CN110147905A - Information processing method, device, system and storage medium - Google Patents
Information processing method, device, system and storage medium Download PDFInfo
- Publication number
- CN110147905A CN110147905A CN201910382630.2A CN201910382630A CN110147905A CN 110147905 A CN110147905 A CN 110147905A CN 201910382630 A CN201910382630 A CN 201910382630A CN 110147905 A CN110147905 A CN 110147905A
- Authority
- CN
- China
- Prior art keywords
- user
- customer service
- reception
- matched
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Present disclose provides a kind of information processing methods, this method comprises: obtaining the user characteristics for waiting M user of reception；Obtain the customer service feature for not receiving N number of customer service of user；It according to the user characteristics of M user and the customer service feature of N number of customer service, determines that the prediction duration of each user in M user is received in N number of customer service, obtains predicting duration collection；And according to prediction duration collection, it is determining at least one customer service of in N number of customer service it is matched at least one by reception user, so that the sum of the matched prediction duration for being received user minimum is received at least one customer service, wherein, each customer service is corresponded with matched by reception user, and M and N are natural number.The disclosure additionally provides a kind of information processing unit, a kind of information processing system and a kind of computer readable storage medium.
Description
Technical field
This disclosure relates to a kind of information processing method, device, system and storage medium.
Background technique
In order to improve customer experience, come into being for the customer service system of offering customers service.In view of the special need of client
It asks, the setting of artificial customer service is indispensable.
In existing customer service system, it is all made of the method based on the sequence of turn-on time precedence and distributes artificial customer service and visitor
Family.Or the demands of individuals in view of client, privately owned team can also be established for each customer service in such a way that client specifies customer service
Column, so that the client in privately owned queue is only received in customer service.Although the method sequentially to sort is simply easily achieved, do not have
Consider the difference between customer service and individual consumers, leads to whole reception inefficiency.Consider that privately owned queue needs client to specify customer service
It could establish, and client's often seldom specified customer service, therefore the method for establishing privately owned queue is difficult to carry out.In summary, existing
It is the method for artificial customer service distribution client in technology, due to cannot effectively consider individual difference, there are customer service reception to imitate
Rate is low, the higher problem of anxiety degree that client waits.
Summary of the invention
An aspect of this disclosure provides a kind of for improving the information processing method of customer service reception efficiency, this method packet
It includes: obtaining the user characteristics for waiting M user of reception；Obtain the customer service feature for not receiving N number of customer service of user；According to M
The user characteristics of user and the customer service feature of N number of customer service determine that the prediction duration of each user in M user is received in N number of customer service,
Obtain prediction duration collection；And according to prediction duration collection, it is determining at least one customer service of in N number of customer service it is matched at least one
By reception user, so that the sum of the matched prediction duration for being received user minimum is received at least one customer service, wherein Mei Geke
Clothes are corresponded with matched by reception user, and M and N are natural number.
Optionally, the prediction duration of each user in M user is received in the N number of customer service of above-mentioned determination, obtains prediction duration collection
It include: using the user characteristics of M user and the customer service feature of N number of customer service as the input of machine learning model, output obtains pre-
Survey duration collection；And/or above-mentioned user characteristics include the feature for indicating user request information, and user request information is used for table
Take over the type of the solicited message at family for use；And/or above-mentioned customer service feature includes indicating the feature of customer service reception information, the visitor
Clothes reception information is used to characterize the type of the solicited message of customer service processing.
Optionally, above- mentioned information processing method further include: obtain at least one customer service reception it is matched at least one connect
To the reception parameter of user, which includes reception duration and reception as a result, whether reception result is successfully located for characterizing
Manage solicited message；And according to reception parameter, optimize machine learning model.
Optionally, above-mentioned according to reception parameter, optimization machine learning model includes: the first customer service at least one customer service
Receive it is matched by reception user reception result characterization be successfully processed solicited message in the case where, with the first customer service receive match
The reception duration by reception user as training objective, with the customer service feature of the first customer service and with the first customer service is matched is connect
User characteristics to user are as sample, training machine learning model.
Optionally, above-mentioned according to prediction duration collection, it is determining at least one customer service of in N number of customer service it is matched at least one
The size relation of M and N are comprised determining that by reception user；And size relation and prediction duration collection according to M and N, determining and N
At least a customer service in a customer service it is matched at least one by reception user.
Optionally, above-mentioned objective at least one of N number of customer service according to the size relation of M and N and prediction duration collection, determination
Take it is matched at least one by reception user include: to determine that M user is to be received user in the case where M is no more than N；With
It is determining matched by reception user with M customer service in N number of customer service and according to prediction duration collection.
Optionally, above-mentioned user characteristics include indicate user's waiting time feature and/or indicate user gradation feature,
Above-mentioned size relation and prediction duration collection according to M and N, determining at least one customer service matched at least one with N number of customer service
It is a by reception user include: M be greater than N in the case where, M user is successively sorted according to according to preset rules, the prediction
Rule includes the size order of the value of user's waiting time and/or the sequence of the user gradation；Determination is successively arranged
The top n user of sequence is by reception user；And when according to predicting that duration concentrates N number of customer service reception to be received the prediction of user
It is long, it is determining matched by reception user with N number of customer service.
Another aspect of the disclosure provides a kind of information processing unit, the device include user characteristics obtain module,
Customer service feature obtains module, prediction duration determining module and matching module.Wherein, user characteristics obtain module for acquisition etc.
The user characteristics of M user to be received.Customer service feature obtains the customer service spy that module is used to obtain the N number of customer service for not receiving user
Sign.It predicts that duration determining module is used for the user characteristics according to M user and the customer service feature of N number of customer service, determines that N number of customer service connects
To the prediction duration of each user in M user, prediction duration collection is obtained.Matching module is used to be determined according to prediction duration collection
With at least one customer service in N number of customer service it is matched at least one by reception user so that at least one customer service reception it is matched
The sum of prediction duration by reception user minimum.Wherein, each customer service is corresponded with matched by reception user, and M is with N
Natural number.
Optionally, above-mentioned prediction duration determining module is specifically used for: by the user characteristics of M user and the visitor of N number of customer service
Input of the feature as machine learning model is taken, output obtains prediction duration collection.And/or above-mentioned user characteristics include referring to
Show the feature of user request information, which is used to characterize the type of the solicited message of user.On and/or
Stating customer service feature includes indicating the feature of customer service reception information, and customer service reception information is used to characterize the solicited message of customer service processing
Type.
Optionally, above- mentioned information processing unit further includes reception parameter acquisition module and model optimization module.Wherein, it receives
Parameter acquisition module be used for obtain at least one customer service receive it is matched at least one by reception user reception parameter, the reception
Parameter includes reception duration and reception as a result, whether the reception result is successfully processed solicited message for characterization.Model optimization mould
Block is used to optimize machine learning model according to reception parameter.
Optionally, above-mentioned model optimization module is connect specifically for the first customer service reception is matched at least one customer service
In the case that reception result characterization to user is successfully processed solicited message, received with the first customer service matched by reception user's
Receive duration be used as training objective, with the customer service feature of the first customer service and with the first customer service it is matched by reception user user spy
Sign is used as sample, training machine learning model.
Optionally, above-mentioned matching module includes that relationship determines submodule and matched sub-block.Wherein, relationship determines submodule
For determining the size relation of M and N.Matched sub-block is used for according to the size relation of M and N and prediction duration collection, it is determining with it is N number of
At least one customer service in customer service it is matched at least one by reception user.
Optionally, above-mentioned matched sub-block includes first reception user's determination unit and first matching user's determination unit.
Wherein, first reception user's determination unit is used in the case where M is not more than N, determines that M user is by reception user.First
User's determination unit is matched to be used for according to prediction duration collection, it is determining matched by reception user with M customer service in N number of customer service.
Optionally, above-mentioned user characteristics include indicate user's waiting time feature and/or indicate user gradation feature,
Above-mentioned matched sub-block includes sequencing unit, second reception user's determination unit and second matching user's determination unit.Wherein, it arranges
Sequence unit is used to that M user successively to sort according to pre-defined rule in the case where M is greater than N, and the preset rules include described
The high order of the size order of the value of user's waiting time and/or the user gradation.Second reception user's determination unit is used
It is to be received user in the determining top n user successively to sort.Second matching user's determination unit is used for according to prediction duration collection
In N number of customer service reception by the prediction duration of reception user, it is determining matched by reception user with N number of customer service.
Another aspect of the present disclosure provides a kind of information processing system, including one or more processors；And storage
Device, for storing one or more programs, wherein when one or more of programs are held by one or more of processors
When row, so that one or more of processors execute above-mentioned information processing method.
Another aspect of the disclosure provides a kind of computer readable storage medium, is stored with the executable finger of computer
It enables, which makes processor execute above-mentioned information processing method when being executed by processor.
Another aspect of the disclosure provides a kind of computer program, which, which includes that computer is executable, refers to
It enables, described instruction is when executed for realizing information processing method as described above.
Detailed description of the invention
In order to which the disclosure and its advantage is more fully understood, referring now to being described below in conjunction with attached drawing, in which:
Fig. 1 diagrammatically illustrates answering according to the information processing method of the embodiment of the present disclosure, device, system and storage medium
With scene figure；
Fig. 2 diagrammatically illustrates the flow chart of the information processing method according to the embodiment of the present disclosure；
Fig. 3 diagrammatically illustrates the input and output process figure according to the information processing method of the embodiment of the present disclosure；
Fig. 4 diagrammatically illustrates the matched flow chart by reception user of determination according to the embodiment of the present disclosure；
Fig. 5 diagrammatically illustrates the matched flow chart by reception user of determination according to another embodiment of the disclosure；
Fig. 6 diagrammatically illustrates the flow chart of the information processing method according to another embodiment of the disclosure；
Fig. 7 diagrammatically illustrates the structural block diagram of the information processing unit according to open embodiment；And
Fig. 8 is diagrammatically illustrated according to the information processing system for being adapted for carrying out information processing method of the embodiment of the present disclosure
Structural block diagram.
Specific embodiment
Hereinafter, will be described with reference to the accompanying drawings embodiment of the disclosure.However, it should be understood that these descriptions are only exemplary
, and it is not intended to limit the scope of the present disclosure.In the following detailed description, to elaborate many specific thin convenient for explaining
Section is to provide the comprehensive understanding to the embodiment of the present disclosure.It may be evident, however, that one or more embodiments are not having these specific thin
It can also be carried out in the case where section.In addition, in the following description, descriptions of well-known structures and technologies are omitted, to avoid
Unnecessarily obscure the concept of the disclosure.
Term as used herein is not intended to limit the disclosure just for the sake of description specific embodiment.It uses herein
The terms "include", "comprise" etc. show the presence of the feature, step, operation and/or component, but it is not excluded that in the presence of
Or add other one or more features, step, operation or component.
There are all terms (including technical and scientific term) as used herein those skilled in the art to be generally understood
Meaning, unless otherwise defined.It should be noted that term used herein should be interpreted that with consistent with the context of this specification
Meaning, without that should be explained with idealization or excessively mechanical mode.
It, in general should be according to this using statement as " at least one in A, B and C etc. " is similar to
Field technical staff is generally understood the meaning of the statement to make an explanation (for example, " system at least one in A, B and C "
Should include but is not limited to individually with A, individually with B, individually with C, with A and B, with A and C, have B and C, and/or
System etc. with A, B, C).Using statement as " at least one in A, B or C etc. " is similar to, generally come
Saying be generally understood the meaning of the statement according to those skilled in the art to make an explanation (for example, " having in A, B or C at least
One system " should include but is not limited to individually with A, individually with B, individually with C, with A and B, have A and C, have
B and C, and/or the system with A, B, C etc.).
Shown in the drawings of some block diagrams and/or flow chart.It should be understood that some sides in block diagram and/or flow chart
Frame or combinations thereof can be realized by computer program instructions.These computer program instructions can be supplied to general purpose computer,
The processor of special purpose computer or other programmable data processing units, so that these instructions are when executed by this processor can be with
Creation is for realizing function/operation device illustrated in these block diagrams and/or flow chart.The technology of the disclosure can be hard
The form of part and/or software (including firmware, microcode etc.) is realized.In addition, the technology of the disclosure, which can be taken, is stored with finger
The form of computer program product on the computer readable storage medium of order, the computer program product is for instruction execution system
System uses or instruction execution system is combined to use.
Embodiment of the disclosure provides a kind of for improving information processing method, the device, system of customer service reception efficiency
And storage medium.Wherein, information processing method includes: the user characteristics for obtaining M user for waiting reception；Use is not received in acquisition
The customer service feature of N number of customer service at family；According to the user characteristics of M user and the customer service feature of N number of customer service, N number of customer service is stated in determination
The prediction duration for receiving each user in M user obtains prediction duration collection；And according to prediction duration collection, determining and N number of visitor
At least one customer service in clothes it is matched at least one by reception user used so that at least one customer service reception is matched by reception
The sum of the prediction duration at family minimum, wherein each customer service is corresponded with matched by reception user, and M and N are natural number.
The information processing method of the disclosure, due to when for customer service distribution by reception user, can according to user characteristics and
Customer service feature, the user that dynamic adjustment customer service is received in real time, so that the sum of whole prediction duration minimum, so as to effective
The reception efficiency of customer service is improved, and therefore improves user satisfaction to a certain extent, the active balance different user waiting time
The problem of.
Fig. 1 diagrammatically illustrates information processing method according to an embodiment of the present disclosure, device, system and storage medium
Application scenario diagram.It should be noted that being only the example that can apply the scene of the embodiment of the present disclosure shown in Fig. 1, to help this
Field technical staff understands the technology contents of the disclosure, but be not meant to the embodiment of the present disclosure may not be usable for other equipment,
System, environment or scene.
As shown in Figure 1, the application scenarios 100 of the embodiment of the present disclosure include at least one customer service, at least one user's kimonos
Business device 130.
Wherein, at least one described customer service for example may include customer service 111,112,113, at least one customer service concrete example
It can be the customer service for being currently in idle state or busy condition, such as to provide service for user for receiving user.
Wherein, at least one described user for example may include user 121,122,123, which for example may be used
To initiate customer service request by first terminal, it is desirably to obtain the help of customer service.Wherein, the terminal for example may include but unlimited
In mobile phone, smartwatch, tablet computer, pocket computer on knee and desktop computer etc..Initiate the mode example of customer service request
It such as may include the mode that user's using terminal dials customer service hotline.Alternatively, the mode of initiation customer service request, which can also be, to be made
The mode requested online is initiated with the various application programs of terminal.Correspondingly, which should be connected with communication network, such as connect
It is connected to 2G, 3G, 4G even 5G communication network or Wireless LAN etc., and is for example also equipped in the terminal various logical
Interrogate client application, such as shopping class application, web browser applications, searching class application, instant messaging tools, mailbox client
(merely illustrative) such as end, social platform softwares.
In accordance with an embodiment of the present disclosure, above-mentioned at least one Client-initiated customer service request specifically can for example pass through network
It is sent to server 130, at least one customer service 111,112,113 is transmitted to by server 130.Wherein, network may include each
Kind connection type, such as wired, wireless communication link or fiber optic cables etc..Server 130 can for example be to provide various
The server of service, such as can receive the customer service request of user, and the customer service of the user is requested assignment into customer service.
Correspondingly, at least one customer service can for example respond the customer service request of user by second terminal, with to user
Corresponding help is provided.The second terminal for example can be the terminal with the same or similar type of first terminal, and can also pass through
Network is communicated with server 130, and details are not described herein.In accordance with an embodiment of the present disclosure, which for example can be with
Real-time status is sent to server by the second terminal, such as after having received user, sends feedback letter to server 130
Breath, when just starting to receive user, sends reception information to server 130, to show to show that it currently belongs to idle state
It currently belongs to busy condition etc..
In accordance with an embodiment of the present disclosure, above-mentioned server 130 can also for example be obtained initiation customer service by first terminal and be asked
That asks is waited for the user characteristics of user, and the customer service feature of customer service is obtained by second terminal, and according to acquisition
User characteristics, customer service feature and the customer service state of at least one customer service, or from database or local obtain the use
Family feature and customer service feature, thus according to the user characteristics and customer service feature, at least one customer service distributing user for described in, so that
Obtain the customer service request of the assigned user of at least one customer service response.
It should be noted that information processing method provided by the embodiment of the present disclosure can generally be executed by server 130.
Correspondingly, information processing unit provided by the embodiment of the present disclosure generally can be set in server 130.The embodiment of the present disclosure
Provided information processing method can also be by being different from server 130 and can be with first terminal and second terminal, and/or clothes
The server or server cluster that business device 130 communicates execute.Correspondingly, information processing unit provided by the embodiment of the present disclosure
It can be set in the service that is different from server 130 and can be communicated with first terminal and second terminal, and/or server 130
In device or server cluster.
It should be understood that the number of type of server and number and user and customer service in Fig. 1 is only schematical.Root
It factually now needs, can have any type and number destination server and any number of user and customer service.
Fig. 2 diagrammatically illustrates the flow chart of the information processing method according to the embodiment of the present disclosure.Fig. 3 is diagrammatically illustrated
According to the input and output process figure of the information processing method of the embodiment of the present disclosure.
As shown in Fig. 2, the information processing method of the embodiment of the present disclosure includes operation S210~operation S240.
In operation S210, the user characteristics for waiting M user of reception are obtained.
Wherein, the M user for waiting reception for example can be with reference to the user 121,122,123 in Fig. 1, wherein M
For natural number.The M user is specifically to have had sent customer service request, but the user not responded also is requested in the customer service.?
In one application scenarios, which for example can be the user for having dialed customer service hotline by terminal, but not being picked up also.With
Family feature, which specifically can be, to be obtained by the server 130 in reference Fig. 1, specifically can be according to sending the first of customer service request
What the ID mark of terminal was transferred from server local or database.It should be then previously stored in the server local or database
There is the corresponding relationship with each user one-to-one ID mark and user characteristics.Wherein, user in the corresponding relationship of the storage
Feature for example can be the history customer service solicited message according to user and the response message accumulation to history customer service request is extracted
It arrives.In accordance with an embodiment of the present disclosure, which for example can also be what the monitoring in real time of server 130 obtained.
In accordance with an embodiment of the present disclosure, which for example may include the feature that instruction has user request information, with
For characterizing the type of the solicited message of user.Alternatively, the user characteristics can also include instruction age of user (a), gender
(s), the feature of the various dimensions of information such as educational background (e), grade (l) and average call duration (t), so that the user characteristics more can
Indicate the demands of individuals of the user.In accordance with an embodiment of the present disclosure, the user characteristics of the M user obtained in aforesaid operations S210
Such as it can be by matrix Xc=(A, S, T, E, L ...) indicates that wherein A, S, T, E, L respectively represent the year of M user of instruction
The vector of the value composition of age a, gender s, average call duration t, educational background e and grade l.Correspondingly, as shown in figure 3, i-th of user
User characteristics can be expressed as
In operation S220, the customer service feature for not receiving N number of customer service of user is obtained.
Wherein, the N number of customer service for not receiving user for example can be with reference in the customer service 111,112,113 in Fig. 1
In the customer service of idle state, wherein N is natural number.In an application scenarios, which, which specifically can be, has answered user
After the customer service hotline dialed, the customer service of new customer service hotline is not answered also.The customer service feature is specifically also possible to by reference Fig. 1
Server 130 obtain, specifically can be according to the ID mark of the second terminal of feedback customer service state from server local or
It is transferred in database.It should be then previously stored and the one-to-one ID mark of each customer service in the server local or database
The corresponding relationship of will and customer service feature.
In accordance with an embodiment of the present disclosure, the customer service feature for example may include indicate customer service reception information feature, with
In the type for characterizing the solicited message (customer service request) that the customer service is capable of handling.Alternatively, the customer service feature can also include instruction
The customer service age (a), gender (s), academic (e), averagely receives the information such as duration (t) and grading system (l) at the length of service (w)
The feature of various dimensions, so that the customer service feature can preferably indicate the professional ability of the customer service.According to the implementation of the disclosure
, the customer service feature of the N number of customer service obtained in aforesaid operations S220 for example can be by matrix Xs=(A, W, S, T, E, L ...) comes
It indicates, wherein A, W, S, T, E, L respectively represent the age a for indicating N number of customer service, length of service w, gender s, averagely receive duration
T, the vector of the value composition of educational background e and grading system l.Correspondingly, as shown in figure 3, the customer service feature of j-th of customer service can indicate
For
In operation S230, according to the user characteristics of M user and the customer service feature of N number of customer service, determine that M is received in N number of customer service
The prediction duration of each user in a user obtains prediction duration collection.
In accordance with an embodiment of the present disclosure, aforesaid operations specifically for example may is that the user characteristics of M user and N number of visitor
Input of the customer service feature of clothes as machine learning model, output obtain prediction duration collection.Specific is that above-mentioned user is special
The matrix X of signcWith the matrix X of customer service featuresIt is input to the machine learning models such as tree, neural network, Bayesian networkIn, output obtains prediction duration collection Tp.Wherein, prediction duration collection TpIn specifically included N*M
It predicts duration value, that is, includes the prediction duration value that each user in M user is received in each customer service in N number of customer service.
In operation S240, according to prediction duration collection, it is determining at least one customer service of in N number of customer service it is matched at least one
By reception user, so that the sum of the matched prediction duration for being received user minimum is received at least one customer service.
In accordance with an embodiment of the present disclosure, operating each customer service at least one customer service finally determined in S240 is and matching
By reception user it is one-to-one.Operation S240 specifically for example may comprise steps of: first determination there may be
Multiple user's customer service matched groups, wherein user and customer service are matched one by one in each user's customer service matched group.Then root again
It is predicted that duration collection, determines the reception duration of the user of each customer service reception pairing in each user's customer service matched group.Then it counts
Calculate the summation of the reception duration of the user of all customer service reception pairings in each user's customer service matched group.Finally, from multiple users
In customer service matched group, determine that the smallest one group of summation of reception duration is optimal user customer service matched group, then optimal user visitor
It takes the user matched one by one in matched group to combine with the optimal user that customer service as finally determines with customer service, user therein is
For at least one customer service it is matched at least one by reception user.
In accordance with an embodiment of the present disclosure, determine that the matched operation by reception user can also for example wrap in operation S240
The operation described with reference to Fig. 4~5 is included, this will not be detailed here.
In summary, the information processing method of the embodiment of the present disclosure, when receiving the prediction of each user due to each customer service
Length is determined based on user characteristics and customer service feature, wherein consider the demand of special user and field is good in customer service,
Therefore it may make the prediction reception duration that can solve the customer service reception user of user's request shorter, without can solve user's request
The prediction reception duration that user is received in customer service is longer, that is, determining prediction duration may make more to meet actual demand, precision
It is higher.Furthermore due to finally determining matched user's customer service clock synchronization, it is confirmed that the always the smallest matching combination of prediction duration, because
This can effectively improve customer service reception efficiency, and therefore can reduce to a certain extent user's waiting time, improve user's body
It tests.
Fig. 4 diagrammatically illustrates the matched flow chart by reception user of determination according to the embodiment of the present disclosure.
In accordance with an embodiment of the present disclosure, as shown in figure 4, the operation S240 in Fig. 2 specifically for example may include operation S441
~operation S442.
In operation S441, the size relation of M Yu the N are determined.In operation S442, according to the size relation and prediction of M and N
Duration collection, it is determining at least one customer service of in N number of customer service it is matched at least one by reception user.
Wherein, operation S441 is specifically the size relation for comparing M and N.In the case where M is not less than N, in operation S442
In then can first determine that N number of user in M user is used as by reception user, then determine N number of customer service with N number of user is all can
The combination of energy, then determine each combined the sum of prediction duration in all combinations, it is finally determined from all combinations pre-
The smallest combination of the sum of duration is surveyed, that is, can determine that matched N number of by reception user one by one with N number of customer service.It is less than N in M
In the case where, M customer service then can be first determined from N number of customer service in operation S442, to be received user's as reception
Customer service, and using the M user as by reception user；Then M customer service and all possible combination of M user are determined, then
Determine each combined the sum of prediction duration in all possible combination, finally determined from all combinations prediction duration it
With the smallest combination, that is, can determine that with M by reception user's matched M customer service one by one.It is understood that above-mentioned determination
The matched method by reception user is only used as example in favor of understanding that the disclosure, the disclosure are not construed as limiting this, for example, the party
Method can also be using the method for Fig. 5 description, and this will not be detailed here.
Fig. 5 diagrammatically illustrates the matched flow chart by reception user of determination according to another embodiment of the disclosure.
In accordance with an embodiment of the present disclosure, as shown in figure 5, the method for the embodiment of the present disclosure for example can operate S541 with judgement
As beginning, subsequent operation is executed further according to judging result.That is, the operation S441 in Fig. 4 specifically can be judgement operation S541:
Judge whether M is greater than N.If M is greater than N, operation S542~operation S544 is executed.If M be not more than N, execute operation S545~
Operate S546.
Wherein, in the case where M is greater than N, operation S542 is executed, M user is successively sorted according to preset rules；Operation
S543 determines that the top n user successively to sort is by reception user；And operation S544, N number of customer service is concentrated according to prediction duration
By the prediction duration of reception user, determining and N number of customer service is matched by reception user for reception.Wherein, operation S544 specifically can be with
Include: to be concentrated according to prediction duration, is determined in each customer service reception operation S543 in N number of customer service N number of by reception user
Each of by the prediction duration of reception user, it is determining matched by reception user with each customer service in N number of customer service.According to the disclosure
Embodiment, aforesaid operations S544 specifically can also include: N number of customer service determining first and it is N number of by reception user all possibility
Combination, obtain N！A combination；Then calculate N number of customer service in each combination receive it is corresponding by reception user prediction duration it
With obtain N！The sum of a prediction duration；Again from the N！Minimum value is determined in the sum of a prediction duration, then predicts that the sum of duration takes
In the combination of the minimum value N number of customer service it is corresponding by reception user as finally determine it is matched by reception user.
In accordance with an embodiment of the present disclosure, the user characteristics for example can also include the feature of instruction user's waiting time
And/or the feature of instruction user gradation l.Then above-mentioned preset rules for example may include that the size of the value of user's waiting time is suitable
Sequence and/or the sequence of user gradation etc..Specifically, the preset rules can be the value of user's waiting time size it is suitable
Sequence then operates S542 specifically and can be and M user successively sorts according to the sequence of the value of waiting time from large to small.This is default
Rule can be the sequence of user gradation, then operates M user S542 specifically and can be according to grade from high to low
Sequence successively sorts.It is understood that operation S542 can also comprehensively consider user's waiting time value size order and
The sequence of user gradation.Specifically for example can be, first by M user according to the value of waiting time sequence from large to small according to
Minor sort；Then In Grade is high again but the sequence of the user of sequence rearward is adjusted, and the sequence of the user is adjusted to row
The forward position of sequence, or the sequence of the user is adjusted to fixed position.Or can also first by M user according to grade from
High to low sequence successively sorts；Then sequence long to waiting time again but the user of sequence rearward is adjusted, by this
The sequence of user is adjusted to forward position of sorting, or the sequence of the user is adjusted to fixed position.Alternatively, can be with
It is that the waiting time for being user and ranking score match normalized coefficient, each user and waiting time in M user is calculated
Then parameters sortnig relevant with grade successively sorts to M user according to the sequence of the value of the parameters sortnig from large to small.
It is understood that the specific implementation of aforesaid operations S542 is only used as example in favor of understanding the disclosure, the disclosure is to this
It is not construed as limiting.
Wherein, in the case where M is not more than N, operation S545 is executed, determines that M user is by reception user；And operation
S546, it is determining matched by reception user with M customer service in N number of customer service according to prediction duration collection.Wherein, operation S546 tool
Body may include: according to prediction duration concentrate each customer service in N number of customer service receive M by reception user each user it is pre-
Duration is surveyed, it is determining matched by reception user with M customer service in N number of customer service.In accordance with an embodiment of the present disclosure, aforesaid operations
S546 can specifically include: determining N number of customer service and the M all possible combinations by reception user first, obtains N！/(N-M)！
A combination；Then it calculates M customer service in each combination and receives corresponding the sum of the prediction duration by reception user, obtain N！/(N-
M)！The sum of a prediction duration；Again from the N！/(N-M)！Minimum value is determined in the sum of a prediction duration, then predicts the sum of duration
Take M in the combination of the minimum value a by the corresponding customer service of reception user as M customer service described in operation S546, to obtain
It is matched by reception user with the M customer service.
In accordance with an embodiment of the present disclosure, aforesaid operations S544 and operation S546 specifically for example can also be maximum using bipartite graph
The algorithm in the prior art such as matching algorithm is to determine customer service and by the corresponding relationship of reception user, so that all quilts determined
The sum of the prediction duration that reception user is received minimum.
In summary, the embodiment of the present disclosure passes through the matched method by reception user of above-mentioned determination, it is ensured that final
Customer service reception is minimum by the total duration of reception user, so as to effectively improve customer service reception efficiency, and therefore reduces user etc.
To duration, user experience is improved.
Fig. 6 diagrammatically illustrates the flow chart of the information processing method according to another embodiment of the disclosure.
As shown in fig. 6, the information processing method of the embodiment of the present disclosure, in addition to operating S210~operation described in Fig. 2
It can also include operation S650~operation S660 outside S240.
In accordance with an embodiment of the present disclosure, operate the prediction duration collection in S230 specifically can for example be grasped using referring in Fig. 6
Make the mode of S630 to obtain, i.e., using the user characteristics of M user and the customer service feature of N number of customer service as machine learning model
Input, output obtain prediction duration collection.
Operation S650, obtain at least one customer service receive it is matched at least one by reception user reception parameter.?
It operates S660 and the machine learning model is optimized according to the reception parameter.
Wherein, the reception parameter that operation S650 is obtained specifically can be to be obtained by the real time monitoring of server 130 in Fig. 1
, it is also possible at least one customer service after completing reception, server 130 is sent to by second terminal.The acquisition
Reception parameter may include having reception duration and reception result.Wherein, reception duration is that customer service reception is matched by reception use
Duration used in family.Reception result is then used to characterize whether be successfully processed solicited message, in one embodiment, reception result tool
Body is for the problem of whether customer service solves user's inquiry to be characterized.
Aforesaid operations S660 is specifically are as follows: with operate determined in S240 by the user characteristics of reception user and matched visitor
The customer service feature of clothes is as training sample, a length of training objective when operating the corresponding reception obtained in S650, to the machine
Device learning model is trained optimization, so that machine learning model can be improved the standard of prediction duration in subsequent use process
Exactness.
In accordance with an embodiment of the present disclosure, in order to avoid receiving the influence to machine learning model accuracy, above-mentioned behaviour in vain
Can specifically include as S660: reception result characterization is to be successfully processed to ask in the reception parameter first obtained in determining operation S650
Ask information or failed processing solicited message；Then only in the case where reception result characterization is successfully processed solicited message,
Using the corresponding user characteristics for being received user of the reception result and the customer service feature of matched customer service as training sample, to machine
Learning model optimizes training, and in the case where handling solicited message not successfully for reception result characterization, then not to machine
Learning model optimizes training.That is operation S660 specifically may is that the first customer service reception is matched at least one customer service
In the case where being successfully processed solicited message by the reception result characterization of reception user, used so that the first customer service reception is matched by reception
The reception duration at family as training objective, with the customer service feature of the first customer service and with the matched use by reception user of the first customer service
Family feature is as sample, training machine learning model.Therefore the technical solution of the present embodiment according to all compared to directly connecing
To the technical solution that parameter optimizes machine learning model, the machine learning model that optimization obtains can be further improved
Precision, to improve the accuracy that the machine learning model predicts duration obtained in subsequent use process.And therefore may be used
To further increase the accuracy rate of customer service distribution to a certain extent, customer service treatment effeciency and user experience are improved.
Fig. 7 diagrammatically illustrates the structural block diagram of the information processing unit according to open embodiment.
As shown in fig. 7, the information processing unit 700 of the embodiment of the present disclosure includes that user characteristics obtain module 710, customer service spy
Sign obtains module 720, prediction duration determining module 730 and matching module 740.
Wherein, user characteristics obtain the user characteristics that module 710 is used to obtain M user for waiting reception.The user is special
Sign for example may include having user request information, which is used to characterize the type of the solicited message of user.Wherein,
M herein is natural number.In accordance with an embodiment of the present disclosure, which obtains module 710 and for example can be used for executing reference
The operation S210 of Fig. 2 description, details are not described herein.
Wherein, customer service feature obtains the customer service feature that module 720 is used to obtain the N number of customer service for not receiving user.The customer service
Feature for example may include customer service reception information, and customer service reception information is used to characterize the type of the solicited message of customer service processing.
Wherein, N herein is natural number.In accordance with an embodiment of the present disclosure, which obtains module 720 and for example can be used for executing
With reference to the operation S220 that Fig. 2 is described, details are not described herein.
Wherein, prediction duration determining module 730 is used for the user characteristics according to M user and the customer service feature of N number of customer service,
It determines that the prediction duration of each user in M user is received in N number of customer service, obtains prediction duration collection.In accordance with an embodiment of the present disclosure,
The prediction duration determining module 730 for example can be used for executing the operation S230 described with reference to Fig. 2, and details are not described herein.
In accordance with an embodiment of the present disclosure, which specifically can be used for the user of M user
The input of feature and the customer service feature of N number of customer service as machine learning model, output obtain prediction duration collection.That is, when the prediction
Long determining module 730 specifically can be also used for executing the operation S630 with reference to Fig. 6 description, and details are not described herein.
Wherein, matching module 740 is used for according to prediction duration collection, and determination is matched at least one customer service in N number of customer service
At least one by reception user so that matched the sum of the prediction duration minimum by reception user is received at least one customer service.
In accordance with an embodiment of the present disclosure, each customer service herein with it is matched by reception user be one-to-one.Matching module 740 is for example
It can be used for executing the operation S240 described with reference to Fig. 2, details are not described herein.
In accordance with an embodiment of the present disclosure, as described in Figure 7, matching module 740 for example may include specifically that relationship determines submodule
Block 741 and matched sub-block 742.Wherein, relationship determines submodule 741 for determining the size relation of M and N.Matched sub-block
742 for the size relation and prediction duration collection according to M and N, determining matched at least at least one customer service of in N number of customer service
One by reception user.In accordance with an embodiment of the present disclosure, relationship determines that submodule 741 and matched sub-block 742 can for example divide
Operation S441~operation S442 with reference to Fig. 4 description Yong Yu not be executed, and relationship therein determines that submodule 741 specifically for example may be used
With for executing the judgement operation S541 for referring to Fig. 5 description, details are not described herein.
In accordance with an embodiment of the present disclosure, as shown in fig. 7, above-mentioned matched sub-block 742 for example may include that the first reception is used
Family determination unit 7421 and first matching user's determination unit 7422.Wherein, first reception user's determination unit 7421 is used in M
In the case where no more than N, determine that M user is by reception user.First matching user's determination unit 7422 is used for according to prediction
Duration collection, it is determining matched by reception user with M customer service in N number of customer service.In accordance with an embodiment of the present disclosure, the first reception is used
Family determination unit 7421 and first matching user's determination unit 7422 for example may be respectively used for executing the operation with reference to Fig. 5 description
S545~operation S546, details are not described herein.
In accordance with an embodiment of the present disclosure, above-mentioned user characteristics include indicating that the feature of user's waiting time and/or instruction are used
The feature of family grade.As described in Figure 7, above-mentioned matched sub-block 742 for example may include that sequencing unit 7423, second receives user
Determination unit 7424 and second matching user's determination unit 7425.Wherein, sequencing unit 7423 is used in the case where M is greater than N,
M user is successively sorted according to preset rules, the preset rules include the value of user's waiting time size order and/or
The sequence of user gradation.Second reception user's determination unit 7424 is for determining that the top n user being arranged successively is to be connect
To user.Second matching user's determination unit 7425 is used to concentrate N number of customer service reception by the pre- of reception user according to prediction duration
Duration is surveyed, it is determining matched by reception user with N number of customer service.In accordance with an embodiment of the present disclosure, sequencing unit 7423, second is received
User's determination unit 7424 and second matching user's determination unit 7425 for example may be respectively used for executing the behaviour with reference to Fig. 5 description
Make S542~operation S544, details are not described herein.
In accordance with an embodiment of the present disclosure, as shown in fig. 7, above- mentioned information processing unit 700 can also include that reception parameter obtains
Modulus block 750 and model optimization module 760.Wherein, reception parameter acquisition module 750 is for obtaining at least one customer service reception
At least one matched is by the reception parameter of reception user.Model optimization module 760 is used to optimize machine learning according to reception parameter
Model.Wherein, reception parameter includes reception duration and reception as a result, whether the reception result is successfully processed request letter for characterizing
Breath.In accordance with an embodiment of the present disclosure, receiving parameter acquisition module 750 and model optimization module 760 for example may be respectively used for holding
Row is with reference to operation S650~operation S660 of Fig. 6 description, and details are not described herein.
In accordance with an embodiment of the present disclosure, model optimization module 760 specifically for example can be used at least one customer service the
One customer service receive it is matched by reception user reception result characterization be successfully processed solicited message in the case where, connect with the first customer service
Reception duration by reception user to be matched is matched as training objective with the customer service feature of the first customer service and with the first customer service
By reception user user characteristics as sample, training machine learning model.
It is module according to an embodiment of the present disclosure, submodule, unit, any number of or in which any more in subelement
A at least partly function can be realized in a module.It is single according to the module of the embodiment of the present disclosure, submodule, unit, son
Any one or more in member can be split into multiple modules to realize.According to the module of the embodiment of the present disclosure, submodule,
Any one or more in unit, subelement can at least be implemented partly as hardware circuit, such as field programmable gate
Array (FPGA), programmable logic array (PLA), system on chip, the system on substrate, the system in encapsulation, dedicated integrated electricity
Road (ASIC), or can be by the hardware or firmware for any other rational method for integrate or encapsulate to circuit come real
Show, or with any one in three kinds of software, hardware and firmware implementations or with wherein any several appropriately combined next reality
It is existing.Alternatively, can be at least by part according to one or more of the module of the embodiment of the present disclosure, submodule, unit, subelement
Ground is embodied as computer program module, when the computer program module is run, can execute corresponding function.
For example, user characteristics obtain module 710, customer service feature obtains module 720, prediction duration determining module 730, matching
Module 740, reception parameter acquisition module 750, model optimization module 760, relationship determine submodule 741, matched sub-block 742,
The first reception matching of user's determination unit 7421, first user's determination unit 7422, the reception user of sequencing unit 7423, second are true
Order member 7424 and second matching user's determination unit 7425 in any number of may be incorporated in a module realize, or
Person's any one module therein can be split into multiple modules.Alternatively, one or more modules in these modules are extremely
Small part function can be combined at least partly function of other modules, and be realized in a module.According to the disclosure
Embodiment, user characteristics obtain module 710, customer service feature obtains module 720, prediction duration determining module 730, matching module
740, parameter acquisition module 750, model optimization module 760, relationship are received and determines submodule 741, matched sub-block 742, first
It receives user's determination unit 7421, first and matches user's determination unit 7422, the determining list of the reception user of sequencing unit 7423, second
At least one of member 7424 and second matching user's determination unit 7425 can at least be implemented partly as hardware circuit,
Such as field programmable gate array (FPGA), programmable logic array (PLA), system on chip, the system on substrate, in encapsulation
System, specific integrated circuit (ASIC), or can be by carrying out integrated or any other rational method encapsulated etc. to circuit
Hardware or firmware realize, or with any one in three kinds of software, hardware and firmware implementations or with wherein any several
Appropriately combined realize.Alternatively, user characteristics obtain module 710, customer service feature obtains module 720, prediction duration determines mould
Block 730, matching module 740, reception parameter acquisition module 750, model optimization module 760, relationship determine submodule 741, matching
Submodule 742, first receives user's determination unit 7421, first and matches user's determination unit 7422, sequencing unit 7423, second
Receiving at least one of user's determination unit 7424 and second matching user's determination unit 7425 can be at least by partly
It is embodied as computer program module, when the computer program module is run, corresponding function can be executed.
Fig. 8 is diagrammatically illustrated according to the information processing system for being adapted for carrying out information processing method of the embodiment of the present disclosure
Structural block diagram.
As shown in figure 8, information processing system 800 includes processor 810 and computer readable storage medium 820.The information
Processing system 800 can execute the method according to the embodiment of the present disclosure.
Specifically, processor 810 for example may include general purpose microprocessor, instruction set processor and/or related chip group
And/or special microprocessor (for example, specific integrated circuit (ASIC)), etc..Processor 810 can also include using for caching
The onboard storage device on way.Processor 810 can be the different movements for executing the method flow according to the embodiment of the present disclosure
Single treatment unit either multiple processing units.
Computer readable storage medium 820, such as can be non-volatile computer readable storage medium, specific example
Including but not limited to: magnetic memory apparatus, such as tape or hard disk (HDD)；Light storage device, such as CD (CD-ROM)；Memory, such as
Random access memory (RAM) or flash memory；Etc..
Computer readable storage medium 820 may include computer program 821, which may include generation
Code/computer executable instructions execute processor 810 according to the embodiment of the present disclosure
Method or its any deformation.
Computer program 821 can be configured to have the computer program code for example including computer program module.Example
Such as, in the exemplary embodiment, the code in computer program 821 may include one or more program modules, for example including
821A, module 821B ....It should be noted that the division mode and number of module are not fixation, those skilled in the art can
To be combined according to the actual situation using suitable program module or program module, when these program modules are combined by processor 810
When execution, processor 810 is executed according to the method for the embodiment of the present disclosure or its any deformation.
According to an embodiment of the invention, user characteristics obtain module 710, customer service feature obtains module 720, prediction duration is true
Cover half block 730, matching module 740, reception parameter acquisition module 750, model optimization module 760, relationship determine submodule 741,
Matched sub-block 742, first receive user's determination unit 7421, first match user's determination unit 7422, sequencing unit 7423,
At least one of second reception user's determination unit 7424 and second matching user's determination unit 7425 can be implemented as joining
Corresponding operating described above may be implemented when being executed by processor 810 in the computer program module for examining Fig. 8 description.
The disclosure additionally provides a kind of computer readable storage medium, which can be above-mentioned reality
It applies included in equipment/device/system described in example；Be also possible to individualism, and without be incorporated the equipment/device/
In system.Above-mentioned computer readable storage medium carries one or more program, when said one or multiple program quilts
When execution, the method according to the embodiment of the present disclosure is realized.
In accordance with an embodiment of the present disclosure, computer readable storage medium can be non-volatile computer-readable storage medium
Matter, such as can include but is not limited to: portable computer diskette, hard disk, random access storage device (RAM), read-only memory
(ROM), erasable programmable read only memory (EPROM or flash memory), portable compact disc read-only memory (CD-ROM), light
Memory device, magnetic memory device or above-mentioned any appropriate combination.In the disclosure, computer readable storage medium can
With to be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
Person is in connection.
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the disclosure, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
It will be understood by those skilled in the art that the feature recorded in each embodiment and/or claim of the disclosure can
To carry out multiple combinations and/or combination, even if such combination or combination are not expressly recited in the disclosure.Particularly, exist
In the case where not departing from disclosure spirit or teaching, the feature recorded in each embodiment and/or claim of the disclosure can
To carry out multiple combinations and/or combination.All these combinations and/or combination each fall within the scope of the present disclosure.
Although the disclosure, art technology has shown and described referring to the certain exemplary embodiments of the disclosure
Personnel it should be understood that in the case where the spirit and scope of the present disclosure limited without departing substantially from the following claims and their equivalents,
A variety of changes in form and details can be carried out to the disclosure.Therefore, the scope of the present disclosure should not necessarily be limited by above-described embodiment,
But should be not only determined by appended claims, also it is defined by the equivalent of appended claims.
Claims (10)
1. a kind of information processing method, which comprises
Obtain the user characteristics for waiting M user of reception；
Obtain the customer service feature for not receiving N number of customer service of user；
According to the user characteristics of the M user and the customer service feature of N number of customer service, determine that the M is received in N number of customer service
The prediction duration of each user in a user obtains prediction duration collection；And
According to the prediction duration collection, it is determining at least one customer service in N number of customer service it is matched at least one received
User, so that the sum of the matched prediction duration for being received user minimum is received at least one described customer service,
Wherein, each customer service is corresponded with matched by reception user, and M and N are natural number.
2. according to the method described in claim 1, wherein:
The prediction duration of each user in the M user is received in determination N number of customer service, obtains prediction duration Ji Bao
It includes: using the user characteristics of the M user and the customer service feature of N number of customer service as the input of machine learning model, output
Obtain the prediction duration collection；And/or
The user characteristics include the feature for indicating user request information, and the user request information is for characterizing the user's
The type of solicited message；And/or
The customer service feature includes indicating the feature of customer service reception information, and the customer service reception information is for characterizing at the customer service
The type of the solicited message of reason.
3. according to the method described in claim 2, further include:
Obtain at least one described customer service receive it is matched it is described at least one by the reception parameter of reception user, the reception is joined
Number includes reception duration and reception as a result, whether the reception result is successfully processed solicited message for characterization；And
According to the reception parameter, optimize the machine learning model.
4. according to the method described in claim 3, wherein, according to the reception parameter, optimizing the machine learning model includes:
The first customer service receives the matched reception result characterization for being received user and is successfully processed institute at least one described customer service
In the case where stating solicited message, the matched reception duration by reception user is received as training objective using first customer service,
Using the customer service feature of first customer service and with the matched user characteristics by reception user of first customer service as sample, instruct
Practice the machine learning model.
5. according to the method described in claim 1, wherein, according to the prediction duration collection, it is determining in N number of customer service extremely
A few customer service it is matched at least one by reception user include:
Determine the size relation of the M Yu the N；And
According to the size relation of the M and N and the prediction duration collection, at least one of determining and N number of customer service
Customer service it is matched at least one by reception user.
6. according to the method described in claim 5, wherein, when the size relation and the prediction according to the M and N
Long collection, it is determining at least one customer service in N number of customer service it is matched at least one by reception user include:
In the case where the M is not more than the N, determine that the M user is by reception user；And
It is determining matched by reception user with M customer service in N number of customer service according to the prediction duration collection.
7. according to the method described in claim 5, wherein, the user characteristics include indicate user's waiting time feature and/
Or the feature of instruction user gradation, the size relation according to the M and N and the prediction duration collection, determining and institute
State at least one customer service in N number of customer service it is matched at least one by reception user include:
In the case where the M is greater than the N, the M user is successively sorted according to preset rules, the preset rules packet
Include the size order of the value of user's waiting time and/or the sequence of the user gradation；
Determine that the top n user successively to sort is by reception user；And
Receive the prediction duration by reception user according to N number of customer service described in the prediction duration collection, it is determining with it is described N number of
Customer service is matched by reception user.
8. a kind of information processing unit, comprising:
User characteristics obtain module, for obtaining the user characteristics for waiting M user of reception；
Customer service feature obtains module, for obtaining the customer service feature for not receiving N number of customer service of user；
Predict duration determining module, for according to the user characteristics of the M user and the customer service feature of N number of customer service, really
The prediction duration of each user in the M user is received in fixed N number of customer service, obtains prediction duration collection；And
Matching module, for according to the prediction duration collection, determination and at least one customer service in N number of customer service to be matched extremely
Few one is received user, so that the sum of the matched prediction duration for being received user minimum is received at least one described customer service,
Wherein, each customer service is corresponded with matched by reception user, and M and N are natural number.
9. a kind of information processing system, comprising:
One or more processors；
Storage device, for storing one or more programs,
Wherein, when one or more of programs are executed by one or more of processors, so that one or more of
Method described in processor execution according to claim 1~any one of 7.
10. a kind of computer readable storage medium, is stored thereon with executable instruction, which makes to handle when being executed by processor
Method described in device execution according to claim 1~any one of 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910382630.2A CN110147905B (en) | 2019-05-08 | 2019-05-08 | Information processing method, device, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910382630.2A CN110147905B (en) | 2019-05-08 | 2019-05-08 | Information processing method, device, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110147905A true CN110147905A (en) | 2019-08-20 |
| CN110147905B CN110147905B (en) | 2022-03-25 |
Family
ID=67594955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910382630.2A Active CN110147905B (en) | 2019-05-08 | 2019-05-08 | Information processing method, device, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110147905B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110837587A (en) * | 2019-09-30 | 2020-02-25 | 北京健康之家科技有限公司 | Data matching method and system based on machine learning |
| CN112217672A (en) * | 2020-09-30 | 2021-01-12 | 安徽极玩云科技有限公司 | Service processing system for CDN platform |
| CN112435037A (en) * | 2019-08-23 | 2021-03-02 | 腾讯科技（深圳）有限公司 | Customer service providing method, device, equipment and storage medium |
| CN113627782A (en) * | 2021-08-09 | 2021-11-09 | 众安在线财产保险股份有限公司 | Customer service seat allocation method, scoring model training method and device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100010802A1 (en) * | 2008-07-14 | 2010-01-14 | International Business Machines Corporation | System and Method for User Skill Determination |
| CN104539814A (en) * | 2014-11-26 | 2015-04-22 | 小米科技有限责任公司 | Customer service call forwarding method and device |
| CN104778532A (en) * | 2015-03-12 | 2015-07-15 | 科大国创软件股份有限公司 | Intelligent calling center management system and intelligent scheduling control method |
| CN105930353A (en) * | 2016-04-08 | 2016-09-07 | 西安美林数据技术股份有限公司 | Feature subdivision method for call center customer service staff in mass data |
| CN106572273A (en) * | 2016-10-19 | 2017-04-19 | 上海携程商务有限公司 | Matching system of user incoming call access customer service line and method thereof |
| CN107888646A (en) * | 2017-09-15 | 2018-04-06 | 广州唯品会研究院有限公司 | A kind of user's customer service enters lines matching method and apparatus |
| CN107909225A (en) * | 2017-12-12 | 2018-04-13 | 链家网（北京）科技有限公司 | A kind of loan in house prosperity transaction is made loans duration prediction method |
| CN107968897A (en) * | 2017-11-03 | 2018-04-27 | 平安科技（深圳）有限公司 | Customer service session distribution method, electronic device and computer-readable recording medium |
| CN108683818A (en) * | 2018-09-03 | 2018-10-19 | 携程旅游信息技术（上海）有限公司 | Call center distributes method, system, equipment and the storage medium attended a banquet |
| CN109272129A (en) * | 2018-09-20 | 2019-01-25 | 重庆先特服务外包产业有限公司 | Call center's business management system |
-
2019
- 2019-05-08 CN CN201910382630.2A patent/CN110147905B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100010802A1 (en) * | 2008-07-14 | 2010-01-14 | International Business Machines Corporation | System and Method for User Skill Determination |
| CN104539814A (en) * | 2014-11-26 | 2015-04-22 | 小米科技有限责任公司 | Customer service call forwarding method and device |
| CN104778532A (en) * | 2015-03-12 | 2015-07-15 | 科大国创软件股份有限公司 | Intelligent calling center management system and intelligent scheduling control method |
| CN105930353A (en) * | 2016-04-08 | 2016-09-07 | 西安美林数据技术股份有限公司 | Feature subdivision method for call center customer service staff in mass data |
| CN106572273A (en) * | 2016-10-19 | 2017-04-19 | 上海携程商务有限公司 | Matching system of user incoming call access customer service line and method thereof |
| CN107888646A (en) * | 2017-09-15 | 2018-04-06 | 广州唯品会研究院有限公司 | A kind of user's customer service enters lines matching method and apparatus |
| CN107968897A (en) * | 2017-11-03 | 2018-04-27 | 平安科技（深圳）有限公司 | Customer service session distribution method, electronic device and computer-readable recording medium |
| CN107909225A (en) * | 2017-12-12 | 2018-04-13 | 链家网（北京）科技有限公司 | A kind of loan in house prosperity transaction is made loans duration prediction method |
| CN108683818A (en) * | 2018-09-03 | 2018-10-19 | 携程旅游信息技术（上海）有限公司 | Call center distributes method, system, equipment and the storage medium attended a banquet |
| CN109272129A (en) * | 2018-09-20 | 2019-01-25 | 重庆先特服务外包产业有限公司 | Call center's business management system |
Non-Patent Citations (2)
| Title |
|---|
| 曹斌等: ""Uroad：一种高效的大规模多对多拼车匹配算法"", 《计算机研究与发展》 * |
| 郑树泉等: "《工业智能技术与应用》", 31 January 2019, 上海科学技术出版社 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112435037A (en) * | 2019-08-23 | 2021-03-02 | 腾讯科技（深圳）有限公司 | Customer service providing method, device, equipment and storage medium |
| CN112435037B (en) * | 2019-08-23 | 2023-10-17 | 腾讯科技（深圳）有限公司 | Customer service providing method, customer service providing device, customer service providing equipment and storage medium |
| CN110837587A (en) * | 2019-09-30 | 2020-02-25 | 北京健康之家科技有限公司 | Data matching method and system based on machine learning |
| CN110837587B (en) * | 2019-09-30 | 2023-05-23 | 北京水滴科技集团有限公司 | Data matching method and system based on machine learning |
| CN112217672A (en) * | 2020-09-30 | 2021-01-12 | 安徽极玩云科技有限公司 | Service processing system for CDN platform |
| CN113627782A (en) * | 2021-08-09 | 2021-11-09 | 众安在线财产保险股份有限公司 | Customer service seat allocation method, scoring model training method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110147905B (en) | 2022-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110147905A (en) | Information processing method, device, system and storage medium | |
| CN102300012B (en) | One-to-one matching in contact center | |
| EP3314873B1 (en) | System and method for intelligent task management and routing | |
| CN102300009B (en) | For without the view of queue call center and criterion | |
| CN102300011B (en) | Automated mechanism for populating and maintaining data structures in queueless contact center | |
| CN108734293A (en) | Task management system, method and apparatus | |
| CN108683818A (en) | Call center distributes method, system, equipment and the storage medium attended a banquet | |
| EP3366025A1 (en) | Optimized routing of interactions to contact center agents based on machine learning | |
| WO2022020796A1 (en) | Method and system for scalable contact center agent scheduling utilizing automated ai modeling and multi-objective optimization | |
| CN102223453A (en) | High performance queueless contact center | |
| WO2020102093A1 (en) | System and method of assigning customer service tickets | |
| CN110264036A (en) | Method for scheduling task and device | |
| CN105094641A (en) | Question-answer interaction method and device based on voice | |
| CN112700199B (en) | Order data processing method and device, storage medium and computer equipment | |
| WO2022104266A1 (en) | Machine learning system for routing optimization based on historical performance data | |
| CN113379229A (en) | Resource scheduling method and device | |
| CN106649743A (en) | Method and system for storing and sharing creative idea classified brain library resources | |
| CN116414955B (en) | Intelligent queuing method, device, equipment and medium based on client intention and intention | |
| US20180211199A1 (en) | Decision engine for generating interfaces to simulate and optimize employee scheduling in work locations | |
| CN109493186A (en) | The method and apparatus for determining pushed information | |
| AU2022345015A1 (en) | System and method for improvements to pre-processing of data for forecasting | |
| WO2021229625A1 (en) | Learning device, learning method, and learning program | |
| CN107688499A (en) | A kind of queued event processing method and system | |
| US20230297909A1 (en) | System and method for predicting service metrics using historical data | |
| KR102564164B1 (en) | Job matching management server based on clustering |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |