CN109872225A - Divide single method and device - Google Patents
Divide single method and device Download PDFInfo
- Publication number
- CN109872225A CN109872225A CN201910130694.3A CN201910130694A CN109872225A CN 109872225 A CN109872225 A CN 109872225A CN 201910130694 A CN201910130694 A CN 201910130694A CN 109872225 A CN109872225 A CN 109872225A
- Authority
- CN
- China
- Prior art keywords
- information
- bill
- order
- sales force
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application provides the single method and devices of one kind point, including, each order information that will acquire is according to pre-set point of single strategy, it is pre-assigned to the sales force that remaining order amount is not zero, pre- point of single information of predetermined quantity is obtained, each pre- point single information includes sales force's information of the sales force of each order information predistribution in each order information；For each pre- point single information, by this pre- point single information input into the sorter model pre-established, the corresponding probability set of signing a bill of this pre- point single information is obtained, the probability set of signing a bill includes sign a bill probability of the sales force to the order information of predistribution of each predistribution；For each probability set of signing a bill, the combined chance for probability of respectively signing a bill in the probability set of signing a bill is calculated；Obtain the corresponding probability set of signing a bill of highest combined chance；According to the sales force that order information each in the corresponding probability set of signing a bill of highest combined chance pre-allocates, a point list is carried out to each order information.The entirety that enterprise can be improved is signed a bill rate.
Description
Technical field
This application involves the technical fields for assigning order, more particularly, to the single method and device of one kind point.
Background technique
As income level of resident and consuming capacity improve increasingly, tourist market is grown at top speed therewith, tourist industry also just from
Niche markets are to popular transformation.Random point of single assignment order mode is taken in the prior art, and enterprise receives from call center
To each order can be randomized to either in can be in the sales force of order state, but since the high speed of tounist market increases
The volume of the flow of passengers brought by long increases, and a this point single device based on randomized policy does not efficiently use limited sales force and goes to mention
The entirety of height travelling enterprise is signed a bill rate, causes the rate of signing a bill low.
Summary of the invention
In view of this, the application's is designed to provide a kind of point of single method and device, the entirety for improving enterprise is signed a bill rate.
In a first aspect, the embodiment of the present application, which provides one kind, divides folk prescription method, comprising:
Each order information that will acquire is pre-assigned to the pin that remaining order amount is not zero according to pre-set point of single strategy
Personnel are sold, pre- point of single information of predetermined quantity is obtained, each pre- point single information includes each order letter in each order information
Cease sales force's information of the sales force of predistribution；
It is somebody's turn to do by this pre- point single information input into the sorter model pre-established for each pre- point single information
The corresponding probability set of signing a bill of pre- point of list information, the probability set of signing a bill includes order of the sales force to predistribution of each predistribution
The probability of signing a bill of information；
For each probability set of signing a bill, the combined chance for probability of respectively signing a bill in the probability set of signing a bill is calculated；
Obtain the corresponding probability set of signing a bill of highest combined chance；
It is right according to the sales force that order information each in the corresponding probability set of signing a bill of the highest combined chance pre-allocates
Each order information carries out a point list.
With reference to first aspect, the embodiment of the present application provides the first possible embodiment of first aspect, wherein institute
Stating sales force's information includes: maximum order amount and current order amount, and each order information that will acquire is according to pre-set point
Single strategy, is pre-assigned to the sales force that remaining order amount is not zero, and obtains pre- point of single information of predetermined quantity, comprising:
From each order information of acquisition, the first order information is extracted, according to the initial sale personal information of storage, by institute
It states the first order information and is pre-assigned to corresponding first sales force of initial sale personal information that remaining order amount is not zero, structure
First pre- point of single information of first sales force's information including the first order information and storage is built, remaining order amount connects for maximum
The difference of single amount and current order amount；
The current order amount in the first sales force information updated storage, until each order information obtained is pre-
It is assigned；
Divide single information, pre- point of single information of building, wherein N is institute in advance according to first pre- point of single information being sequentially generated to N
State the order information item number in each order information；
Described pre- point of confirmation building single information finishes, and the sales force's information updated storage is initial sale personal information.
The possible embodiment of with reference to first aspect the first, the embodiment of the present application provide second of first aspect
Possible embodiment, wherein the current order amount in the first sales force information updated storage, until obtaining
Each order information pre-allocated and finished, comprising:
After the current order amount in the first sales force's information updated storage, then from each order information of acquisition,
The second order information in addition to the first order information is extracted, according to the sales force's information updated storage, the second order is believed
Breath is pre-assigned to corresponding second sales force of sales force's information that remaining order amount is not zero, and building includes that the second order is believed
The second of the second sales force's information pre- point of single information for ceasing and updating storage, in the second sales force's information updated storage
Current order amount, until each order information obtained is pre-allocated and finished.
The possible embodiment of with reference to first aspect the first, the embodiment of the present application provide the third of first aspect
Possible embodiment, wherein sales force's information further includes History Order information, and History Order information includes when signing a bill
Between and time of the signing a bill corresponding History Order, in each order information from acquisition, extract the first order information it
Before, the method also includes:
The sales force that is not zero of remaining order amount for extracting storage it is corresponding it is same sign a bill the time, according to pre-set
First Replacement Strategy replaces time of the signing a bill corresponding History Order.
The possible embodiment of with reference to first aspect the first, the embodiment of the present application provide the 4th kind of first aspect
Possible embodiment, wherein sales force's information further includes History Order information, and the History Order information includes label
Single time and time of the signing a bill corresponding History Order are initial sales force in the sales force's information updated storage
After information, the method also includes:
Judge whether pre- point of single information bar number of building reaches the predetermined quantity；
If it is not, the sales force that is not zero of remaining order amount for extracting storage it is corresponding it is same sign a bill the time, according in advance
The first Replacement Strategy being arranged replaces time of the signing a bill corresponding History Order, executes each order from acquisition
In information, the step of extracting the first order information, until pre- point of single information bar number of building reaches the predetermined quantity.
The possible embodiment of with reference to first aspect the first, the embodiment of the present application provide the 5th kind of first aspect
Possible embodiment, wherein sales force's information further includes History Order information, in the sale people updated storage
After member's information is initial sale personal information, the method also includes:
Judge whether pre- point of single information bar number of building reaches the predetermined quantity；
If it is not, being directed to sales force's information, according to pre-set second Replacement Strategy, other sales forces letter is chosen
The History Order information of selection is added in sales force's information by the History Order information in breath, is executed described from acquisition
Each order information in, the step of extracting the first order information, until pre- point of single information bar number of building reaches the predetermined number
Amount.
The possible embodiment of with reference to first aspect the first, the embodiment of the present application provide the 6th kind of first aspect
Possible embodiment, wherein sales force's information further includes History Order information, and History Order information includes that history is ordered
The single and corresponding time of received orders of the History Order is initial sale personal information in the sales force's information updated storage
Later, the method also includes:
Judge whether pre- point of single information bar number of building reaches the predetermined quantity；
If it is not, sales force's information is directed to, according to pre-set third Replacement Strategy, in sales force's information
The corresponding time of received orders of each History Order for including is replaced, and described from each order information of acquisition, extraction first is executed
The step of order information, until the single information bar number of pre- point of building reaches the predetermined quantity.
With reference to first aspect, the first of first aspect to any possible embodiment in the 6th kind, the application is implemented
Example provides the 7th kind of possible embodiment of first aspect, wherein establishes the sorter model, comprising:
It the corresponding sample History Order information of collecting sample sales force information, sample sales force's information and signs a bill
As a result, based on a sample sales force information and corresponding sample History Order information, the single information of building equally one's duty；
According to the corresponding feature vector group of the sorter model, the feature vector of the single information of sample point is extracted, according to institute
It states the single Vector Groups of format building sample point of feature vector group and obtains the unidirectional quantity set of sample point；
The single Vector Groups collection of the sample point is divided into the unidirectional quantity set of training sample point and the unidirectional quantity set of test specimens one's duty；
Using the single Vector Groups of training sample point in training sample point unidirectional quantity set as the input of the sorter model, with
Corresponding output of the result as the sorter model of signing a bill of the single Vector Groups of the training sample point, to the sorter model into
Row training；
Using the unidirectional amount group of test specimens one's duty in the unidirectional quantity set of test specimens one's duty as the sorter model of training
Input obtains test sample and signs a bill result；
Result is signed a bill based on test sample and the test sample signs a bill that result is corresponding to sign a bill as a result, calculating the institute of training
State the precision of sorter model；
If the precision calculated is greater than pre-set precision threshold, the sorter model established, if calculate
Precision is not more than pre-set precision threshold, executes the unidirectional amount of training sample point in the unidirectional quantity set of training sample point
The step of organizing the input as the sorter model.
With reference to first aspect, the first of first aspect to any possible embodiment in the 6th kind, the application is implemented
Example provides the 8th kind of possible embodiment of first aspect, wherein probability of respectively signing a bill in the calculating probability set of signing a bill
Combined chance, comprising:
Probability of respectively signing a bill in probability set of signing a bill successively is multiplied, the combined chance is obtained.
Second aspect, the embodiment of the present application also provide a kind of point of single device, comprising:
Forward allocator module, each order information for will acquire are pre-assigned to residue according to pre-set point of single strategy
The sales force that order amount is not zero obtains pre- point of single information of predetermined quantity, and each pre- point single information includes each order
Sales force's information of the sales force of each order information predistribution in information；
Probability set of signing a bill obtains module, for for each pre- point single information, by this pre- point single information input to building in advance
In vertical sorter model, the corresponding probability set of signing a bill of this pre- point list information is obtained, the probability set of signing a bill includes each predistribution
Sales force to the probability of signing a bill of the order information of predistribution；
Combined chance computing module calculates probability of respectively signing a bill in the probability set of signing a bill for being directed to each probability set of signing a bill
Combined chance；
Comparison module, for obtaining the corresponding probability set of signing a bill of highest combined chance；
Divide single module, for pre-allocating according to order information each in the corresponding probability set of signing a bill of the highest combined chance
Sales force, each order information is carried out point single.
The embodiment of the present application bring it is following the utility model has the advantages that
The application is by combining order information and sales force's information, according to the probability of signing a bill of the sales force of prediction
A point list is carried out, rather than uses randomized policy that can carry out a point list in the sales force of order, the whole of enterprise can be improved and sign
Single rate.
Other feature and advantage of the application will illustrate in the following description, also, partly become from specification
It obtains it is clear that being understood and implementing the application.The purpose of the application and other advantages are in specification, claims
And specifically noted structure is achieved and obtained in attached drawing.
To enable the above objects, features, and advantages of the application to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the application specific embodiment or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the application, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 is the flow chart of provided by the embodiments of the present application point of folk prescription method；
Fig. 2 is the structural framing figure of provided by the embodiments of the present application point of single device；
Fig. 3 is a kind of structural schematic diagram of computer equipment 300 provided by the embodiments of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with attached drawing to the application
Technical solution be clearly and completely described, it is clear that described embodiment is some embodiments of the present application, rather than
Whole embodiments.Based on the embodiment in the application, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall in the protection scope of this application.
Limited sales force is not efficiently used currently based on a point single device for randomized policy to take a trip to improve enterprise
Entirety is signed a bill rate, causes the rate of signing a bill low, is based on this, one kind provided by the embodiments of the present application divides folk prescription method and system, Ke Yitong
It crosses and point singly, sign a bill rate to improve the entirety of enterprise in conjunction with order information and sales force's information.
To divide folk prescription method to carry out one kind disclosed in the embodiment of the present application first detailed convenient for understanding the present embodiment
It is thin to introduce, as shown in Figure 1, specifically including following steps S101~S105:
S101, according to pre-set point of single strategy, be pre-assigned to remaining order amount is not each order information that will acquire
Zero sales force obtains pre- point of single information of predetermined quantity, and each pre- point single information includes each in each order information
Sales force's information of the sales force of order information predistribution；
In the embodiment of the present application, after user generates order information by network, it is transmitted to the foreground of network, thus, order
Information can be obtained by foreground, meanwhile, sales force's information is stored and safeguarded in background system, is getting order information
When, by background system, it can inquire and obtain sales force's information.
In the embodiment of the present application, as an alternative embodiment, foreground be can be according to pre-set periodicity extraction order
Information obtains sales force's information that remaining order amount is not zero from background system, according to acquisition after extracting order information
Sales force's information, each order information of extraction is pre-allocated.
In the embodiment of the present application, as an alternative embodiment, order information includes but is not limited to: customer name, gender, connection
It is the travel informations such as the personal information such as mode and Reiseziel information, order source, order type.Wherein, order type
It include: individual tour, double person travelling and other more front yard trips etc..
Sales force's information includes but is not limited to: sales force's name, gender, the length of service, history are signed a bill probability, maximum order
Amount and current order amount etc..Wherein, by maximum order amount and current order amount, the remaining order of the sales force can be calculated
Amount.
In the embodiment of the present application, for multiple order informations, one or more sales forces are pre-assigned to, need to ensure pre-
One or more sales forces of distribution are as a team, so that team is as a whole, to the label of multiple order informations
Single maximum probability, in this way, last point of single efficiency optimization can be ensured.It is then desired to comprehensively consider various pre-distribution schemes, from
One optimal pre-distribution scheme of middle selection, as an alternative embodiment, sales force's information includes: maximum order amount and currently connects
Dan Liang, each order information that will acquire are pre-assigned to the sale that remaining order amount is not zero according to pre-set point of single strategy
Personnel obtain pre- point of single information of predetermined quantity, comprising:
A11, from each order information of acquisition, the first order information of extraction, the initial sale personal information of foundation storage,
First order information is pre-assigned to the corresponding first sale people of initial sale personal information that remaining order amount is not zero
Member, building include first pre- point of single information of first sales force's information of the first order information and storage, and remaining order amount is
The difference of maximum order amount and current order amount；
A12, the current order amount in the first sales force information updated storage, until each order information obtained
It is finished by predistribution；
A13 divides single information, pre- point of single information of building, wherein N according to first pre- point of single information being sequentially generated to N in advance
For the order information item number in each order information；
A14, described pre- point of confirmation building single information finish, and the sales force's information updated storage is initial sales force letter
Breath.
In the embodiment of the present application, after the current order amount in the first sales force's information updated storage, then from acquisition
Each order information in, the second order information in addition to the first order information is extracted, according to the sales force's letter updated storage
Breath, is pre-assigned to corresponding second sales force of sales force's information that remaining order amount is not zero, structure for the second order information
Build second including the second order information and the second sales force's information updated storage pre- point of single information, second updated storage
Current order amount in sales force's information, until each order information obtained is pre-allocated and finished.
In the embodiment of the present application, the predistribution of each order information of each round forms a point single information in advance, due to ordering
The predistribution mode of single information is different, therefore, it is possible to form multiple pre- points single information.For example, each order information obtained includes:
First order information and the second order information, the sales force that the remaining order amount before predistribution is not zero include: the first sale
Personnel and the second sales force, it is assumed that the remaining order amount before predistribution is not zero and is greater than or equal to 2, then in predistribution,
There is following pre-distribution scheme:
First pre-distribution scheme: the first order information is pre-assigned to the first sales force, and the second order information is pre-assigned to
First sales force；
Second pre-distribution scheme: the second order information is pre-assigned to the first sales force, and the first order information is pre-assigned to
First sales force；
Third pre-distribution scheme: the first order information is pre-assigned to the first sales force, and the second order information is pre-assigned to
Second sales force；
4th pre-distribution scheme: the first order information is pre-assigned to the second sales force, and the second order information is pre-assigned to
First sales force；
5th pre-distribution scheme: the first order information is pre-assigned to the second sales force, and the second order information is pre-assigned to
Second sales force；
6th pre-distribution scheme: the second order information is pre-assigned to the second sales force, and the first order information is pre-assigned to
Second sales force.
In the embodiment of the present application, point single information, different order informations are pre-assigned to each pre-distribution scheme corresponding one in advance
The sequence of same sales force is different, also will form different pre-distribution schemes.In practical application, predetermined quantity can be according to order
The item number of information determines that the item number of order information is more, and predetermined quantity is bigger.Certainly, predetermined quantity can also be according to order information
Item number and sales force's number for being not zero of remaining order amount determine that the embodiment of the present application is not construed as limiting this.
In the embodiment of the present application, after according to the predistribution of the first pre-distribution scheme, i.e., first pre- point of confirmation building single
Information finishes, and the sales force's information updated storage is initial sale personal information, in order to pre- point of next pre-distribution scheme
Match.After according to the predistribution of the second pre-distribution scheme, the sales force's information updated storage again is initial sales force
Information.
In the embodiment of the present application, as another alternative embodiment, sales force's information further includes History Order information, history
Order information includes sign a bill time and time of the signing a bill corresponding History Order, in each order information from acquisition,
Before extracting the first order information, this method further include:
The sales force that is not zero of remaining order amount for extracting storage it is corresponding it is same sign a bill the time, according to pre-set
First Replacement Strategy replaces time of the signing a bill corresponding History Order.
In the embodiment of the present application, since sales force is at same time or moment, the different History Orders of signing are signed a bill
Probability may will affect the probability of signing a bill of current order information, therefore, according to the first Replacement Strategy, by the same time of signing a bill
History Order is replaced to different sales forces, so that sales force's information to storage is updated, and can be based on update
Sales force's information carry out order information predistribution.
In the embodiment of the present application, as an alternative embodiment, carrying out displacement to time of the signing a bill corresponding History Order is
Finger interacts different sales forces in the History Order that the same time signs a bill, alternatively, being exchanged at random.
In the embodiment of the present application, as yet another alternative embodiment, sales force's information further includes History Order information, history
Order information includes sign a bill time and time of the signing a bill corresponding History Order, in the sales force's information updated storage
After initially selling personal information, this method further include:
Judge whether pre- point of single information bar number of building reaches the predetermined quantity, if it is not, extracting the remaining order of storage
Measure the sales force that is not zero it is corresponding it is same sign a bill the time, according to pre-set first Replacement Strategy, sign a bill the time to this
The step of corresponding History Order is replaced, and execution is described from each order information of acquisition, extracts the first order information, directly
Pre- point of single information bar number to building reaches the predetermined quantity.
In the embodiment of the present application, if the single information bar number of pre- point of building reaches the predetermined quantity, it can execute subsequent
Process.
In the embodiment of the present application, it can also virtually increase sales force History Order, thus expand pre-distribution scheme, because
And as yet another alternative embodiment, sales force's information further includes History Order information, in the sales force updated storage
Information is this method after initial sale personal information further include:
Judge whether pre- point of single information bar number of building reaches the predetermined quantity；
If it is not, being directed to sales force's information, according to pre-set second Replacement Strategy, other sales forces letter is chosen
The History Order information of selection is added in sales force's information by the History Order information in breath, is executed described from acquisition
Each order information in, the step of extracting the first order information, until pre- point of single information bar number of building reaches the predetermined number
Amount.
In the embodiment of the present application, which can also be applied in each order information from acquisition, extracted first and ordered
Before the step of single information.
In the embodiment of the present application, as yet another alternative embodiment, sales force's information further includes History Order information, history
Order information includes History Order and the corresponding time of received orders of the History Order, in the sales force's information updated storage
After initially selling personal information, this method further include:
Judge whether pre- point of single information bar number of building reaches the predetermined quantity；
If it is not, sales force's information is directed to, according to pre-set third Replacement Strategy, in sales force's information
The corresponding time of received orders of each History Order for including is replaced, and described from each order information of acquisition, extraction first is executed
The step of order information, until the single information bar number of pre- point of building reaches the predetermined quantity.
In the embodiment of the present application, by the History Order information of same sales force, inversion sequence is carried out according to time of received orders,
Change the corresponding time of received orders of History Order of the sales force.
S102 is obtained by this pre- point single information input into the sorter model pre-established for each pre- point single information
To the corresponding probability set of signing a bill of this pre- point list information, the probability set of signing a bill includes the sales force of each predistribution to predistribution
The probability of signing a bill of order information；
In the embodiment of the present application, for example, probability set of signing a bill includes: that the first order information is pre- for the first pre-distribution scheme
The probability of signing a bill of the first sales force is distributed to, and, the second order information is pre-assigned to the probability of signing a bill of the first sales force.
In the embodiment of the present application, as an alternative embodiment, the sorter model is established, comprising:
B11, the corresponding sample History Order information of collecting sample sales force information, sample sales force's information and
It signs a bill as a result, constructing the single information of equally one's duty based on a sample sales force information and corresponding sample History Order information；
In the embodiment of the present application, obtains a large amount of sample sales force information and each sample sales force information is corresponding
Sample History Order information.
In the embodiment of the present application, result of signing a bill is the execution of the corresponding sample History Order information of sample sales force information
As a result, comprising: sign a bill successfully and sign a bill unsuccessfully, the equally single information correspondence of one's duty signs a bill successfully or signs a bill unsuccessfully.
B12 extracts the feature vector of the single information of sample point, presses according to the corresponding feature vector group of the sorter model
Divide single Vector Groups according to the format building sample of described eigenvector group and obtains the unidirectional quantity set of sample point；
In the embodiment of the present application, it is assumed that the corresponding feature vector group of sorter model is the row of n dimensional feature vector composition
Feature vector group fills the feature vector of extraction to this feature vector in feature vector group from the single information of sample point
At position, if a feature vector in feature vector group, there is no corresponding feature vector in the single information of sample point, then by feature to
Position zero setting in amount group where this feature vector, to obtain the single Vector Groups of sample point.
In the embodiment of the present application, as an alternative embodiment, feature that the corresponding feature vector group of sorter model includes
Vector includes but is not limited to: customer name, gender, contact method, Reiseziel information, order source, order type, sale
Personnel's name, gender, the length of service, history are signed a bill probability, maximum order amount, current order amount, destination instruction evaluation and test achievement.
The single Vector Groups collection of the sample point is divided into the unidirectional quantity set of training sample point and the unidirectional amount of test specimens one's duty by B13
Collection；
B14, using the single Vector Groups of training sample point in the unidirectional quantity set of training sample point as the defeated of the sorter model
Enter, using the single Vector Groups of the training sample point it is corresponding sign a bill result as the sorter model output, to the classifier
Model is trained；
In the embodiment of the present application, sorter model includes but is not limited to: Bayes classifier, deep neural network classification
Device, support vector machine classifier, Boost classifier, decision tree classifier.In the present embodiment, as an alternative embodiment, use
Deep neural network classifier, and during training deep neural network classifier, use Bayes classifier as deeply
The control group of neural network classifier is spent, i.e., using the single Vector Groups of successfully corresponding training sample point and the failure pair of signing a bill of signing a bill
The single Vector Groups of the training sample answered point are trained.
B15, using the unidirectional amount group of test specimens one's duty in the unidirectional quantity set of test specimens one's duty as the classifier mould of training
The input of type obtains test sample and signs a bill result；
B16, signs a bill result based on test sample and the test sample signs a bill that result is corresponding to sign a bill as a result, calculating training
The sorter model precision；
In the embodiment of the present application, test sample signs a bill the corresponding result of signing a bill of result as test specimens one's duty list as input
The corresponding result of signing a bill of Vector Groups.
B17, if the precision calculated is greater than pre-set precision threshold, the sorter model established, if meter
The precision of calculation is not more than pre-set precision threshold, executes described single with the training sample point in the unidirectional quantity set of training sample point
The step of input of the Vector Groups as the sorter model.
S103 calculates the combined chance for probability of respectively signing a bill in the probability set of signing a bill for each probability set of signing a bill；
In the embodiment of the present application, probability set of signing a bill corresponding for N number of order information includes N number of probability of signing a bill.
In the embodiment of the present application, as an alternative embodiment, the synthesis for calculating probability of respectively signing a bill in the probability set of signing a bill is general
Rate, comprising:
Probability of respectively signing a bill in probability set of signing a bill successively is multiplied, the combined chance is obtained.
S104 obtains the corresponding probability set of signing a bill of highest combined chance；
In the embodiment of the present application, it is assumed that probability set of signing a bill shares 6 (first sign a bill probability set sign a bill probability set to the 6th),
The first pre-distribution scheme is respectively corresponded to the 6th pre-distribution scheme, wherein the first combined chance for signing a bill probability set is 0.7, the
Two combined chances for signing a bill probability set are 0.62, and the sign a bill combined chance of probability set of third is 0.5, and the 4th signs a bill the comprehensive of probability set
Closing probability is 0.68, and the 5th combined chance for signing a bill probability set is 0.2, and the 6th combined chance for signing a bill probability set is 0.31, then
Highest combined chance is corresponding, and probability set of signing a bill is first to sign a bill probability set.
S105, the sale people pre-allocated according to order information each in the corresponding probability set of signing a bill of the highest combined chance
Member carries out a point list to each order information.
In the embodiment of the present application, highest combined chance is corresponding, and probability set of signing a bill is first to sign a bill probability set, then divides unijunction
Fruit are as follows: the first order information and the second order information distribute to the first sales force.
The embodiment of the present application also provides the single devices of one kind point, as shown in Figure 2, comprising:
Forward allocator module 201, each order information for will acquire are pre-assigned to surplus according to pre-set point of single strategy
The sales force that remaining order amount is not zero, obtains pre- point of predetermined quantity single information, and each pre- point single information includes described respectively ordering
Sales force's information of the sales force of each order information predistribution in single information；
In the embodiment of the present application, as an alternative embodiment, sales force's information includes: maximum order amount and current
Order amount, forward allocator module 201 are specifically used for:
From each order information of acquisition, the first order information is extracted, according to the initial sale personal information of storage, by institute
It states the first order information and is pre-assigned to corresponding first sales force of initial sale personal information that remaining order amount is not zero, structure
First pre- point of single information of first sales force's information including the first order information and storage is built, remaining order amount connects for maximum
The difference of single amount and current order amount；
The current order amount in the first sales force information updated storage, until each order information obtained is pre-
It is assigned；
Divide single information, pre- point of single information of building, wherein N is institute in advance according to first pre- point of single information being sequentially generated to N
State the order information item number in each order information；
Described pre- point of confirmation building single information finishes, and the sales force's information updated storage is initial sale personal information.
In the embodiment of the present application, as an alternative embodiment, in the first sales force information updated storage
Current order amount, until each order information obtained is pre-allocated and is finished, comprising:
After the current order amount in the first sales force's information updated storage, then from each order information of acquisition,
The second order information in addition to the first order information is extracted, according to the sales force's information updated storage, the second order is believed
Breath is pre-assigned to corresponding second sales force of sales force's information that remaining order amount is not zero, and building includes that the second order is believed
The second of the second sales force's information pre- point of single information for ceasing and updating storage, in the second sales force's information updated storage
Current order amount, until each order information obtained is pre-allocated and finished.
In the embodiment of the present application, as another alternative embodiment, sales force's information further includes History Order information,
History Order information includes sign a bill time and time of the signing a bill corresponding History Order, in each order information from acquisition
In, before extracting the first order information, forward allocator module 201 is also used to:
The sales force that is not zero of remaining order amount for extracting storage it is corresponding it is same sign a bill the time, according to pre-set
First Replacement Strategy replaces time of the signing a bill corresponding History Order.
In the embodiment of the present application, as yet another alternative embodiment, sales force's information further includes History Order information,
The History Order information includes sign a bill time and time of the signing a bill corresponding History Order, the device further include:
Whether first judgment module (not shown), pre- point of single information bar number for judging building reach described predetermined
Quantity；
If it is not, the sales force that is not zero of remaining order amount for extracting storage it is corresponding it is same sign a bill the time, according in advance
The first Replacement Strategy being arranged replaces time of the signing a bill corresponding History Order, executes each order from acquisition
In information, the step of extracting the first order information, until pre- point of single information bar number of building reaches the predetermined quantity.
In the embodiment of the present application, as yet another alternative embodiment, sales force's information further includes History Order information,
The device further include:
Second judgment module (not shown), judges whether pre- point of single information bar number of building reaches the predetermined number
Amount；
If it is not, being directed to sales force's information, according to pre-set second Replacement Strategy, other sales forces letter is chosen
The History Order information of selection is added in sales force's information by the History Order information in breath, is executed described from acquisition
Each order information in, the step of extracting the first order information, until pre- point of single information bar number of building reaches the predetermined number
Amount.
In the embodiment of the present application, as yet another alternative embodiment, sales force's information further includes History Order information,
History Order information includes History Order and the corresponding time of received orders of the History Order, the device further include:
Second judgment module (not shown), judges whether pre- point of single information bar number of building reaches the predetermined number
Amount；
If it is not, sales force's information is directed to, according to pre-set third Replacement Strategy, in sales force's information
The corresponding time of received orders of each History Order for including is replaced, and described from each order information of acquisition, extraction first is executed
The step of order information, until the single information bar number of pre- point of building reaches the predetermined quantity.
Probability set of signing a bill obtains module 202, for being directed to each pre- point single information, by this pre- point single information input in advance
In the sorter model of foundation, the corresponding probability set of signing a bill of this pre- point list information is obtained, the probability set of signing a bill includes each pre- point
Sign a bill probability of the sales force matched to the order information of predistribution；
In the embodiment of the present application, as an alternative embodiment, the sorter model is established, comprising:
It the corresponding sample History Order information of collecting sample sales force information, sample sales force's information and signs a bill
As a result, based on a sample sales force information and corresponding sample History Order information, the single information of building equally one's duty；
According to the corresponding feature vector group of the sorter model, the feature vector of the single information of sample point is extracted, according to institute
It states the single Vector Groups of format building sample point of feature vector group and obtains the unidirectional quantity set of sample point；
The single Vector Groups collection of the sample point is divided into the unidirectional quantity set of training sample point and the unidirectional quantity set of test specimens one's duty；
Using the single Vector Groups of training sample point in training sample point unidirectional quantity set as the input of the sorter model, with
Corresponding output of the result as the sorter model of signing a bill of the single Vector Groups of the training sample point, to the sorter model into
Row training；
Using the unidirectional amount group of test specimens one's duty in the unidirectional quantity set of test specimens one's duty as the sorter model of training
Input obtains test sample and signs a bill result；
Result is signed a bill based on test sample and the test sample signs a bill that result is corresponding to sign a bill as a result, calculating the institute of training
State the precision of sorter model；
If the precision calculated is greater than pre-set precision threshold, the sorter model established, if calculate
Precision is not more than pre-set precision threshold, executes the unidirectional amount of training sample point in the unidirectional quantity set of training sample point
The step of organizing the input as the sorter model.
In the embodiment of the present application, result of signing a bill is the execution of the corresponding sample History Order information of sample sales force information
As a result, comprising: sign a bill successfully and sign a bill unsuccessfully, the equally single information correspondence of one's duty signs a bill successfully or signs a bill unsuccessfully.
In the embodiment of the present application, as an alternative embodiment, feature that the corresponding feature vector group of sorter model includes
Vector includes but is not limited to: customer name, gender, contact method, Reiseziel information, order source, order type, sale
Personnel's name, gender, the length of service, history are signed a bill probability, maximum order amount, current order amount, destination instruction evaluation and test achievement.
Combined chance computing module 203 is calculated and is respectively signed a bill in the probability set of signing a bill generally for being directed to each probability set of signing a bill
The combined chance of rate；
In the embodiment of the present application, probability set of signing a bill corresponding for N number of order information includes N number of probability of signing a bill.
In the embodiment of the present application, as an alternative embodiment, the comprehensive of probability of respectively signing a bill in described calculating probability set of signing a bill
Close probability, comprising:
Probability of respectively signing a bill in probability set of signing a bill successively is multiplied, the combined chance is obtained.
Comparison module 204, for obtaining the corresponding probability set of signing a bill of highest combined chance；
Divide single module 205, for pre- according to each order information in the corresponding probability set of signing a bill of the highest combined chance
The sales force of distribution carries out a point list to each order information.
Based on above-mentioned analysis it is found that point single device based on randomized policy does not efficiently use limited pin in the prior art
The personnel of selling take a trip to the entirety for improving enterprise to sign a bill rate, cause the rate of signing a bill low, and by conjunction with order information and pin in the application
It sells personal information and carries out point single, signed a bill rate with improving the entirety of enterprise.
As shown in figure 3, one embodiment of the application provides a kind of computer equipment 300, divide folk prescription for executing in Fig. 1
Method, the equipment include memory 301, processor 302 and are stored on the memory 301 and can run on the processor 302
Computer program, wherein the step of above-mentioned processor 302 realizes above-mentioned point of folk prescription method when executing above-mentioned computer program.
Specifically, above-mentioned memory 301 and processor 302 can be general memory and processor, do not do have here
Body limits, and when the computer program of 302 run memory 301 of processor storage, is able to carry out above-mentioned point of folk prescription method.
Divide folk prescription method corresponding in Fig. 1, the embodiment of the present application also provides a kind of computer readable storage medium, the meters
It is stored with computer program on calculation machine readable storage medium storing program for executing, which executes above-mentioned point of folk prescription method when being run by processor
The step of.
Specifically, which can be general storage medium, such as mobile disk, hard disk, on the storage medium
Computer program when being run, the method for being able to carry out above-mentioned optimization instant messaging network link connection.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description
It with the specific work process of device, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
In addition, in the description of the embodiment of the present application unless specifically defined or limited otherwise, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected；It can
To be mechanical connection, it is also possible to be electrically connected；It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition
Concrete meaning in application.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) execute each embodiment the method for the application all or part of the steps.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
In the description of the present application, it should be noted that term " center ", "upper", "lower", "left", "right", "vertical",
The orientation or positional relationship of the instructions such as "horizontal", "inner", "outside" be based on the orientation or positional relationship shown in the drawings, merely to
Convenient for describe the application and simplify description, rather than the device or element of indication or suggestion meaning must have a particular orientation,
It is constructed and operated in a specific orientation, therefore should not be understood as the limitation to the application.In addition, term " first ", " second ",
" third " is used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance.
Finally, it should be noted that embodiment described above, the only specific embodiment of the application, to illustrate the application
Technical solution, rather than its limitations, the protection scope of the application is not limited thereto, although with reference to the foregoing embodiments to this Shen
It please be described in detail, those skilled in the art should understand that: anyone skilled in the art
Within the technical scope of the present application, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of the embodiment of the present application technical solution, should all cover the protection in the application
Within the scope of.Therefore, the protection scope of the application shall be subject to the protection scope of the claim.
Claims (10)
1. one kind divides folk prescription method characterized by comprising
Each order information that will acquire is pre-assigned to the sale people that remaining order amount is not zero according to pre-set point of single strategy
Member, obtains pre- point of predetermined quantity single information, each pre- point single information include in each order information each order information it is pre-
Sales force's information of the sales force of distribution；
This pre- point is obtained by this pre- point single information input into the sorter model pre-established for each pre- point single information
The corresponding probability set of signing a bill of single information, the probability set of signing a bill include order information of the sales force to predistribution of each predistribution
Probability of signing a bill；
For each probability set of signing a bill, the combined chance for probability of respectively signing a bill in the probability set of signing a bill is calculated；
Obtain the corresponding probability set of signing a bill of highest combined chance；
According to the sales force that order information each in the corresponding probability set of signing a bill of the highest combined chance pre-allocates, to described
Each order information carries out a point list.
2. the method according to claim 1, wherein sales force's information includes: maximum order amount and works as
Preceding order amount, each order information that will acquire are pre-assigned to what remaining order amount was not zero according to pre-set point of single strategy
Sales force obtains pre- point of single information of predetermined quantity, comprising:
From each order information of acquisition, the first order information is extracted, according to the initial sale personal information of storage, by described the
One order information is pre-assigned to corresponding first sales force of initial sale personal information that remaining order amount is not zero, building packet
First pre- point of single information of first sales force's information of the first order information and storage is included, remaining order amount is maximum order amount
With the difference of current order amount；
The current order amount in the first sales force information updated storage, until each order information obtained is pre-allocated
It finishes；
Divide single information, pre- point of single information of building, wherein N is described each in advance according to first pre- point of single information being sequentially generated to N
Order information item number in order information；
Described pre- point of confirmation building single information finishes, and the sales force's information updated storage is initial sale personal information.
3. according to the method described in claim 2, it is characterized in that, in the first sales force information updated storage
Current order amount, until each order information obtained is pre-allocated and is finished, comprising:
After the current order amount in the first sales force's information updated storage, then from each order information of acquisition, extract
The second order information in addition to the first order information, it is according to the sales force's information updated storage, the second order information is pre-
Distribute to corresponding second sales force of sales force's information that remaining order amount is not zero, building include the second order information and
The second of the second sales force's information updated storage divides single information in advance, current in the second sales force's information updated storage
Order amount, until each order information obtained is pre-allocated and finished.
4. according to the method described in claim 2, it is characterized in that, sales force's information further includes History Order information,
History Order information includes sign a bill time and time of the signing a bill corresponding History Order, in each order information from acquisition
In, before extracting the first order information, the method also includes:
The sales force that is not zero of remaining order amount for extracting storage it is corresponding it is same sign a bill the time, according to pre-set first
Replacement Strategy replaces time of the signing a bill corresponding History Order.
5. according to the method described in claim 2, it is characterized in that, sales force's information further includes History Order information,
The History Order information includes sign a bill time and time of the signing a bill corresponding History Order, in the sale updated storage
After personal information is initial sale personal information, the method also includes:
Judge whether pre- point of single information bar number of building reaches the predetermined quantity；
If it is not, the sales force that is not zero of remaining order amount for extracting storage it is corresponding it is same sign a bill the time, according to presetting
The first Replacement Strategy, which is replaced, each order information from acquisition is executed
In, the step of extracting the first order information, until pre- point of single information bar number of building reaches the predetermined quantity.
6. according to the method described in claim 2, it is characterized in that, sales force's information further includes History Order information,
After the sales force's information updated storage is initial sale personal information, the method also includes:
Judge whether pre- point of single information bar number of building reaches the predetermined quantity；
If it is not, be directed to sales force's information, according to pre-set second Replacement Strategy, choose except sales force's information it
The History Order information of selection is added in sales force's information by the History Order information in outer sales force's information,
The step of execution is described from each order information of acquisition, extracts the first order information, until pre- point of list information bar number of building
Reach the predetermined quantity.
7. according to the method described in claim 2, it is characterized in that, sales force's information further includes History Order information,
History Order information includes History Order and the corresponding time of received orders of the History Order, in the sales force updated storage
After information is initial sale personal information, the method also includes:
Judge whether pre- point of single information bar number of building reaches the predetermined quantity；
If it is not, be directed to sales force's information, according to pre-set third Replacement Strategy, to including in sales force's information
The corresponding time of received orders of each History Order replaced, execute described from each order information of acquisition, extract the first order
The step of information, until the single information bar number of pre- point of building reaches the predetermined quantity.
8. method according to any one of claims 1 to 7, which is characterized in that establish the sorter model, comprising:
The corresponding sample History Order information of collecting sample sales force information, sample sales force's information and knot of signing a bill
Fruit, based on a sample sales force information and corresponding sample History Order information, the single information of building equally one's duty；
According to the corresponding feature vector group of the sorter model, the feature vector of the single information of sample point is extracted, according to the spy
The single Vector Groups of format building sample point of sign Vector Groups simultaneously obtain the unidirectional quantity set of sample point；
The single Vector Groups collection of the sample point is divided into the unidirectional quantity set of training sample point and the unidirectional quantity set of test specimens one's duty；
Using the single Vector Groups of training sample point in the unidirectional quantity set of training sample point as the input of the sorter model, with the instruction
Practice corresponding output of the result as the sorter model of signing a bill of the single Vector Groups of sample point, the sorter model is instructed
Practice；
The input of the sorter model using the unidirectional amount group of test specimens one's duty in the well-behaved unidirectional quantity set of test specimens as training,
Test sample is obtained to sign a bill result；
Result is signed a bill based on test sample and the test sample signs a bill that result is corresponding to sign a bill as a result, calculating described in training point
The precision of class device model；
If the precision calculated is greater than pre-set precision threshold, the sorter model established, if the precision calculated
No more than pre-set precision threshold, executes the single Vector Groups of training sample point in the unidirectional quantity set of training sample point and make
For the sorter model input the step of.
9. method according to any one of claims 1 to 7, which is characterized in that respectively signed in the calculating probability set of signing a bill
The combined chance of single probability, comprising:
Probability of respectively signing a bill in probability set of signing a bill successively is multiplied, the combined chance is obtained.
10. the single device of one kind point characterized by comprising
Forward allocator module, each order information for will acquire are pre-assigned to remaining order according to pre-set point of single strategy
The sales force being not zero is measured, obtains pre- point of single information of predetermined quantity, each pre- point single information includes each order information
In the predistribution of each order information sales force sales force's information；
Probability set of signing a bill obtains module, for for each pre- point single information, by this pre- point single information input to pre-establishing
In sorter model, the corresponding probability set of signing a bill of this pre- point list information is obtained, the probability set of signing a bill includes the pin of each predistribution
Personnel are sold to the probability of signing a bill of the order information of predistribution；
Combined chance computing module calculates the comprehensive of probability of respectively signing a bill in the probability set of signing a bill for being directed to each probability set of signing a bill
Close probability；
Comparison module, for obtaining the corresponding probability set of signing a bill of highest combined chance；
Divide single module, the pin for pre-allocating according to order information each in the corresponding probability set of signing a bill of the highest combined chance
Personnel are sold, a point list is carried out to each order information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910130694.3A CN109872225A (en) | 2019-02-21 | 2019-02-21 | Divide single method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910130694.3A CN109872225A (en) | 2019-02-21 | 2019-02-21 | Divide single method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109872225A true CN109872225A (en) | 2019-06-11 |
Family
ID=66919037
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910130694.3A Pending CN109872225A (en) | 2019-02-21 | 2019-02-21 | Divide single method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109872225A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112232612A (en) * | 2019-06-28 | 2021-01-15 | 百度在线网络技术（北京）有限公司 | Intelligent client data distribution method and device |
| CN116797001A (en) * | 2023-08-16 | 2023-09-22 | 四川享宇科技有限公司 | Management system and method for financial industry practitioners |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563816A (en) * | 2017-09-08 | 2018-01-09 | 携程计算机技术（上海）有限公司 | The Forecasting Methodology and system of the customer loss of e-commerce website |
| CN107845012A (en) * | 2017-09-07 | 2018-03-27 | 北京小度信息科技有限公司 | Order processing method and apparatus |
| CN108681857A (en) * | 2018-05-18 | 2018-10-19 | 北京顺丰同城科技有限公司 | A kind of dispatching order allocation method and device, computer readable storage medium |
| CN109523152A (en) * | 2018-11-12 | 2019-03-26 | 达疆网络科技(上海)有限公司 | Order processing method, storage medium and device |
-
2019
- 2019-02-21 CN CN201910130694.3A patent/CN109872225A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107845012A (en) * | 2017-09-07 | 2018-03-27 | 北京小度信息科技有限公司 | Order processing method and apparatus |
| CN107563816A (en) * | 2017-09-08 | 2018-01-09 | 携程计算机技术（上海）有限公司 | The Forecasting Methodology and system of the customer loss of e-commerce website |
| CN108681857A (en) * | 2018-05-18 | 2018-10-19 | 北京顺丰同城科技有限公司 | A kind of dispatching order allocation method and device, computer readable storage medium |
| CN109523152A (en) * | 2018-11-12 | 2019-03-26 | 达疆网络科技(上海)有限公司 | Order processing method, storage medium and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112232612A (en) * | 2019-06-28 | 2021-01-15 | 百度在线网络技术（北京）有限公司 | Intelligent client data distribution method and device |
| CN116797001A (en) * | 2023-08-16 | 2023-09-22 | 四川享宇科技有限公司 | Management system and method for financial industry practitioners |
| CN116797001B (en) * | 2023-08-16 | 2023-10-27 | 四川享宇科技有限公司 | Management system and method for financial industry practitioners |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108171280A (en) | A kind of grader construction method and the method for prediction classification | |
| CN111079015B (en) | Recommendation method and device, computer equipment and storage medium | |
| Han et al. | Appointment scheduling and routing optimization of attended home delivery system with random customer behavior | |
| CN110222880B (en) | Service risk determining method, model training method and data processing method | |
| CN111310938A (en) | Semi-supervision-based horizontal federal learning optimization method, equipment and storage medium | |
| CN109583468A (en) | Training sample acquisition methods, sample predictions method and corresponding intrument | |
| CN108734361A (en) | Share-car order processing method and apparatus | |
| CN109670546B (en) | Commodity matching and quantity regression recognition algorithm based on preset template | |
| CN115345355B (en) | Energy consumption prediction model construction method, short-term energy consumption prediction method and related devices | |
| CN109598368A (en) | Path decision evaluation and order distribution method and device, electronic equipment and medium | |
| CN109284956B (en) | Task duration determining method and device and electronic equipment | |
| CN109842563A (en) | Content delivery network flow dispatching method, device and computer readable storage medium | |
| CN110263979A (en) | Method and device based on intensified learning model prediction sample label | |
| CN109872225A (en) | Divide single method and device | |
| CN110245310B (en) | Object behavior analysis method, device and storage medium | |
| CN110222996A (en) | Method for allocating tasks and device | |
| CN103684850A (en) | Service neighborhood based Web Service quality prediction method | |
| CN110263136B (en) | Method and device for pushing object to user based on reinforcement learning model | |
| CN105160403B (en) | A kind of resource service sequence verification method under cloud manufacturing environment | |
| Levy et al. | Dynamic ordering learning in multivariate forecasting | |
| CN117574238A (en) | High-frequency electric appliance identification model construction method and system based on multi-gate expert network | |
| CN115186855A (en) | Logistics network cargo quantity prediction method, device, equipment and computer storage medium | |
| CN110955879A (en) | Device control method, device, computer device and storage medium | |
| CN111782774B (en) | Method and device for recommending problems | |
| CN111275062A (en) | Model training method, device, server and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190611 |