CN109377317A - Data processing method and device - Google Patents

Data processing method and device Download PDF

Info

Publication number
CN109377317A
CN109377317A CN201811261237.XA CN201811261237A CN109377317A CN 109377317 A CN109377317 A CN 109377317A CN 201811261237 A CN201811261237 A CN 201811261237A CN 109377317 A CN109377317 A CN 109377317A
Authority
CN
China
Prior art keywords
driver
orders
score
competition
probability
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201811261237.XA
Other languages
Chinese (zh)
Other versions
CN109377317B (en
Inventor
罗梅菲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin 58 Home Technology Co Ltd
Original Assignee
Tianjin 58 Home Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianjin 58 Home Technology Co Ltd filed Critical Tianjin 58 Home Technology Co Ltd
Priority to CN201811261237.XA priority Critical patent/CN109377317B/en
Publication of CN109377317A publication Critical patent/CN109377317A/en
Application granted granted Critical
Publication of CN109377317B publication Critical patent/CN109377317B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
    • G06Q30/0635—Processing of requisition or of purchase orders

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

This application discloses a kind of data processing method and devices, which comprises is directed to freight orders to be allocated, determines at least one driver for meeting competition for orders condition；History Order based on each driver determines the competition for orders probability of each driver；According to the respective competition for orders probability of at least one described driver, the middle single probability for obtaining each driver is calculated.The embodiment of the present invention improves the accuracy of single probability in driver.

Description

Data processing method and device
Technical field
The invention relates to technical field of the computer network, specifically, being related to a kind of data processing method and dress It sets.
Background technique
The rapid development of internet economy has driven the rapid development of cargo service on line.Cargo service scene on line In, user can submit shipment request to server-side by user terminal, wherein may include transport start bit in the shipment request Set and transport the freight demands such as final position；Server-side is based on the freight demand and generates freight orders, and freight orders are divided The corresponding driver of dispensing；Driver executes order operation by driver end, if order success, it can carry out goods based on freight orders Object transport.
In general, in order to promote freight orders successful execution, for a certain freight orders, can determine it is each meet rob single Middle single probability of the driver of part, and middle single probability is pushed into driver end, to promote driver to receive the freight orders.Existing skill It in art, generallys use statistical and determines driver's history competition for orders success rate, any one successful probability of driver's competition for orders is 1 and symbol Close the ratio of the total quantity for robbing single driver of competition for orders condition, middle single probability of as all drivers.
The statistical used above can obtain the successful probability of the competition for orders of all drivers on the whole, any one driver A possibility that competition for orders success is identical.But above-mentioned statistical is inaccurate, can not Accurate Prediction driver middle list it is general Rate.
Summary of the invention
In view of this, being mainly used for solving prior art middle line this application provides a kind of data processing method and device After upper freight orders are completed, user produces the time without using on the line the technical issues of customer churn of freight transport system shape.
In order to solve the above-mentioned technical problem, this application provides a kind of data processing methods, which comprises
For freight orders to be allocated, at least one driver for meeting competition for orders condition is determined；
History Order based on each driver determines the competition for orders probability of each driver；
According to the respective competition for orders probability of at least one described driver, the middle single probability for obtaining each driver is calculated.
Preferably, the respective competition for orders probability of at least one driver according to is calculated and is obtained in each driver Single probability includes:
For the competition for orders probability of any one driver, according to the respective competition for orders probability of at least one described driver, determine described in First kind driver and the second class driver at least one driver；
When determining that the first kind driver executes the first generic operation and the second class driver the second generic operation of execution, Middle single probability of any one driver, to obtain middle single probability of each driver.
Preferably, the History Order based on each driver determines that the competition for orders probability of each driver includes:
For the History Order of each driver, the service score of each driver is determined；
The service score of each driver and the ratio of basic score are calculated, the competition for orders of each driver is obtained Probability.
Preferably, the History Order based on each driver determines that the competition for orders probability of each driver includes:
Determine the History Order of each driver and the similarity degree of the freight orders to be allocated；
According to the similarity degree of the History Order of each driver and the freight orders to be allocated, calculates and obtain each The competition for orders probability of driver.
Preferably, the History Order for each driver, determines the service score of each driver Include:
For the History Order of each driver, multiple order groups are determined；Wherein, each order group includes that at least one is ordered It is single；
It determines the corresponding order score of each order group, obtains multiple order scores；
Determine the corresponding attenuation coefficient of multiple order groups；
The corresponding order score of multiple order groups and attenuation coefficient are weighted processing, obtain it is described each The service score of driver.
Preferably, the corresponding order score of each order group of the determination, obtaining multiple order scores includes:
Determine at least one service parameter；
For each described order group, the corresponding service score of at least one described service parameter is determined；
The sum of corresponding service score of at least one described service parameter is calculated, each described order group pair is obtained The service score answered, to obtain multiple order scores.
Preferably, described to be directed to each order group, determine the corresponding service point of at least one described service parameter Number includes:
For each order group, determine that at least one described service parameter respectively corresponds parameter probability；
Determine at least one service parameter respectively respective weights；
Based on the corresponding parameter probability of each service parameter and respective weight, each described service is obtained Parameter corresponding with service score, to obtain the corresponding service score of at least one described service parameter.
Preferably, at least one described service parameter include: competition for orders Success parameter, order complete parameter, favorable comment parameter and/ Or online hours parameter；
It is described to be directed to each order group, determine that at least one described service parameter respectively corresponds parameter probability and includes:
For each order group, determine that the corresponding competition for orders rate of the competition for orders Success parameter, the order complete parameter pair The completion rate answered, the corresponding positive rating of the favorable comment parameter and/or state the corresponding online rate of online hours；
Respectively reciprocal fraction weight includes: for the determination at least one service parameter
It determines the corresponding first weight score of the competition for orders Success parameter, determine that the order completes corresponding second weight of parameter Score determines that the favorable comment parameter corresponds to third weight score and/or determines the corresponding 4th weight score of the online hours；
The product for calculating the corresponding parameter probability of each service parameter and weight, obtain it is described each Service parameter corresponding with service score includes: to obtain the corresponding service score of at least one service parameter
Unit fraction, the completion rate and second weight are robbed based on the competition for orders rate and the first weight score acquisition It obtains and completes score, the positive rating and the well received score of the third weight and the online rate and/or the described 4th Weight obtains online score.
Preferably, the competition for orders probability for any one driver, it is general according to the respective competition for orders of at least one driver Rate determines that first kind driver and the second class driver include: at least one described driver
It is determined for the competition for orders probability of any one driver according to the respective competition for orders probability of at least one described driver It is first kind driver that competition for orders probability, which is greater than the driver of the competition for orders probability of any one driver, at least one described driver, and The driver that competition for orders probability is less than the competition for orders probability of any one driver is the second class driver；
The determination first kind driver executes the first generic operation and the second class driver executes the second generic operation When, middle single probability of any one driver includes: to obtain middle single probability of each driver
It determines that the first kind driver does not execute and robs single operation and the second class driver and execute that rob single operation be institute Middle single probability of any one driver is stated, to obtain middle single probability of each driver.
The present invention also provides a kind of data processing equipments, comprising:
Driver's matching module determines at least one driver for meeting competition for orders condition for being directed to freight orders to be allocated；
Competition for orders probabilistic module determines that the competition for orders of each driver is general for the History Order based on each driver Rate；
Middle list probabilistic module, for calculating and obtaining each department according to the respective competition for orders probability of at least one described driver Middle single probability of machine.
Preferably, middle single probabilistic module includes:
First determination unit, it is respective according at least one described driver for being directed to the competition for orders probability of any one driver Competition for orders probability determines first kind driver and the second class driver at least one described driver；
Second determination unit, for determining that the first kind driver executes the first generic operation and the second class driver When executing the second generic operation, middle single probability of any one driver, to obtain middle single probability of each driver.
Preferably, the competition for orders probabilistic module includes:
Third determination unit determines the clothes of each driver for the History Order for each driver Business score；
4th determination unit obtains institute for calculating the service score of each driver and the ratio of basic score State the competition for orders probability of each driver.
Preferably, the competition for orders probabilistic module includes:
5th determination unit, for determining the History Order of each driver and the similar journey of the freight orders to be allocated Degree；
First computing unit, for according to the History Order of each driver and the similar journey of the freight orders to be allocated Degree calculates the competition for orders probability for obtaining each driver.
Preferably, the third determination unit includes:
It is grouped subelement, for being directed to the History Order of each driver, determines multiple order groups；Wherein, each order Group includes at least one order；
Score obtains subelement and obtains multiple order scores for determining the corresponding order score of each order group；
Coefficient determines subelement, for determining the corresponding attenuation coefficient of multiple order groups；
Score handles subelement, for the corresponding order score of multiple order groups and attenuation coefficient to be weighted Processing obtains the service score of each driver.
Preferably, the score obtains subelement and is specifically used for:
Parameter determination module, for determining at least one service parameter；Score determining module, for for it is described each Order group determines the corresponding service score of at least one described service parameter；Score computing module, for calculate it is described extremely The sum of few corresponding service score of a service parameter obtains the corresponding service score of each described order group, to obtain Obtain multiple order scores.
Preferably, the score determining module includes:
Probability determining unit determines that at least one described service parameter respectively corresponds ginseng for being directed to each order group Number probability；
Weight determining unit, for determining at least one service parameter respectively respective weights；
Score determination unit, for being based on the corresponding parameter probability of each service parameter and respective weight, Each described service parameter corresponding with service score is obtained, to obtain the corresponding service point of at least one described service parameter Number.
Preferably, at least one described service parameter include: competition for orders Success parameter, order complete parameter, favorable comment parameter and/ Or online hours parameter；
The probability determining unit includes:
Determine the probability subelement, for be directed to each order group, determine the corresponding competition for orders rate of the competition for orders Success parameter, The order complete the corresponding completion rate of parameter, the corresponding positive rating of the favorable comment parameter and/or state online hours it is corresponding Line rate；
The weight determining unit includes:
Score determines subelement, for determining the corresponding first weight score of the competition for orders Success parameter, determining the order When completing the corresponding second weight score of parameter, determining that the favorable comment parameter corresponds to third weight score and/or determines described online Long corresponding 4th weight score；
The score determination unit includes:
Score obtains subelement, robs unit fraction, described for obtaining based on the competition for orders rate and the first weight score Completion rate and second weight, which obtain, completes score, the positive rating and the well received score of the third weight and described Online rate and/or the 4th weight obtain online score.
Preferably, first determination unit includes:
It is grouped subelement, for the competition for orders probability for any one driver, respectively according at least one described driver Competition for orders probability, determine that the driver for the competition for orders probability that competition for orders probability is greater than any one driver at least one described driver is The driver that first kind driver and competition for orders probability are less than the competition for orders probability of any one driver is the second class driver；
Second determination unit includes:
Middle list unit robs single operation and the second class driver holds for determining that the first kind driver does not execute Rob single operation when, middle single probability of any one driver, to obtain middle single probability of each driver.
In the embodiment of the present invention, for freight orders to be allocated, acquisition meets the competition for orders condition of the freight orders at least One driver, the actual conditions of the freight orders received in the History Order of each driver comprising driver, and then can be with base Receive the competition for orders of the freight orders to be allocated in the freight orders to be allocated and the similarity judgement of the History Order driver Probability.And the driver due to meeting competition for orders condition can may be calculated and be obtained based on the competition for orders probability of all drivers comprising multiple Middle single probability of each driver namely middle single probability of each driver not be only rely upon driver oneself competition for orders it is general Rate, but middle single probability of any one driver is associated with the competition for orders probability of other drivers, and then no longer independent calculating Middle single probability of each driver improves middle single probability of estimation to determine influence of other drivers to each driver's competition for orders Order of accuarcy.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present application, constitutes part of this application, this Shen Illustrative embodiments and their description please are not constituted an undue limitation on the present application for explaining the application.In the accompanying drawings:
Fig. 1 is a kind of flow chart of one embodiment of data processing method provided in an embodiment of the present invention；
Fig. 2 is a kind of flow chart of another embodiment of data processing method provided in an embodiment of the present invention；
Fig. 3 is a kind of flow chart of another embodiment of data processing method provided in an embodiment of the present invention；
Fig. 4 is a kind of structural schematic diagram of one embodiment of data processing equipment provided in an embodiment of the present invention；
Fig. 5 is a kind of structural schematic diagram of another embodiment of data processing equipment provided in an embodiment of the present invention.
Specific embodiment
Presently filed embodiment is described in detail below in conjunction with accompanying drawings and embodiments, how the application is applied whereby Technological means solves technical problem and reaches the realization process of technical effect to fully understand and implement.
The embodiment of the present invention is mainly used on line in freight transport system, passes through middle single possibility of all drivers of Balance Treatment Property, carry out middle single probability of each driver of accurate judgement.
In the prior art, there is the scene of middle single probability of estimation driver on line in freight transport system, by assessment driver Single probability is to judge a possibility that freight orders strike a bargain on line.Statistical is generallyd use, estimates the successful probability of driver's competition for orders, But this mode be remove individually to estimate the competition for orders probability of each driver on the whole, and between each driver estimation when It is not associated with, the competition for orders probability of the estimation of acquisition is not accurate enough, can not accurately estimate every with actual competition for orders environmental correclation connection Middle single probability of one driver.
In the embodiment of the present invention, for freight orders to be allocated, at least one driver for meeting competition for orders condition can be determined, It that is to say the driver for selecting to match with the conditions of carriage of the freight orders to be allocated from all drivers.It later, can be with base In the History Order of each driver, the competition for orders probability of each driver is determined, finally, robbing according at least one driver is respective Single probability, can calculate the middle single probability for obtaining each driver, and the History Order by that will be dependent on each driver determines Competition for orders probability, calculate the middle single probability for obtaining each driver.Middle list probability is based at least one department for meeting competition for orders condition The competition for orders probability of machine obtains, namely in horizontal amount driver in single probabilistic process, joins with the competition for orders probability correlation of other drivers, to mention When high driver's competition for orders, the model of the correlation degree of success or not and other drivers, middle single probability of acquisition is more accurate.
The embodiment of the present invention is described in detail below in conjunction with attached drawing.
As shown in Figure 1, be a kind of flow chart of one embodiment of data processing method provided in an embodiment of the present invention, it should Method may include following steps:
101: being directed to freight orders to be allocated, determine at least one driver for meeting competition for orders condition.
Wherein it is possible to be directed to freight orders to be allocated by server-side, at least one driver for meeting competition for orders condition is determined.To Distribution freight orders can be generated by server-side, can specifically be generated based on the shipment request that user terminal is sent wait divide by server-side With freight orders.
Freight orders to be allocated are being directed to, are being determined before meeting at least one driver of competition for orders condition, the method may be used also To include: the shipment request for receiving any one user terminal and sending；Based on the shipment request that any one user terminal is sent, generate wait divide With freight orders.
In certain embodiments, the competition for orders condition can refer at least one shipping number with the freight orders to be allocated According to matching.Wherein, at least one ship data may include: shipping initial position, shipment month and/or shipping vehicle.
It is described to be directed to freight orders to be allocated, determine that at least one driver for meeting competition for orders condition may include:
For at least one ship data in the freight orders to be allocated, determining and at least one described ship data At least one driver to match.
Described at least one ship data for the freight orders to be allocated, determining and at least one described shipping number May include: according at least one driver to match
From multiple drivers to be selected, it is determining match with the shipping initial position, match with the shipment month and/ Or at least one driver to match with the shipping vehicle.
Match with the shipping initial position may include: driver to be selected position and the shipping initial position Distance be in distance threshold.Match with the shipment month may include: that may include working time of driver to be selected The shipment month.And the shipping vehicle match may include driver to be selected vehicle it is identical as the shipping vehicle.
102: the History Order based on each driver determines the competition for orders probability of each driver.
The competition for orders probability of each driver can be associated with its history order, the competition for orders of each driver whether can lead to The History Order situation of the driver is crossed to judge, to improve the accuracy of the competition for orders probability of the driver obtained.
The competition for orders probability of each driver can also refer to that the probability of single operation is robbed in the triggering of each driver's actual capabilities.It robs A possibility that a possibility that single probability is bigger, and single operation is robbed in driver's triggering is higher, and competition for orders probability is smaller, and single operation is robbed in driver's triggering It is lower.
103: according to the respective competition for orders probability of at least one described driver, calculating the middle single probability for obtaining each driver.
Middle single probability of each driver can be obtained according to the respective competition for orders probability of at least one driver.Each driver Middle single probability be no longer individually to estimate process, can be respective by the competition for orders probability of each driver and at least one driver Competition for orders probability correlation connection, whether establishing each driver's competition for orders from associated angle between connection, and then middle list can be improved The accuracy of probability.
The respective competition for orders probability of at least one driver according to, middle single probability that calculating obtains each driver can To include:
It calculates according to default middle single model according to the respective competition for orders probability of at least one described driver and obtains each department Middle single probability of machine.
Single model can determine at least one described first quantity of driver with pointer to the driver of middle single probability to be determined in this Driver's competition for orders, when driver's not competition for orders of the second quantity, the driver of middle single probability to be determined.
In the embodiment of the present invention, for freight orders to be allocated, at least one driver for meeting competition for orders condition can be determined, Namely the driver to match with the reality order to be sorted of user is screened from all drivers, and then each driver can be directed to History Order, can determine the competition for orders probability of each driver, and then can rob according at least one driver is corresponding Single probability calculates the middle single probability for obtaining each driver.Middle single probability of each driver is met into competition for orders condition with all Driver it is associated, each successful feasibility of driver's competition for orders is associated with other participation drivers of competition for orders, it is contemplated that One-state is robbed in real time, and the accuracy of middle single probability of each driver of acquisition is higher.
As shown in Fig. 2, be a kind of flow chart of another embodiment of data processing method provided in an embodiment of the present invention, This method and embodiment shown in FIG. 1 the difference is that, the step 103: respective according at least one described driver Competition for orders probability, middle single probability that calculating obtains each driver may include:
201: being determined for the competition for orders probability of any one driver according to the respective competition for orders probability of at least one described driver First kind driver and the second class driver at least one described driver；
202: determining that the first kind driver executes the first generic operation and the second class driver executes the second generic operation When, middle single probability of any one driver, to obtain middle single probability of each driver.
Influence when by considering that part driver robs single part driver's not competition for orders to the middle single probability for accordingly robbing single driver, I.e. practical comprehensive consideration driver competition for orders when, what other can rob single driver robs influence of the one-state to probability single in driver, further Obtain more accurate middle single probability.
Optionally, it is determined extremely for the competition for orders probability of any one driver according to the respective competition for orders probability of at least one driver First kind driver and the second class driver may include: in a few driver
It is determined for the competition for orders probability of any one driver according to the respective competition for orders probability of at least one described driver It is first kind driver that competition for orders probability, which is greater than the driver of the competition for orders probability of any one driver, at least one described driver, and The driver that competition for orders probability is less than the competition for orders probability of any one driver is the second class driver；
The determination first kind driver executes the first generic operation and the second class driver executes the second generic operation When, middle single probability of any one driver includes: to obtain middle single probability of each driver
It determines that the first kind driver does not execute and robs single operation and the second class driver and execute that rob single operation be institute Middle single probability of any one driver is stated, to obtain middle single probability of each driver.
It, can be by general according to respective competition for orders by least one driver in the competition for orders probability for determining any one driver Rate, carries out the division of different types of driver, and it is corresponding when robbing single operation to determine that different types of driver executes, described Middle single probability of any one driver.By this calculation, middle single probability of each driver can be accurately estimated.
As shown in figure 3, be a kind of flow chart of another embodiment of data processing method provided in an embodiment of the present invention, This method and embodiment shown in FIG. 1 the difference is that, the step 102: the History Order based on each driver, really The competition for orders probability of each driver may include: calmly
301: for the History Order of each driver, determining the service score of each driver.
302: calculating the service score of each driver and the ratio of basic score, obtain each driver's Competition for orders probability.
The service score of each driver can be according to the generation of the History Order of the driver.
Service score can be used for evaluating the actual service scenario of driver, and when service score is higher, the service of driver is got over Good, service score is lower, and the service of driver is poorer.Score can will be serviced as the calculating of driver's competition for orders probability basis.That is, The service score of driver is higher, illustrates that the service wish of driver is higher, at this moment the competition for orders probability of driver is also higher.Due to driver Service score can be obtained by multiple service parameters, therefore, service score can from multi-angle, multi-direction measure user Real work situation.
When the basis score can refer to the service score of practical each driver of determination, score when full marks is obtained. The competition for orders probability that the ratio of the service score and basic score, as the service score correspond to driver.
As a kind of possible implementation, the History Order for each driver is determined described each The service score of a driver includes:
For the History Order of each driver, multiple order groups are determined；Wherein, each order group includes that at least one is ordered It is single；
It determines the corresponding order score of each order group, obtains multiple order scores；
Determine the corresponding attenuation coefficient of multiple order groups；
The corresponding order score of multiple order groups and attenuation coefficient are weighted processing, obtain it is described each The service score of driver.
It is alternatively possible to which the order placement service time according to the History Order of each driver is grouped, multiple order is obtained Single group.The order placement service time be driver it is practical be user execute cargo service when time.That is, can be according to order placement service when Between, the History Order of each driver is divided into multiple order groups.An order is included at least in each order group.
Corresponding attenuation coefficient is respectively corresponded for multiple order groups, each order group can be corresponding with corresponding decaying system Number.Attenuation coefficient can be set according to actual needs, and the attenuation coefficient of different order groups may be the same or different, It is defined herein not to this.
In practical applications, multiple packet time sections can be preset, by the History Order of each driver according to its reality The order placement service time, matched with preset packet time section, determine each packet time section it is matched at least one Order, and then obtain multiple order groups.
Wherein it is possible to determine in nearest one month, the History Order of each driver orders the history in nearest one month Singly it is divided into multiple groups order group.
It is alternatively possible to which nearest one month History Order is divided according to the order placement service time.It can as one kind The implementation of energy can determine nearest one week order, obtain the first order group；Order apart from nearest second week, is obtained Obtain the second order group；Apart from the order in nearest third week, third order group is obtained；And ordering apart from nearest 4th week It is single, obtain the 4th order group.The corresponding attenuation coefficient of multiple order groups, can refer to, the first order group corresponding first decaying system Number, corresponding second attenuation coefficient of the second order group, the corresponding third attenuation coefficient of third order group and the 4th order group pair The 4th attenuation coefficient answered.
The current service scenario of driver more can be represented apart from the nearest time, it is alternatively possible to according to each order group The order period sequencing, the attenuation coefficient of each order group is successively reduced.For example, above-mentioned first can be ordered First attenuation coefficient of single group is set as 1.2, and the second attenuation coefficient of the second order group is set as 1.1, by third order group Third attenuation coefficient be set as 1, the attenuation coefficient of the 4th order group is set as 0.9.
The History Order of driver is carried out detailed order group to divide, it can be by each History Order according to different orders Combination is targetedly handled, and then corresponding attenuation coefficient can be arranged for order group, real by the setting of attenuation coefficient Now the influence by order group to order score is layered, and by hierarchical design, can be calculated and user's active service situation More matched service score.
In order to obtain accurate order score, in certain embodiments, each corresponding order of order group of the determination Score, obtaining multiple order scores includes:
Determine at least one service parameter.
For each described order group, the corresponding service score of at least one described service parameter is determined.
The sum of corresponding service score of at least one described service parameter is calculated, each described order group pair is obtained The service score answered, to obtain multiple order scores.
It is described to be directed to each order group in a kind of possible design, determine at least one service parameter difference Corresponding service score includes:
For each order group, determine that at least one described service parameter respectively corresponds parameter probability.
Determine at least one service parameter respectively respective weights.
Based on the corresponding parameter probability of each service parameter and respective weight, each described service is obtained Parameter corresponding with service score, to obtain the corresponding service score of at least one described service parameter.
Using the design method of service parameter mark different parameters data, can make from different directions in view of different numbers According to the influence to user service score.
Wherein, at least one described service parameter may include: competition for orders Success parameter, order completion parameter, favorable comment parameter And/or online hours parameter；
The order group for each driver, at least one determining described service parameter respectively corresponds parameter probability can To include:
For each order group, determine that the corresponding competition for orders rate of the competition for orders Success parameter, the order complete parameter pair Completion rate, the corresponding positive rating of the favorable comment parameter and/or the corresponding online rate of the online hours answered.
Respectively reciprocal fraction weight may include: for the determination at least one service parameter
It determines the corresponding first weight score of the competition for orders Success parameter, determine that the order completes corresponding second weight of parameter Score determines that the favorable comment parameter corresponds to third weight score and/or determines the corresponding 4th weight score of the online hours；
The product for calculating the corresponding parameter probability of each service parameter and weight, obtain it is described each Service parameter corresponding with service score includes: to obtain the corresponding service score of at least one service parameter
Unit fraction is robbed, based on the completion rate and described second based on the competition for orders rate and the first weight score acquisition Weight, which obtains, completes score, based on the positive rating and the well received score of the third weight and/or based on the online rate Online score is obtained with the 4th weight.
Optionally, for each order group, determine that the corresponding competition for orders rate of competition for orders Success parameter may include:
Based on the order contents in each order group, competition for orders success quantity and push quantity on order are determined；Calculate competition for orders Success quantity and the quotient for pushing order success quantity, obtain the corresponding competition for orders rate of competition for orders Success parameter.Wherein, competition for orders success quantity For calculate the product of difference odd number amount and poor monosystem number, common odd number amount and common monosystem number product and good odd number amount with it is good single The sum of products of coefficient.Push quantity on order be push difference odd number amount with the product of poor monosystem number, push it is common it is singular measure with it is general The sum of products of the product of logical monosystem number and push good odd number amount and good monosystem number.Namely it is calculated by the following formula and is robbed Single rate.
Competition for orders rate=(good odd number amount * c of the common odd number amount * b+ of difference odd number amount * a+)/(push difference odd number amount * a+ push is common Odd number amount * b+ pushes good odd number amount * c).Wherein, the coefficient of all kinds of orders can decay according to the difficulty of order, for example, a It can be 1.5, b can be 1, c can be 0.9.
In practical applications, difference is single can refer to order or competition for orders rate ordering less than 0.1 of the practical competition for orders number less than 2 people It is single；Common list can refer to that practical competition for orders number is more than or equal to 2 and order of the competition for orders rate between (0.1~0.5)；Poor list can To refer to that practical competition for orders number is greater than 3 people, and order of the competition for orders rate between (0.5~1).
Optionally, for each order group, determine that order completes the corresponding completion rate of parameter and may include:
It determines the completion list amount in each order group and cancels single amount, and cancel the cancellation list rate of user in list；
It calculates and the sum of cancels single amount and cancel the product of single rate and complete list amount, obtain and complete total amount；
The quotient for completing single amount and completing total amount is calculated, completion rate is obtained.
Optionally, for each order group, determine that the corresponding positive rating of favorable comment parameter may include:
Determine the respective order comment point of at least one order in each order group；It is respective at least one order Order comment point, statistics favorable comment odd number and difference comment odd number；
It calculates favorable comment odd number and difference comments the difference of odd number, the quotient with the order performance of at least one order obtains Comment rate.
Wherein, the respective order comment point of at least one order can be calculated by the following formula acquisition:
Order comment point=any one order user comment point/average review divides the user comment point of any one order of *.
Wherein, when the order comment point of order is more than or equal to 4 timesharing, which is favorable comment order, when being averaged for order is commented By dividing less than 4 timesharing, which is that difference comments order.
Optionally, for each order group, determine that the corresponding online rate of the online hours may include:
For each order group, nearest one week average online hours of driver are counted；
If average online hours are greater than preset duration threshold value, the first online rate is determined；
If average online hours are less than preset duration threshold value, determine that the quotient of average online hours and duration threshold value is second Online rate.
Optionally, unit fraction is robbed based on the acquisition of competition for orders rate and the first weight score to may include: that determining competition for orders rate is corresponding robs Unit fraction is robbed in the product of single mapping probabilities and the first weight score, acquisition.
Competition for orders mapping probabilities can be calculated by the following formula acquisition: tanh (ratio*100, -0.02)
Wherein, tanh is mapping function, and ratio is competition for orders rate, and competition for orders rate is mapped to some model by mapping function In enclosing, better function control is realized.For different completion rates, different score calculations can be set, to realize more Tool targetedly calculates, and obtains more accurate order score, to improve the levels of precision of final middle single probability.
Optionally, obtaining completion score with second weight based on completion rate may include:
It, can be by calculating completion rate and default completion rate threshold value if the completion rate is less than default completion rate threshold value Quotient, the product with the second weight obtain and complete score；
If the completion rate is greater than default completion rate threshold value, acquisition can be calculated by the following formula and complete score:
Completion rate score=the second weight+tanh ((completion rate-completion rate threshold value)/(1- completion rate threshold value) * 100 ,- 0.015) the second weight of * 10.0/9.0*.
Optionally, acquisition can be calculated by the following formula based on positive rating and the well received score of third weight: Positive rating score=1.0/ (1+1.5*math.exp (positive rating * (- 3)))/93.0*100* third weight.
Optionally, obtaining online score with the 4th weight based on the online rate may include:
If online rate is the first online rate, the product of the first online rate and the 4th weight is calculated, online score is obtained；Such as The online rate of fruit is the second online rate, is calculated by the following formula and obtains online score:
The 4th weight of online score=tanh (the second online rate * 100, -0.015) * 10.0/9*.
In certain embodiments, the History Order for each driver, determines each driver's After servicing score, the method also includes:
It counts in nearest preset time, the complaint quantity that each driver receipt arrives；
If the complaint quantity is greater than default complaint quantity, default score value is deducted on the service fraction basis, again Obtain the service score of each driver.
Angle is complained to driver from user, measures the service score of driver, more comprehensively, the service data of acquisition is more quasi- for content Really.
In certain embodiments, the History Order for each driver, determines each driver's Servicing score may include:
The service of each driver is determined for the History Order of each driver at interval of the predetermined time Score.
It is described to refer to the service score that a driver is calculated at interval of the set time at interval of the set time.For example, can To calculate the service score of a driver at interval of 24 hours.That is, calculating the service score of a driver daily.
It is described to determine each driver's for the History Order of each driver at interval of the predetermined time Servicing score may include:
Judge whether driver is online；
If online, the current service score of each driver is determined for the History Order of each driver；
If not online, the continuous online service number of days of driver is determined；
If continuous online number of days is less than or equal to preset number of days, the service score that the last time obtains is decayed, is obtained The service score of each driver；
If continuous online number of days is greater than preset number of days, the service score that the last time is obtained is as each described driver Service score.
When calculating the service score of driver, counted for the online number of days of driver, to obtain more accurate clothes Be engaged in score, so in realizing single probability raising.
In certain embodiments, in order to by Order splitting to be allocated to being more likely to receive the driver of its order, to improve The order situation of order to be allocated, the History Order based on each driver determine that the competition for orders of each driver is general Rate may include:
Determine the History Order of each driver and the similarity degree of the freight orders to be allocated；
According to the similarity degree of the History Order of each driver and the freight orders to be allocated, calculates and obtain each The competition for orders probability of driver.
Can order information based on History Order and freight orders to be allocated order information matching degree, determine phase Like degree.The order information of History Order may include: history starting shipping place, history terminates shipping place and history is ordered Monovalent lattice etc., the order information of freight orders to be allocated may include: origin, end place and order price etc. Deng.In practical applications can for history starting shipping place and origin similarity, history terminate shipping place with The similarity degree of end place and the similarity degree of History Order price and order price, determine final similarity degree.
As shown in figure 4, being a kind of structural representation of one embodiment of data processing equipment provided in an embodiment of the present invention Figure, the apparatus may include following modules:
Driver's matching module 401: for being directed to freight orders to be allocated, at least one department for meeting competition for orders condition is determined Machine.
Wherein it is possible to be directed to freight orders to be allocated by server-side, at least one driver for meeting competition for orders condition is determined.To Distribution freight orders can be generated by server-side, can specifically be generated based on the shipment request that user terminal is sent wait divide by server-side With freight orders.
Driver's matching module can be also used for: receive the shipment request of any one user terminal transmission；Based on any one user The shipment request sent is held, freight orders to be allocated are generated.
In certain embodiments, the competition for orders condition can refer at least one shipping number with the freight orders to be allocated According to matching.Wherein, at least one ship data may include: shipping initial position, shipment month and/or shipping vehicle.
Driver's matching module can be used for: at least one ship data in the freight orders to be allocated, Determining at least one driver to match at least one described ship data.
Driver's matching module can be also used for: from multiple drivers to be selected, determination and shipping initial position phase Matching, at least one driver for matching and/or matching with the shipping vehicle with the shipment month.
Driver's matching module specifically can be also used for: the position of driver to be selected is at a distance from the shipping initial position In distance threshold.Match with the shipment month may include: that working time of driver to be selected may include the goods Transport the time.And the shipping vehicle match may include driver to be selected vehicle it is identical as the shipping vehicle.
Competition for orders probabilistic module 402: for the History Order based on each driver, the competition for orders of each driver is determined Probability.
The competition for orders probability of each driver can be associated with its history order, the competition for orders of each driver whether can lead to The History Order situation of the driver is crossed to judge, to improve the accuracy of the competition for orders probability of the driver obtained.
The competition for orders probability of each driver can also refer to that the probability of single operation is robbed in the triggering of each driver's actual capabilities.It robs A possibility that a possibility that single probability is bigger, and single operation is robbed in driver's triggering is higher, and competition for orders probability is smaller, and single operation is robbed in driver's triggering It is lower.
Middle list probabilistic module 403: for calculating and obtaining each according to the respective competition for orders probability of at least one described driver Middle single probability of driver.
Middle single probability of each driver can be obtained according to the respective competition for orders probability of at least one driver.Each driver Middle single probability be no longer individually to estimate process, can be respective by the competition for orders probability of each driver and at least one driver Competition for orders probability correlation connection, whether establishing each driver's competition for orders from associated angle between connection, and then middle list can be improved The accuracy of probability.
Middle single probabilistic module may include:
It calculates according to default middle single model according to the respective competition for orders probability of at least one described driver and obtains each department Middle single probability of machine.
Single model can determine at least one described first quantity of driver with pointer to the driver of middle single probability to be determined in this Driver's competition for orders, when driver's not competition for orders of the second quantity, the driver of middle single probability to be determined.
In the embodiment of the present invention, for freight orders to be allocated, at least one driver for meeting competition for orders condition can be determined, Namely the driver to match with the reality order to be sorted of user is screened from all drivers, and then each driver can be directed to History Order, can determine the competition for orders probability of each driver, and then can rob according at least one driver is corresponding Single probability calculates the middle single probability for obtaining each driver.Middle single probability of each driver is met into competition for orders condition with all Driver it is associated, each successful feasibility of driver's competition for orders is associated with other participation drivers of competition for orders, it is contemplated that One-state is robbed in real time, and the accuracy of middle single probability of each driver of acquisition is higher.
As shown in figure 5, being that a kind of structure of another embodiment of data processing equipment provided in an embodiment of the present invention is shown Be intended to, the device and embodiment shown in Fig. 4 the difference is that, middle single probabilistic module 403 includes:
First determination unit 501: for being directed to the competition for orders probability of any one driver, respectively according at least one described driver Competition for orders probability, determine first kind driver and the second class driver at least one described driver；
Second determination unit 502: for determining that the first kind driver executes the first generic operation and second class department When machine executes the second generic operation, middle single probability of any one driver, to obtain middle single probability of each driver.
Influence when by considering that part driver robs single part driver's not competition for orders to the middle single probability for accordingly robbing single driver, I.e. practical comprehensive consideration driver competition for orders when, what other can rob single driver robs influence of the one-state to probability single in driver, further Obtain more accurate middle single probability.
Optionally, first determination unit may include:
It is grouped subelement, for the competition for orders probability for any one driver, respectively according at least one described driver Competition for orders probability, determine that the driver for the competition for orders probability that competition for orders probability is greater than any one driver at least one described driver is The driver that first kind driver and competition for orders probability are less than the competition for orders probability of any one driver is the second class driver；
Second determination unit includes:
Middle list unit robs single operation and the second class driver holds for determining that the first kind driver does not execute Rob single operation when, middle single probability of any one driver, to obtain middle single probability of each driver.
It, can be by general according to respective competition for orders by least one driver in the competition for orders probability for determining any one driver Rate, carries out the division of different types of driver, and it is corresponding when robbing single operation to determine that different types of driver executes, described Middle single probability of any one driver.By this calculation, middle single probability of each driver can be accurately estimated.
As one embodiment, the competition for orders probabilistic module includes:
Third determination unit determines the clothes of each driver for the History Order for each driver Business score.
4th determination unit obtains institute for calculating the service score of each driver and the ratio of basic score State the competition for orders probability of each driver.
The service score of each driver can be according to the generation of the History Order of the driver.
Service score can be used for evaluating the actual service scenario of driver, and when service score is higher, the service of driver is got over Good, service score is lower, and the service of driver is poorer.Score can will be serviced as the calculating of driver's competition for orders probability basis.That is, The service score of driver is higher, illustrates that the service wish of driver is higher, at this moment the competition for orders probability of driver is also higher.Due to driver Service score can be obtained by multiple service parameters, therefore, service score can from multi-angle, multi-direction measure user Real work situation.
When the basis score can refer to the service score of practical each driver of determination, score when full marks is obtained. The competition for orders probability that the ratio of the service score and basic score, as the service score correspond to driver.
As a kind of possible implementation, the third determination unit may include:
It is grouped subelement, for being directed to the History Order of each driver, determines multiple order groups；Wherein, each order Group includes at least one order；
Score obtains subelement and obtains multiple order scores for determining the corresponding order score of each order group；
Coefficient determines subelement, for determining the corresponding attenuation coefficient of multiple order groups；
Score handles subelement, for the corresponding order score of multiple order groups and attenuation coefficient to be weighted Processing obtains the service score of each driver.
It is alternatively possible to which the order placement service time according to the History Order of each driver is grouped, multiple order is obtained Single group.The order placement service time be driver it is practical be user execute cargo service when time.That is, can be according to order placement service when Between, the History Order of each driver is divided into multiple order groups.An order is included at least in each order group.
Corresponding attenuation coefficient is respectively corresponded for multiple order groups, each order group can be corresponding with corresponding decaying system Number.Attenuation coefficient can be set according to actual needs, and the attenuation coefficient of different order groups may be the same or different, It is defined herein not to this.
In practical applications, multiple packet time sections can be preset, by the History Order of each driver according to its reality The order placement service time, matched with preset packet time section, determine each packet time section it is matched at least one Order, and then obtain multiple order groups.
Wherein it is possible to determine in nearest one month, the History Order of each driver orders the history in nearest one month Singly it is divided into multiple groups order group.
It is alternatively possible to which nearest one month History Order is divided according to the order placement service time.It can as one kind The implementation of energy can determine nearest one week order, obtain the first order group；Order apart from nearest second week, is obtained Obtain the second order group；Apart from the order in nearest third week, third order group is obtained；And ordering apart from nearest 4th week It is single, obtain the 4th order group.The corresponding attenuation coefficient of multiple order groups, can refer to, the first order group corresponding first decaying system Number, corresponding second attenuation coefficient of the second order group, the corresponding third attenuation coefficient of third order group and the 4th order group pair The 4th attenuation coefficient answered.
The current service scenario of driver more can be represented apart from the nearest time, it is alternatively possible to according to each order group The order period sequencing, the attenuation coefficient of each order group is successively reduced.For example, above-mentioned first can be ordered First attenuation coefficient of single group is set as 1.2, and the second attenuation coefficient of the second order group is set as 1.1, by third order group Third attenuation coefficient be set as 1, the attenuation coefficient of the 4th order group is set as 0.9.
The History Order of driver is carried out detailed order group to divide, it can be by each History Order according to different orders Combination is targetedly handled, and then corresponding attenuation coefficient can be arranged for order group, real by the setting of attenuation coefficient Now the influence by order group to order score is layered, and by hierarchical design, can be calculated and user's active service situation More matched service score.
In order to obtain accurate order score, in certain embodiments, the score obtains subelement and includes:
Parameter determination module, for determining at least one service parameter；Score determining module, for for it is described each Order group determines the corresponding service score of at least one described service parameter；Score computing module, for calculate it is described extremely The sum of few corresponding service score of a service parameter obtains the corresponding service score of each described order group, to obtain Obtain multiple order scores.
In a kind of possible design, the score determining module may include:
Probability determining unit determines that at least one described service parameter respectively corresponds ginseng for being directed to each order group Number probability；
Weight determining unit, for determining at least one service parameter respectively respective weights；
Score determination unit, for being based on the corresponding parameter probability of each service parameter and respective weight, Each described service parameter corresponding with service score is obtained, to obtain the corresponding service point of at least one described service parameter Number.
Using the design method of service parameter mark different parameters data, can make from different directions in view of different numbers According to the influence to user service score.
Wherein, at least one described service parameter may include: competition for orders Success parameter, order completion parameter, favorable comment parameter And/or online hours parameter；
The probability determining unit may include:
Determine the probability subelement, for be directed to each order group, determine the corresponding competition for orders rate of the competition for orders Success parameter, The order complete the corresponding completion rate of parameter, the corresponding positive rating of the favorable comment parameter and/or state online hours it is corresponding Line rate；
The weight determining unit may include:
Score determines subelement, for determining the corresponding first weight score of the competition for orders Success parameter, determining the order When completing the corresponding second weight score of parameter, determining that the favorable comment parameter corresponds to third weight score and/or determines described online Long corresponding 4th weight score；
The score determination unit may include:
Score obtains subelement, robs unit fraction, described for obtaining based on the competition for orders rate and the first weight score Completion rate and second weight, which obtain, completes score, the positive rating and the well received score of the third weight and described Online rate and/or the 4th weight obtain online score.
Optionally, probability determining unit can be used for:
Based on the order contents in each order group, competition for orders success quantity and push quantity on order are determined；Calculate competition for orders Success quantity and the quotient for pushing order success quantity, obtain the corresponding competition for orders rate of competition for orders Success parameter.Wherein, competition for orders success quantity For calculate the product of difference odd number amount and poor monosystem number, common odd number amount and common monosystem number product and good odd number amount with it is good single The sum of products of coefficient.Push quantity on order be push difference odd number amount with the product of poor monosystem number, push it is common it is singular measure with it is general The sum of products of the product of logical monosystem number and push good odd number amount and good monosystem number.Namely it is calculated by the following formula and is robbed Single rate.
Competition for orders rate=(good odd number amount * c of the common odd number amount * b+ of difference odd number amount * a+)/(push difference odd number amount * a+ push is common Odd number amount * b+ pushes good odd number amount * c).Wherein, the coefficient of all kinds of orders can decay according to the difficulty of order, for example, a It can be 1.5, b can be 1, c can be 0.9.
In practical applications, difference is single can refer to order or competition for orders rate ordering less than 0.1 of the practical competition for orders number less than 2 people It is single；Common list can refer to that practical competition for orders number is more than or equal to 2 and order of the competition for orders rate between (0.1~0.5)；Poor list can To refer to that practical competition for orders number is greater than 3 people, and order of the competition for orders rate between (0.5~1).
Optionally, probability determining unit can be used for:
It determines the completion list amount in each order group and cancels single amount, and cancel the cancellation list rate of user in list；
It calculates and the sum of cancels single amount and cancel the product of single rate and complete list amount, obtain and complete total amount；
The quotient for completing single amount and completing total amount is calculated, completion rate is obtained.
Optionally, probability determining unit can be used for:
Determine the respective order comment point of at least one order in each order group；It is respective at least one order Order comment point, statistics favorable comment odd number and difference comment odd number；
It calculates favorable comment odd number and difference comments the difference of odd number, the quotient with the order performance of at least one order obtains Comment rate.
Wherein, the respective order comment point of at least one order can be calculated by the following formula acquisition:
Order comment point=any one order user comment point/average review divides the user comment point of any one order of *.
Wherein, when the order comment point of order is more than or equal to 4 timesharing, which is favorable comment order, when being averaged for order is commented By dividing less than 4 timesharing, which is that difference comments order.
Optionally, probability determining unit can be used for:
For each order group, nearest one week average online hours of driver are counted；
If average online hours are greater than preset duration threshold value, the first online rate is determined；
If average online hours are less than preset duration threshold value, determine that the quotient of average online hours and duration threshold value is second Online rate.
Optionally, score determination unit can be used for: determine that competition for orders rate corresponds to competition for orders mapping probabilities and the first weight score Product, acquisition rob unit fraction.
Competition for orders mapping probabilities can be calculated by the following formula acquisition: tanh (ratio*100, -0.02)
Wherein, tanh is mapping function, and ratio is competition for orders rate, and competition for orders rate is mapped to some model by mapping function In enclosing, better function control is realized.For different completion rates, different score calculations can be set, to realize more Tool targetedly calculates, and obtains more accurate order score, to improve the levels of precision of final middle single probability.
Optionally, score determination unit can be used for:
It, can be by calculating completion rate and default completion rate threshold value if the completion rate is less than default completion rate threshold value Quotient, the product with the second weight obtain and complete score；
If the completion rate is greater than default completion rate threshold value, acquisition can be calculated by the following formula and complete score:
Completion rate score=the second weight+tanh ((completion rate-completion rate threshold value)/(1- completion rate threshold value) * 100 ,- 0.015) the second weight of * 10.0/9.0*.
Optionally, score determination unit, which can be calculated by the following formula, obtains third weight score: positive rating score= 1.0/ (1+1.5*math.exp (positive rating * (- 3)))/93.0*100* third weight.
Optionally, score determination unit can be used for:
If online rate is the first online rate, the product of the first online rate and the 4th weight is calculated, online score is obtained；Such as The online rate of fruit is the second online rate, is calculated by the following formula and obtains online score:
The 4th weight of online score=tanh (the second online rate * 100, -0.015) * 10.0/9*.
In certain embodiments, the competition for orders probabilistic module further include:
Quantity statistics unit, for counting in nearest preset time, complaint quantity that each driver receipt arrives；
Score obtaining unit, if being greater than default complaint quantity for the complaint quantity, on the service fraction basis Default score value is deducted, the service score of each driver is regained.
Angle is complained to driver from user, measures the service score of driver, more comprehensively, the service data of acquisition is more quasi- for content Really.
In certain embodiments, the third determination unit can be used for:
The service of each driver is determined for the History Order of each driver at interval of the predetermined time Score.
It is described to refer to the service score that a driver is calculated at interval of the set time at interval of the set time.For example, can To calculate the service score of a driver at interval of 24 hours.That is, calculating the service score of a driver daily.
The third determination unit is at interval of the predetermined time, for the History Order of each driver, determine described in The service score of each driver can specifically refer to:
Judge whether driver is online；
If online, the current service score of each driver is determined for the History Order of each driver；
If not online, the continuous online service number of days of driver is determined；
If continuous online number of days is less than or equal to preset number of days, the service score that the last time obtains is decayed, is obtained The service score of each driver；
If continuous online number of days is greater than preset number of days, the service score that the last time is obtained is as each described driver Service score.
When calculating the service score of driver, counted for the online number of days of driver, to obtain more accurate clothes Be engaged in score, so in realizing single probability raising.
In certain embodiments, in order to by Order splitting to be allocated to being more likely to receive the driver of its order, to improve The order situation of order to be allocated, the competition for orders probabilistic module may include:
5th determination unit, for determining the History Order of each driver and the similar journey of the freight orders to be allocated Degree；
First computing unit, for according to the History Order of each driver and the similar journey of the freight orders to be allocated Degree calculates the competition for orders probability for obtaining each driver.
Can order information based on History Order and freight orders to be allocated order information matching degree, determine phase Like degree.The order information of History Order may include: history starting shipping place, history terminates shipping place and history is ordered Monovalent lattice etc., the order information of freight orders to be allocated may include: origin, end place and order price etc. Deng.In practical applications can for history starting shipping place and origin similarity, history terminate shipping place with The similarity degree of end place and the similarity degree of History Order price and order price, determine final similarity degree.
In a typical configuration, user terminal, driver end and server-side may include one or more processors (CPU), input/output interface, network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/or The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data. The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM), Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.
As used some vocabulary to censure specific components in the specification and claims.Those skilled in the art answer It is understood that hardware manufacturer may call the same component with different nouns.This specification and claims are not with name The difference of title is as the mode for distinguishing component, but with the difference of component functionally as the criterion of differentiation.Such as logical The "comprising" of piece specification and claim mentioned in is an open language, therefore should be construed to " include but do not limit In "." substantially " refer within the acceptable error range, those skilled in the art can within a certain error range solve described in Technical problem basically reaches the technical effect.Specification subsequent descriptions are to implement the better embodiment of the application, so described Description is being not intended to limit the scope of the present application for the purpose of the rule for illustrating the application.The protection scope of the application As defined by the appended claims.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability Include, so that commodity or system including a series of elements not only include those elements, but also including not clear The other element listed, or further include for this commodity or the intrinsic element of system.In the feelings not limited more Under condition, the element that is limited by sentence "including a ...", it is not excluded that in the commodity or system for including the element also There are other identical elements.
Above description shows and describes several preferred embodiments of the present application, but as previously described, it should be understood that the application Be not limited to forms disclosed herein, should not be regarded as an exclusion of other examples, and can be used for various other combinations, Modification and environment, and the above teachings or related fields of technology or knowledge can be passed through in application contemplated scope described herein It is modified.And changes and modifications made by those skilled in the art do not depart from spirit and scope, then it all should be in this Shen It please be in the protection scope of appended claims.

Claims (18)

1. a kind of data processing method characterized by comprising
For freight orders to be allocated, at least one driver for meeting competition for orders condition is determined；
History Order based on each driver determines the competition for orders probability of each driver；
According to the respective competition for orders probability of at least one described driver, the middle single probability for obtaining each driver is calculated.
2. the method according to claim 1, wherein the respective competition for orders of at least one driver according to is general Rate, middle single probability that calculating obtains each driver include:
For the competition for orders probability of any one driver, according to the respective competition for orders probability of at least one described driver, determination is described at least First kind driver and the second class driver in one driver；
It is described when determining that the first kind driver executes the first generic operation and the second class driver the second generic operation of execution Middle single probability of any one driver, to obtain middle single probability of each driver.
3. the method according to claim 1, wherein the History Order based on each driver, determines institute The competition for orders probability for stating each driver includes:
For the History Order of each driver, the service score of each driver is determined；
The service score of each driver and the ratio of basic score are calculated, the competition for orders for obtaining each driver is general Rate.
4. the method according to claim 1, wherein the History Order based on each driver, determines institute The competition for orders probability for stating each driver includes:
Determine the History Order of each driver and the similarity degree of the freight orders to be allocated；
According to the similarity degree of the History Order of each driver and the freight orders to be allocated, calculates and obtain each driver Competition for orders probability.
5. according to method described in right 3, which is characterized in that the History Order for each driver determines institute The service score for stating each driver includes:
For the History Order of each driver, multiple order groups are determined；Wherein, each order group includes at least one order；
It determines the corresponding order score of each order group, obtains multiple order scores；
Determine the corresponding attenuation coefficient of multiple order groups；
The corresponding order score of multiple order groups and attenuation coefficient are weighted processing, obtain each described driver Service score.
6. according to the method described in claim 5, it is characterized in that, the corresponding order score of each order group of the determination, Obtaining multiple order scores includes:
Determine at least one service parameter；
For each described order group, the corresponding service score of at least one described service parameter is determined；
The sum of corresponding service score of at least one described service parameter is calculated, it is corresponding to obtain each described order group Score is serviced, to obtain multiple order scores.
7. according to the method described in claim 6, it is characterized in that, described be directed to each order group, determination described at least one The corresponding service score of a service parameter includes:
For each order group, determine that at least one described service parameter respectively corresponds parameter probability；
Determine at least one service parameter respectively respective weights；
Based on the corresponding parameter probability of each service parameter and respective weight, each described service parameter is obtained Corresponding with service score, to obtain the corresponding service score of at least one described service parameter.
8. the method according to the description of claim 7 is characterized in that at least one described service parameter includes: that competition for orders is successfully joined Number, order complete parameter, favorable comment parameter and/or online hours parameter；
It is described to be directed to each order group, determine that at least one described service parameter respectively corresponds parameter probability and includes:
For each order group, determine that the corresponding competition for orders rate of the competition for orders Success parameter, order completion parameter are corresponding Completion rate, the corresponding positive rating of the favorable comment parameter and/or state the corresponding online rate of online hours；
Respectively reciprocal fraction weight includes: for the determination at least one service parameter
It determines the corresponding first weight score of the competition for orders Success parameter, determine that the order completes corresponding second weight point of parameter Number determines that the favorable comment parameter corresponds to third weight score and/or determines the corresponding 4th weight score of the online hours；
The product for calculating the corresponding parameter probability of each service parameter and weight obtains each described service Parameter corresponding with service score includes: to obtain the corresponding service score of at least one service parameter
Unit fraction, the completion rate and second weight is robbed based on the competition for orders rate and the first weight score acquisition to obtain Complete score, the positive rating and the well received score of the third weight and the online rate and/or the 4th weight Obtain online score.
9. according to the method described in claim 2, it is characterized in that, the competition for orders probability for any one driver, according to institute The respective competition for orders probability of at least one driver is stated, determines first kind driver and the second class driver packet at least one described driver It includes:
For the competition for orders probability of any one driver, according to the respective competition for orders probability of at least one described driver, determine described in It is first kind driver and competition for orders that competition for orders probability, which is greater than the driver of the competition for orders probability of any one driver, at least one driver The driver that probability is less than the competition for orders probability of any one driver is the second class driver；
When the determination first kind driver executes the first generic operation and the second class driver the second generic operation of execution, Middle single probability of any one driver includes: to obtain middle single probability of each driver
It determines that the first kind driver does not execute and robs single operation and the second class driver and execute that rob single operation be described Middle single probability of one driver, to obtain middle single probability of each driver.
10. a kind of data processing equipment characterized by comprising
Driver's matching module determines at least one driver for meeting competition for orders condition for being directed to freight orders to be allocated；
Competition for orders probabilistic module determines the competition for orders probability of each driver for the History Order based on each driver；
Middle list probabilistic module, for calculating and obtaining each driver's according to the respective competition for orders probability of at least one described driver Middle list probability.
11. device according to claim 10, which is characterized in that middle single probabilistic module includes:
First determination unit, for being directed to the competition for orders probability of any one driver, according to the respective competition for orders of at least one driver Probability determines first kind driver and the second class driver at least one described driver；
Second determination unit, for determining that the first kind driver executes the first generic operation and the second class driver executes When the second generic operation, middle single probability of any one driver, to obtain middle single probability of each driver.
12. device according to claim 10, which is characterized in that the competition for orders probabilistic module includes:
Third determination unit determines the service point of each driver for the History Order for each driver Number；
4th determination unit obtains described every for calculating the service score of each driver and the ratio of basic score The competition for orders probability of one driver.
13. device according to claim 10, which is characterized in that the competition for orders probabilistic module includes:
5th determination unit, for determining the History Order of each driver and the similarity degree of the freight orders to be allocated；
First computing unit, for the similarity degree according to the History Order of each driver and the freight orders to be allocated, Calculate the competition for orders probability for obtaining each driver.
14. according to device described in right 12, which is characterized in that the third determination unit includes:
It is grouped subelement, for being directed to the History Order of each driver, determines multiple order groups；Wherein, each order group packet Include at least one order；
Score obtains subelement and obtains multiple order scores for determining the corresponding order score of each order group；
Coefficient determines subelement, for determining the corresponding attenuation coefficient of multiple order groups；
Score handles subelement, for the corresponding order score of multiple order groups and attenuation coefficient to be weighted place Reason obtains the service score of each driver.
15. device according to claim 14, which is characterized in that the score obtains subelement and is specifically used for:
Parameter determination module, for determining at least one service parameter；Score determining module, for for each described order Group determines the corresponding service score of at least one described service parameter；Score computing module, for calculating described at least one The sum of corresponding service score of a service parameter obtains the corresponding service score of each described order group, more to obtain A order score.
16. device according to claim 15, which is characterized in that the score determining module includes:
It is general to determine that at least one described service parameter respectively corresponds parameter for being directed to each order group for probability determining unit Rate；
Weight determining unit, for determining at least one service parameter respectively respective weights；
Score determination unit is obtained for being based on the corresponding parameter probability of each service parameter and respective weight Each described service parameter corresponding with service score, to obtain the corresponding service score of at least one described service parameter.
17. device according to claim 16, which is characterized in that at least one described service parameter includes: competition for orders success Parameter, order complete parameter, favorable comment parameter and/or online hours parameter；
The probability determining unit includes:
Determine the probability subelement determines the corresponding competition for orders rate of the competition for orders Success parameter, described for being directed to each order group Order completes the corresponding completion rate of parameter, the corresponding positive rating of the favorable comment parameter and/or states the corresponding online rate of online hours；
The weight determining unit includes:
Score determines subelement, for determining the corresponding first weight score of the competition for orders Success parameter, determining that the order is completed Parameter corresponds to the second weight score, determines that the favorable comment parameter corresponds to third weight score and/or determines the online hours pair Answer the 4th weight score；
The score determination unit includes:
Score obtains subelement, for robbing unit fraction, the completion based on the competition for orders rate and the first weight score acquisition Rate and second weight, which obtain, completes score, the positive rating and the well received score of the third weight and described online Rate and/or the 4th weight obtain online score.
18. device according to claim 11, which is characterized in that first determination unit includes:
It is grouped subelement, for the competition for orders probability for any one driver, is robbed according at least one described driver is respective Single probability determines that the driver for the competition for orders probability that competition for orders probability is greater than any one driver at least one described driver is first The driver that class driver and competition for orders probability are less than the competition for orders probability of any one driver is the second class driver；
Second determination unit includes:
Middle list unit is robbed for determining that the first kind driver does not execute to rob single operation and the second class driver and execute When single operation, middle single probability of any one driver, to obtain middle single probability of each driver.
CN201811261237.XA 2018-10-26 2018-10-26 Data processing method and device Active CN109377317B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811261237.XA CN109377317B (en) 2018-10-26 2018-10-26 Data processing method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811261237.XA CN109377317B (en) 2018-10-26 2018-10-26 Data processing method and device

Publications (2)

Publication Number Publication Date
CN109377317A true CN109377317A (en) 2019-02-22
CN109377317B CN109377317B (en) 2021-03-30

Family

ID=65389748

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811261237.XA Active CN109377317B (en) 2018-10-26 2018-10-26 Data processing method and device

Country Status (1)

Country Link
CN (1) CN109377317B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109886603A (en) * 2019-03-12 2019-06-14 北京同城必应科技有限公司 Order method for pushing, device, equipment and storage medium
CN112418616A (en) * 2020-11-05 2021-02-26 深圳依时货拉拉科技有限公司 Order broadcasting method and device, computer equipment and computer-readable storage medium
CN112700074A (en) * 2019-10-22 2021-04-23 北京四维图新科技股份有限公司 Express task planning method and device

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130290128A1 (en) * 2012-04-28 2013-10-31 Xerox Corporation Methods and Systems to Evaluate and Rank Bids Based At Least in Part on the Provider's Past Performance
CN104599168A (en) * 2015-02-02 2015-05-06 北京嘀嘀无限科技发展有限公司 Method and device for allocating taxi-calling orders
CN104915821A (en) * 2015-06-10 2015-09-16 百度在线网络技术（北京）有限公司 Order data processing method, client and server
CN107292703A (en) * 2017-05-27 2017-10-24 卓集送信息科技（武汉）有限公司 A kind of freight orders method for pushing and system
CN107341636A (en) * 2017-06-30 2017-11-10 镇江五八到家供应链管理服务有限公司 Method is subsidized in a kind of shipping driver competition for orders
CN107357852A (en) * 2017-06-28 2017-11-17 镇江五八到家供应链管理服务有限公司 A kind of determination methods of shipping driver to order wish
CN108537352A (en) * 2017-03-02 2018-09-14 北京嘀嘀无限科技发展有限公司 A kind of data processing method, device and server
CN108985819A (en) * 2018-06-15 2018-12-11 天津五八到家科技有限公司 Driver's portrait method, system and equipment

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130290128A1 (en) * 2012-04-28 2013-10-31 Xerox Corporation Methods and Systems to Evaluate and Rank Bids Based At Least in Part on the Provider's Past Performance
CN104599168A (en) * 2015-02-02 2015-05-06 北京嘀嘀无限科技发展有限公司 Method and device for allocating taxi-calling orders
CN104915821A (en) * 2015-06-10 2015-09-16 百度在线网络技术（北京）有限公司 Order data processing method, client and server
CN108537352A (en) * 2017-03-02 2018-09-14 北京嘀嘀无限科技发展有限公司 A kind of data processing method, device and server
CN107292703A (en) * 2017-05-27 2017-10-24 卓集送信息科技（武汉）有限公司 A kind of freight orders method for pushing and system
CN107357852A (en) * 2017-06-28 2017-11-17 镇江五八到家供应链管理服务有限公司 A kind of determination methods of shipping driver to order wish
CN107341636A (en) * 2017-06-30 2017-11-10 镇江五八到家供应链管理服务有限公司 Method is subsidized in a kind of shipping driver competition for orders
CN108985819A (en) * 2018-06-15 2018-12-11 天津五八到家科技有限公司 Driver's portrait method, system and equipment

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109886603A (en) * 2019-03-12 2019-06-14 北京同城必应科技有限公司 Order method for pushing, device, equipment and storage medium
CN112700074A (en) * 2019-10-22 2021-04-23 北京四维图新科技股份有限公司 Express task planning method and device
CN112700074B (en) * 2019-10-22 2024-05-03 北京四维图新科技股份有限公司 Express delivery task planning method and device
CN112418616A (en) * 2020-11-05 2021-02-26 深圳依时货拉拉科技有限公司 Order broadcasting method and device, computer equipment and computer-readable storage medium
CN112418616B (en) * 2020-11-05 2024-01-23 深圳依时货拉拉科技有限公司 Order broadcasting method, order broadcasting device, computer equipment and computer readable storage medium

Also Published As

Publication number Publication date
CN109377317B (en) 2021-03-30

Similar Documents

Publication Publication Date Title
CN109598368B (en) Path decision evaluation and order distribution method and device, electronic equipment and medium
Cont et al. Order book dynamics in liquid markets: limit theorems and diffusion approximations
CN109377317A (en) Data processing method and device
CN108256893A (en) The analysis method and device of advertisement delivery effect
CN107845016B (en) Information output method and device
CN109583819A (en) Order scheduling method, order scheduling device, storage medium and electronic equipment
CN109993367A (en) Distribution time length estimation method, distribution time length estimation device, storage medium and electronic equipment
AU2010202869A1 (en) Marketing model determination system
CN107844877A (en) Order allocation method and device
CN109583670B (en) Control experiment method, system and computer device based on time slice rotation
CN112561285A (en) Recommendation method and device for website, electronic equipment and computer readable storage medium
CN106339578A (en) Multi-strategy integration hospital patient registration recommendation method
CN106257507A (en) The methods of risk assessment of user behavior and device
CN115018596A (en) False positioning identification and model training method, device, equipment and medium
WO2022142064A1 (en) Driving evaluation method and apparatus, and non-transitory computer-readable storage medium
CN110009154A (en) A kind of reimbursement prediction technique, device, terminal device and storage medium
CN105654326A (en) Information processing system and information processing method
CN111325572B (en) Data processing method and device
CN109597680A (en) Task queue's response parameter evaluation method and device
CN107480703A (en) Transaction fault detection method and device
CN110689177A (en) Method and device for predicting order preparation time, electronic equipment and storage medium
CN110210645A (en) A kind of development trend data capture method, device and readable storage medium storing program for executing
Lee et al. Forecasting korean stock price index (kospi) using back propagation neural network model, bayesian chiao's model, and sarima model
CN108564194A (en) A kind of artificial intelligence estimation supermarket checks out the system and training method of queuing time
CN107122865A (en) Method, system and the terminal device estimated are counted by flow

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant