CN109670031A - Data processing method and device - Google Patents
Data processing method and device Download PDFInfo
- Publication number
- CN109670031A CN109670031A CN201811646050.1A CN201811646050A CN109670031A CN 109670031 A CN109670031 A CN 109670031A CN 201811646050 A CN201811646050 A CN 201811646050A CN 109670031 A CN109670031 A CN 109670031A
- Authority
- CN
- China
- Prior art keywords
- data
- client
- questions
- label
- historical interaction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present application discloses a kind of data processing method and device, during electronic customer care and client interact, when getting the instruction for artificial customer service of transferring, if the data volume of the historical interaction data of electronic customer care and client is without departing from preset threshold, all historical interaction datas are then transmitted to manual board client with road, otherwise, it is filtered out from historical interaction data and meets the data of preset condition and be transmitted to manual board client with road, to guarantee that the data volume for being transmitted to operator attendance with road is less, scenario reduction is quickly carried out convenient for operator attendance.
Description
Technical field
This application involves technical field of data processing, more specifically to a kind of data processing method and device.
Background technique
Currently, online customer service is combined using electronic customer care (carrying out response to client questions by machine) and artificial customer service
Mode, provide timely service in various applications for client.It, can be excellent when general online customer service gets the service request of client
First select electronic customer care for offering customers service, when electronic customer care can not solve the problems, such as user, then artificial customer service of transferring.
By electronic customer care transfer artificial customer service when, online customer service system can hand over the history of existing customer and electronic customer care
Mutual data are transferred to manual board client with road, for operator attendance browsing, are convenient for quick location client problem.However, working as
When the historical interaction data of client and electronic customer care is excessive, not only data are transmitted and generate pressure, it is clear also to extend operator attendance
Time of data is look at, the efficiency of location client problem is reduced.
Therefore, how to help the quick location client problem of operator attendance to become while reducing volume of transmitted data urgently to solve
Certainly the technical issues of.
Summary of the invention
The purpose of the application is to provide a kind of data processing method and device, with it is at least part of overcome deposit in the prior art
The technical issues of.
To achieve the above object, this application provides following technical solutions:
A kind of data processing method, comprising:
During electronic customer care and client interact, when getting the instruction for artificial customer service of transferring, institute is judged
Whether the data volume for stating electronic customer care and the historical interaction data of the client exceeds preset threshold；
If judging result be it is no, the historical interaction data is transmitted to manual board client with road；
If the determination result is YES, the data for meeting preset condition are filtered out from the historical interaction data, will be filtered out
Data be transmitted to manual board client with road, so that operator attendance quickly carries out scenario reduction.
The above method, it is preferred that described that the data for meeting preset condition, packet are filtered out from the historical interaction data
It includes:
Temporally the sequence for the row of falling determines the data of preset quantity from the historical interaction data；
Target data, the target data are filtered out from the part data beyond the preset quantity are as follows: with business
Relevant client questions, machine response corresponding with the client questions, the machine response miss answer；
The data of the preset quantity and the target data are to meet the data of preset condition.
The above method, it is preferred that further include:
During electronic customer care and client interact, the first label is carried out to client questions, to the client
Corresponding machine response is putd question to carry out the second label；
Whether first label is related to business for characterizing the client questions, and second label is for characterizing
State whether machine response hits answer.
The above method, it is preferred that described that first label is carried out to client questions, comprising:
Word segmentation processing is carried out to the client questions, obtains multiple participles；
Judge with the presence or absence of at least one of the multiple participle in preset business dictionary, if the determination result is YES,
By the client questions labeled as related to business, otherwise the client questions are labeled as unrelated with business.
The above method, it is preferred that described that second label is carried out to machine response corresponding with the client questions, comprising:
It is miss answer by the machine respond flag if the machine response is obtained from preset knowledge base,
It otherwise is hit answer by the machine respond flag.
The above method, it is preferred that it is described to filter out target data from the part data beyond the preset quantity, it wraps
It includes:
According to the corresponding label of data, target data is filtered out from the part data beyond the preset quantity.
A kind of data processing equipment, comprising:
Judgment module, for during electronic customer care and client interact, when getting the artificial customer service of switching
When instruction, judge whether the electronic customer care and the data volume of the historical interaction data of the client exceed preset threshold；
Processing module, if for judging result be it is no, the historical interaction data is transmitted to operator attendance client with road
End；If the determination result is YES, the data for meeting preset condition are filtered out from the historical interaction data, the data that will be filtered out
It is transmitted to manual board client with road, so that operator attendance quickly carries out scenario reduction.
Above-mentioned apparatus, it is preferred that the processing module is filtered out from the historical interaction data meets preset condition
Data, comprising:
The sequence that the processing module is temporally arranged determines the data of preset quantity from the historical interaction data；From
Target data, the target data are filtered out in part data beyond the preset quantity are as follows: client relevant to business
It puts question to, machine response corresponding with the client questions, the machine response miss answer；The data of the preset quantity with
And the target data is to meet the data of preset condition.
Above-mentioned apparatus, it is preferred that further include:
Mark module, for carrying out the first label to client questions during electronic customer care and client interact,
Second label is carried out to machine response corresponding with the client questions；First label for characterizing the client questions is
No related to business, second label is for characterizing whether the machine response hits answer.
Above-mentioned apparatus, it is preferred that mark module carries out the first label to client questions, comprising: mark module mentions client
It asks carry out word segmentation processing, obtains multiple participles；Judge to whether there is at least one of multiple participles in preset business dictionary,
If the determination result is YES, by client questions labeled as related to business, otherwise client questions are labeled as unrelated with business.
Above-mentioned apparatus, it is preferred that mark module pair machine response corresponding with client questions carries out the second label, comprising:
It is miss answer by machine respond flag, otherwise by machine response mark if machine response is obtained from preset knowledge base
It is denoted as hit answer.
Above-mentioned apparatus, it is preferred that the processing module filters out mesh from the part data beyond the preset quantity
Mark data, comprising:
The processing module is filtered out from the part data beyond the preset quantity according to the corresponding label of data
Target data.
Data processing method provided by the present application and device, during electronic customer care and client interact, when obtaining
When getting the instruction for artificial customer service of transferring, if the data volume of the historical interaction data of electronic customer care and client is without departing from default threshold
Value, then be transmitted to manual board client with road for all historical interaction datas, otherwise, symbol filtered out from historical interaction data
The data for closing preset condition are transmitted to manual board client with road, thus guarantee to be transmitted to road the data volume of operator attendance compared with
It is few, scenario reduction is quickly carried out convenient for operator attendance.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of implementation flow chart of data processing method provided by the embodiments of the present application；
Fig. 2 filters out the one kind for meeting the data of preset condition to be provided by the embodiments of the present application from historical interaction data
Implementation flow chart；
Fig. 3 is another implementation flow chart of data processing method provided by the embodiments of the present application；
Fig. 4 is a kind of structural schematic diagram of data processing equipment provided by the embodiments of the present application.
Specification and claims and term " first " in above-mentioned attached drawing, " second ", " third " " the 4th " etc. (if
In the presence of) it is part for distinguishing similar, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so that embodiments herein described herein can be in addition to illustrating herein
Sequence in addition is implemented.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under that premise of not paying creative labor
Embodiment shall fall within the protection scope of the present invention.
A kind of implementation flow chart of data processing method provided by the present application is as shown in Figure 1, may include:
Step S11: during electronic customer care and client interact, when the instruction for getting artificial customer service of transferring
When, judge whether the data volume of electronic customer care and the historical interaction data of client exceeds preset threshold, if judging result be it is no, hold
Row step S12 if the determination result is YES executes step S13.
During electronic customer care and client interact, if electronic customer care can not provide effective service for client,
Client may select switching human customer, alternatively, online customer service system can actively be the artificial customer service of user call, therefore, on
The instruction for stating artificial customer service of transferring may be to be triggered to generate by client, it is also possible to which online customer service system automatic trigger generates.
Step S12: historical interaction data is transmitted to manual board client with road.
In the application, if the data volume of the historical interaction data of electronic customer care and client is smaller, since operator attendance is clear
It lookes at no pressure, therefore historical interaction data is not screened and directly transmitted with road, when can save the response of customer service system
Between and process resource.
Step S13: filtering out the data for meeting preset condition from historical interaction data, and the data filtered out are passed with road
Manual board client is transported to, so that operator attendance quickly carries out scenario reduction.
In the application, if the data volume of the historical interaction data of electronic customer care and client is bigger, filter out meet it is pre-
If the data of condition are transmitted with road, in order to which operator attendance can accomplish that synchronizing information and scene quickly restore.Wherein, meet pre-
If the data of condition are the historical interaction datas for referring to that operator attendance is helped quickly to carry out scenario reduction.
When transmitting the data screened with road, the data screened are transmitted with road according to chronological order
To manual board client.
Data processing method provided by the present application turns during electronic customer care and client interact when getting
It is not that the historical interaction data of electronic customer care and client are directly transmitted to operator attendance visitor with road when connecing the instruction of artificial customer service
Family end, but first judge whether the data volume of historical interaction data exceeds preset threshold, it is determined and is needed with road according to judging result
The historical interaction data of transmission guarantees that the data volume for being transmitted to operator attendance with road is less, at the same convenient for operator attendance quickly into
Row scenario reduction.
It is above-mentioned that the one kind for meeting the data of preset condition is filtered out from historical interaction data in an optional embodiment
Implementation flow chart is as shown in Fig. 2, may include:
Step S21: temporally the sequence for the row of falling determines the data of preset quantity from historical interaction data.
That is, the data of identified preset quantity are in above-mentioned historical interaction data, it is nearest apart from current time
Interaction data several times.
Step S22: target data is filtered out from the part data beyond preset quantity, the target data are as follows: with industry
It is engaged in relevant client questions, machine response corresponding with the client questions, the machine response miss answer.
Machine response, that is, electronic customer care is directed to the answer that client questions provide.Specific screening process can be with are as follows:
The part data that will exceed preset quantity are cut into several sub- friendships in the way of " client questions-machine response "
Mutual segment, sub- interacting fragments go to judge whether client questions are related to business one by one, and whether machine response hits answer, and group is handed over
Client questions in mutual segment are related to business, and when machine response miss answer, determine that the sub- interacting fragments are number of targets
According to.
In the application, for identified above-mentioned preset quantity data without screening, and only to historical interaction data
In in the data interaction data that is screened, and screened beyond above-mentioned preset quantity, including client questions and corresponding machine
Device response, wherein client questions are related to business, but corresponding machine response miss answer.
The data of above-mentioned preset quantity and above-mentioned target data are to meet the data of preset condition.
For example, it is assumed that client A is interacted since 9:00 with electronic customer care, electronic customer care prompt is wanted when 9:05
It transfers artificial customer service, then the historical interaction data of electronic customer care and client A are the interaction numbers from 9:00 to 9:05 in this period
According to.Assuming that interaction data amount in this time is 614KB, and above-mentioned preset quantity is 512KB, then in the application, according to when
Between sequence from back to front, i.e., determine the data of 512KB forward since 9:05, it is assumed that from 9:02 to 9:05 in this period
Interaction data is 512KB, then screens to the interaction data in this period from 9:00 to 9:02, obtain target data,
That is target data is a part of the interaction data from 9:00 to 9:02 in this period.The number of targets then screened
According to, and interaction data from 9:02 to 9:05 in this period is the data for meeting preset condition.
The application thinks the nearest (number for the preset quantity that the sequence of the i.e. above-mentioned temporally row of falling determines of intersection record several times
According to) it can most reflect that client's selection turns artificial concrete reason, so nearest intersection record is not dealt with, and only to other portions
The data divided are screened, and accomplish synchronizing information convenient for operator attendance, scene quickly restores.
In an optional embodiment, data processing method provided by the present application can also include:
During electronic customer care and client interact, the first label is carried out to client questions, to client questions
Corresponding machine response carries out the second label.
Whether the first label is related to business for characterizing client questions, and the second label is for characterizing whether machine response orders
Middle answer.
In the embodiment of the present application, during electronic customer care and client interact to client questions and machine response into
Line flag, so that after the instruction for getting artificial customer service of transferring data processing can be improved according to quick garbled data is marked
Efficiency.
In an optional embodiment, a kind of above-mentioned implementation for carrying out the first label to client questions can be with are as follows:
Word segmentation processing is carried out to client questions, obtains multiple participles.
Judge with the presence or absence of at least one of above-mentioned multiple participles in preset business dictionary, if the determination result is YES,
By client questions labeled as related to business, otherwise client questions are labeled as unrelated with business.
The vocabulary stored in business dictionary is business relative words.When there is at least one participle to be industry in above-mentioned more participles
Be engaged in dictionary in word when, illustrate that client questions are related to business, otherwise, illustrate that client questions are unrelated with business.
In an optional embodiment, a kind of above-mentioned reality that the second label is carried out to machine response corresponding with client questions
Existing mode can be with are as follows:
It is miss answer by machine respond flag, otherwise by machine if machine response is obtained from preset knowledge base
Device respond flag is hit answer.
For electronic customer care during interacting with client, the answer of electronic customer care is from knowledge base (knowledge base
For storing model answer), after carrying out a series of logical process to client questions, answered if not finding standard in knowledge base
Case can then provide the response of non-answer that is, without hit answer.Therefore, if machine response is obtained from preset knowledge base,
Illustrate machine response miss answer, otherwise illustrates that answer is hit in machine response.
Wherein, a series of process for carrying out logical process to client questions may include:
Word segmentation processing is carried out to client questions, obtains several participles；Keyword is extracted from several participles, preset
The knowledge entry comprising extracted keyword is searched in knowledge base；If finding knowledge entry, illustrate there is model answer, otherwise
Illustrate no model answer.
For example, it is assumed that client questions are as follows: how I, which open, in Mobile banking is exempted from close payment.The client questions are by participle
Reason, can be segmented as follows: Mobile banking, it is upper, I, how, open, exempt from close payment, extract keyword from above-mentioned 6 participles
Are as follows: Mobile banking opens, exempts from close payment, then in knowledge base search comprising Mobile banking, open, exempt from it is close payment these three
The knowledge entry found is fed back to client, machine response at this time if finding knowledge entry by the knowledge entry of keyword
Answer is hit, if not finding knowledge entry, other response contents, at this time machine response are returned to client according to logic of propositions
Miss answer.
Due to being marked during electronic customer care is with customer interaction to client questions and machine response, from
It, can be directly according to the corresponding label of data, from beyond preset quantity when screening target data in the data beyond preset quantity
Data in filter out target data, without analyzing whether data meet preset condition again, to further increase at data
Manage efficiency.
Another implementation flow chart of data processing method provided by the present application is as shown in figure 3, may include:
Step S301: client enters electronic customer care scene.
Step S302: electronic customer care is repeatedly interacted with client, in interactive process, mark client questions whether with business phase
It closes, whether machine response hits answer.
Step S303: selection turns artificial.Client's selection or electronic customer care automatically select.
Does is step S304: the data volume for judging historical interaction data more than threshold value? if it is not, S305 is entered step, if so,
Then enter step S306.
Step S305: not handled historical data, is all transmitted with road.
Step S306: historical interaction data is temporally arranged.
Step S307: the interaction data within number of thresholds is as basic interacting fragments.
Step S308: beyond the interaction data other than threshold value by " client questions-machine response " if in the way of be cut into
Do sub- interacting fragments.
Step S309: selection one sub- interacting fragments not judged, judge the sub- interacting fragments client questions whether with
Business is related, if it is not, then entering step S310, enters step S311 if so, sentencing.
Step S310: skipping this sub- interacting fragments, i.e., no longer analyzes the sub- interacting fragments.
Step S311: judging whether the machine response of sub- interacting fragments hits answer, if so, S310 is entered step, if
It is no, then enter step S312.
Step S312: sub- interacting fragments are spliced in basic interacting fragments.
Step S313: judge whether all traversal finishes all sub- interacting fragments, if so, entering step S314, otherwise
Return step S309.
Step S314: spliced data are transmitted with road.
Corresponding with embodiment of the method, the application also provides a kind of data processing equipment, data processing provided by the present application
A kind of structural schematic diagram of device is as shown in figure 4, may include:
Judgment module 41 and processing module 42；Wherein,
Judgment module 41 is used for during electronic customer care and client interact, when getting the artificial customer service of switching
When instruction, judge whether the data volume of electronic customer care and the historical interaction data of client exceeds preset threshold；
If processing module 42 for judging result be it is no, historical interaction data is transmitted to manual board client with road；
If the determination result is YES, the data for meeting preset condition are filtered out from historical interaction data, and the data filtered out are passed with road
Manual board client is transported to, so that operator attendance quickly carries out scenario reduction.
In the application, if the data volume of the historical interaction data of electronic customer care and client is smaller, since operator attendance is clear
It lookes at no pressure, therefore historical interaction data is not screened and directly transmitted with road, when can save the response of customer service system
Between and process resource.
If the data volume of the historical interaction data of electronic customer care and client is bigger, the number for meeting preset condition is filtered out
It is transmitted according to road, in order to which operator attendance can accomplish that synchronizing information and scene quickly restore.Wherein, meet the number of preset condition
According to being to refer to that operator attendance is helped quickly to carry out the historical interaction data of scenario reduction.
When transmitting the data screened with road, the data screened are transmitted with road according to chronological order
To manual board client.
Data processing equipment provided by the present application turns during electronic customer care and client interact when getting
It is not that the historical interaction data of electronic customer care and client are directly transmitted to operator attendance visitor with road when connecing the instruction of artificial customer service
Family end, but first judge whether the data volume of historical interaction data exceeds preset threshold, it is determined and is needed with road according to judging result
The historical interaction data of transmission guarantees that the data volume for being transmitted to operator attendance with road is less, at the same convenient for operator attendance quickly into
Row scenario reduction.
In an optional embodiment, processing module 42 filters out the number for meeting preset condition from historical interaction data
According to, comprising:
The sequence that processing module 42 is temporally arranged determines the data of preset quantity from historical interaction data；From beyond pre-
It sets in the part data of quantity and filters out target data, target data are as follows: client questions relevant to business, with client questions
Corresponding machine response, wherein machine response miss answer；The data and target data of the preset quantity of above-mentioned determination are
For the data for meeting preset condition.
In an optional embodiment, above-mentioned data processing equipment can also include:
Mark module, for carrying out the first label to client questions during electronic customer care and client interact,
Second label is carried out to machine response corresponding with client questions；First label for characterize client questions whether with business phase
It closes, the second label is for characterizing whether machine response hits answer.
In an optional embodiment, mark module carries out the first label to client questions, comprising: mark module is to client
It puts question to and carries out word segmentation processing, obtain multiple participles；Judge in preset business dictionary with the presence or absence of at least one in multiple participles
It is a, if the determination result is YES, by client questions labeled as related to business, otherwise client questions are labeled as unrelated with business.
In an optional embodiment, mark module pair machine response corresponding with client questions carries out the second label, packet
It includes: being miss answer by machine respond flag, otherwise by machine response if machine response is obtained from preset knowledge base
Labeled as hit answer.
In an optional embodiment, processing module 42 filters out number of targets from the part data beyond preset quantity
According to, comprising: processing module 42 filters out number of targets from the part data beyond preset quantity according to the corresponding label of data
According to.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, it can be with
It realizes by another way.Another point, shown or discussed mutual coupling, direct-coupling or communication connection can
To be the indirect coupling or communication connection of device or unit through some interfaces, it can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
It should be appreciated that can be combined with each other combination in the embodiment of the present application from power, each embodiment, feature, can realize
Solve aforementioned technical problem.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (10)
1. a kind of data processing method characterized by comprising
During electronic customer care and client interact, when getting the instruction for artificial customer service of transferring, the electricity is judged
Whether the data volume of the historical interaction data of sub- customer service and the client exceeds preset threshold；
If judging result be it is no, the historical interaction data is transmitted to manual board client with road；
If the determination result is YES, the data for meeting preset condition are filtered out from the historical interaction data, the number that will be filtered out
It is transmitted to manual board client according to road, so that operator attendance quickly carries out scenario reduction.
2. the method according to claim 1, wherein it is described filtered out from the historical interaction data meet it is pre-
If the data of condition, comprising:
Temporally the sequence for the row of falling determines the data of preset quantity from the historical interaction data；
Target data, the target data are as follows: related to business are filtered out from the part data beyond the preset quantity
Client questions, machine response corresponding with the client questions, the machine response miss answer；
The data of the preset quantity and the target data are to meet the data of preset condition.
3. according to the method described in claim 2, it is characterized by further comprising:
During electronic customer care and client interact, the first label is carried out to client questions, to the client questions
Corresponding machine response carries out the second label；
Whether first label is related to business for characterizing the client questions, and second label is for characterizing the machine
Whether device response hits answer.
4. according to the method described in claim 3, it is characterized in that, described carry out the first label to client questions, comprising:
Word segmentation processing is carried out to the client questions, obtains multiple participles；
Judge with the presence or absence of at least one of the multiple participle in preset business dictionary, if the determination result is YES, by institute
Client questions are stated labeled as related to business, are otherwise labeled as the client questions unrelated with business.
5. according to the method described in claim 3, it is characterized in that, it is described to machine response corresponding with the client questions into
Row second marks, comprising:
It is miss answer by the machine respond flag, otherwise if the machine response is obtained from preset knowledge base
It is hit answer by the machine respond flag.
6. according to the method described in claim 3, it is characterized in that, described from the part data beyond the preset quantity
Filter out target data, comprising:
According to the corresponding label of data, target data is filtered out from the part data beyond the preset quantity.
7. a kind of data processing equipment characterized by comprising
Judgment module, for during electronic customer care and client interact, when the instruction for getting artificial customer service of transferring
When, judge whether the electronic customer care and the data volume of the historical interaction data of the client exceed preset threshold；
Processing module, if for judging result be it is no, the historical interaction data is transmitted to manual board client with road；If
Judging result be it is yes, the data for meeting preset condition are filtered out from the historical interaction data, by the data filtered out with road
It is transmitted to manual board client, so that operator attendance quickly carries out scenario reduction.
8. device according to claim 7, which is characterized in that the processing module is screened from the historical interaction data
Meet the data of preset condition out, comprising:
The sequence that the processing module is temporally arranged determines the data of preset quantity from the historical interaction data；From exceeding
Target data, the target data are filtered out in the part data of the preset quantity are as follows: client questions relevant to business,
Machine response corresponding with the client questions, the machine response miss answer；The data of the preset quantity and institute
Stating target data is to meet the data of preset condition.
9. device according to claim 8, which is characterized in that further include:
Mark module, for carrying out the first label to client questions during electronic customer care and client interact, to
The corresponding machine response of the client questions carries out the second label；It is described first label for characterize the client questions whether with
Business is related, and second label is for characterizing whether the machine response hits answer.
10. device according to claim 9, which is characterized in that the processing module from exceed the preset quantity that
Target data is filtered out in partial data, comprising:
The processing module filters out target from the part data beyond the preset quantity according to the corresponding label of data
Data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811646050.1A CN109670031A (en) | 2018-12-29 | 2018-12-29 | Data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811646050.1A CN109670031A (en) | 2018-12-29 | 2018-12-29 | Data processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109670031A true CN109670031A (en) | 2019-04-23 |
Family
ID=66147465
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811646050.1A Pending CN109670031A (en) | 2018-12-29 | 2018-12-29 | Data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109670031A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105553833A (en) * | 2015-12-30 | 2016-05-04 | 上海智臻智能网络科技股份有限公司 | Customer service system and service method and robot customer service thereof |
| CN105592237A (en) * | 2014-10-24 | 2016-05-18 | ***通信集团公司 | Method and apparatus for session switching, and intelligent customer service robot |
| US20170053653A1 (en) * | 2013-07-17 | 2017-02-23 | Verint Systems Ltd. | Blind Diarization of Recorded Calls With Arbitrary Number of Speakers |
| CN108198017A (en) * | 2017-12-22 | 2018-06-22 | 中国联合网络通信集团有限公司 | Personalized customer service processing method and processing device |
-
2018
- 2018-12-29 CN CN201811646050.1A patent/CN109670031A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170053653A1 (en) * | 2013-07-17 | 2017-02-23 | Verint Systems Ltd. | Blind Diarization of Recorded Calls With Arbitrary Number of Speakers |
| CN105592237A (en) * | 2014-10-24 | 2016-05-18 | ***通信集团公司 | Method and apparatus for session switching, and intelligent customer service robot |
| CN105553833A (en) * | 2015-12-30 | 2016-05-04 | 上海智臻智能网络科技股份有限公司 | Customer service system and service method and robot customer service thereof |
| CN108198017A (en) * | 2017-12-22 | 2018-06-22 | 中国联合网络通信集团有限公司 | Personalized customer service processing method and processing device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109472608A (en) | Business confirmation method and terminal device based on Emotion identification | |
| CN109214290A (en) | A kind of shops's client management method and device based on recognition of face | |
| CN107871232A (en) | A kind of generation method and its terminal of customer visit plan | |
| CN107040863A (en) | Real time business recommends method and system | |
| CN102447743A (en) | System and method for cloud enterprise services | |
| CN109472656B (en) | Virtual article display method and device and storage medium | |
| CN106341703A (en) | Bullet screen processing method and device | |
| CN107248230A (en) | The online rent and sale method and system of intelligent graphic bookcase, books | |
| CN108595314A (en) | The user equipment moon enlivens number calculating method, device, terminal device and storage medium | |
| CN110458207A (en) | A kind of corpus Intention Anticipation method, corpus labeling method and electronic equipment | |
| CN110020099A (en) | A kind of the user's recommended method and device of video friend-making | |
| CN106355485A (en) | User interface display method and user interface display device as well as resource allocation method and resource allocation device | |
| CN107392614A (en) | The implementation method and device of off-line transaction | |
| CN109800571A (en) | Event-handling method and device and storage medium and electronic device | |
| CN106294601A (en) | Data processing method and device | |
| CN109829821A (en) | A kind of abnormal processing method of digital asset address transfer, apparatus and system | |
| CN110399191A (en) | Automatic interactive processing method and device for program graphical user interface | |
| CN109522505A (en) | Information issuing method, device, storage medium and electronic device | |
| CN109670031A (en) | Data processing method and device | |
| CN106844467A (en) | Method for exhibiting data and device | |
| CN101770626A (en) | Method, device and system for identifying agents with card-laundering behavior | |
| CN111680236A (en) | Menu display method and device, terminal equipment and storage medium | |
| CN107437174A (en) | virtual card management method and device | |
| CN107346323A (en) | The method and label recommendations device of a kind of label recommendations | |
| CN109858900A (en) | A kind of payment information method for pushing, device and terminal device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190423 |