CN107977825A - A kind of method and device for distributing Service events - Google Patents
A kind of method and device for distributing Service events Download PDFInfo
- Publication number
- CN107977825A CN107977825A CN201711071959.4A CN201711071959A CN107977825A CN 107977825 A CN107977825 A CN 107977825A CN 201711071959 A CN201711071959 A CN 201711071959A CN 107977825 A CN107977825 A CN 107977825A
- Authority
- CN
- China
- Prior art keywords
- service
- service events
- time
- processing end
- events
- 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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
- G06Q10/1093—Calendar-based scheduling for persons or groups
- G06Q10/1097—Task assignment
-
- 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
- G06Q30/012—Providing warranty services
-
- 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
Abstract
The embodiment of present disclosure provides a kind of method being distributed to Service events, including：Obtain the description information for the Service events that user submits；Temporal information is extracted from description information；According at least to the temporal information, the affair character of Service events is determined；Obtain the attributive character of multiple processing ends；And according to the affair character and the attributive character of the multiple processing end, the Service events are distributed to corresponding processing end.Additionally provide device corresponding with the above method.By this method and device, Service events can be more timely and effectively distributed to appropriate person liable.
Description
Technical field
Multiple embodiments that this specification discloses are related to the processing of service request, more particularly to a kind of Service events that distribute
Method and device.
Background technology
The people that develop into of Internet technology and social economy provide more and more products and diversified service.
During people use these products or service, the problem of various is inevitably run into.In order to efficiently solve
The provider of these problems, product or service often provides customer service or after sale Resolving probiems portion using some e-platforms,
Receive and process the consulting, request or even complaint of user.
For this kind of service request of user, routinely, different responsible persons is randomly assigned them to.Further
Ground, considers the working status of responsible person, and the service request of user is distributed to the responsible person of free time.In some schemes,
The service quality of customer service also to answering user of incoming call carries out quality inspection and assessment (for example, method of CN104168394A descriptions).
However, these methods of salary distribution still cannot reach preferable effect, customer problem is handled not in time and when continuing to complain of initiation
There is generation.
Therefore, it is necessary to improved plan, the service request of user can be distributed to appropriate responsible person, so as to be lifted
User experience.
The content of the invention
In order to overcome deficiency of the prior art, present specification describes it is a kind of based on the feature of time dimension to service thing
The method and apparatus that part is distributed,
According to first aspect, there is provided a kind of method being distributed to Service events, it is characterised in that including：Obtain
The description information for the Service events that user submits；Temporal information is extracted from the description information；According at least to the time
Information, determines the affair character of the Service events, and the affair character includes at least time correlation feature；Obtain multiple processing
The attributive character at end；And according to the affair character and the attributive character of the multiple processing end, by the Service events point
Issue corresponding processing end.
In one embodiment, obtaining the description information for the Service events that user submits includes：By the voice messaging of user
Be converted to text message, and the description information using the text message being converted to as Service events.
In one embodiment, it is described obtain user submit Service events description information include it is following at least one
：Obtain user submit the Service events via interactive entrance information；Obtain associated with the Service events order
Single information.
In one embodiment, the time correlation feature includes at least one in the following：Lower list time, risk occur
Time, the stand-by period determined based on lower single time and current time, based on risk time of origin and predetermined threshold time
Definite service overdue deadline, the service remaining time determined based on service overdue deadline and current time.
In one embodiment, the affair character further includes risk class.
In one embodiment, it is described according to affair character and the attributive character of the multiple processing end, by the service
Case distribution includes to corresponding processing end：The definite probability that the Service events are distributed to each processing end respectively；Compare
The corresponding probable value in each processing end；The Service events are distributed to the processing end with maximum probability value.
In one embodiment, it is described to determine that the probability that the Service events are distributed to each processing end includes respectively：
Determine for the Service events to be distributed to the probability of each processing end, the bayesian probability model using bayesian probability model
In the statistical sample training that is handled by history Service events of parameter obtain.
In one embodiment, the method further includes：Judge whether the Service events are processed；In the service thing
In the case of part is untreated, the time correlation feature in the affair character of the Service events is updated；It is special according to the event of renewal
Seek peace the attributive character, distribute the Service events again.
In one embodiment, in the case of the Service events are untreated, the category of the multiple processing end is also updated
Property feature.
According to second aspect, a kind of device being distributed to Service events is additionally provided, it is characterised in that including：Retouch
Acquiring unit is stated, is configured to obtain the description information for the Service events that user submits；Time extraction unit, is configured to retouch from described
State and temporal information is extracted in information；Characteristics determining unit, is configured to according at least to the temporal information, determines the service thing
The affair character of part, the affair character include at least time correlation feature；Attribute acquiring unit, is configured to obtain multiple processing
The attributive character at end；And Dispatching Unit, the attributive character according to the affair character and the multiple processing end is configured to, will
The Service events are distributed to corresponding processing end.
According to the third aspect, there is provided a kind of computer-readable recording medium, is stored thereon with computer program, when described
When computer program performs in a computer, computer is made to perform the method in first aspect.
According to fourth aspect, there is provided a kind of computing device, including memory and processor, it is characterised in that described to deposit
Executable code is stored with reservoir, when the processor performs the executable code, realizes the side described in first aspect
Method.
The distribution method and device that this specification provides, distribute Service events based on the feature of time dimension.Due to
The aging factor of Service events is considered during distribution so that Service events are distributed to appropriate responsibility according to urgency level
People, being more advantageous to being in due course solves Service events, avoids the occurrence of risk or risk upgrading.
Brief description of the drawings
The technical solution of the multiple embodiments disclosed in order to illustrate more clearly of this specification, below will describe embodiment
Needed in attached drawing be briefly described, it should be apparent that, drawings in the following description be only this specification disclose
Multiple embodiments, for those of ordinary skill in the art, without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is the application scenarios schematic diagram for the distribution method that one embodiment that this specification discloses provides；
Fig. 2 is the flow chart for the distribution method that one embodiment that this specification discloses provides；
Fig. 3 a show to describe the example of service request by online mode；
Fig. 3 b show to describe the example of service request by online mode；
Fig. 3 c show to describe the example of service request by online mode；
Fig. 4 shows the flow chart of the distribution Service events according to one embodiment；
Fig. 5 shows the schematic block diagram of the device of the distribution Service events according to one embodiment.
Embodiment
Below in conjunction with the accompanying drawings, the multiple embodiments disclosed this specification are described.
Fig. 1 is the application scenarios schematic diagram for the distribution method that one embodiment that this specification discloses provides.In Fig. 1, use
Family can send service request when service encounters problems by various terminals.Terminal for example can be mobile phone, tablet electricity
Brain, wearable smart machine etc..The service request sent for example can be hot line incoming call, on-line consulting etc..Such service
Request passes through transmission of network to server.Server, which docks received service request, to be analyzed, and will be serviced based on analysis result
The involved Service events of request are distributed to corresponding processing end, such as customer service, customer service supervisor, corresponding department owner etc..
Specifically, server determines Service events (for example, customer complaint from the service request received：It is predetermined
Do not draw a bill after paying ticket fee during air ticket), description information of the user to the Service events is obtained, from these description informations
Extract temporal information.Above-mentioned temporal information is at least based on, server determines the affair character of the Service events.The opposing party
Face, server can obtain the attributive character for being possible to the multiple processing ends for handling the Service events.Thing based on Service events
The Service events are distributed to corresponding processing end by part feature and the attributive character of processing end, server.
Fig. 2 is the flow chart for the distribution Service events that one embodiment that this specification discloses provides.The method is held
Row main body can be the equipment with disposal ability：Server either system or platform, for example, the server in Fig. 1.Such as figure
Shown in 2, it the described method comprises the following steps：S22, obtains the description information for the Service events submitted to user；Step S23, from
Temporal information is extracted in the description information；Step S24, according at least to the temporal information, determines the Service events
Affair character；Step S25, obtains the attributive character of multiple processing ends；Step S26, according at least to the affair character and described
The Service events are distributed to corresponding processing end by the attributive character of multiple processing ends.
With reference to the specific executive mode of more than specific example description each step.
As described above, in step S22, the description information for the Service events submitted to user is obtained.Normally, user passes through
Send service request (for example, being sent a telegraph to hot line customer service, to online customer service enquirement etc.) and submit Service events.
It is appreciated that the service request of user may relate to polytype Service events, including for example seek advice from or inquire
A certain item, it is also possible to including the content such as interrogating, complain, requirement is handled.In one embodiment, step S22 includes, and sentences
The type for the Service events that disconnected user submits is as its description information..In some cases, service platform please to different services
Ask and be provided with different access passages, then the type of Service events can be judged by accessing passage.For example, service
Platform can disclose different telephone numbers, and number 1 is used to answer pre-sales consulting telephone, and number 2 is used to seek advice from after sale, number 3
For customer complaint, in this case, the type of Service events can be judged by access code.In another example service is flat
Platform can provide multigroup online customer service, and indicate that customer service group 1 is used for pre-sales consulting, and customer service group 2 is used to handle after sale and complains.That
, the classification for judging Service events can be encoded by customer service group.
In one embodiment, in step S22, description information of the user to the Service events is obtained.
In one embodiment, user submits Service events by online mode.It is appreciated that service platform can be to use
Family provides online interactive entrance, and user utilizes such friendship by various terminals (mobile phone, PC, tablet computer etc.)
Mutual entrance, can submit Service events online.
More specifically, in one example, user can input the description text to Service events by interactive entrance.Figure
3a, 3b and 3c show to describe the example of service request by online mode.As shown in Figure 3a, in this example embodiment, user is buying
After commodity, the icon of " application after sale " is provided with the interface of purchase order information for showing the commodity.In an example
In, as shown in Figure 3b, user, which clicks on the icon, can enter interface with customer service online communication, the problem of inputting oneself and will
Ask.Alternatively, as shown in Figure 3c, user shows a dialog box after clicking on icon, and user can input oneself in the dialog box
The problem of, then click on " submission ".In this case, user directly can be obtained to the clothes by text input by user
The description information of business event.
In another example, service platform provides the interactive entrance of more details, and distinct interaction entrance also serves as thing in itself
A part for part description information.For example, user provides multiple passes after " winged pig " platform is purchased the air ticket, at air ticket order interface
The interactive entrance of connection：" quick check-in ", " move back and change label ", " not drawing a bill ".User will just buy machine by clicking on " not drawing a bill " icon
This event that fails after ticket to draw a bill has submitted to service platform.Alternatively, user is after taking out platform purchase and taking out, it is outer at this
Sell order interface and multiple associated interactive entrances are provided：" checking ", " cancellation ", " reminder ".User clicks on " reminder " icon, actual
It is upper that the Service events for failing to receive take-away in time, request is handled as early as possible have just been submitted into service platform.In this case,
The interactive entrance information in itself that can be selected by user, obtains the description information to Service events.
In another embodiment, user's access service platform by way of hotline, is linked up, word picture with customer service
It is required that solve the problems, such as.In this case, in step S22, the voice messaging of user is converted into text message, and will turn
Description information of the text message got in return as Service events.It is appreciated that there are the realization that multiple voice turns text
Mode, sharp can realize the conversion of speech-to-text in various manners, this is not construed as limiting.
In one embodiment, the voice messaging of user is converted into text in real time, the description as Service events is believed
Breath.
In one embodiment, in step S22, the sequence information associated with Service events is also obtained, as service thing
The description information of part.For example, user clicks on " reminder " icon at some take-away order interface, then can accordingly obtain this and order
Single details, such as lower single time, it is desirable to the time of dispatching, dispatching place etc..Such sequence information can also be made
For the description information of Service events.In another example, user has dialed service hotline by registering cell-phone number, then Ke Yitong
The cell-phone number for crossing user identifies user account, and then obtains the recent sequence information of the user.Can also further it combine
The voice description of user, determines the order associated with Service events, and then obtain the information of the order.For example, user dials
Make hot line and reflect that the air ticket of oneself fails to draw a bill.User account can be identified by the cell-phone number of user, and then determine to use
There are three orders at family in the recent period：The order A in predetermined hotel before one week, buys the order B of train ticket, and the purchase machine that yesterday occurs
The order C of ticket.It can determine that associated order is order C with reference to user's description, and then obtain the details of the order,
Such as lower single time, the amount of money, destination etc..Alternatively, user is also possible in the communication with customer service (online or hot line) description
The order number of oneself, under such circumstances, can describe directly to determine associated sequence information, as service according to user
The description information of event.
On the basis of the description information of Service events is obtained, in step S22, the time is extracted from foregoing description information
Information.
For example, in user's air ticket fails the example drawn a bill, it is assumed that the description information of acquisition includes：Predetermined CA111 boats
The air ticket of class fails to draw a bill, flight tomorrow afternoon (October 3) 18:00 takes off, and departure place is Beijing, and destination is Hangzhou,
Single time is on October 1 12 under order:00.The temporal information that can be extracted from such description information includes：During air ticket
Between on October 3 18:00, lower list 1 day 12 October of time:00.In another example in the example that user's reminder is taken out, it is assumed that acquisition
Description information includes：Noon 11:A restaurants outside 00 order 2km 2 are especially sold, 56 yuan of payment, it is desirable to 12:30 are sent to,
System is that the delivery time that user estimates is 12:00.The temporal information that can be extracted from such description information includes：Under
Single time 11:00, it is desirable to delivery time 12:30, estimate delivery time 12:10.For the description information of other Service events,
It similarly can therefrom extract time related information.
Based on the temporal information of step S23 extractions, in step S24, according at least to the temporal information, Service events are determined
Affair character.Correspondingly, the affair character determined includes at least time correlation feature.When time correlation feature can include
Between information in itself, for example, it is lower list the time, the time that risk time of origin, i.e. order may fail in air ticket (for example, do not draw a bill
Example in, be on October 3 18:00, it is 12 in the example that reminder is taken out:30) etc..
Time correlation feature can also include the feature determined based on temporal information.
In one example, time correlation feature includes, the stand-by period determined based on lower single time and current time.Example
Such as, it is assumed that current time is on October 2 12:00, then in the example that air ticket is not drawn a bill, when the stand-by period is 24 small, outside
Sell in the example of reminder, stand-by period 60min.
In one example, time correlation feature includes, and is determined based on risk time of origin and predetermined threshold time
Service overdue deadline.If overdue deadline is serviced it is meant that cannot effectively handle service thing before the time
Part, then be likely to occur risk, either risk can upgrade or service can be aborted.For example it is assumed that the threshold value that air ticket is drawn a bill
Time is to take off preceding 4 hours, then in the example that air ticket is not drawn a bill, it is on October 3 14 to service overdue deadline:00.
It is assumed that the scheduled time for taking out food delivery is 20 minutes after the delivery time of user's requirement, then is taking out the example of reminder
In, overdue deadline is serviced as 12:20.
In one example, time correlation feature further includes, and is determined based on service overdue deadline and current time
Remaining time is serviced, that is, also how long current time distance service overdue deadline.It is assumed that current time is October 2
12:00, then in the example that air ticket is not drawn a bill, when service remaining time is 26 small, in the example for taking out reminder, service is surplus
The remaining time is 20min.
It is appreciated that the temporal information for being also based on extraction determines other time correlation features, as service thing
A part for the affair character of part.
Definite event feature can also include otherwise feature in step S24.In one embodiment, event is special
Sign can include risk class.In one example, based on the description information to Service events, mould is detected using complaint risk
Type, determines the complaint risk of outgoing event.In another example, using public sentiment risk supervision model, the public sentiment risk of event is determined.
It is also based on other factors and determines otherwise risk.Risk based on each side, synthesis determine the Service events
Risk class.In one example, the risk class of complaint risk grade, public sentiment risk class etc. can also be distinguished
Characteristic parameter as affair character.
Affair character except determining Service events in step s 24, on the other hand, in step S25, obtains multiple processing
The attributive character at end.The multiple processing end is possible to handle the processing end of the Service events, such as including general customer service (its
In again including being firstly received the customer service and other customer services of user's access), customer service supervisor, the full-time group of certain class event is objective
Clothes, sole duty group supervisor etc..For example, for offer include the tourist service platform of air ticket business for, its processing end except including
General customer service and customer service supervisor, further includes full-time group directly docked with airline, the customer service of the sole duty group is responsible for specially solving
Certainly air ticket relevant issues.Other service platforms also accordingly have the processing end of a variety of processing Service events.Correspondingly, acquisition
The attributive character of processing end can include, and whether target processing end is online, and work saturation degree, ability to work, full-time type of service
Etc..These attributive character can obtain by conventional method.
On the basis of the affair character and the attributive character of processing end for obtaining Service events, in step S26, at least root
According to the affair character and the attributive character, Service events are distributed to corresponding processing end.
In one embodiment, affair character includes at least risk class and service remaining time.Correspondingly, in step
In S26, in the case where sole duty group supervisor is online, risk class is more than some risk threshold value, and service remaining time is less than
The Service events of some time threshold (for example, 2 hours), are distributed to full-time group supervisor；Risk class is more than above-mentioned risk
Threshold value, and Service events of the remaining time more than above-mentioned time threshold are serviced, it is distributed to full-time group customer service；Risk class is less than
Above-mentioned risk threshold value, service remaining time are less than the Service events of above-mentioned time threshold, are distributed to general customer service supervisor；And according to
The work saturation degree of each general customer service, is less than risk threshold value by risk class, and service remaining time is more than above-mentioned time threshold
The Service events of value, are distributed to the customer service of free time.
More universally, the processing end of distribution is determined using probability distribution model.In one embodiment, step S26 is adopted
The processing end of distribution is determined with bayesian probability model.Specifically, step S26 includes, and determines above-mentioned service thing respectively
Part is distributed to the probability of each processing end, and the corresponding probable value in more each processing end, which is distributed to most
The processing end of high probability values.
For example, in one example, the affair character of Service events includes R1, and R2 ... Rk, wherein R1, R2 ... Rk can
To be the various features for including time correlation feature of above citing, such as R1 is complaint risk grade, and R2 is public sentiment risk etc.
Level, R3 are lower single time, and R4 is service overdue deadline, etc..On the other hand, processing end Ci can include for example receiving
The customer service C1 of user's access, other general customer service C2, customer service supervisor C3, sole duty group customer service C4, etc..The attribute of processing end
Feature includes A1, A2 ..., Am, wherein A1, and A2 ..., Am can be a variety of attributive character of above citing, such as A1 is to work as
Whether preceding online, A2 is work saturation degree, and A3 is full-time type of service, etc..
By affair character R1, R2 ... the Rk of the Service events and attributive character A1 of processing end, A2 ..., Am is collectively as general
Parameter attribute F1, F2 ... the Fn of rate model, is calculated by bayesian probability model the Service events being distributed to processing end Ci's
Probability P i：
Wherein：
P(F1F2...Fn|Ci)P(Ci)=P (F1 | Ci)P(F2|Ci)...P(Fn|Ci)P(Ci) (2)
The each single item on right side can be by obtaining in statistical sample that history Service events are handled in equation (2).More
Body, above-mentioned statistical sample can be drawn by artificial mark (addition label) or historical events disposal options.Thus, then will
(2) in formula generation, returns (1) formula, can be processed the corresponding probability P i of end Ci.
The probability that Service events are distributed to each processing end is similarly calculated, compares result of calculation, will be general with highest
The processing end of rate is considered to be adapted to the processing end for handling the Service events, so that the Service events are distributed to the processing end.
It is appreciated that more than distribute during, using based on the time dependent parameter that temporal information determines as distribute
Based on characteristic parameter, this causes the distribution of Service events to consider timeliness sexual factor, thus as far as possible avoid missing solution service
On the opportunity of event, be more advantageous to efficiently solving Service events, avoids the occurrence of risk or risk upgrading.On the other hand, for user
For, problem can be solved more quickly, also improve user experience.
Further, in one embodiment, the affair character of above Analysis Service event, and distribute them to it is appropriate
The process of director, can carry out in real time during user's access service platform is linked up with customer service.For example, user to
While customer service A describes problem, the method that performs Fig. 2, analyzes the Service events that customer problem is related to, distributes them in real time
Sole duty group customer service.Then it is possible that in the case where user not yet terminates with the call of customer service A, sole duty group customer service has just solved
The problem of user, further improve user experience.
Further, in one embodiment, the disposition of automatic regular polling Service events, in the feelings not handled
Under condition, its time correlated characteristic is updated, and it is distributed again.Fig. 4 shows to service thing according to the distribution of one embodiment
The flow chart of part.Step S22-S26 in the flow chart is identical with shown in Fig. 2, and details are not described herein.
In one embodiment, after performing step S26 and Service events are distributed to some processing end, the service is marked
The ID of the event and ID for the processing end distributed, which is put into processing pond.In one example, it is also the clothes
The addition of business event handles state tag, such as non-start to process, and start to process does not complete, is disposed.Once processing end
The start to process Service events, just correspondingly change its state tag.Alternatively, in one example, the service that will be disposed
Event is deleted from processing pond.
Correspondingly, step S27 shown in Fig. 4, judges whether Service events are processed.Such judgement can be by such as
The state tag is gone up to realize.In the case where Service events have obtained processing, terminate flow；It is untreated in Service events
In the case of, S28 is entered step, updates the time correlation feature in the affair character of Service events.It is appreciated that time correlation
The feature determined based on current time, such as stand-by period, service remaining time etc. may be included in feature.With time mistake
Go, these characteristic parameters can change.Therefore, such feature is updated in step S28, recalculates feature
Parameter value.
In one embodiment, alternatively, in step S29, the attributive character of multiple processing ends is updated.It is appreciated that place
The part attributive character at reason end is also possible to change with the time, such as whether target processing end is online, its work saturation degree
Etc..Therefore, it is also desirable to be also updated to these attributive character, its parameter value is recalculated.
Then, flow returns to step S26, the attributive character of affair character and processing end again according to Service events,
Distribute Service events.Affair character and attributive character at this time is the feature of renewal, correspondingly, it is possible to distribute Service events
The different processing end in processing end before giving.For example, as time go by, service remaining time shortens, and event is more urgent,
More advanced director is needed to handle.
In one embodiment, at predetermined time intervals (such as 10min), the judgement of a step S27 is performed, and subsequently
Renewal and distribute again, to ensure that Service events are properly processed.
In the embodiment above, be continuously updated over time affair character, thus dynamically adjust Service events distribution and
Processing so that Service events are distributed to most suitable director according to newest situation instantly.In this way, can further it carry
The solution efficiency of Service events is risen, also improves user experience.
In the embodiment for the another aspect that this specification discloses, there is provided a kind of dress being distributed to Service events
Put.Fig. 5 shows the schematic block diagram of the device of the distribution Service events according to one embodiment.As shown in figure 5, the device 500 wraps
Include：Acquiring unit 52 is described, is configured to obtain the description information for the Service events submitted to user；Time extraction unit 53, matches somebody with somebody
It is set to and extracts temporal information from the description information；Characteristics determining unit 54, is configured to according at least to the temporal information,
Determine the affair character of the Service events；Attribute acquiring unit 55, is configured to obtain the attributive character of multiple processing ends；And
Dispatching Unit 56, is configured to the attributive character according to the affair character and the multiple processing end, by the Service events point
Issue corresponding processing end.
In one embodiment, user submits the service request of oneself by online mode.In this case, describe
Acquiring unit 52 directly can describe description information of the text as Service events using input by user.In one embodiment,
The problem of user's access service platform by way of hotline, voice describe oneself and requirement.In this case, retouch
Acquiring unit 52 is stated to be configured to：The voice messaging of user is converted into text message, and using the text message being converted to as
The description information of Service events.
In one embodiment, description acquiring unit 52 is additionally configured to perform at least one in the following：User is obtained to carry
Hand over the Service events via interactive entrance information；The sequence information associated with the Service events is obtained, will so
Description information of the information as Service events.
Description information based on acquisition, time extraction unit 53 extract temporal information from the description information.Time
Information is for example including the lower list time, risk time of origin etc..Further, characteristics determining unit 54 is according at least to the time
Information, determines the affair character of the Service events, and the affair character includes at least time correlation feature.
In one embodiment, time correlation feature includes at least one in the following：The lower list time, when risk occurs
Between, it is stand-by period for being determined based on lower single time and current time, true based on risk time of origin and predetermined threshold time
Fixed service overdue deadline, the service remaining time determined based on service overdue deadline and current time.
In one embodiment, affair character further includes risk class.Risk class can be based on complaint risk grade, carriage
The factors such as feelings risk class determine.
On the other hand, attribute acquiring unit 55 obtains the attributive character of multiple processing ends.In one embodiment, attribute is special
Sign includes at least one in the following：Whether target processing end is online, and work saturation degree, ability to work, full-time type of service.
54 definite event feature of feature based determination unit, and the attribute of the processing end of the acquisition of attribute acquiring unit 55 are special
Service events are distributed to corresponding processing end by sign, Dispatching Unit 56.
In one embodiment, more specifically, Dispatching Unit 56 determines the Service events being distributed to each place respectively
Manage the probability at end；The corresponding probable value in more each processing end；The Service events are distributed to the processing with maximum probability value
End.
In one embodiment, Dispatching Unit 56 is further configured to determine the service using bayesian probability model
Case distribution is to the probability of each processing end, the system that the parameter in the bayesian probability model is handled by history Service events
Sample training is counted to obtain.
In one embodiment, device 500 further includes judging unit (not shown), is configured to judge that the Service events are
It is no processed；Updating block (not shown), is configured in the case of the Service events are untreated, updates the Service events
Affair character in time correlation feature；And Dispatching Unit 56 is additionally configured to, according to the affair character of renewal and the category
Property feature, distributes the Service events again.
In one embodiment, updating block is additionally configured to：In the case of the Service events are untreated, described in renewal
The attributive character of multiple processing ends.
Service events, appropriate processing end is distributed to based on time factor by diostribution device in this way so that service
The processing of event is effective much sooner.
According on the other hand, the embodiment of specification also provides a kind of computer-readable recording medium, is stored thereon with meter
Calculation machine program, when the computer program performs in a computer, makes computer perform the distributor of above example description
Method, such as the method shown in Fig. 2.
Further, according to one embodiment, a kind of computing device is also provided, which is, for example, the service shown in Fig. 1
Device.Computing device includes memory and processor, and executable code is wherein stored with memory, can be held described in processor execution
During line code, the distribution method of above example description, such as the method shown in Fig. 2 are realized.
Those of ordinary skill in the art should further appreciate that, be described with reference to the embodiments described herein
Each exemplary unit and algorithm steps, can be realized with electronic hardware, computer software or the combination of the two, in order to clear
Illustrate to Chu the interchangeability of hardware and software, generally describe each exemplary group according to function in the above description
Into and step.These functions hold track with hardware or software mode actually, depending on technical solution application-specific and set
Count constraints.Those of ordinary skill in the art can be described to be realized using distinct methods to each specific application
Function, but this realization is it is not considered that exceed scope of the present application.
Track can be held with reference to the step of method or algorithm that the embodiments described herein describes with hardware, processor
Software module, or the two combination implemented.Software module can be placed in random access memory (RAM), memory, read-only storage
Device (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology neck
In any other form of storage medium well known in domain.
Above-described embodiment, has carried out the purpose of the present invention, technical solution and beneficial effect further
Describe in detail, it should be understood that the foregoing is merely the embodiment of the present invention, be not intended to limit the present invention
Protection domain, within the spirit and principles of the invention, any modification, equivalent substitution, improvement and etc. done, should all include
Within protection scope of the present invention.
Claims (22)
- A kind of 1. method that Service events are distributed, it is characterised in that including：Obtain the description information for the Service events submitted to user；Temporal information is extracted from the description information；According at least to the temporal information, the affair character of the Service events is determined；Obtain the attributive character of multiple processing ends；AndAccording to the affair character and the attributive character of the multiple processing end, the Service events are distributed to corresponding processing End.
- 2. according to the method described in claim 1, it is characterized in that, the description for obtaining the Service events submitted to user is believed Breath includes：The voice messaging of user is converted into text message, and is believed the text message being converted to as the description of Service events Breath.
- 3. according to the method described in claim 1, it is characterized in that, the description for obtaining the Service events submitted to user is believed Breath includes at least one in the following：Obtain user submit the Service events via interactive entrance information；Obtain the sequence information associated with the Service events.
- 4. method according to any one of claim 1-3, it is characterised in that it is special that the affair character includes time correlation Sign, the time correlation feature include at least one in the following：Lower list time, risk time of origin, the stand-by period determined based on lower single time and current time, when being occurred based on risk Between and predetermined threshold time and definite service overdue deadline, based on servicing overdue deadline and current time determines Service remaining time.
- 5. according to the method described in claim 1, it is characterised in that the affair character further includes risk class.
- 6. according to the method described in claim 1, it is characterized in that, the attributive character includes at least one in the following：It is No online, work saturation degree, ability to work, full-time type of service.
- It is 7. according to the method described in claim 1, it is characterized in that, described according to affair character and the category of the multiple processing end Property feature, the Service events are distributed to corresponding processing end includes：The definite probability that the Service events are distributed to each processing end respectively；The corresponding probable value in more each processing end；The Service events are distributed to the processing end with maximum probability value.
- 8. the method according to the description of claim 7 is characterized in that it is described respectively determine the Service events are distributed to it is each The probability of processing end includes：Determine for the Service events to be distributed to the probability of each processing end using bayesian probability model, The statistical sample training that parameter in the bayesian probability model is handled by historical events obtains.
- 9. according to the method described in claim 1, it is characterized in that, further include：Judge whether the Service events are processed；In the case of the Service events are untreated, the time correlation feature in the affair character of the Service events is updated；According to the affair character of renewal and the attributive character, distribute the Service events again.
- 10. according to the method described in claim 9, it is characterized in that, further include：In the case of the Service events are untreated, the attributive character of the multiple processing end is updated.
- A kind of 11. device that Service events are distributed, it is characterised in that including：Acquiring unit is described, is configured to obtain the description information for the Service events submitted to user；Time extraction unit, is configured to extract temporal information from the description information；Characteristics determining unit, is configured to, according at least to the temporal information, determine the affair character of the Service events；Attribute acquiring unit, is configured to obtain the attributive character of multiple processing ends；AndDispatching Unit, is configured to the attributive character according to the affair character and the multiple processing end, by the Service events It is distributed to corresponding processing end.
- 12. according to the devices described in claim 11, it is characterised in that the description acquiring unit is configured to：The voice messaging of user is converted into text message, and is believed the text message being converted to as the description of Service events Breath.
- 13. according to the devices described in claim 11, it is characterised in that during the description acquiring unit is configured to below execution At least one of：Obtain user submit the Service events via interactive entrance information；Obtain the sequence information associated with the Service events.
- 14. according to the device any one of claim 11-13, it is characterised in that the affair character includes time phase Feature is closed, the time correlation feature includes at least one in the following：Lower list time, risk time of origin, the stand-by period determined based on lower single time and current time, when being occurred based on risk Between and predetermined threshold time and definite service overdue deadline, based on servicing overdue deadline and current time determines Service remaining time.
- 15. according to the device described in claim 11, it is characterised in that the affair character further includes risk class.
- 16. according to the devices described in claim 11, it is characterised in that the attributive character includes at least one in the following： Whether online, work saturation degree, ability to work, full-time type of service.
- 17. according to the devices described in claim 11, it is characterised in that the Dispatching Unit is configured to：The definite probability that the Service events are distributed to each processing end respectively；The corresponding probable value in more each processing end；The Service events are distributed to the processing end with maximum probability value.
- 18. device according to claim 17, it is characterised in that the Dispatching Unit is configured to：Using Bayesian probability Model determines for the Service events to be distributed to the probability of each processing end, and the parameter in the bayesian probability model is by going through The statistical sample training of history event handling obtains.
- 19. according to the devices described in claim 11, it is characterised in that further include：Judging unit, is configured to judge whether the Service events are processed；Updating block, is configured in the case of the Service events are untreated, in the affair character for updating the Service events Time correlation feature；The Dispatching Unit is additionally configured to, and according to the affair character of renewal and the attributive character, distributes the service thing again Part.
- 20. device according to claim 19, it is characterised in that the updating block is additionally configured to：In the case of the Service events are untreated, the attributive character of the multiple processing end is updated.
- 21. a kind of computer-readable recording medium, is stored thereon with computer program, when the computer program in a computer During execution, computer perform claim is made to require the method for any one of 1-10.
- 22. a kind of computing device, including memory and processor, it is characterised in that executable generation is stored with the memory Code, when the processor performs the executable code, realizes the method any one of claim 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711071959.4A CN107977825A (en) | 2017-11-03 | 2017-11-03 | A kind of method and device for distributing Service events |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711071959.4A CN107977825A (en) | 2017-11-03 | 2017-11-03 | A kind of method and device for distributing Service events |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107977825A true CN107977825A (en) | 2018-05-01 |
Family
ID=62012981
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711071959.4A Pending CN107977825A (en) | 2017-11-03 | 2017-11-03 | A kind of method and device for distributing Service events |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107977825A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111565151A (en) * | 2020-04-27 | 2020-08-21 | 中国银行股份有限公司 | Customer service line routing method and device |
| CN112686619A (en) * | 2019-10-18 | 2021-04-20 | 北京京东振世信息技术有限公司 | Method and device for reminding order collection |
| CN113723053A (en) * | 2020-12-28 | 2021-11-30 | 京东城市(北京)数字科技有限公司 | Event aided decision-making method and device, electronic equipment and storage medium |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739745A (en) * | 2009-12-01 | 2010-06-16 | 中国建设银行股份有限公司 | Queuing processing device and processing method thereof and queuing machine |
| CN101951393A (en) * | 2010-08-20 | 2011-01-19 | 深圳市迪威特数字视讯技术有限公司 | Browser/server mode-based online real-time customer service method and system |
| CN101997996A (en) * | 2009-08-13 | 2011-03-30 | 华为技术有限公司 | Method and device for queuing routing |
| CN102467763A (en) * | 2010-10-29 | 2012-05-23 | 爱立信电话股份有限公司 | Queuing control system and method |
| CN103647885A (en) * | 2013-12-31 | 2014-03-19 | 上海大学 | Multi-attribute intelligent vehicle-mounted call center queuing method |
| CN103684874A (en) * | 2013-12-31 | 2014-03-26 | 成都金铠甲科技有限公司 | Method and device for automatically distributing online customer service executives to conduct customer service |
| CN104135578A (en) * | 2014-08-15 | 2014-11-05 | 国家电网公司 | Service data processing method and system based on calling platform |
| CN104168394A (en) * | 2014-06-27 | 2014-11-26 | 国家电网公司 | Sampling quality inspection method and system in calling center |
| CN105357239A (en) * | 2014-08-20 | 2016-02-24 | 杭州华三通信技术有限公司 | Method and device for providing service, and method and device for acquiring service |
| CN105491085A (en) * | 2014-09-16 | 2016-04-13 | 阿里巴巴集团控股有限公司 | Method and device for on-line requesting for queuing |
| CN105657201A (en) * | 2016-01-26 | 2016-06-08 | 北京京东尚科信息技术有限公司 | Method and system for processing call based on decision tree model |
| CN106303113A (en) * | 2015-06-23 | 2017-01-04 | 阿里巴巴集团控股有限公司 | A kind of shunt method and equipment |
| CN106709758A (en) * | 2016-12-19 | 2017-05-24 | 浙江网新恒天软件有限公司 | Intelligent recommendation and distribution solution for service class commodities in electronic commerce products |
| CN106817701A (en) * | 2015-11-30 | 2017-06-09 | 中兴通讯股份有限公司 | Resource allocation methods and device |
| CN106997541A (en) * | 2017-04-11 | 2017-08-01 | 新站保险代理股份有限公司 | A kind of method and system for insuring customer service quality evaluation |
| CN107094208A (en) * | 2016-09-28 | 2017-08-25 | 北京小度信息科技有限公司 | Worksheet method and device |
-
2017
- 2017-11-03 CN CN201711071959.4A patent/CN107977825A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101997996A (en) * | 2009-08-13 | 2011-03-30 | 华为技术有限公司 | Method and device for queuing routing |
| CN101739745A (en) * | 2009-12-01 | 2010-06-16 | 中国建设银行股份有限公司 | Queuing processing device and processing method thereof and queuing machine |
| CN101951393A (en) * | 2010-08-20 | 2011-01-19 | 深圳市迪威特数字视讯技术有限公司 | Browser/server mode-based online real-time customer service method and system |
| CN102467763A (en) * | 2010-10-29 | 2012-05-23 | 爱立信电话股份有限公司 | Queuing control system and method |
| CN103647885A (en) * | 2013-12-31 | 2014-03-19 | 上海大学 | Multi-attribute intelligent vehicle-mounted call center queuing method |
| CN103684874A (en) * | 2013-12-31 | 2014-03-26 | 成都金铠甲科技有限公司 | Method and device for automatically distributing online customer service executives to conduct customer service |
| CN104168394A (en) * | 2014-06-27 | 2014-11-26 | 国家电网公司 | Sampling quality inspection method and system in calling center |
| CN104135578A (en) * | 2014-08-15 | 2014-11-05 | 国家电网公司 | Service data processing method and system based on calling platform |
| CN105357239A (en) * | 2014-08-20 | 2016-02-24 | 杭州华三通信技术有限公司 | Method and device for providing service, and method and device for acquiring service |
| CN105491085A (en) * | 2014-09-16 | 2016-04-13 | 阿里巴巴集团控股有限公司 | Method and device for on-line requesting for queuing |
| CN106303113A (en) * | 2015-06-23 | 2017-01-04 | 阿里巴巴集团控股有限公司 | A kind of shunt method and equipment |
| CN106817701A (en) * | 2015-11-30 | 2017-06-09 | 中兴通讯股份有限公司 | Resource allocation methods and device |
| CN105657201A (en) * | 2016-01-26 | 2016-06-08 | 北京京东尚科信息技术有限公司 | Method and system for processing call based on decision tree model |
| CN107094208A (en) * | 2016-09-28 | 2017-08-25 | 北京小度信息科技有限公司 | Worksheet method and device |
| CN106709758A (en) * | 2016-12-19 | 2017-05-24 | 浙江网新恒天软件有限公司 | Intelligent recommendation and distribution solution for service class commodities in electronic commerce products |
| CN106997541A (en) * | 2017-04-11 | 2017-08-01 | 新站保险代理股份有限公司 | A kind of method and system for insuring customer service quality evaluation |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112686619A (en) * | 2019-10-18 | 2021-04-20 | 北京京东振世信息技术有限公司 | Method and device for reminding order collection |
| CN111565151A (en) * | 2020-04-27 | 2020-08-21 | 中国银行股份有限公司 | Customer service line routing method and device |
| CN113723053A (en) * | 2020-12-28 | 2021-11-30 | 京东城市(北京)数字科技有限公司 | Event aided decision-making method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107147621B (en) | Method for realizing risk control of internet medical cattle | |
| Johnston | A framework for developing a quality strategy in a customer processing operation | |
| US20210058509A1 (en) | System and method for utilizing customer data in a communication system | |
| CN104103113A (en) | Queuing server and queuing method | |
| CN102930485A (en) | Five-star hotel management system | |
| CN107977825A (en) | A kind of method and device for distributing Service events | |
| CN107451912A (en) | The processing method and processing device of credit information | |
| CN108256721A (en) | A kind of method for scheduling task, terminal device and medium | |
| CN110349039A (en) | Complaint risk appraisal procedure, system, computer equipment and readable storage medium storing program for executing | |
| CN108734550A (en) | Method, apparatus, equipment and the storage medium of propelling data | |
| CN109145590A (en) | A kind of function hook detection method, detection device and computer-readable medium | |
| CN111639299A (en) | Method, system and storage medium for evaluating follow-up performance of client of business consultant | |
| CN110245959A (en) | The treating method and apparatus of specific aim request | |
| CN109726315A (en) | Data query method, apparatus calculates equipment and storage medium | |
| US11093983B1 (en) | Systems and methods for backend fulfillment of a sales product | |
| CN109242665B (en) | Business rule multi-channel sharing method, device, equipment and storage medium | |
| CN110070392A (en) | Customer churn method for early warning and device | |
| KR102415999B1 (en) | A method to identify a food menu using speech recognition and a system using the same | |
| KR102025862B1 (en) | System and method for responding to no-show customer | |
| KR102325398B1 (en) | A method to provide an automatic call order service using an ai callbot and a system using the same | |
| CN111985948A (en) | Automatic tracking and monitoring platform for mobile advertisement data | |
| KR102345043B1 (en) | A method to acquire information of a consumer in an order service and a system using the same | |
| US11361267B1 (en) | System and method for determining loss resulting from data privacy and security breach | |
| CN113591005B (en) | Information pushing method, device and terminal | |
| WO2012150586A1 (en) | System and method for fulfilling service requests and dispatching |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1253995 Country of ref document: HK |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20200924 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20200924 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180501 |
|
| RJ01 | Rejection of invention patent application after publication |