in that dispense number according to the history
Include: according to the dispatching Parameter sensitivity for obtaining user
Conversion ratio prediction model is obtained according to the history allocation data；
Determine that first dispenses parameter with reference to dispatching parameter and the second reference according to scheduled dispatching parameter area；
Described first is obtained respectively with reference to the corresponding conversion ratio of dispatching parameter and described second according to the conversion ratio prediction model
With reference to the corresponding conversion ratio of dispatching parameter；
The dispatching Parameter sensitivity is calculated according to the conversion ratio.
4. dispatching determination method for parameter according to claim 3, which is characterized in that obtained according to the history allocation data
The conversion ratio prediction model is taken to include:
Linear regression is carried out to history dispatching parameter, obtains original conversion ratio prediction model；
The optimization of L2 canonical is carried out to the original conversion ratio prediction model, obtains the conversion ratio prediction model.
5. dispatching determination method for parameter according to claim 3, which is characterized in that according to conversion ratio calculating
Dispensing Parameter sensitivity includes:
The first business parameter is obtained with reference to dispatching parameter and corresponding conversion ratio according to described first, wherein first business
The product of first reference match parameter and corresponding conversion ratio described in parameter characterization；
The second business parameter is obtained with reference to dispatching parameter and corresponding conversion ratio according to described second, wherein second business
The product of second reference match parameter and corresponding conversion ratio described in parameter characterization；
According to the first dispatching parameter and the difference of the second dispatching parameter and the first business parameter and the second business parameter
Difference calculates the dispatching Parameter sensitivity.
6. dispatching determination method for parameter according to claim 3, which is characterized in that described first is with reference to dispatching parameter
The upper limit of the scheduled dispatching parameter area, the second reference dispatching parameter is under the scheduled dispatching parameter area
Limit.
7. dispatching determination method for parameter according to claim 3, which is characterized in that the dispatching Parameter sensitivity are as follows:
The difference of the first business parameter and the second business parameter is joined with the first dispatching parameter and second dispatching
The absolute value of the ratio of several differences；Or
Function comprising the absolute value.
8. a kind of determining device for dispensing parameter, which is characterized in that described device includes:
Historical data acquiring unit, for obtaining the history allocation data of same trade company or same class trade company, wherein the history
Allocation data includes history dispatching parameter and corresponding conversion ratio, the conversion ratio characterize the order quantity performed of the trade company with
The ratio of accessed quantity；
Susceptibility acquiring unit, for obtaining the dispatching Parameter sensitivity of the trade company according to the history allocation data, wherein
It is described dispatching Parameter sensitivity be used for characterize dispatching parameter variation to do business parameter variation influence degree；
Parameter prediction unit is dispensed, for determining that the prediction of the trade company dispenses parameter according to the dispatching Parameter sensitivity.
9. a kind of computer readable storage medium, stores computer program instructions thereon, which is characterized in that the computer program
Such as method of any of claims 1-7 is realized in instruction when being executed by processor.
10. a kind of electronic equipment, including memory and processor, which is characterized in that the memory is for storing one or more
Computer program instructions, wherein one or more computer program instructions are executed by the processor to realize such as power
Benefit requires method described in any one of 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811247116.XA CN109376929B (en) | 2018-10-24 | 2018-10-24 | Distribution parameter determination method, distribution parameter determination device, storage medium, and electronic apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811247116.XA CN109376929B (en) | 2018-10-24 | 2018-10-24 | Distribution parameter determination method, distribution parameter determination device, storage medium, and electronic apparatus |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109376929A true CN109376929A (en) | 2019-02-22 |
| CN109376929B CN109376929B (en) | 2021-04-23 |
Family
ID=65401976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811247116.XA Active CN109376929B (en) | 2018-10-24 | 2018-10-24 | Distribution parameter determination method, distribution parameter determination device, storage medium, and electronic apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109376929B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111126914A (en) * | 2019-12-24 | 2020-05-08 | 拉扎斯网络科技（上海）有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN111369137A (en) * | 2020-03-03 | 2020-07-03 | 拉扎斯网络科技（上海）有限公司 | Distribution method, distribution device, server and storage medium of distribution tasks |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103208039A (en) * | 2012-01-13 | 2013-07-17 | 株式会社日立制作所 | Method and device for evaluating software project risks |
| CN107094165A (en) * | 2016-08-31 | 2017-08-25 | 阿里巴巴集团控股有限公司 | Distribution capacity is determined, dispatching task obtains, dispenses resource regulating method and equipment |
| CN107093081A (en) * | 2016-11-24 | 2017-08-25 | 北京小度信息科技有限公司 | Service strategy formulating method and device |
| CN107092974A (en) * | 2016-11-29 | 2017-08-25 | 北京小度信息科技有限公司 | Dispense pressure prediction method and device |
| CN107590688A (en) * | 2017-08-24 | 2018-01-16 | 平安科技（深圳）有限公司 | The recognition methods of target customer and terminal device |
| CN107944645A (en) * | 2017-12-29 | 2018-04-20 | 浪潮软件股份有限公司 | A kind of feasibility analysis method of tobacco distribution line optimization |
| CN107944737A (en) * | 2017-12-07 | 2018-04-20 | 北京小度信息科技有限公司 | Information processing method, device, electronic equipment and computer-readable recording medium |
| CN108171530A (en) * | 2017-12-06 | 2018-06-15 | 口碑(上海)信息技术有限公司 | It is a kind of to be used for visitor's unit price and the again method for improving and device of purchase rate |
| WO2019183973A1 (en) * | 2018-03-30 | 2019-10-03 | 香港纺织及成衣研发中心有限公司 | Machine learning-based method and device for forecast of garment sales |
-
2018
- 2018-10-24 CN CN201811247116.XA patent/CN109376929B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103208039A (en) * | 2012-01-13 | 2013-07-17 | 株式会社日立制作所 | Method and device for evaluating software project risks |
| CN107094165A (en) * | 2016-08-31 | 2017-08-25 | 阿里巴巴集团控股有限公司 | Distribution capacity is determined, dispatching task obtains, dispenses resource regulating method and equipment |
| CN107093081A (en) * | 2016-11-24 | 2017-08-25 | 北京小度信息科技有限公司 | Service strategy formulating method and device |
| CN107092974A (en) * | 2016-11-29 | 2017-08-25 | 北京小度信息科技有限公司 | Dispense pressure prediction method and device |
| CN107590688A (en) * | 2017-08-24 | 2018-01-16 | 平安科技（深圳）有限公司 | The recognition methods of target customer and terminal device |
| CN108171530A (en) * | 2017-12-06 | 2018-06-15 | 口碑(上海)信息技术有限公司 | It is a kind of to be used for visitor's unit price and the again method for improving and device of purchase rate |
| CN107944737A (en) * | 2017-12-07 | 2018-04-20 | 北京小度信息科技有限公司 | Information processing method, device, electronic equipment and computer-readable recording medium |
| CN107944645A (en) * | 2017-12-29 | 2018-04-20 | 浪潮软件股份有限公司 | A kind of feasibility analysis method of tobacco distribution line optimization |
| WO2019183973A1 (en) * | 2018-03-30 | 2019-10-03 | 香港纺织及成衣研发中心有限公司 | Machine learning-based method and device for forecast of garment sales |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111126914A (en) * | 2019-12-24 | 2020-05-08 | 拉扎斯网络科技（上海）有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN111126914B (en) * | 2019-12-24 | 2023-09-26 | 拉扎斯网络科技（上海）有限公司 | Data processing method, device, electronic equipment and storage medium |
| CN111369137A (en) * | 2020-03-03 | 2020-07-03 | 拉扎斯网络科技（上海）有限公司 | Distribution method, distribution device, server and storage medium of distribution tasks |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109376929B (en) | 2021-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6588655B2 (en) | Vehicle insurance research mission announcement system, apparatus, method and readable storage medium | |
| CN108846520A (en) | Overdue loan prediction technique, device and computer readable storage medium | |
| CN110119847A (en) | A kind of prediction technique, device, storage medium and electronic equipment dispensing duration | |
| US20040153187A1 (en) | Systems and methods for improving planning, scheduling, and supply chain management | |
| WO2018013475A1 (en) | Systems and methods for optimizing parallel task completion | |
| WO2022221461A1 (en) | Orchestrated intelligent supply chain optimizer | |
| CN109697667B (en) | Quota management and control method and device based on trust mode | |
| CN109242496A (en) | Prediction technique, device and the computer-readable medium of the means of payment | |
| CN109376929A (en) | Dispense determination method for parameter, determining device, storage medium and electronic equipment | |
| CN109213729A (en) | As a result the case management driven | |
| US8473389B2 (en) | Methods and systems of purchase contract price adjustment calculation tools | |
| Gupta et al. | Decomposition and adaptive sampling for data-driven inverse linear optimization | |
| Emms | Pricing general insurance in a reactive and competitive market | |
| CN110363468A (en) | Determination method, apparatus, server and the readable storage medium storing program for executing of purchase order | |
| US11062293B2 (en) | Method and system for negotiating, generating, documenting, and fulfilling vendor financing opportunities | |
| CN112686470A (en) | Power grid saturation load prediction method and device and terminal equipment | |
| KR970004105B1 (en) | Simulation system for measured economic model | |
| Yadav et al. | Function point based estimation of effort and cost in agile software development | |
| CN111639784B (en) | Inventory management method and related device | |
| Spedicato et al. | The use of GAMLSS in assessing the distribution of unpaid claims reserves | |
| CN113298510A (en) | Deduction instruction initiating method and device | |
| KR102415826B1 (en) | Method for providing automatic collection service for moneybox | |
| US20230351294A1 (en) | Forecasting periodic inter-entity exposure for prophylactic mitigation | |
| US20230359881A1 (en) | Training a centralized repository and data sharing hub to establish model sufficiency | |
| Felsen | Artificial intelligence techniques applied to reduction of uncertainty in decision analysis through learning |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100084 Room 202, 2 / F, 1-3 / F, No. 11, Shangdi Information Road, Haidian District, Beijing Applicant after: Beijing Xingxuan Technology Co.,Ltd. Address before: Room 202, 2 floors, 1-3 floors, No. 11 Shangdi Information Road, Haidian District, Beijing 100085 Applicant before: Beijing Xiaodu Information Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |