CN104616065B - Method and apparatus for order-processing - Google Patents
Method and apparatus for order-processing Download PDFInfo
- Publication number
- CN104616065B CN104616065B CN201510078862.0A CN201510078862A CN104616065B CN 104616065 B CN104616065 B CN 104616065B CN 201510078862 A CN201510078862 A CN 201510078862A CN 104616065 B CN104616065 B CN 104616065B
- Authority
- CN
- China
- Prior art keywords
- probability
- order
- prediction
- user
- grouping
- 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.)
- Active
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"
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Embodiment of the disclosure discloses a kind of method and apparatus for order-processing.This method includes：Prediction user executes the probability for robbing single operation for order；Determine that the user actually executes the probability for robbing single operation for the order；And based on the probability predicted and identified probability, determine the accuracy of the prediction.Embodiment of the disclosure determines the accuracy of the prediction based on the probability predicted with identified probability, can improve the accuracy of the prediction, to which order more rapidly, to be accurately sent to user appropriate.
Description
Technical field
Embodiment of the disclosure is related to a kind of method and apparatus for order-processing.
Background technology
With universal and mobile Internet the high speed development of smart machine, user (such as taxi driver) has been accustomed to
In using taxi-hailing software.Specifically, the order from service server is sent to the mobile terminal of user and in the shifting
It presents or plays in the interface for the taxi-hailing software installed in dynamic terminal, so that the user can carry out competition for orders.If competition for orders success,
Then the user can obtain the contact details of the order to welcome the emperor.In such manner, it is possible to reduce the free travel distance of the user.
However, with using the user of taxi-hailing software increasing, how that order is quick challenging problem is
Ground is accurately sent to user appropriate.Specifically, if order can not accurately be sent, for example, if being not added with differentiation
All orders around one user in preset range (such as 3 kilometers) are all sent to the user by ground, then not only waste order
Resource is sent, and high value order will be influenced for the transmission of valueless or low value a large amount of orders for the user
It sends.
In the related technology, usually consider that one or more of following reference factor rapidly, accurately sends out order
User appropriate is given, these reference factors include the origin of the order, the destination of the order, predetermined model around the order
The position of number of users, the user in enclosing and the current direction of travel etc. of the user.Specifically, according to these reference factors
And its weight and use corresponding prediction technique, predict that each user in multiple users executes competition for orders for the order respectively
Then the order is preferentially sent to the higher user of the probability by the probability of operation.
However, for above-mentioned according to different reference factors and its different prediction techniques of weight, there is currently no a kind of sides
Method can assess the accuracy for the probability that it is predicted, to be difficult to effective rapidly, accurately be sent to order
User appropriate.
Invention content
Embodiment of the disclosure is intended to provide a kind of method and apparatus for order-processing, can solve in the related technology
There are the problem of.
According to one aspect of the disclosure, a kind of method for order-processing is provided.This method includes：Predict user
The probability for robbing single operation is executed for order；Determine that the user actually executes the probability for robbing single operation for the order；With
And based on the probability predicted and identified probability, determine the accuracy of the prediction.
A kind of equipment for order-processing another aspect of the present disclosure provides, the equipment include：Prediction dress
It sets, the probability of single operation is robbed for predicting that user executes for order；First determining device is somebody's turn to do for determining that the user is directed to
Order and actually execute the probability for robbing single operation；And second determining device, for based on the probability predicted with it is identified
Probability determines the accuracy of the prediction.
Embodiment of the disclosure determines the accuracy of the prediction based on the probability predicted with identified probability, can
The accuracy of the prediction is improved, to which order more rapidly, to be accurately sent to user appropriate.
Description of the drawings
Attached drawing described herein is used for providing further understanding of the disclosure, constitutes part of this application, this public affairs
The illustrative embodiments and their description opened do not constitute the improper restriction to the disclosure for explaining the disclosure.In the accompanying drawings：
Fig. 1 is to illustrate embodiment of the disclosure to realize in the figure of system 100 therein；
Fig. 2 is the flow chart of the method 200 according to an embodiment of the present disclosure for order-processing；
Fig. 3 is the flow chart of the method 300 according to an embodiment of the present disclosure for order-processing；And
Fig. 4 is the structure diagram of the equipment 400 according to an embodiment of the present disclosure for order-processing.
Specific implementation mode
Several illustrative embodiments shown in below with reference to the accompanying drawings describe the principle and spirit of the disclosure.It should
Understand, describe these embodiments just for the sake of making those skilled in the art can better understand that realize the disclosure in turn,
And it not limits the scope of the present disclosure in any way.
Fig. 1 is to illustrate embodiment of the disclosure to realize in the figure of system 100 therein.The system 100 includes movement
Terminal 102A to 102F, mobile terminal 102A to 102F are communicated each by network 106 with service server 104.It should
Network 106 may include the mainframe computer net of any number of mobile terminal of connection, fixed terminal and service server 104
Network, such as LAN (LAN), wide area network (WAN), internet, cellular network.The service server 104 includes
One or more computing devices 110 and one or more machine-readable storage libraries or database 112.Those skilled in the art answer
Work as understanding, which can both represent the individual server of such as computer server, can also represent work together
Make to execute multiple servers (such as Cloud Server hadoop) of function.
Within system 100, mobile terminal 102A to 102F is equipped with taxi-hailing software, is taken from business for presenting or playing
The order of business device 104, to carry out competition for orders by user 108A to 108F.If such as user's 108D competition for orders is successful, the user
108D can obtain the contact details of the order to be welcomed the emperor.
It will be appreciated by those skilled in the art that mobile terminal 102A to 102F can include respectively any kind of mobile whole
End, such as handheld computer, personal digital assistant (PDA), cellular phone, network home appliance, smart phone, enhanced general point
At group wireless traffic (EGPRS) mobile phone, media player, navigation equipment or these data processing equipments or other data
Manage any two in equipment or multiple combinations.It should also be appreciated by one skilled in the art that system 100 is merely illustrative mesh
, it is not intended that limit the range of embodiment of the disclosure.In some cases, certain components can increase according to specific need
Add or reduces.
Fig. 2 is the flow chart of the method 200 according to an embodiment of the present disclosure for order-processing.Those skilled in the art
It should be appreciated that this method 200 can be by executing with reference to service server 104 shown in FIG. 1.It for convenience of description, hereafter will ginseng
System 100 shown in FIG. 1 is examined to describe this method 200.
After the beginning of method 200, in step S202, prediction user executes the probability for robbing single operation for order.
In accordance with an embodiment of the present disclosure, feature in the order can be extracted and according to predetermined power corresponding with this feature
Predict that the user executes the probability for robbing single operation for the order again.Wherein, according to scheduled prediction technique, in the order
Feature can be assigned different weights, which can be based on machine learning model, corresponding in usage history order
Feature determines.For example, if according to machine learning model, the origin of History Order is confirmed as and is somebody's turn to do at a distance from user
User executed for the History Order rob single operation the degree of association it is larger, then be used for indicating in order origin and user away from
From feature will be assigned larger weight.
Next, this method 200 proceeds to step S204, determine that the user actually executes for the order and robs single operation
Probability.
It in accordance with an embodiment of the present disclosure, can during an order is distributed to the user in preset range around
To determine that the order is distributed to the publication number of the user respectively, then according to the competition for orders number and the publication number and the use
Family actually executes the competition for orders number for robbing single operation for the order, determines that the user actually executes competition for orders behaviour for the order
The probability of work.For example, if the order is distributed to around the order 100 users in preset range, the publication number
It is 100, meanwhile, if single operation is robbed in 5 users in this 100 users practical execution, which is 5.Therefore,
The user actually executed for the order rob the probability of single operation can be for example equal to the competition for orders number and the publication number
Than that is, 5%.
This method 200 then proceeds to step S206, based on the probability predicted and identified probability, determines the prediction
Accuracy.It specifically, can be by the phase between the probability predicted (such as 6%) and identified probability (such as 5%)
It is determined as the accuracy of the prediction to deviation.For example, the accuracy of the prediction can be calculated by following formula (1).
PB=| A-R |/R (1)
Wherein, PB can indicate the probable deviation between predicted probability and identified probability, to indicate that this is pre-
The accuracy of survey；A can indicate predicted probability；R can indicate identified probability.
Therefore, by above-mentioned formula (1), the accuracy of the prediction can be equal to | 6%-5% |/5%=0.2.
It will be understood by those skilled in the art that S202 to step S206 through the above steps, based on the probability predicted with
Identified probability determines the accuracy of the prediction, can improve the accuracy of the prediction, to by order more rapidly,
Accurately it is sent to user appropriate.
It in accordance with an embodiment of the present disclosure, can during the user being distributed to multiple orders in preset range around
To determine that multiple order is distributed to the publication number of the user and the user actually executes for multiple order respectively
Rob the competition for orders number of single operation, then according to the competition for orders number and the publication number, determine the user for the order reality
Execute the probability for robbing single operation.For example, if 100 orders are distributed to around the order 100 users in preset range,
Then the publication number is 10000, meanwhile, if for each order in this 100 orders, all exist in this 100 users
The practical execution of 5 users rob single operation, then the competition for orders number is 500.Therefore, the user for multiple order reality
Execute rob single operation probability can for example equal to the ratio of the competition for orders number and the publication number, i.e., 5%.
It will be appreciated by those skilled in the art that the present embodiment by multiple orders as a whole come count publication number and
Competition for orders number, and determine that the user actually executes and robs for multiple order with the publication number according to the competition for orders number
The probability of single operation.In such manner, it is possible to the accuracy of probability determined by improving, so that it is guaranteed that the prediction finally determined is accurate
The reliability of degree.Meanwhile those skilled in the art are also understood that, this mode of the present embodiment is only a kind of citing, real
In the application of border, other are used for determining that the user actually executes the mode for the probability for robbing single operation for multiple order, such as
Determine that the user actually executes the probability for robbing single operation for each order in multiple order and then determines respectively
The average value of these probability should all be included in the protection domain of the disclosure.
In this embodiment, if 100 users predicted execute for 100 orders and rob single operation
Probability is as follows：It is 6% for the probability that wherein 50 orders are predicted；It is for the probability that wherein 30 orders are predicted
5.66%；It is 5% for the probability that wherein 20 orders are predicted, then multiple predictions corresponding with multiple order is general
The average value of rate is (50 × 6%+30 × 5.66%+20 × 5%) ÷ 100=5.7%.
It is then possible to by relatively inclined between the probability predicted (such as 5.7%) and identified probability (such as 5%)
Difference is determined as the accuracy of the prediction.For example, the accuracy of the prediction can be calculated by following formula (2).
PBi=| Ai–Ri|/Ri (2)
Wherein, PBiThe probable deviation between predicted probability and identified probability can be indicated, to indicate that this is pre-
The accuracy of survey；AiIt can indicate that predicted user executes the probability for robbing single operation for multiple orders；RiIt can indicate institute
Determining user actually executes the probability for robbing single operation for multiple order.
Therefore, by above-mentioned formula (2), the accuracy of the prediction can be equal to | 5.7%-5% |/5%=0.14.
In accordance with an embodiment of the present disclosure, multiple order can be obtained from an order grouping.Wherein, order grouping can
To obtain in the following manner：Order is ranked up according to the sequence of the probability predicted from small to large；And it will be through row
The order of sequence is divided into multiple order groupings.Specifically, in practical implementation, in order to ensure the prediction finally determined
Accuracy reliability, greater number of order, such as 1,000,000 orders can be used.Then, prediction user is directed to respectively
Each order in 1,000,000 orders and execute the probability for robbing single operation, according to the sequence of the probability predicted from small to large
1,000,000 orders are ranked up；And ranked 1,000,000 orders are divided into multiple orders and are grouped.Wherein, exist
Can have large number of order, such as 10,000 orders in each grouping.In this embodiment, it can reduce as far as possible
Identified probability is influenced by the difference between each order, so that it is guaranteed that finally determine the prediction accuracy can
By property.Meanwhile those skilled in the art are also understood that, this mode of the present embodiment is only a kind of citing, practical application
In, other are used for predicting that the user executes the mode for the probability for robbing single operation for the order, such as general according to what is predicted
Order is ranked up or even without sequence, should all be included in the protection domain of the disclosure by the sequence of rate from big to small.
In this embodiment, each order in being grouped for the above order is grouped, true by above-mentioned formula (2)
It, can be by the flat of these relative deviations after relative deviation between the fixed probability predicted accordingly and corresponding determining probability
Mean value is determined as the accuracy of the prediction.For example, the accuracy of the prediction can be calculated by following formula (3).
Wherein, APB can indicate the average value of probable deviation, to indicate the accuracy of the prediction；AiIt can indicate institute
The user of prediction executes the probability for robbing single operation for the order in i-th of order grouping；RiIt can indicate identified use
Family actually executes the probability for robbing single operation for the order in i-th of order grouping, and n can indicate the above order grouping
Grouping number.
For example, for each order grouping in the grouping of above-mentioned 100 orders, if determined by above-mentioned formula (2)
The probability predicted accordingly and corresponding determining probability between relative deviation it is as follows：It is grouped for wherein 50 orders
Relative deviation is 0.2；Relative deviation for the grouping of wherein 30 orders is 0.166；For the phase of wherein 20 orders grouping
0.15 to deviation, then accuracy APB=(50 × 0.2+30 × 0.166+20 × 0.15) ÷ 100=0.18 of the prediction.
Alternatively or additionally, the accuracy of the prediction can be calculated by following formula (4).
Wherein, APB can indicate the root-mean-square value of probable deviation, to indicate the accuracy of the prediction；AiIt can indicate
The user predicted executes the probability for robbing single operation for the order in i-th of order grouping；RiDetermined by can indicating
User actually executes the probability for robbing single operation for the order in i-th of order grouping, and n can indicate that the above order is grouped
Grouping number.
For example, for each order grouping in the grouping of above-mentioned 100 orders, if determined by above-mentioned formula (2)
The probability predicted accordingly and corresponding determining probability between relative deviation it is as follows：It is grouped for wherein 50 orders
Relative deviation is 0.2；Relative deviation for the grouping of wherein 30 orders is 0.166；For the phase of wherein 20 orders grouping
0.15 to deviation, then the accuracy APB=(50 × 0.2 of the prediction2+30×0.1662+20×0.152) ÷ 100=
0.0328。
Those skilled in the art are also understood that two described in this embodiment kind are used for calculating the mode of APB only
Only it is a kind of citing, in practical application, other are used for calculating the mode of APB, should all be included in the protection domain of the disclosure.
In accordance with an embodiment of the present disclosure, during order is distributed to multiple users, can generate it is multiple broadcast list,
In each broadcast the user for being applied alone and being distributed to the order in multiple user.It is determined in such manner, it is possible to further increase
Probability accuracy, so that it is guaranteed that finally determine the prediction accuracy reliability.
Specifically, it broadcasts single for this according to each user of prediction and executes and rob the probability of single operation from small to large suitable
This is broadcast and is singly ranked up by sequence；Ranked this is broadcast singly to be divided into and multiple broadcasts single grouping；And broadcast single grouping based on multiple
Each of broadcast single grouping, determine that corresponding user broadcasts broadcasting single and actually execute and rob the general of single operation in single grouping for this
Rate.For example, during 1,000,000 orders are distributed to 100 users, 100,000,000 can be generated and broadcast list,.Then, prediction should
100 users broadcast each of list for this 100,000,000 respectively and broadcast the probability that single operation is robbed in single and execution, according to the probability predicted
This 100,000,000 are broadcast and are singly ranked up by sequence from small to large；And ranked this 100,000,000 are broadcast singly to be divided into and multiple broadcasts single point
Group.Wherein, list can be broadcast with large number of in each broadcast during list is grouped, such as 100,000 are broadcast list.In this embodiment,
Probability is broadcast influencing for the difference between list by each determined by capable of reducing as far as possible, so that it is guaranteed that this finally determined is pre-
The reliability of the accuracy of survey.Meanwhile those skilled in the art are also understood that, this mode of the present embodiment is only one kind
Citing, in practical application, other are used for predicting that the user broadcasts mode that is single and executing the probability for robbing single operation for this, such as by
It will be broadcast according to the sequence of the probability predicted from big to small and singly be ranked up or even without sequence, the disclosure should all be included in
Protection domain.
In this embodiment, it broadcasts each of single grouping for above-mentioned and broadcasts single grouping, true by above-mentioned formula (2)
It, can be by the flat of these relative deviations after relative deviation between the fixed probability predicted accordingly and corresponding determining probability
Mean value is determined as the accuracy of the prediction, and the root-mean-square value of these relative deviations can be determined as to the accuracy of the prediction.This
Field technology personnel it is understood that these be used for determine the prediction accuracy method with above with respect to order grouping in it is every
A described method of order grouping is similar, therefore repeats no more.
Fig. 3 is the flow chart of the method 300 according to an embodiment of the present disclosure for order-processing, for being described in detail such as
What determines the accuracy of prediction by using such as 1,000,000 orders.It will be appreciated by those skilled in the art that this method 300
It can be by being executed with reference to service server 104 shown in FIG. 1.For convenience of description, hereinafter with reference to system 100 shown in FIG. 1
To describe this method 300.
After the beginning of method 300, in step S302, prediction user is directed to each of 1,000,000 orders and orders respectively
The probability of single operation is robbed in single and execution.The prediction technique being had been described in such as above-mentioned steps S202 may be used in the prediction,
This is repeated no more.
Next, this method 300 proceeds to step S304, according to the sequence of the probability predicted from small to large by this 100
Ten thousand orders are ranked up, and ranked 1,000,000 orders, which are divided into multiple orders, to be grouped.Wherein, in each grouping
Can have large number of order, such as 10,000 orders.Therefore, group result can be as follows：
Grouping 1：P1、P2、P3、……、P10000
Grouping 2：Pk+1、Pk+2、Pk+3、……、P2k
……
It is grouped i：P(i-1)k+1、P(i-1)k+2、P(i-1)k+3、……、Pik
……
Wherein P indicates that predicted user executes the probability for robbing single operation for corresponding order, and k indicates each grouping
In the number of order that has, such as k=10000.
Next, this method 300 proceeds to step S306, by taking n-th of order is grouped entirety as an example, pass through following formula
(5) prediction user executes the probability for robbing single operation for all orders in n-th of order grouping, and passes through following formula
(6) determine that user actually executes the probability for robbing single operation for all orders in n-th of order grouping.
Ri=Qi/Bi (6)
Wherein AiIt indicates the order during predicted user is grouped for i-th of order and executes the probability for robbing single operation, Ri
User determined by indicating actually executes the probability for robbing single operation for the order in i-th of order grouping, QiIt indicates to use
Family actually executes the competition for orders number for robbing single operation for the order in i-th of order grouping, BiIndicate i-th of order point
Order in group is distributed to the publication number of the user.
This method 300 then proceeds to step S308, determines that the average value of probable deviation is used as this by following formula (7)
The accuracy of prediction.
Wherein, APB can indicate the average value of probable deviation, to indicate the accuracy of the prediction；AiIt can indicate institute
The user of prediction executes the probability for robbing single operation for the order in i-th of order grouping；RiIt can indicate identified use
Family actually executes the probability for robbing single operation for the order in i-th of order grouping, and n can indicate the above order grouping
Grouping number.
Fig. 4 is the structure diagram of the equipment 400 according to an embodiment of the present disclosure for order-processing.As shown in figure 4, should
Equipment 400 includes：Prediction meanss 402 rob the probability of single operation for predicting that user executes for order；First determining device
404, for determining that the user actually executes the probability for robbing single operation for the order；And second determining device 406, it is used for
Based on the probability predicted and identified probability, the accuracy of the prediction is determined.
In accordance with an embodiment of the present disclosure, wherein the prediction meanss 402 include：Extraction unit, for extracting in the order
Feature；And predicting unit, for according to predefined weight corresponding with this feature, predicting that the user executes and robs for the order
The probability of single operation.
In accordance with an embodiment of the present disclosure, wherein first determining device 404 includes：First determination unit, should for determining
User actually executes the competition for orders number for robbing single operation for the order；Second determination unit, for determining that the order is published
To the publication number of the user；And third determination unit, for according to the competition for orders number and the publication number, determining the user
The probability for robbing single operation is actually executed for the order.
In accordance with an embodiment of the present disclosure, wherein second determining device 406 includes：4th determination unit, for by it is pre-
Relative deviation between the probability of survey and identified probability is determined as the accuracy of the prediction.
In accordance with an embodiment of the present disclosure, wherein first determining device 404 includes：5th determination unit, should for determining
User actually executes the competition for orders number for robbing single operation for multiple orders respectively；6th determination unit, it is multiple for determining
Order is distributed to the publication number of the user；And the 7th determination unit, for according to the competition for orders number and the publication number,
Determine that the user actually executes the probability for robbing single operation for multiple order.
In accordance with an embodiment of the present disclosure, wherein second determining device 406 includes：8th determination unit, for determine with
The average value of corresponding multiple the predicted probability of multiple order；And the 9th determination unit, for by the average value
Relative deviation between identified probability is determined as the accuracy of the prediction.
In accordance with an embodiment of the present disclosure, wherein first determining device 404 includes：Sequencing unit, for according to being predicted
Probability sequence from small to large the order is ranked up；First division unit, for the ranked order to be divided into
Multiple order groupings；And first acquisition unit, it is multiple for being obtained from the order grouping in the grouping of multiple order
Order.
In accordance with an embodiment of the present disclosure, wherein second determining device 406 includes：Tenth determination unit, should for being directed to
Each order grouping in the grouping of multiple orders, determine respectively the probability and corresponding identified probability predicted accordingly it
Between relative deviation；And the 11st determination unit, the accuracy for the average value of the relative deviation to be determined as to the prediction.
In accordance with an embodiment of the present disclosure, wherein second determining device 406 includes：12nd determination unit, for being directed to
Each order grouping in multiple order grouping determines the probability predicted accordingly and corresponding identified probability respectively
Between relative deviation；And the 13rd determination unit, the standard for the root-mean-square value of the relative deviation to be determined as to the prediction
Exactness.
In accordance with an embodiment of the present disclosure, wherein first determining device 404 includes：Second sequencing unit, for for use
The each user's order being distributed in multiple users broadcasts list, broadcasts list for this according to each user of the prediction and holds
This is broadcast and is singly ranked up by the probability sequence from small to large of single operation of robbing；Second division unit, for ranked to be somebody's turn to do
It broadcasts singly to be divided into and multiple broadcasts single grouping；And the 14th determination unit, for broadcasting each of single grouping based on multiple and broadcasting list
Grouping determines that corresponding user broadcasts broadcasting in singly grouping for this and singly actually executes the probability for robbing single operation.
In accordance with an embodiment of the present disclosure, wherein second determining device 406 includes：15th determination unit, for being directed to
It is multiple to broadcast each of single grouping and broadcast single grouping, determine respectively the probability predicted accordingly with it is corresponding determined by probability
Between relative deviation；And the 16th determination unit, for the average value of the relative deviation to be determined as the accurate of the prediction
Degree.
In accordance with an embodiment of the present disclosure, wherein second determining device 406 includes：17th determination unit, for being directed to
It is multiple to broadcast each of single grouping and broadcast single grouping, determine respectively the probability predicted accordingly with it is corresponding determined by probability
Between relative deviation；And the 18th determination unit, the standard for the root-mean-square value of the relative deviation to be determined as to the prediction
Exactness.
In conclusion according to above-mentioned embodiment of the disclosure, a kind of method and apparatus for order-processing is provided.It should
Method includes：Prediction user executes the probability for robbing single operation for order；Determine that the user actually executes for the order
Rob the probability of single operation；And based on the probability predicted and identified probability, determine the accuracy of the prediction.The disclosure
Embodiment determines the accuracy of the prediction based on the probability predicted with identified probability, can improve the accurate of the prediction
Degree, to which order more rapidly, to be accurately sent to user appropriate.
The realization of the disclosure and all feature operations provided herein with Fundamental Digital Circuit or can use computer
Software, firmware or hardware, including this specification and its structure disclosed in structural equivalents or one of those or it is more
A combination is realized.The realization of the disclosure can be implemented as one or more computer program products, i.e., computer-readable
One or more modules of the computer program instructions encoded on medium, these instructions are executed or are used by data processing equipment
To control the operation of data processing equipment.The computer-readable medium can be machine readable storage device, machine readable storage
Substrate, memory devices, the composition for influencing machine readable transmitting signal or one or more combination.Term
" data processing equipment " covers all devices, equipment and the machine for handling data, including such as programmable processor, calculating
Machine or multiple processors or computer.In addition to hardware, which may include being created for described computer program
The code of performing environment, such as constitute processor firmware, protocol stack, data base management system, operating system or therein one
The code of a or multiple combination.
Computer program (also referred to as program, software, software application, script or code) can use any type of programming language
(including compiler language or interpretative code) is sayed to write, and computer program can be disposed with any form, including conduct
Stand-alone program either as module, component, subroutine or is suitble to other units used in a computing environment.Computer program
Not necessarily correspond to the file in file system.Program, which can be stored in, keeps other programs or data (such as markup language
The one or more scripts stored in document) file part in, be stored in the single text for being exclusively used in described program
In part, it is either stored in multiple coordinated files (such as text of the part of the one or more modules of storage, subprogram or code
Part) in.Computer program can be deployed on a computer to execute, or at a website or be distributed in
At multiple websites and pass through interconnection of telecommunication network multiple computers on execute.
Process and logic flow described in the disclosure can be by one or more of the one or more computer programs of execution
A programmable processor is executed by operation input data and to generate output and execute function.The process and logic flow
It can be executed by dedicated logic circuit, and device can also be embodied as the dedicated logic circuit, the dedicated logic circuit example
Such as it is FPGA (field programmable gate array) or ASIC (application-specific integrated circuit).
The processor for being suitably executed computer program includes both for example general and special microprocessors and any type
Digital computer any one or more processors.In general, processor is from read-only memory or random access memory
Or the two receives instruction and data.The element of computer may include processor for executing instruction and refer to for storing
Enable one or more memory devices with data.In general, computer will also include one or more mass memory units so as to
Storage data or the computer are operationally coupled to be received from mass memory unit or transmit data to mass memory unit
Either the two mass memory unit is, for example, disk, magneto-optic disk or CD.However, computer need not be with such
Equipment.In addition, computer can be embedded in another equipment, which is, for example, mobile phone, personal digital assistant
(PDA), Mobile audio player, global positioning system (GPS) receiver etc..It is suitble to storage computer program instructions and data
Computer-readable medium includes the nonvolatile memory, medium and memory devices of form of ownership, including for example：Semiconductor is deposited
Storage device, such as EPROM, EEPROM and flash memory device；Disk, such as built-in hard disk or removable disk；Magneto-optic disk；And CD ROM
With DVD-ROM disks.The processor and memory can be supplemented or are incorporated in the dedicated logic circuit with dedicated logic circuit.
In order to provide the interaction with user, realizing for the disclosure can be with for showing that the display of information is set to user
Standby (such as CRT (cathode-ray tube) or LCD (liquid crystal display) monitor) and keyboard and pointing device (such as mouse or with
Track ball can provide input by its user to computer) computer on realize.Other kinds of equipment can also be used
To provide the interaction with user；For example, the feedback provided a user can be any type of sense feedback, such as vision is anti-
Feedback, audio feedback or touch feedback；And input from the user can receive in any form, including the sense of hearing, voice
Or sense of touch.
Although the disclosure includes some details, these details should not be interpreted as to the disclosure or be claimed
Content range limitation, but should be understood as the description of the feature to the example implementation of the disclosure.In the disclosure
Certain features described in the situation being implemented separately can also be provided with individually realizeing combination.On the contrary, individually realizing
Each feature described in situation can also be provided in multiple realizations or be carried in any suitable sub-portfolio respectively
For.Although in addition, can describe feature as protecting in this way to execute and even initially require in some combination above, so
And the one or more features from claimed combination can be removed from combination in some cases, and be claimed
Combination can be related to the variation of sub-portfolio or sub-portfolio.
Similarly, although describing operation according to particular order in the accompanying drawings, this is understood not to require this
The operation of sample particular order shown in either executes or requires all illustrated operations all to be held according to sequential order
Row, to realize desired result.In some circumstances, it may be advantageous for multitask and parallel processing.In addition, described above
The separation of various system units in realization is understood not to require such separation in all realizations, and should
Understanding, described program element and system usually can integrate or be packaged into single software product multiple
Software product.
Therefore, the specific implementation of the disclosure has been described, and other are realized in the range of following claims.Example
Such as, the action described in claim can execute in a different order, and these actions still may be implemented it is expected
Result.A large amount of realize has been described.It will be appreciated, however, that can be without departing from spirit and scope of the present disclosure the case where
Under make various modifications.It is, for example, possible to use each form of flow illustrated above, wherein step can be reordered,
Addition or removal.Therefore, other are realized in the range of following claims.
Claims (24)
1. a kind of method for order-processing, including：
Prediction user executes the probability for robbing single operation for order；
Determine that the user actually executes the probability for robbing single operation for the order；And
Based on the probability of the probability and the determination of the prediction, the accuracy of the prediction is determined.
2. according to the method described in claim 1, wherein predicting that the user executes for the order and robs the general of single operation
Rate includes：
Extract the feature in the order；And
According to predefined weight corresponding with the feature, predict that the user executes for the order and robs the general of single operation
Rate.
3. according to the method described in claim 1, wherein determining that the user actually executes for the order and robs single operation
Probability include：
Determine that the user actually executes the competition for orders number for robbing single operation for the order；
Determine that the order is distributed to the publication number of the user；And
According to the competition for orders number and the publication number, determine that the user actually executes for the order and robs single operation
Probability.
4. according to the method in any one of claims 1 to 3, wherein based on the general of the probability of the prediction and the determination
Rate determines that the accuracy of the prediction includes：
Relative deviation between the probability of the prediction and the probability of the determination is determined as to the accuracy of the prediction.
5. according to the method described in claim 1, wherein determining that the user actually executes for the order and robs single operation
Probability include：
Determine that the user actually executes the competition for orders number for robbing single operation for multiple orders respectively；
Determine that the multiple order is distributed to the publication number of the user；And
According to the competition for orders number and the publication number, determine that the user actually executes competition for orders for the multiple order
The probability of operation.
6. according to the method described in claim 5, the probability wherein based on the probability and the determination of the prediction, determine described in
The accuracy of prediction includes：
Determine the average value of the probability of multiple predictions corresponding with the multiple order；And
Relative deviation between the average value and the probability of the determination is determined as to the accuracy of the prediction.
7. according to the method described in claim 1,2,5 or 6, wherein determining that the user actually executes and robs for the order
The probability of single operation includes：
The order is ranked up according to the probability sequence from small to large of the prediction；
The ranked order is divided into multiple order groupings；And
The multiple order is obtained from the order grouping in the grouping of the multiple order.
8. according to the method described in claim 7, the probability wherein based on the probability and the determination of the prediction, determine described in
The accuracy of prediction includes：
Each order grouping in being grouped for the multiple order, determine respectively the probability of the corresponding prediction with it is corresponding
Relative deviation between the probability of the determination；And
The average value of the relative deviation is determined as to the accuracy of the prediction.
9. according to the method described in claim 7, the probability wherein based on the probability and the determination of the prediction, determine described in
The accuracy of prediction includes：
Each order grouping in being grouped for the multiple order, determine respectively the probability of the corresponding prediction with it is corresponding
Relative deviation between the probability of the determination；And
The root-mean-square value of the relative deviation is determined as to the accuracy of the prediction.
10. method according to claim 1 or 2, wherein determining that the user actually executes competition for orders for the order
The probability of operation includes：
List is broadcast for for each user that the order is distributed in multiple users, according to the described each of the prediction
User broadcasts single for described in and execution robs the sequence of the probability of single operation from small to large and is singly ranked up described broadcast；
It broadcasts singly to be divided into described in will be ranked and multiple broadcasts single grouping；And
It broadcasts each of single grouping based on the multiple and broadcasts single grouping, determine that corresponding user broadcasts broadcasting in single grouping for described
Singly actually execute the probability for robbing single operation.
11. according to the method described in claim 10, the probability wherein based on the probability and the determination of the prediction, determines institute
The accuracy for stating prediction includes：
Broadcast each of single grouping for the multiple and broadcast single grouping, determine respectively the probability of the corresponding prediction with it is corresponding
Relative deviation between the probability of the determination；And
The average value of the relative deviation is determined as to the accuracy of the prediction.
12. according to the method described in claim 10, the probability wherein based on the probability and the determination of the prediction, determines institute
The accuracy for stating prediction includes：
Broadcast each of single grouping for the multiple and broadcast single grouping, determine respectively the probability of the corresponding prediction with it is corresponding
Relative deviation between the probability of the determination；And
The root-mean-square value of the relative deviation is determined as to the accuracy of the prediction.
13. a kind of equipment for order-processing, including：
Prediction meanss rob the probability of single operation for predicting that user executes for order；
First determining device, for determining that the user actually executes the probability for robbing single operation for the order；And
Second determining device determines the accuracy of the prediction for the probability of probability and the determination based on the prediction.
14. equipment according to claim 13, wherein the prediction meanss include：
Extraction unit, for extracting the feature in the order；And
Predicting unit, for according to predefined weight corresponding with the feature, predicting that the user executes for the order
Rob the probability of single operation.
15. equipment according to claim 13, wherein first determining device includes：
First determination unit, for determining that the user actually executes the competition for orders number for robbing single operation for the order；
Second determination unit, for determining that the order is distributed to the publication number of the user；And
Third determination unit, for according to the competition for orders number and the publication number, determining that the user is directed to the order
And actually execute the probability for robbing single operation.
16. the equipment according to any one of claim 13 to 15, wherein second determining device includes：
4th determination unit, it is described for the relative deviation between the probability of the prediction and the probability of the determination to be determined as
The accuracy of prediction.
17. equipment according to claim 13, wherein first determining device includes：
5th determination unit, for determine the user actually executed for multiple orders respectively rob single operation rob single
Number；
6th determination unit, for determining that the multiple order is distributed to the publication number of the user；And
7th determination unit, for according to the competition for orders number and the publication number, determining the user for the multiple
Order and actually execute the probability for robbing single operation.
18. equipment according to claim 17, wherein second determining device includes：
8th determination unit, the average value of the probability for determining multiple predictions corresponding with the multiple order；
And
9th determination unit, for the relative deviation between the average value and the probability of the determination to be determined as the prediction
Accuracy.
19. according to the equipment described in claim 13,14,17 or 18, wherein first determining device includes：
The order is ranked up by the first sequencing unit for the sequence of the probability according to the prediction from small to large；
First division unit is grouped for the ranked order to be divided into multiple orders；And
Acquiring unit, for obtaining the multiple order from the order grouping in the grouping of the multiple order.
20. equipment according to claim 19, wherein second determining device includes：
Tenth determination unit, for for each order grouping in the grouping of the multiple order, determining respectively corresponding described
Relative deviation between the probability of prediction and the probability of the corresponding determination；And
11st determination unit, the accuracy for the average value of the relative deviation to be determined as to the prediction.
21. equipment according to claim 19, wherein second determining device includes：
12nd determination unit, for for each order grouping in the grouping of the multiple order, determining corresponding institute respectively
State the relative deviation between the probability of prediction and the probability of the corresponding determination；And
13rd determination unit, the accuracy for the root-mean-square value of the relative deviation to be determined as to the prediction.
22. the equipment according to claim 13 or 14, wherein first determining device includes：
Second sequencing unit, for broadcasting list for for each user that the order is distributed in multiple users, according to
Each user of the prediction broadcasts single for described in and execution is robbed the sequence of the probability of single operation from small to large and broadcast described
Singly it is ranked up；
Second division unit multiple broadcasts single grouping for broadcasting described in will be ranked to be singly divided into；And
14th determination unit determines corresponding user's needle for being broadcast each of single grouping based on the multiple and being broadcast single grouping
Broadcasting single and actually execute the probability for robbing single operation in single grouping is broadcast to described.
23. equipment according to claim 22, wherein second determining device includes：
15th determination unit determines corresponding institute respectively for broadcasting each of single grouping for the multiple and broadcasting single grouping
State the relative deviation between the probability of prediction and the probability of the corresponding determination；And
16th determination unit, the accuracy for the average value of the relative deviation to be determined as to the prediction.
24. equipment according to claim 22, wherein second determining device includes：
17th determination unit determines corresponding institute respectively for broadcasting each of single grouping for the multiple and broadcasting single grouping
State the relative deviation between the probability of prediction and the probability of the corresponding determination；And
18th determination unit, the accuracy for the root-mean-square value of the relative deviation to be determined as to the prediction.
Priority Applications (9)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510078862.0A CN104616065B (en) | 2015-02-13 | 2015-02-13 | Method and apparatus for order-processing |
| PCT/CN2016/072840 WO2016119749A1 (en) | 2015-01-29 | 2016-01-29 | Order allocation system and method |
| US15/547,221 US10977585B2 (en) | 2015-01-29 | 2016-01-29 | Order allocation system and method |
| KR1020177024089A KR20180013843A (en) | 2015-01-29 | 2016-01-29 | Order allocation system and method |
| EP16742811.9A EP3252705A4 (en) | 2015-01-29 | 2016-01-29 | Order allocation system and method |
| SG11201706188YA SG11201706188YA (en) | 2015-01-29 | 2016-01-29 | Order allocation system and method |
| PH12017501364A PH12017501364A1 (en) | 2015-01-29 | 2017-07-28 | Order allocation system and method |
| HK18104774.4A HK1245473A1 (en) | 2015-01-29 | 2018-04-12 | Order allocation system and method |
| US17/227,439 US20210232984A1 (en) | 2015-01-29 | 2021-04-12 | Order allocation system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510078862.0A CN104616065B (en) | 2015-02-13 | 2015-02-13 | Method and apparatus for order-processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104616065A CN104616065A (en) | 2015-05-13 |
| CN104616065B true CN104616065B (en) | 2018-07-13 |
Family
ID=53150501
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510078862.0A Active CN104616065B (en) | 2015-01-29 | 2015-02-13 | Method and apparatus for order-processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104616065B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108596401B (en) | 2016-11-25 | 2020-04-24 | 口碑(上海)信息技术有限公司 | Traffic prediction method and device |
| CN107451904A (en) * | 2017-08-18 | 2017-12-08 | 深圳易嘉恩科技有限公司 | Bill document order display systems and method |
| CN109190791A (en) * | 2018-07-25 | 2019-01-11 | 广州优视网络科技有限公司 | Using the appraisal procedure of recommended models, device and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1903493A1 (en) * | 2005-06-16 | 2008-03-26 | Yahoo Japan Corporation | Computer processing method, and program |
| CN101620781A (en) * | 2008-06-30 | 2010-01-06 | 株式会社查纳位资讯情报 | System and method for forecasting passenger information and searching the same |
| CN102833680A (en) * | 2012-09-11 | 2012-12-19 | 中国水产科学研究院东海水产研究所 | Position-based marine fishery information serving method |
-
2015
- 2015-02-13 CN CN201510078862.0A patent/CN104616065B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1903493A1 (en) * | 2005-06-16 | 2008-03-26 | Yahoo Japan Corporation | Computer processing method, and program |
| CN101620781A (en) * | 2008-06-30 | 2010-01-06 | 株式会社查纳位资讯情报 | System and method for forecasting passenger information and searching the same |
| CN102833680A (en) * | 2012-09-11 | 2012-12-19 | 中国水产科学研究院东海水产研究所 | Position-based marine fishery information serving method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104616065A (en) | 2015-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106202453B (en) | Multimedia resource recommendation method and device | |
| US10372703B2 (en) | Systems and methods for automated identification of applications for deletion recommendation on a user device | |
| US20170097743A1 (en) | Recommending Applications | |
| US10699187B2 (en) | Selecting action slates using reinforcement learning | |
| CN104808892B (en) | A kind of application icon sort method, device, system and relevant device | |
| US11361046B2 (en) | Machine learning classification of an application link as broken or working | |
| CN104715426B (en) | Method and apparatus for order-processing | |
| US20170085678A1 (en) | Recommending Applications | |
| CN110023928B (en) | Predictive search engine ranking signal values | |
| CN104599217A (en) | Method and device for determining current destination of passenger | |
| CN106462801A (en) | Training neural networks on partitioned training data | |
| CN109831532B (en) | Data sharing method, device, equipment and medium | |
| KR20160123377A (en) | Methods and systems for providing functional extensions with a landing page of a creative | |
| CN104616065B (en) | Method and apparatus for order-processing | |
| CN106469113A (en) | Applied program testing method and system | |
| US9300712B2 (en) | Stream processing with context data affinity | |
| CN109828859A (en) | Mobile terminal memory analysis method, apparatus, storage medium and electronic equipment | |
| CN104636966B (en) | For sending the method and apparatus of order | |
| CN104599092B (en) | For monitoring the method and apparatus of order business | |
| CN106796587B (en) | Method and system for verifying analysis results | |
| US20180027064A1 (en) | Program and statistical processing system | |
| CN104766262A (en) | Order processing method and device | |
| US9075670B1 (en) | Stream processing with context data affinity | |
| CN103942230A (en) | Method, device and system for voice webpage navigation | |
| US9532165B2 (en) | Method and apparatus for location prediction using short text |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |