CN109409970A - Abnormal order processing system and method - Google Patents
Abnormal order processing system and method Download PDFInfo
- Publication number
- CN109409970A CN109409970A CN201710322027.6A CN201710322027A CN109409970A CN 109409970 A CN109409970 A CN 109409970A CN 201710322027 A CN201710322027 A CN 201710322027A CN 109409970 A CN109409970 A CN 109409970A
- Authority
- CN
- China
- Prior art keywords
- duty
- order
- module
- sentences
- complaint
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
-
- 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
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The embodiment of the present application provides a kind of abnormal order processing system and method, it is related to field of computer technology, which includes: that machine sentences duty module, for according to the preset order information for sentencing duty model and target exception order, duty goal is carried out to target exception order, machine is obtained and sentences duty result；Module is appealed, sentences the complaint request that duty result is made for machine for receiving user, and complaint request is issued to and manually sentences duty module；Manually sentence duty module, for receiving the complaint request appealing module and issuing, and duty result is sentenced according to the machine that duty module generation is sentenced in complaint request and machine, duty goal is carried out to target exception order, manually sentenced duty result.The embodiment of the present application can establish a closed-loop system for being handled abnormal order, the system can sentence duty in conjunction with the complaint for sentencing duty model, order user or bill user and manually, reasonable duty goal is carried out to abnormal order, to reduce to order user or bill user's bring trouble.
Description
Technical field
The invention relates to field of computer technology, in particular to a kind of abnormal order processing system and method.
Background technique
With the development of internet technology, the O2O based on Internet technology (Online To Offline, it is online offline/
To under line on line) service (such as calling call a taxi, take out dispatching etc.) is that people's lives bring more and more conveniences.Mesh
Before, in O2O service system, for some abnormal orders, such as the order or complained order that are cancelled, there is no a kind of
Reasonable treatment mechanism, and then some troubles are brought to order user or bill user.As it can be seen that proposing a kind of abnormal order processing
System, it has also become those skilled in the art's urgent problem to be solved.
Summary of the invention
To solve the above-mentioned problems, the embodiment of the present application provides a kind of abnormal order processing system and method.
Specifically, the embodiment of the present application is achieved by the following technical solution:
According to the embodiment of the present application in a first aspect, provide a kind of abnormal order processing system, the system comprises:
Machine sentences duty module, complaint module and manually sentences duty module, wherein
The machine sentences duty module, for according to it is preset sentence duty model and target exception order order information, to institute
It states target exception order and carries out duty goal, obtain machine and sentence duty result；
The complaint module sentences what duty result was made for the machine that the machine sentences duty module generation for receiving user
Complaint request, and complaint request is issued to and described artificial sentences duty module；
The complaint request that is described manually to sentence duty module, being issued for receiving the complaint module, and asked according to the complaint
It asks and the machine sentences the machine that duty module generates and sentences duty result to target exception order progress duty goal, obtain artificial
Sentence duty result.
In the embodiment of the present application, the system also includes:
Sentence duty model training module, it is different from the multiple history for obtaining the order information of multiple history exception orders
Respective characteristic information is extracted in the order information of normal order, using logistic regression LR algorithm to the spy of the history exception order
Reference breath is trained, and obtains sentencing duty model, and by it is described sentence duty model and be supplied to the machine sentence duty module.
It is described to sentence duty model training module in the embodiment of the present application, be also used to receive it is described manually sentence duty module generate
Duty is manually sentenced as a result, and sentencing duty mould according to the order information amendment for manually sentencing duty result and the target exception order
Type.
In the embodiment of the present application, the system also includes:
User property correction module, for receive it is described manually sentence duty module generate manually sentence duty as a result, and according to institute
State manually sentence duty as a result, correcting the attribute of the association user of the target exception order, wherein the attribute include: service point,
And/or probability of transaction.
In the embodiment of the present application, the complaint module, comprising:
Request receiving submodule is appealed, sentences duty result for receiving the machine that user sentences duty module generation for the machine
The complaint request made；
Request type determines submodule, for determining the type of the complaint request；
Complaint request issues submodule, for issuing pair of priority according to preset complaint request type and complaint request
It should be related to, complaint request is issued to and described manually sentences duty module.
In the embodiment of the present application, the output for sentencing duty model is the result is that a probability value, the value range of the probability value
Be 0~1, judged to cause according to the value of probability value target exception order exception reason be order user responsibility, still
The responsibility of bill user；Wherein, for the value of probability value closer to 0, the cancellation behavior of target order is more likely to be order use
The responsibility at family, for the value of probability value closer to 1, the cancellation behavior of target order is more likely to be the responsibility of bill user.
According to the second aspect of the embodiment of the present application, a kind of abnormal order processing method is provided, the method is based on above-mentioned
Abnormal order processing system, comprising:
Machine sentences duty module when receiving target exception order, sentences duty model and target exception order according to preset
Order information carries out duty goal to the target exception order, obtains machine and sentence duty result；
Complaint module receives user and sentences the complaint request that duty result is made for the machine that the machine sentences duty module generation,
And complaint request is issued to and described manually sentences duty module；
Manually sentence duty module and receive the complaint request that the complaint module issues, and according to complaint request and the machine
Device sentences the machine that duty module generates and sentences duty result to target exception order progress duty goal, is manually sentenced duty result.
In the embodiment of the present application, the exception order processing system further includes sentencing duty model training module, and the method is also
Include:
The order information that duty model training module obtains multiple history exception orders is sentenced, from the multiple history exception order
Order information in extract respective characteristic information, using logistic regression LR algorithm to the characteristic information of the history exception order
Be trained, obtain sentencing duty model, and by it is described sentence duty model and be supplied to the machine sentence duty module.
In the embodiment of the present application, the method also includes:
Sentence duty model training module receive it is described manually sentence that duty module generates manually sentence duty as a result, and according to described artificial
Duty model is sentenced described in the order information amendment for sentencing duty result and the target exception order.
In the embodiment of the present application, the exception order processing system further includes user property correction module, and the method is also
Include:
User property correction module, for receive it is described manually sentence duty module generate manually sentence duty as a result, and according to institute
State manually sentence duty as a result, correcting the attribute of the association user of the target exception order, wherein the attribute include: service point,
And/or probability of transaction.
In the embodiment of the present application, the complaint module includes: that complaint request receiving submodule, request type determine submodule
And complaint request issues submodule；
The complaint module receives user and sentences the complaint that duty result is made for the machine that the machine sentences duty module generation
Request, and complaint request is issued to and described artificial sentences duty module, comprising:
Complaint request receiving submodule reception user sentences duty result for the machine that the machine sentences duty module generation and makes
Complaint request；
Request type determines that submodule determines the type of the complaint request；
Complaint request issues the corresponding pass that submodule issues priority according to preset complaint request type with complaint request
Complaint request is issued to and described artificial sentences duty module by system.
In the embodiment of the present application, the output for sentencing duty model is the result is that a probability value, the value range of the probability value
Be 0~1, judged to cause according to the value of probability value target exception order exception reason be order user responsibility, still
The responsibility of bill user；Wherein, for the value of probability value closer to 0, the cancellation behavior of target order is more likely to be order use
The responsibility at family, for the value of probability value closer to 1, the cancellation behavior of target order is more likely to be the responsibility of bill user.
According to the third aspect of the embodiment of the present application, a kind of computer storage medium is provided, is stored in the storage medium
There is program instruction, described program instruction includes:
Machine sentences duty module when receiving target exception order, sentences duty model and target exception order according to preset
Order information carries out duty goal to the target exception order, obtains machine and sentence duty result；
Complaint module receives user and sentences the complaint request that duty result is made for the machine that the machine sentences duty module generation,
And complaint request is issued to and described manually sentences duty module；
Manually sentence duty module and receive the complaint request that the complaint module issues, and according to complaint request and the machine
Device sentences the machine that duty module generates and sentences duty result to target exception order progress duty goal, is manually sentenced duty result.
In the embodiment of the present application, a closed-loop system for being handled abnormal order, the system can establish
Abnormal order can reasonably be blamed in conjunction with sentencing duty model, order user or the complaint of bill user and manually sentencing duty
Appoint and determine, to reduce to order user or bill user's bring trouble.
It should be understood that the above general description and the following detailed description are merely exemplary, this can not be limited
Apply for embodiment.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows and meets the application implementation
Example, and be used to explain the principle of the present invention together with specification.
Fig. 1 is a kind of the embodiment of the present application block diagram of abnormal order processing system shown according to an exemplary embodiment；
Fig. 2 is the frame of the embodiment of the present application another abnormal order processing system shown according to an exemplary embodiment
Figure；
Fig. 3 is the frame of the embodiment of the present application another abnormal order processing system shown according to an exemplary embodiment
Figure；
Fig. 4 is the frame of the embodiment of the present application another abnormal order processing system shown according to an exemplary embodiment
Figure；
Fig. 5 is a kind of the embodiment of the present application process of abnormal order processing method shown according to an exemplary embodiment
Figure；
Fig. 6 is the process of the embodiment of the present application another abnormal order processing method shown according to an exemplary embodiment
Figure；
Fig. 7 is a kind of the embodiment of the present application one for abnormal order processing system shown according to an exemplary embodiment
Structural schematic diagram.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the embodiment of the present application.On the contrary, they be only with
The example of the consistent device and method of as detailed in the attached claim, the embodiment of the present application some aspects.
It is only merely for for the purpose of describing particular embodiments, being not intended to be limiting this in the term that the embodiment of the present application uses
Apply for embodiment.The embodiment of the present application and the "an" of singular used in the attached claims, " described " and
"the" is also intended to including most forms, unless the context clearly indicates other meaning.It is also understood that art used herein
Language "and/or" refers to and includes that one or more associated any or all of project listed may combine.
It will be appreciated that though various letters may be described using term first, second, third, etc. in the embodiment of the present application
Breath, but these information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other out.For example,
In the case where not departing from the embodiment of the present application range, the first information can also be referred to as the second information, similarly, the second information
The first information can also be referred to as.Depending on context, word as used in this " if " can be construed to " ...
When " or " when ... " or " in response to determination ".
With the development of internet technology, the O2O based on Internet technology (Online To Offline, it is online offline/
To under line on line) service (such as calling call a taxi, take out dispatching etc.) is that people's lives bring more and more conveniences.Mesh
Before, in O2O service system, for some abnormal orders, such as the order or complained order that are cancelled, there is no a kind of
Reasonable treatment mechanism, and then some troubles are brought to order user or bill user.As it can be seen that proposing a kind of abnormal order processing
System, it has also become those skilled in the art's urgent problem to be solved.To solve the above-mentioned problems, the embodiment of the present application provides one
The abnormal order processing system of kind and method.
A kind of abnormal order processing system provided by the embodiments of the present application is introduced first below.
As shown in Figure 1, Fig. 1 is a kind of the embodiment of the present application abnormal order processing system shown according to an exemplary embodiment
The block diagram of system, the system may include: that machine sentences duty module 110, complaint module 120 and manually sentences duty module 130, wherein
Machine sentence duty module 110, for according to it is preset sentence duty model and target exception order order information, to the mesh
It marks abnormal order and carries out duty goal, obtain machine and sentence duty result；
In the embodiment of the present application, sentencing duty model is based on the history exception order that correct confirmation of responsibility is largely completed
Generate LR (Logistic Regression, logistic regression) model, wherein LR model is a kind of nonlinear regression model (NLRM), is to work as
A kind of preceding more commonly used machine learning method in the industry, a possibility that for estimating certain things, LR model is one by multiple
The probability function that feature and the corresponding weighted value of each feature are constituted.
In the embodiment of the present application, target exception order includes but is not limited to following kind of order: abnormal trip order, different
Often take out other types of abnormal order etc. in order and O2O service system, wherein abnormal trip order may include: by
The trip order of cancellation and complained trip order, taking out abnormal order may include: complained take-away order.
In the embodiment of the present application, it is the responsibility or bill of order user that confirmation of responsibility, which refers to that judgement leads to order extremely,
The responsibility of user, in the case where scene is called a taxi in calling, order user refers to that driver, bill user refer to passenger；It is dispensed taking out
Under scene, order user refers to taking out dispatching person, and bill user refers to the customer to order.
In the embodiment of the present application, when target exception order is the trip order being cancelled, the duty model of sentencing of use is base
LR (Logistic is generated in history that correct confirmation of responsibility is largely completed, being cancelled trip order
Regression, logistic regression) model, and sentence duty model using this and judge that the cancellation behavior of order is the responsibility of driver or multiplies
The responsibility of visitor；Wherein, it may include: to obtain largely to be completed correctly that is used under the scene, which sentences the generating process of duty model,
Confirmation of responsibility, the history that is cancelled trip order；The characteristic information of aforementioned history trip order is extracted, this feature information includes
But be not limited to following information: time of received orders, cancellation of order time, the longitude and latitude of order track, order user are with bill user's
History Order cancellation record, the distance of worksheet processing, order user are connected to the time of bill user, order estimated distance length, order
Starting point and the characteristic informations such as destination geographical location and order scheduled time length；Logistic regression LR algorithm pair is used later
The aforementioned characteristic information extracted is trained, and obtains sentencing duty model.
In the embodiment of the present application, when target exception order is complained trip order, the duty model of sentencing of use is base
In history trip order generation LR (Logistic that correct confirmation of responsibility is largely completed, complained
Regression, logistic regression) model, and sentence duty model using this and judge that the complaint behavior of order is the responsibility of driver or multiplies
The responsibility of visitor；Wherein, it may include: to obtain largely to be completed correctly that is used under the scene, which sentences the generating process of duty model,
Confirmation of responsibility, complained history trip order；The characteristic information of aforementioned history trip order is extracted, this feature information includes
But be not limited to following information: time of received orders, order complain time, the longitude and latitude of order track, order user and bill user
History Order complains record, the distance of worksheet processing, order user to be connected to the time of bill user, order estimated distance length, order
Starting point and the characteristic informations such as destination geographical location and order scheduled time length；Logistic regression LR algorithm pair is used later
The aforementioned characteristic information extracted is trained, and obtains sentencing duty model.
In the embodiment of the present application, when target exception order is complained take-away order, the duty model of sentencing of use is base
In history take-away order generation LR (Logistic that correct confirmation of responsibility is largely completed, complained
Regression, logistic regression) model, and sentence duty model using this and judge that the complaint behavior of order is to take out the responsibility of dispatching person
Still the responsibility of the customer to order；Wherein, it may include: to obtain largely that is used under the scene, which sentences the generating process of duty model,
Correct confirmation of responsibility, complained history take-away order is completed；The characteristic information that aforementioned history takes out order is extracted, it should
Characteristic information includes but is not limited to following information: time of received orders, the longitude and latitude of order track, order user go through with bill user's
History order complains record, the distance of worksheet processing, order user to be connected to the time of bill user, the estimated distance length of order, order
Begin ground and the characteristic informations such as destination geographical location and order scheduled time length；Later using logistic regression LR algorithm to preceding
It states the characteristic information extracted to be trained, obtains sentencing duty model.
It should be noted that the input for sentencing duty model is the order information of target exception order in the embodiment of the present application, sentence
The output of model is blamed the result is that a probability value, the value range of the probability value is 0~1, can according to the value of probability value come
Judgement causes the reason of target exception order exception to be the responsibility of order user or the responsibility of bill user；Wherein, probability value
Value closer to 0, the cancellation behavior of target order is more likely to be the responsibility of order user, and the value of probability value is closer
In 1, the cancellation behavior of target order is more likely to be the responsibility of bill user.By taking the trip order being cancelled as an example, probability value
Value closer to 0, the cancellation behavior of target order is more likely to be the responsibility of driver, the value of probability value closer to 1,
The cancellation behavior of target order is more likely to be the responsibility of passenger.
Module 120 is appealed, sentences the Shen that duty result is made for the machine that machine sentences the duty generation of module 110 for receiving user
Appeal is asked, and complaint request is issued to and manually sentences duty module 130；
In the embodiment of the present application, after making machine and sentencing duty, order user and bill user can sentence duty result to machine
Trust or not mistrustful selection are made, when distrusting machine to sentence duty result, can be appealed.
In the embodiment of the present application, when order user or bill user's machine sentence duty result it is wrong when, order user and Fa
Single user has feedback to export, that is, appeals.
In the embodiment of the present application, software complaint interface can be provided, phone complaint interface can also be provided, can also be provided
Short message appeals interface, wherein software complaint interface can be provided by the client software of O2O, such as net about vehicle client software
User interface on a complaint icon or button, user are provided click the icon or button, that is, can trigger complaint and request.
Manually sentence duty module 130, for receives complaint module 120 issue complaint request, and according to the complaint request and
Machine sentences the machine that duty module 110 generates and sentences duty result to target exception order progress duty goal, is manually sentenced duty result.
In the embodiment of the present application, after the complaint for receiving order user or bill user is requested, customer service be will do it manually
Intervention is taken in duty result, the order information of target exception order and the complaint of user request specifically, customer service can be sentenced according to machine
The content of band makes final confirmation of responsibility.
In the embodiment of the present application, correct confirmation of responsibility is carried out to target exception order, helps to maintain O2O service system
Normal work, increase order user and bill user to the trust of service system, at the same also contribute to comprising order user or
The equity of bill user.
As seen from the above-described embodiment, which can establish a closed loop system for being handled abnormal order
System, the system can carry out abnormal order in conjunction with sentencing duty model, order user or the complaint of bill user and manually sentencing duty
Reasonable duty goal, to reduce to order user or bill user's bring trouble.
As shown in Fig. 2, Fig. 2 is the embodiment of the present application another abnormal order processing shown according to an exemplary embodiment
The block diagram of system in the embodiment of the present application, can be autonomously generated and sentence duty model, at this point, the system may include: to sentence duty model instruction
Practice module 200, machine sentences duty module 210, appeal module 220 and manually sentences duty module 230, wherein
Sentence duty model training module 200, it is different from multiple history for obtaining the order information of multiple history exception orders
Respective characteristic information is extracted in the order information of normal order, using logistic regression LR algorithm to the feature of the history exception order
Information is trained, and obtains sentencing duty model, and this is sentenced duty model is supplied to machine and sentence duty module 210.
In the embodiment of the present application, order information may include order after the demand information of bill user publication, order publication
Behavioural information and order user and the historical behavior information of bill user of user and bill user etc..
By taking target exception order is the trip order being cancelled as an example, the order information of target exception order may include multiplying
The behavioural information of driver and passenger and the history travel behaviour of driver and passenger after the trip requirements information of visitor's publication, order are issued
Information specifically may include: time of received orders, cancellation of order time, the longitude and latitude of order track, order user and bill user
History Order cancel record, the distance of worksheet processing, order user are connected to the time of bill user, order is it is expected that distance length, order
Single starting point and the characteristic informations such as destination geographical location and order scheduled time length, wherein the trip order being cancelled can
Being cancelled by order user, it is also possible to be cancelled by bill user, wherein order user refers to driver, and bill is used
Family refers to passenger.
By taking the take-away order that target exception order is complained as an example, the order information of target exception order may include a little
The ordering and dispense of customer's publication of meal takes out dispatching person and the customer behavior information ordered and outside after demand information, order publication
The historical behavior information of customer selling dispatching person and ordering, specifically may include: time of received orders, order track longitude and latitude,
The History Order of order user and bill user complain record, at a distance from worksheet processing, order user is connected to the time of bill user, orders
Single estimated distance length, order starting point and the characteristic informations such as destination geographical location and order scheduled time length, wherein
Order user refers to that take-away dispatching person, bill user refer to the customer to order.
Machine sentence duty module 210, for according to it is preset sentence duty model and target exception order order information, to the mesh
It marks abnormal order and carries out duty goal, obtain machine and sentence duty result；
Module 220 is appealed, sentences the Shen that duty result is made for the machine that machine sentences the duty generation of module 210 for receiving user
Appeal is asked, and complaint request is issued to and manually sentences duty module 230；
Manually sentence duty module 230, for receives complaint module 220 issue complaint request, and according to the complaint request and
Machine sentences the machine that duty module 210 generates and sentences duty result to target exception order progress duty goal, is manually sentenced duty result.
Machine in the embodiment of the present application sentences duty module 210, complaint module 220 and manually sentences duty module 230, with Fig. 1 institute
Show the machine in embodiment sentence duty module 110, complaint module 120 and manually sentence duty module 130 it is similar, the embodiment of the present application is to this
It repeats no more, detail as per the content in embodiment illustrated in fig. 1.
As seen from the above-described embodiment, which can establish a closed loop system for being handled abnormal order
System, which, which can be generated, independently sentences duty model, and sentences duty model, order user or the complaint of bill user and artificial in conjunction with this
Sentence duty, reasonable duty goal is carried out to abnormal order, to reduce to order user or bill user's bring trouble.
In another kind embodiment provided by the embodiments of the present application, on the basis of which can be with embodiment shown in Fig. 2,
Duty model training module 200 is sentenced in the embodiment of the present application, be can be also used for receiving and is manually sentenced manually sentencing for the duty generation of module 230
Duty as a result, and according to this manually sentence duty result and target exception order order information correct sentence duty model.
In the embodiment of the present application, it is contemplated that the accuracy rate for manually sentencing duty result is relatively high, is good data resource, because
This, and duty result will can be manually sentenced as the training data for sentencing duty model training module, it is modified to duty model is sentenced, constantly
It improves and sentences duty model and sentence duty accuracy rate.
As shown in figure 3, Fig. 3 is the embodiment of the present application another abnormal order processing shown according to an exemplary embodiment
The block diagram of system, it is contemplated that in actual O2O service system, abnormal order, such as order are cancelled and can cause under probability of transaction
Drop, order is complained to cause service point to reduce, and then influences the subsequent reward of order user and provide, therefore in order to safeguard
The equity of order user, at this point, the system may include: that machine sentences duty module 310, complaint module 320, manually sentences duty module
330 and user property correction module 340, wherein
Machine sentence duty module 310, for according to it is preset sentence duty model and target exception order order information, to the mesh
It marks abnormal order and carries out duty goal, obtain machine and sentence duty result；
Module 320 is appealed, sentences the Shen that duty result is made for the machine that machine sentences the duty generation of module 310 for receiving user
Appeal is asked, and complaint request is issued to and manually sentences duty module 330；
Manually sentence duty module 330, for receives complaint module 320 issue complaint request, and according to the complaint request and
Machine sentences the machine that duty module 310 generates and sentences duty result to target exception order progress duty goal, is manually sentenced duty result.
Machine in the embodiment of the present application sentences duty module 310, complaint module 320 and manually sentences duty module 330, with Fig. 1 institute
Show the machine in embodiment sentence duty module 110, complaint module 120 and manually sentence duty module 130 it is similar, the embodiment of the present application is to this
It repeats no more, detail as per the content in embodiment illustrated in fig. 1.
User property correction module 340, for receive manually sentence that duty module 330 generates manually sentence duty as a result, simultaneously basis
This manually sentence duty as a result, amendment target exception order association user attribute, wherein the attribute include: service point, and/or
Probability of transaction.
In the embodiment of the present application, the association user of target exception order may include: the order user of target exception order
Order user is generally referred in practical application scene with bill user.
By taking scene is called a taxi in calling as an example, it is directed to the case where order is cancelled, if manually sentencing duty result is driver without duty
Appoint, then return to former probability of transaction when the order probability of transaction of driver reduces, former service point etc. is returned to when service point reduces, to tie up
Protect the just rights and interests of proper driver.
As shown in figure 4, Fig. 4 is the embodiment of the present application another abnormal order processing shown according to an exemplary embodiment
The block diagram of system, on the basis of which can be with embodiment shown in Fig. 1, the embodiment of the present application can be according to complaint request
Type determines the transmitting sequence of complaint request, the Shen to guarantee the processing timeliness of all kinds of complaint requests, in the embodiment of the present application
It tells module 120, may include: to appeal request receiving submodule 121, request type determines submodule 122 and appeal request to issue
Submodule 123, wherein
Request receiving submodule 121 is appealed, sentences duty knot for receiving the machine that user sentences the duty generation of module 110 for machine
The complaint request that fruit is made；
Request type determines submodule 122, for determining the type of complaint request；
In the embodiment of the present application, the type for appealing request may include: the complaint carried out by client software, pass through electricity
The complaint talking about the complaint carried out and being carried out by short message.
Complaint request issues submodule 123, for issuing priority according to preset complaint request type and complaint request
Corresponding relationship, will appeal request receiving submodule 121 receive complaint request be issued to manually sentence duty module 130.
In view of in practical application, complaint module usually will receive a large amount of complaint request in a short time, come sometimes not
And each complaint received request is all issued in time and manually sentences duty module, and in view of the time limit of phone complaint is compared to it
The complaint of his type is usually relatively more urgent, therefore, it is contemplated that being preferentially issued to phone complaint artificial in the embodiment of the present application
Sentence duty module.
System embodiment described above is only schematical, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules realize the purpose of the embodiment of the present application scheme.Those of ordinary skill in the art are not paying wound
In the case that the property made is worked, it can understand and implement.
Corresponding with the aforementioned abnormal embodiment of order processing system, the embodiment of the present application also provides abnormal order processing sides
The embodiment of method.
As shown in figure 5, Fig. 5 is a kind of the embodiment of the present application abnormal order processing side shown according to an exemplary embodiment
The flow chart of method, this method may comprise steps of:
In step 501, machine sentences duty module when receiving target exception order, sentences duty model and mesh according to preset
The order information for marking abnormal order carries out duty goal to target exception order, obtains machine and sentence duty result.
In the embodiment of the present application, sentencing duty model is based on the history exception order that correct confirmation of responsibility is largely completed
Generate LR (Logistic Regression, logistic regression) model, wherein LR model is a kind of nonlinear regression model (NLRM), is to work as
A kind of preceding more commonly used machine learning method in the industry, a possibility that for estimating certain things, LR model is one by multiple
The probability function that feature and the corresponding weighted value of each feature are constituted.
In the embodiment of the present application, target exception order includes but is not limited to following kind of order: abnormal trip order, different
Often take out other types of abnormal order etc. in order and O2O service system, wherein abnormal trip order may include: by
The trip order of cancellation and complained trip order, taking out abnormal order may include: complained take-away order.
In the embodiment of the present application, it is the responsibility or bill of order user that confirmation of responsibility, which refers to that judgement leads to order extremely,
The responsibility of user, in the case where scene is called a taxi in calling, order user refers to that driver, bill user refer to passenger；It is dispensed taking out
Under scene, order user refers to taking out dispatching person, and bill user refers to the customer to order.
In the embodiment of the present application, when target exception order is the trip order being cancelled, the duty model of sentencing of use is base
LR (Logistic is generated in history that correct confirmation of responsibility is largely completed, being cancelled trip order
Regression, logistic regression) model, and sentence duty model using this and judge that the cancellation behavior of order is the responsibility of driver or multiplies
The responsibility of visitor；Wherein, it may include: to obtain largely to be completed correctly that is used under the scene, which sentences the generating process of duty model,
Confirmation of responsibility, the history that is cancelled trip order；The characteristic information of aforementioned history trip order is extracted, this feature information includes
But be not limited to following information: time of received orders, cancellation of order time, the longitude and latitude of order track, order user are with bill user's
History Order cancellation record, the distance of worksheet processing, order user are connected to the time of bill user, order estimated distance length, order
Starting point and the characteristic informations such as destination geographical location and order scheduled time length；Logistic regression LR algorithm pair is used later
The aforementioned characteristic information extracted is trained, and obtains sentencing duty model.
In the embodiment of the present application, when target exception order is complained trip order, the duty model of sentencing of use is base
In history trip order generation LR (Logistic that correct confirmation of responsibility is largely completed, complained
Regression, logistic regression) model, and sentence duty model using this and judge that the complaint behavior of order is the responsibility of driver or multiplies
The responsibility of visitor；Wherein, it may include: to obtain largely to be completed correctly that is used under the scene, which sentences the generating process of duty model,
Confirmation of responsibility, complained history trip order；The characteristic information of aforementioned history trip order is extracted, this feature information includes
But be not limited to following information: time of received orders, order complain time, the longitude and latitude of order track, order user and bill user
History Order complains record, the distance of worksheet processing, order user to be connected to the time of bill user, order estimated distance length, order
Starting point and the characteristic informations such as destination geographical location and order scheduled time length；Logistic regression LR algorithm pair is used later
The aforementioned characteristic information extracted is trained, and obtains sentencing duty model.
In the embodiment of the present application, when target exception order is complained take-away order, the duty model of sentencing of use is base
In history take-away order generation LR (Logistic that correct confirmation of responsibility is largely completed, complained
Regression, logistic regression) model, and sentence duty model using this and judge that the complaint behavior of order is to take out the responsibility of dispatching person
Still the responsibility of the customer to order；Wherein, it may include: to obtain largely that is used under the scene, which sentences the generating process of duty model,
Correct confirmation of responsibility, complained history take-away order is completed；The characteristic information that aforementioned history takes out order is extracted, it should
Characteristic information includes but is not limited to following information: time of received orders, the longitude and latitude of order track, order user go through with bill user's
History order complains record, the distance of worksheet processing, order user to be connected to the time of bill user, the estimated distance length of order, order
Begin ground and the characteristic informations such as destination geographical location and order scheduled time length；Later using logistic regression LR algorithm to preceding
It states the characteristic information extracted to be trained, obtains sentencing duty model.
It should be noted that the input for sentencing duty model is the order information of target exception order in the embodiment of the present application, sentence
The output of model is blamed the result is that a probability value, the value range of the probability value is 0~1, can according to the value of probability value come
Judgement causes the reason of target exception order exception to be the responsibility of order user or the responsibility of bill user；Wherein, probability value
Value closer to 0, the cancellation behavior of target order is more likely to be the responsibility of order user, and the value of probability value is closer
In 1, the cancellation behavior of target order is more likely to be the responsibility of bill user.By taking the trip order being cancelled as an example, probability value
Value closer to 0, the cancellation behavior of target order is more likely to be the responsibility of driver, the value of probability value closer to 1,
The cancellation behavior of target order is more likely to be the responsibility of passenger.
In step 502, complaint module reception user sentences duty result for the machine that the machine sentences duty module generation and makes
Complaint request, and complaint request is issued to and manually sentences duty module.
In the embodiment of the present application, after making machine and sentencing duty, order user and bill user can sentence duty result to machine
Trust or not mistrustful selection are made, when distrusting machine to sentence duty result, can be appealed.
In the embodiment of the present application, when order user or bill user's machine sentence duty result it is wrong when, order user and Fa
Single user has feedback to export, that is, appeals.
In the embodiment of the present application, software complaint interface can be provided, phone complaint interface can also be provided, can also be provided
Short message appeals interface, wherein software complaint interface can be provided by the client software of O2O, such as net about vehicle client software
User interface on a complaint icon or button, user are provided click the icon or button, that is, can trigger complaint and request.
In step 503, manually sentence duty module receive complaint module issue complaint request, and according to the complaint request and
Machine sentences the machine that duty module generates and sentences duty result to target exception order progress duty goal, is manually sentenced duty result.
In the embodiment of the present application, after the complaint for receiving order user or bill user is requested, customer service be will do it manually
Intervention is taken in duty result, the order information of target exception order and the complaint of user request specifically, customer service can be sentenced according to machine
The content of band makes final confirmation of responsibility.
In the embodiment of the present application, correct confirmation of responsibility is carried out to target exception order, helps to maintain O2O service system
Normal work, increase order user and bill user to the trust of service system, at the same also contribute to comprising order user or
The equity of bill user.
As seen from the above-described embodiment, which can establish a closed loop system for being handled abnormal order
System, the system can carry out abnormal order in conjunction with sentencing duty model, order user or the complaint of bill user and manually sentencing duty
Reasonable duty goal, to reduce to order user or bill user's bring trouble.
As shown in fig. 6, Fig. 6 is the embodiment of the present application another abnormal order processing shown according to an exemplary embodiment
The flow chart of method in the embodiment of the present application, can be autonomously generated and sentence duty model, at this point, the exception in the embodiment of the present application is ordered
Uniprocesser system can also include: to sentence duty model training module, and this method may comprise steps of:
In step 600, sentences the order information that duty model training module obtains multiple history exception orders, gone through from multiple
Respective characteristic information is extracted in the order information of history exception order, using logistic regression LR algorithm to the history exception order
Characteristic information is trained, and obtains sentencing duty model, and this is sentenced duty model is supplied to machine and sentence duty module.
In the embodiment of the present application, order information may include order after the demand information of bill user publication, order publication
Behavioural information and order user and the historical behavior information of bill user of user and bill user etc..
By taking target exception order is the trip order being cancelled as an example, the order information of target exception order may include multiplying
The behavioural information of driver and passenger and the history travel behaviour of driver and passenger after the trip requirements information of visitor's publication, order are issued
Information specifically may include: time of received orders, cancellation of order time, the longitude and latitude of order track, order user and bill user
History Order cancel record, the distance of worksheet processing, order user are connected to the time of bill user, order is it is expected that distance length, order
Single starting point and the characteristic informations such as destination geographical location and order scheduled time length, wherein the trip order being cancelled can
Being cancelled by order user, it is also possible to be cancelled by bill user, wherein order user refers to driver, and bill is used
Family refers to passenger.
By taking the take-away order that target exception order is complained as an example, the order information of target exception order may include a little
The ordering and dispense of customer's publication of meal takes out dispatching person and the customer behavior information ordered and outside after demand information, order publication
The historical behavior information of customer selling dispatching person and ordering, specifically may include: time of received orders, order track longitude and latitude,
The History Order of order user and bill user complain record, at a distance from worksheet processing, order user is connected to the time of bill user, orders
Single estimated distance length, order starting point and the characteristic informations such as destination geographical location and order scheduled time length, wherein
Order user refers to that take-away dispatching person, bill user refer to the customer to order.
In step 601, machine sentences duty module when receiving target exception order, sentences duty model and mesh according to preset
The order information for marking abnormal order carries out duty goal to target exception order, obtains machine and sentence duty result.
In step 602, complaint module reception user sentences duty result for the machine that the machine sentences duty module generation and makes
Complaint request, and complaint request is issued to and manually sentences duty module；
In step 603, manually sentence duty module receive complaint module issue complaint request, and according to the complaint request and
Machine sentences the machine that duty module generates and sentences duty result to target exception order progress duty goal, is manually sentenced duty result.
Step 601, step 602 in the embodiment of the present application and the step 501 in step 603, with embodiment illustrated in fig. 5,
Step 502 and step 503 are similar, and the embodiment of the present application repeats no more this, detail as per the content in embodiment illustrated in fig. 5.
In step 604, sentence duty model training module receive manually sentence that duty module generates manually sentence duty as a result, simultaneously basis
This manually sentences duty result and duty model is sentenced in the order information amendment of target exception order.
In the embodiment of the present application, it is contemplated that the accuracy rate for manually sentencing duty result is relatively high, is good data resource, because
This, and duty result will can be manually sentenced as the training data for sentencing duty model training module, it is modified to duty model is sentenced, constantly
It improves and sentences duty model and sentence duty accuracy rate.
As seen from the above-described embodiment, which can establish a closed loop system for being handled abnormal order
System, which, which can be generated, independently sentences duty model, and sentences duty model, order user or the complaint of bill user and artificial in conjunction with this
Sentence duty, reasonable duty goal is carried out to abnormal order, to reduce to order user or bill user's bring trouble.
In view of in actual O2O service system, abnormal order, such as order are cancelled and probability of transaction can be caused to decline,
Order is complained to cause service point to reduce, and then influences the subsequent reward of order user and provide, therefore connect to safeguard
The equity of single user, at this point, the embodiment can be in Fig. 6 or Fig. 7 institute in another embodiment provided by the embodiments of the present application
On the basis of showing embodiment of the method, the abnormal order processing system in the embodiment of the present application can also include that user property corrects mould
Block, at this point, this method can also increase following steps:
User property correction module, for receive manually sentence that duty module generates manually sentence duty as a result, and according to this it is artificial
Duty is sentenced as a result, correcting the attribute of the association user of target exception order, wherein the attribute includes: service point, and/or probability of transaction.
In the embodiment of the present application, the association user of target exception order may include: the order user of target exception order
Order user is generally referred in practical application scene with bill user.
By taking scene is called a taxi in calling as an example, it is directed to the case where order is cancelled, if manually sentencing duty result is driver without duty
Appoint, then return to former probability of transaction when the order probability of transaction of driver reduces, former service point etc. is returned to when service point reduces, to tie up
Protect the just rights and interests of proper driver.
In another kind embodiment provided by the embodiments of the present application, which can be in the base of any of the above-described embodiment of the method
On plinth, the embodiment of the present application can determine the transmitting sequence of complaint request, according to the type of complaint request to guarantee all kinds of complaints
The processing timeliness of request, the complaint module in the embodiment of the present application may include: complaint request receiving submodule, request type
Determine that submodule and complaint request issue submodule；At this point, step 502 or step 602 in the embodiment of the present application, may include
S80, S81 and S82, in which:
In S80, complaint request receiving submodule receives the machine that user sentences duty module generation for machine and sentences duty result
The complaint request made.
In S81, request type determines that submodule determines the type of complaint request；
In the embodiment of the present application, the type for appealing request may include: the complaint carried out by client software, pass through electricity
The complaint talking about the complaint carried out and being carried out by short message.
In S82, complaint request issues submodule and issues priority according to preset complaint request type and complaint request
Corresponding relationship, request receiving submodule received complaint request will be appealed and be issued to and manually sentence duty module.
In view of in practical application, complaint module usually will receive a large amount of complaint request in a short time, come sometimes not
And each complaint received request is all issued in time and manually sentences duty module, and in view of the time limit of phone complaint is compared to it
The complaint of his type is usually relatively more urgent, therefore, it is contemplated that being preferentially issued to phone complaint artificial in the embodiment of the present application
Sentence duty module.
For embodiment of the method, since it corresponds essentially to system embodiment, so related place is referring to method reality
Apply the part explanation of example.It should be noted that although describing the behaviour of the embodiment of the present application method in the accompanying drawings with particular order
Make, still, this does not require that or implies must execute these operations in this particular order, or have to carry out whole institutes
The operation shown just is able to achieve desired result.On the contrary, the step of describing in flow chart can change and execute sequence.It is additionally or standby
Selection of land, it is convenient to omit multiple steps are merged into step and executed by certain steps, and/or a step are decomposed into multiple
Step executes.
The realization process that step is corresponded in the above method is specifically detailed in the function of modules and effect in above system
Realization process, details are not described herein for the embodiment of the present application.
The embodiment of the present application also provides a kind of computer storage medium, it is stored with program instruction in the storage medium,
Described program instruction includes: that machine sentences duty module when receiving target exception order, sentences duty model and target according to preset
The order information of abnormal order carries out duty goal to the target exception order, obtains machine and sentence duty result；Complaint module connects
Receive user for the machine sentence duty module generate machine sentence duty result make complaint request, and will the complaint request under
It is sent to and described manually sentences duty module；Manually sentence duty module and receive the complaint request that the complaint module issues, and according to the Shen
Appeal is asked and the machine sentences the machine that duty module generates and sentences duty result to target exception order progress duty goal, is obtained
Manually sentence duty result.
It is (including but unlimited that the storage medium for wherein including program code in one or more can be used in the embodiment of the present application
In magnetic disk storage, CD-ROM, optical memory etc.) on the form of computer program product implemented.Computer can use storage
Medium includes permanent and non-permanent, removable and non-removable media, can be accomplished by any method or technique information
Storage.Information can be computer readable instructions, data structure, the module of program or other data.The storage medium of computer
Example include but is not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory
(DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electrically 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-biography
Defeated medium, can be used for storage can be accessed by a computing device information.
As shown in fig. 7, Fig. 7 is that the embodiment of the present application one kind shown according to an exemplary embodiment is used at abnormal order
One structural schematic diagram of reason system 700.For example, device 700 may be provided as a server.Referring to Fig. 7, device 700 includes
Processing component 722 further comprises one or more processors, and the memory resource as representated by memory 732, is used
It can be by the instruction of the execution of processing component 722, such as application program in storage.The application program stored in memory 732 can be with
Including it is one or more each correspond to one group of instruction module.Refer in addition, processing component 722 is configured as executing
It enables, to execute abnormal order processing method provided by the embodiments of the present application, this method comprises: machine, which sentences duty module, is receiving mesh
When marking abnormal order, according to the preset order information for sentencing duty model and target exception order, to the target exception order into
Row duty goal obtains machine and sentences duty result；Complaint module receives the machine that user sentences duty module generation for the machine and sentences
The complaint request that duty result is made, and complaint request is issued to and described artificial sentences duty module；Manually sentence duty module to receive
The complaint request that the complaint module issues, and the machine that duty module generates is sentenced according to the complaint request and the machine and sentences duty
As a result duty goal is carried out to the target exception order, is manually sentenced duty result.
Device 700 can also include the power management that a power supply module 726 is configured as executive device 700, and one has
Line or radio network interface 750 are configured as device 700 being connected to network and input and output (I/O) interface 758.Dress
Setting 700 can operate based on the operating system for being stored in memory 732, such as Windows ServerTM, Mac OS XTM,
UnixTM, LinuxTM, FreeBSDTM or similar.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory 732 of instruction, above-metioned instruction can be executed by the processing component 722 of device 700 to complete the embodiment of the present application
The above-mentioned abnormal order processing method provided.For example, the non-transitorycomputer readable storage medium can be ROM, random
Access memory (RAM), CD-ROM, tape, floppy disk and optical data storage devices etc..
Those skilled in the art will readily occur to the application implementation after considering specification and practicing disclosure disclosed herein
Other embodiments of example.Any modification, purposes or the adaptability that the embodiment of the present application is intended to cover the embodiment of the present application become
Change, these variations, uses, or adaptations follow the general principle of the application and are not disclosed including the embodiment of the present application
Common knowledge or conventional techniques in the art.The description and examples are only to be considered as illustrative, the application
The true scope and spirit of embodiment are indicated by the following claims.
It should be understood that the embodiment of the present application is not limited to the accurate knot for being described above and being shown in the accompanying drawings
Structure, and various modifications and changes may be made without departing from the scope thereof.The range of the embodiment of the present application is only by appended right
It is required that limit.
Claims (13)
1. a kind of exception order processing system, which is characterized in that the system comprises:
Machine sentences duty module, complaint module and manually sentences duty module, wherein
The machine sentences duty module, for according to it is preset sentence duty model and target exception order order information, to the mesh
It marks abnormal order and carries out duty goal, obtain machine and sentence duty result；
The complaint module sentences the complaint that duty result is made for the machine that the machine sentences duty module generation for receiving user
Request, and complaint request is issued to and described artificial sentences duty module；
It is described manually to sentence duty module, for receive it is described complaint module issue complaint request, and according to the complaint request and
The machine sentences the machine that duty module generates and sentences duty result to target exception order progress duty goal, is manually sentenced duty
As a result.
2. system according to claim 1, which is characterized in that the system also includes:
Sentence duty model training module, for obtaining the order information of multiple history exception orders, is ordered extremely from the multiple history
Respective characteristic information is extracted in single order information, is believed using feature of the logistic regression LR algorithm to the history exception order
Breath is trained, and obtains sentencing duty model, and by it is described sentence duty model and be supplied to the machine sentence duty module.
3. system according to claim 2, which is characterized in that it is described to sentence duty model training module, it is also used to receive described
That manually sentences duty module generation manually sentences duty as a result, and according to the order for manually sentencing duty result and the target exception order
Duty model is sentenced described in Information revision.
4. system according to claim 1, which is characterized in that the system also includes:
User property correction module, for receive it is described manually sentence duty module generate manually sentence duty as a result, and according to the people
Work sentence duty as a result, correcting the attribute of the association user of the target exception order, wherein the attribute include: service point and/
Or probability of transaction.
5. system according to claim 1, which is characterized in that the complaint module, comprising:
Appeal request receiving submodule, for receive user for the machine sentence duty module generate machine sentence duty result make
Complaint request；
Request type determines submodule, for determining the type of the complaint request；
Complaint request issues submodule, for issuing the corresponding pass of priority with complaint request according to preset complaint request type
Complaint request is issued to and described artificial sentences duty module by system.
6. system according to claim 1, which is characterized in that the output for sentencing duty model the result is that a probability value,
The value range of the probability value is 0~1, is judged that the reason of target exception order exception is caused to be to connect according to the value of probability value
The responsibility of single user or the responsibility of bill user；Wherein, the value of probability value is closer to 0, the cancellation behavior of target order
It is more likely to be the responsibility of order user, for the value of probability value closer to 1, the cancellation behavior of target order is more likely to be hair
The responsibility of single user.
7. a kind of exception order processing method, which is characterized in that the method is based on abnormal order processing described in claim 1
System, comprising:
Machine sentences duty module when receiving target exception order, according to the preset order for sentencing duty model and target exception order
Information carries out duty goal to the target exception order, obtains machine and sentence duty result；
Complaint module receives user and sentences the complaint request that duty result is made for the machine that the machine sentences duty module generation, and will
Complaint request, which is issued to, described manually sentences duty module；
Manually sentence duty module and receive the complaint request that the complaint module issues, and is sentenced according to complaint request and the machine
The machine that duty module generates sentences duty result and carries out duty goal to the target exception order, is manually sentenced duty result.
8. the method according to the description of claim 7 is characterized in that the exception order processing system further includes sentencing duty model instruction
Practice module, the method also includes:
The order information that duty model training module obtains multiple history exception orders is sentenced, from ordering for the multiple history exception order
Respective characteristic information is extracted in single information, is carried out using characteristic information of the logistic regression LR algorithm to the history exception order
Training, obtains sentencing duty model, and by it is described sentence duty model and be supplied to the machine sentence duty module.
9. according to the method described in claim 8, it is characterized in that, the method also includes:
Sentence duty model training module receive it is described manually sentence that duty module generates manually sentence duty as a result, and manually sentencing duty according to described
As a result and described in the amendment of the order information of the target exception order sentence duty model.
10. the method according to the description of claim 7 is characterized in that the exception order processing system further includes user property
Correction module, the method also includes:
User property correction module, for receive it is described manually sentence duty module generate manually sentence duty as a result, and according to the people
Work sentence duty as a result, correcting the attribute of the association user of the target exception order, wherein the attribute include: service point and/
Or probability of transaction.
11. the method according to the description of claim 7 is characterized in that the complaint module includes: that complaint request receives submodule
Block, request type determine that submodule and complaint request issue submodule；
The complaint module receives user and sentences the complaint request that duty result is made for the machine that the machine sentences duty module generation,
And complaint request is issued to and described manually sentences duty module, comprising:
Complaint request receiving submodule receives user and sentences the Shen that duty result is made for the machine that the machine sentences duty module generation
Appeal is asked；
Request type determines that submodule determines the type of the complaint request；
Complaint request issues the corresponding relationship that submodule issues priority according to preset complaint request type and complaint request, will
Complaint request, which is issued to, described manually sentences duty module.
12. the method according to the description of claim 7 is characterized in that the output for sentencing duty model is the result is that a probability value,
The value range of the probability value is 0~1, is judged that the reason of target exception order exception is caused to be to connect according to the value of probability value
The responsibility of single user or the responsibility of bill user；Wherein, the value of probability value is closer to 0, the cancellation behavior of target order
It is more likely to be the responsibility of order user, for the value of probability value closer to 1, the cancellation behavior of target order is more likely to be hair
The responsibility of single user.
13. a kind of computer storage medium, which is characterized in that be stored with program instruction in the storage medium, described program refers to
Order includes:
Machine sentences duty module when receiving target exception order, according to the preset order for sentencing duty model and target exception order
Information carries out duty goal to the target exception order, obtains machine and sentence duty result；
Complaint module receives user and sentences the complaint request that duty result is made for the machine that the machine sentences duty module generation, and will
Complaint request, which is issued to, described manually sentences duty module；
Manually sentence duty module and receive the complaint request that the complaint module issues, and is sentenced according to complaint request and the machine
The machine that duty module generates sentences duty result and carries out duty goal to the target exception order, is manually sentenced duty result.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710322027.6A CN109409970A (en) | 2017-05-09 | 2017-05-09 | Abnormal order processing system and method |
| PCT/CN2017/113573 WO2018205561A1 (en) | 2017-05-09 | 2017-11-29 | Systems and methods for processing an abnormal order |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710322027.6A CN109409970A (en) | 2017-05-09 | 2017-05-09 | Abnormal order processing system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109409970A true CN109409970A (en) | 2019-03-01 |
Family
ID=65453937
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710322027.6A Pending CN109409970A (en) | 2017-05-09 | 2017-05-09 | Abnormal order processing system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109409970A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110363419A (en) * | 2019-07-10 | 2019-10-22 | 拉扎斯网络科技（上海）有限公司 | Task data processing method and device, electronic equipment and medium |
| CN110363544A (en) * | 2019-07-18 | 2019-10-22 | 拉扎斯网络科技（上海）有限公司 | Event-handling method, device, electronic equipment and storage medium |
| CN110784435A (en) * | 2019-04-15 | 2020-02-11 | 北京嘀嘀无限科技发展有限公司 | Abnormal service identification method and device, electronic equipment and storage medium |
| CN111028053A (en) * | 2019-12-03 | 2020-04-17 | 北京嘀嘀无限科技发展有限公司 | Order processing method and device, electronic equipment and storage medium |
| CN111489170A (en) * | 2020-05-15 | 2020-08-04 | 支付宝(杭州)信息技术有限公司 | Processing method, device and equipment for refusal payment information |
| CN111488236A (en) * | 2020-04-16 | 2020-08-04 | 北京思特奇信息技术股份有限公司 | Order abnormity processing method, server, storage medium and processing device |
| CN111612402A (en) * | 2020-06-11 | 2020-09-01 | 上海乾臻信息科技有限公司 | Automatic arbitration method and device |
| CN111833137A (en) * | 2020-01-14 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Order processing method, order processing device, computer equipment and storage medium |
| CN111833074A (en) * | 2020-01-06 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Dispute responsibility confirmation method and device for network appointment vehicle and computer readable storage medium |
| CN111832852A (en) * | 2019-04-15 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Order information processing method and device, computer equipment and storage medium |
| CN111860927A (en) * | 2019-12-20 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Model training method, service request processing method, device, equipment and medium |
| CN111861501A (en) * | 2019-12-16 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Complaint processing method, complaint processing system, computer device, and storage medium |
| CN111862601A (en) * | 2020-06-23 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Freight vehicle navigation method and device, electronic equipment and storage medium |
| CN111861074A (en) * | 2019-04-30 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Behavior responsibility determination method and device |
| CN112053087A (en) * | 2020-09-22 | 2020-12-08 | 北京嘀嘀无限科技发展有限公司 | Complaint work order processing method, device, equipment and storage medium |
| CN112837119A (en) * | 2021-01-28 | 2021-05-25 | 天津五八到家货运服务有限公司 | Abnormal order identification method and device, electronic equipment and storage medium |
| CN112837013A (en) * | 2021-02-02 | 2021-05-25 | 拉扎斯网络科技（上海）有限公司 | Service processing method, device and equipment |
| CN113034158A (en) * | 2021-03-19 | 2021-06-25 | 北京嘀嘀无限科技发展有限公司 | Machine responsibility judgment method and device, electronic equipment and readable storage medium |
| CN113077114A (en) * | 2020-01-03 | 2021-07-06 | 北京三快在线科技有限公司 | Method and device for monitoring operation of distributor, storage medium and electronic equipment |
| CN113313553A (en) * | 2021-06-03 | 2021-08-27 | 首约科技(北京)有限公司 | Automatic processing method for order complaints |
| CN118037407A (en) * | 2024-04-12 | 2024-05-14 | 浙江口碑网络技术有限公司 | Interaction method, interaction device, interaction system, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101730118A (en) * | 2008-10-31 | 2010-06-09 | 中国移动通信集团广西有限公司 | Method and device for monitoring customer complaints |
| CN102496130A (en) * | 2011-11-15 | 2012-06-13 | 王家庆 | Real-time mobile business system of high efficiency operation taxi |
| CN105701580A (en) * | 2016-04-19 | 2016-06-22 | 重庆喜玛拉雅科技有限公司 | Automobile resource sharing system |
| CN107133645A (en) * | 2017-05-03 | 2017-09-05 | 百度在线网络技术（北京）有限公司 | Passenger is estimated to cancel an order method, equipment and the storage medium of behavior |
-
2017
- 2017-05-09 CN CN201710322027.6A patent/CN109409970A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101730118A (en) * | 2008-10-31 | 2010-06-09 | 中国移动通信集团广西有限公司 | Method and device for monitoring customer complaints |
| CN102496130A (en) * | 2011-11-15 | 2012-06-13 | 王家庆 | Real-time mobile business system of high efficiency operation taxi |
| CN105701580A (en) * | 2016-04-19 | 2016-06-22 | 重庆喜玛拉雅科技有限公司 | Automobile resource sharing system |
| CN107133645A (en) * | 2017-05-03 | 2017-09-05 | 百度在线网络技术（北京）有限公司 | Passenger is estimated to cancel an order method, equipment and the storage medium of behavior |
Non-Patent Citations (1)
| Title |
|---|
| 叶杰平: ""拆解滴滴大脑，谈出行领域算法技术"", 《中国信息化周报》 * |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111832852A (en) * | 2019-04-15 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Order information processing method and device, computer equipment and storage medium |
| CN110784435A (en) * | 2019-04-15 | 2020-02-11 | 北京嘀嘀无限科技发展有限公司 | Abnormal service identification method and device, electronic equipment and storage medium |
| CN111832852B (en) * | 2019-04-15 | 2024-04-26 | 北京嘀嘀无限科技发展有限公司 | Order information processing method, device, computer equipment and storage medium |
| CN111861074A (en) * | 2019-04-30 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Behavior responsibility determination method and device |
| CN110363419A (en) * | 2019-07-10 | 2019-10-22 | 拉扎斯网络科技（上海）有限公司 | Task data processing method and device, electronic equipment and medium |
| CN110363544A (en) * | 2019-07-18 | 2019-10-22 | 拉扎斯网络科技（上海）有限公司 | Event-handling method, device, electronic equipment and storage medium |
| CN111028053A (en) * | 2019-12-03 | 2020-04-17 | 北京嘀嘀无限科技发展有限公司 | Order processing method and device, electronic equipment and storage medium |
| WO2021121169A1 (en) * | 2019-12-16 | 2021-06-24 | 北京嘀嘀无限科技发展有限公司 | Complaint handling method, handling system, computer apparatus, and storage medium |
| CN111861501A (en) * | 2019-12-16 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Complaint processing method, complaint processing system, computer device, and storage medium |
| CN111860927B (en) * | 2019-12-20 | 2024-06-14 | 北京嘀嘀无限科技发展有限公司 | Model training method, service request processing method, device, equipment and medium |
| CN111860927A (en) * | 2019-12-20 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Model training method, service request processing method, device, equipment and medium |
| CN113077114A (en) * | 2020-01-03 | 2021-07-06 | 北京三快在线科技有限公司 | Method and device for monitoring operation of distributor, storage medium and electronic equipment |
| CN111833074A (en) * | 2020-01-06 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Dispute responsibility confirmation method and device for network appointment vehicle and computer readable storage medium |
| CN111833137A (en) * | 2020-01-14 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Order processing method, order processing device, computer equipment and storage medium |
| CN111488236A (en) * | 2020-04-16 | 2020-08-04 | 北京思特奇信息技术股份有限公司 | Order abnormity processing method, server, storage medium and processing device |
| CN111488236B (en) * | 2020-04-16 | 2023-09-05 | 北京思特奇信息技术股份有限公司 | Order exception processing method, server, storage medium and processing device |
| CN111489170A (en) * | 2020-05-15 | 2020-08-04 | 支付宝(杭州)信息技术有限公司 | Processing method, device and equipment for refusal payment information |
| CN111612402A (en) * | 2020-06-11 | 2020-09-01 | 上海乾臻信息科技有限公司 | Automatic arbitration method and device |
| CN111612402B (en) * | 2020-06-11 | 2023-08-18 | 上海乾臻信息科技有限公司 | Automatic arbitration method and device |
| CN111862601A (en) * | 2020-06-23 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Freight vehicle navigation method and device, electronic equipment and storage medium |
| CN112053087A (en) * | 2020-09-22 | 2020-12-08 | 北京嘀嘀无限科技发展有限公司 | Complaint work order processing method, device, equipment and storage medium |
| CN112053087B (en) * | 2020-09-22 | 2024-04-26 | 北京嘀嘀无限科技发展有限公司 | Complaint work order processing method, device, equipment and storage medium |
| CN112837119A (en) * | 2021-01-28 | 2021-05-25 | 天津五八到家货运服务有限公司 | Abnormal order identification method and device, electronic equipment and storage medium |
| CN112837013B (en) * | 2021-02-02 | 2023-08-11 | 拉扎斯网络科技（上海）有限公司 | Service processing method, device and equipment |
| CN112837013A (en) * | 2021-02-02 | 2021-05-25 | 拉扎斯网络科技（上海）有限公司 | Service processing method, device and equipment |
| CN113034158A (en) * | 2021-03-19 | 2021-06-25 | 北京嘀嘀无限科技发展有限公司 | Machine responsibility judgment method and device, electronic equipment and readable storage medium |
| CN113313553A (en) * | 2021-06-03 | 2021-08-27 | 首约科技(北京)有限公司 | Automatic processing method for order complaints |
| CN118037407A (en) * | 2024-04-12 | 2024-05-14 | 浙江口碑网络技术有限公司 | Interaction method, interaction device, interaction system, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109409970A (en) | Abnormal order processing system and method | |
| US20180053127A1 (en) | Project and resource planning methods and systems | |
| US11816620B2 (en) | Plan modeling visualization | |
| CN109409971A (en) | Abnormal order processing method and device | |
| DE112016002381T5 (en) | Improve functionality of virtual assistants and dialog systems through a plug-in marketplace | |
| US9454732B1 (en) | Adaptive machine learning platform | |
| US20130283211A1 (en) | Dynamic location-aware coordination method and system | |
| US20200226519A1 (en) | System and method for managing resources in a worksite | |
| CN104956330A (en) | Workload distribution with resource awareness | |
| Ponte et al. | Holism versus reductionism in supply chain management: An economic analysis | |
| US20190050786A1 (en) | Task Assisted Resources Assignment Based On Schedule Impact | |
| US20170140306A1 (en) | Business graph model | |
| CN111507673A (en) | Method and device for managing commodity inventory | |
| US20140351001A1 (en) | Business enterprise sales and operations planning through a big data and big memory computational architecture | |
| Otto et al. | Corporate data quality: Prerequisite for successful business models | |
| CN117010541A (en) | Time sequence prediction method, device and storage medium | |
| US20170178221A1 (en) | Method and system for inventory availability prediction | |
| Brown | A case study in agile-at-scale delivery | |
| US20140330742A1 (en) | Tailored subscription customer saving procedures | |
| BRPI0803389B1 (en) | computer-implemented methods for managing correlated event message sequence and a sequence of correlated service requests | |
| CN105283888A (en) | Distributed worker-sourced process engineering | |
| EP3572994A1 (en) | Processing contractual templates of modelled contracts for train systems | |
| US11010817B2 (en) | Systems and method for coordinating trend data via a hub | |
| Horowitz et al. | Assembling off-the-shelf components:" Learn as you Go" systems engineering | |
| US20140288991A1 (en) | Project estimation and planning using feature granularity |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190301 |