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
- customer
- service
- preset
- marking
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 13
- 230000003993 interaction Effects 0.000 claims abstract description 56
- 230000004044 response Effects 0.000 claims description 64
- 238000012545 processing Methods 0.000 claims description 42
- 238000000034 method Methods 0.000 claims description 40
- 230000002452 interceptive effect Effects 0.000 claims description 35
- 230000008569 process Effects 0.000 claims description 24
- 238000012216 screening Methods 0.000 claims description 21
- 230000011218 segmentation Effects 0.000 claims description 6
- 241001269238 Data Species 0.000 abstract 1
- 230000005540 biological transmission Effects 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
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
The present application relates to the field of data processing technologies, and in particular, to a data processing method and apparatus.
Background
At present, the online customer service provides timely service for customers in various applications by combining an electronic customer service (i.e. a machine answers questions of customers) and a manual customer service. Generally, when an online customer service obtains a service request of a customer, an electronic customer service is preferentially selected to provide service for the customer, and when the electronic customer service cannot solve the problem of the customer, manual customer service is switched.
When the electronic customer service is switched to the manual customer service, the on-line customer service system transmits the historical interactive data of the current customer and the electronic customer service to the manual agent client along with the route so as to be browsed by the manual agent and be convenient for quickly positioning the customer problem. However, when the historical interaction data of the customer and the electronic customer service is too much, not only is pressure on data transmission generated, but also the time for a human agent to browse data is prolonged, and the efficiency of locating the customer problems is reduced.
Therefore, the technical problem of how to help the human agent to quickly locate the client while reducing the data transmission amount becomes an urgent solution.
Disclosure of Invention
The present application is directed to a data processing method and apparatus, which at least partially overcome the technical problems in the prior art.
In order to achieve the purpose, the application provides the following technical scheme:
a method of data processing, comprising:
in the process of interaction between the electronic customer service and a customer, when an instruction for switching to the manual customer service is obtained, judging whether the data volume of historical interaction data of the electronic customer service and the customer exceeds a preset threshold value or not;
if the judgment result is negative, transmitting the historical interactive data to a manual seat client along the path;
if the judgment result is yes, screening out data meeting preset conditions from the historical interactive data, and transmitting the screened data to the manual seat client along with the path, so that the manual seat can rapidly restore the scene.
Preferably, in the method, the screening out data meeting preset conditions from the historical interaction data includes:
determining a preset amount of data from the historical interactive data according to the time reverse sequence;
screening target data from the data which exceed the preset number, wherein the target data are as follows: a customer question related to a service, a machine response corresponding to the customer question, the machine response missing an answer;
the preset amount of data and the target data are data meeting preset conditions.
The above method, preferably, further comprises:
in the process of interaction between the electronic customer service and a customer, carrying out first marking on a customer question and carrying out second marking on a machine response corresponding to the customer question;
the first label is used for representing whether the customer question is relevant to business or not, and the second label is used for representing whether the machine response hits an answer or not.
The above method, preferably, the first marking of the customer questions includes:
performing word segmentation processing on the customer question to obtain a plurality of words;
and judging whether at least one of the multiple participles exists in a preset service word bank, if so, marking the customer question as being related to the service, otherwise, marking the customer question as being unrelated to the service.
Preferably, the second marking of the machine response corresponding to the customer question includes:
if the machine response is not obtained from a preset knowledge base, marking the machine response as a missed answer, otherwise marking the machine response as a hit answer.
The method preferably, the screening target data from the part of the data exceeding the preset number includes:
and screening out target data from the data exceeding the preset number according to the marks corresponding to the data.
A data processing apparatus comprising:
the system comprises a judging module, a processing module and a processing module, wherein the judging module is used for judging whether the data volume of historical interaction data of an electronic customer service and a customer exceeds a preset threshold value when an instruction of switching to an artificial customer service is obtained in the process of interaction between the electronic customer service and the customer;
the processing module is used for transmitting the historical interaction data to a manual seat client along with the path if the judgment result is negative; if the judgment result is yes, screening out data meeting preset conditions from the historical interactive data, and transmitting the screened data to the manual seat client along with the path, so that the manual seat can rapidly restore the scene.
Preferably, in the above apparatus, the processing module screens out data meeting a preset condition from the historical interaction data, and includes:
the processing module determines a preset amount of data from the historical interactive data according to the time reverse sequence; screening target data from the data which exceed the preset number, wherein the target data are as follows: a customer question related to a service, a machine response corresponding to the customer question, the machine response missing an answer; the preset amount of data and the target data are data meeting preset conditions.
The above apparatus, preferably, further comprises:
the system comprises a marking module, a query module and a response module, wherein the marking module is used for carrying out first marking on a customer question and carrying out second marking on a machine response corresponding to the customer question in the process of interaction between an electronic customer service and the customer; the first label is used for representing whether the customer question is relevant to business or not, and the second label is used for representing whether the machine response hits an answer or not.
The above apparatus, preferably, the marking module performs a first marking on the customer's question, including: the marking module carries out word segmentation processing on the questions of the client to obtain a plurality of words; and judging whether at least one of the multiple participles exists in a preset service word bank, if so, marking the customer question as being related to the service, otherwise, marking the customer question as being unrelated to the service.
Preferably, the apparatus further includes a marking module for second marking the machine response corresponding to the customer's question, including: if the machine response is not obtained from the preset knowledge base, the machine response is marked as a missed answer, otherwise, the machine response is marked as a hit answer.
The above apparatus, preferably, the processing module screens out target data from the part of the data exceeding the preset number, and includes:
and the processing module screens out target data from the data exceeding the preset number according to the marks corresponding to the data.
According to the data processing method and device, in the process of interaction between the electronic customer service and the customer, when an instruction for switching to the manual customer service is obtained, if the data volume of historical interaction data of the electronic customer service and the customer does not exceed a preset threshold value, all historical interaction data are transmitted to the manual seat client along the way, otherwise, data meeting preset conditions are screened from the historical interaction data and transmitted to the manual seat client along the way, and therefore the data volume transmitted to the manual seat along the way is small, and rapid scene restoration of the manual seat is facilitated.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of an implementation of a data processing method according to an embodiment of the present application;
FIG. 2 is a flowchart of an implementation of screening historical interaction data to meet a predetermined condition according to an embodiment of the present disclosure;
fig. 3 is a flowchart of another implementation of a data processing method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be practiced otherwise than as specifically illustrated.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
As shown in fig. 1, an implementation flowchart of the data processing method provided by the present application may include:
step S11: in the process of interaction between the electronic customer service and the customer, when an instruction for switching to the manual customer service is obtained, whether the data volume of historical interaction data of the electronic customer service and the customer exceeds a preset threshold value is judged, if the judgment result is negative, step 12 is executed, and if the judgment result is positive, step 13 is executed.
In the process of interaction between the electronic customer service and the customer, if the electronic customer service cannot provide effective service for the customer, the customer may select to transfer the artificial customer, or the online customer service system may actively transfer the artificial customer service for the customer, so that the instruction for transferring the artificial customer service may be generated by triggering of the customer or may be generated by automatic triggering of the online customer service system.
Step S12: and transmitting the historical interactive data to the manual agent client along the path.
In the application, if the data size of the historical interactive data of the electronic customer service and the customer is small, because no pressure exists in manual agent browsing, the historical interactive data is not screened and is directly transmitted along with the route, and the response time and the processing resources of the customer service system can be saved.
Step S13: and screening out data meeting preset conditions from the historical interactive data, and transmitting the screened data to the manual seat client along with a path so as to facilitate the manual seat to rapidly restore the scene.
In the application, if the data volume of the historical interactive data of the electronic customer service and the customer is large, the data meeting the preset conditions are screened out and transmitted along with the path, so that the manual agent can achieve information synchronization and scene quick restoration. The data meeting the preset conditions refers to historical interactive data which can help a human agent to quickly restore the scene.
And when the screened data is transmitted along with the path, the screened data is transmitted along with the path to the manual seat client according to the time sequence.
According to the data processing method, in the process of interaction between the electronic customer service and the customer, when the instruction for switching the artificial customer service is obtained, the historical interactive data of the electronic customer service and the customer are not directly transmitted to the artificial seat client along with the route, whether the data volume of the historical interactive data exceeds a preset threshold value or not is judged first, the historical interactive data needing transmission along with the route is determined according to the judgment result, the data volume transmitted to the artificial seat along with the route is small, and meanwhile, the artificial seat can conveniently and rapidly perform scene restoration.
In an alternative embodiment, an implementation flowchart of the above-mentioned method for screening out data meeting the preset condition from the historical interaction data is shown in fig. 2, and may include:
step S21: a preset amount of data is determined from the historical interaction data in reverse chronological order.
That is, the determined preset amount of data is the interaction data of the number of times closest to the current time among the above-mentioned historical interaction data.
Step S22: screening out target data from the data which exceed the preset number, wherein the target data are as follows: a customer question associated with a business, a machine response corresponding to the customer question, the machine response missing an answer.
The machine response is the answer given by the e-customer service to the customer's question. The specific screening process can be as follows:
and cutting the data which exceeds the preset number into a plurality of sub-interactive segments according to a mode of 'customer question-machine response', judging whether the customer question is related to the service or not and whether the machine response hits the answer or not one by one, and determining the sub-interactive segment as the target data when the customer question in the sub-interactive segment is related to the service and the machine response does not hit the answer.
In the application, the determined preset amount of data is not screened, only the data exceeding the preset amount in the historical interactive data is screened, and the screened interactive data includes customer questions and corresponding machine responses, wherein the customer questions are related to the service, but the corresponding machine responses do not hit the answers.
The preset amount of data and the target data are data meeting preset conditions.
For example, assuming that the client a interacts with the e-customer service from 9:00, and the e-customer service prompts the transfer of the manual customer service at 9:05, the historical interaction data of the e-customer service and the client a is the interaction data in the period from 9:00 to 9: 05. Assuming that the amount of the interactive data in the period is 614KB and the preset amount is 512KB, in the present application, the data of 512KB is determined in the order from the back to the front, that is, from 9:05, and assuming that the interactive data in the period from 9:02 to 9:05 is 512KB, the interactive data in the period from 9:00 to 9:02 is filtered to obtain the target data, that is, the target data is a part of the interactive data in the period from 9:00 to 9: 02. The obtained target data is screened, and the interaction data in the period from 9:02 to 9:05 is the data meeting the preset condition.
According to the method and the device, the latest interaction records (namely the preset number of data determined according to the time inverted sequence) can reflect the specific reason that the customer selects to change into manual work most, so that the latest interaction records are not processed, and only the data of other parts are screened, so that the information synchronization of the manual agents is facilitated, and the scene is quickly restored.
In an optional embodiment, the data processing method provided in the present application may further include:
and in the process of interaction between the electronic customer service and the customer, carrying out first marking on the customer question and carrying out second marking on the machine response corresponding to the customer question.
The first label is used for representing whether the customer question is relevant to the business or not, and the second label is used for representing whether the machine response hits the answer or not.
In the embodiment of the application, the customer questions and the machine response are marked in the interaction process of the electronic customer service and the customer, so that after the instruction of the switching manual customer service is obtained, data can be rapidly screened according to the mark, and the data processing efficiency is improved.
In an optional embodiment, one implementation manner of the first marking of the customer question may be:
and performing word segmentation processing on the questions of the clients to obtain a plurality of words.
And judging whether at least one of the multiple participles exists in a preset service word bank, if so, marking the customer question as being related to the service, otherwise, marking the customer question as being unrelated to the service.
The vocabularies stored in the service word bank are all service related vocabularies. When at least one word in the multi-word is a word in the service word bank, the fact that the customer question is related to the service is explained, otherwise, the fact that the customer question is not related to the service is explained.
In an alternative embodiment, one implementation of the second marking of the machine response corresponding to the customer question may be:
if the machine response is not obtained from the preset knowledge base, the machine response is marked as a missed answer, otherwise, the machine response is marked as a hit answer.
In the process of interaction between the electronic customer service and the customer, the answer of the electronic customer service comes from a knowledge base (the knowledge base is used for storing standard answers), and after a series of logic processing is carried out on the customer question, if the standard answer is not found in the knowledge base, namely the answer is not hit, a non-answer response is given. Therefore, if the machine response is not obtained from the preset knowledge base, the machine response is not hit, otherwise, the machine response is hit.
The process of performing a series of logic processing on the customer question may include:
performing word segmentation processing on the questions of the clients to obtain a plurality of words; extracting key words from the multiple word segments, and searching knowledge items containing the extracted key words in a preset knowledge base; if the knowledge item is found, the standard answer is shown, otherwise, the standard answer is not shown.
For example, assume that the customer asks: how to open the password-free payment on the mobile bank. The customer's question is participled to obtain the following participles: mobile banking, last, me, how, open, exempt from secret payment, extract the keyword from above-mentioned 6 participles and do: the method comprises the steps of mobile banking, opening and secret-free payment, searching knowledge items comprising three key words of the mobile banking, the opening and the secret-free payment in a knowledge base, if the knowledge items are searched, feeding the searched knowledge items back to a client, and returning other response contents to the client according to preset logic if the knowledge items are not searched, wherein the machine responds to the missed answers.
Because the customer questions and the machine responses are marked in the interaction process of the electronic customer service and the customers, when the target data are screened from the data exceeding the preset number, the target data can be screened from the data exceeding the preset number directly according to the marks corresponding to the data, and whether the data meet the preset conditions does not need to be analyzed, so that the data processing efficiency is further improved.
Another implementation flowchart of the data processing method provided by the present application is shown in fig. 3, and may include:
step S301: and the client enters an electronic customer service scene.
Step S302: the electronic customer service interacts with the customer for multiple times, and in the interaction process, whether the customer question is related to the service or not and whether the answer is hit or not is marked by the machine response or not are marked.
Step S303: and selecting to change into manual work. Customer selection or e-customer service automatic selection.
Step S304: determine if the amount of historical interaction data exceeds a threshold? If not, the process proceeds to step S305, and if yes, the process proceeds to step S306.
Step S305: historical data is not processed, and all data is transmitted along the channel.
Step S306: the historical interaction data is inverted by time.
Step S307: and taking the interaction data within the threshold quantity as a basic interaction segment.
Step S308: interaction data beyond the threshold is cut into a plurality of sub-interaction segments in a mode of 'customer question-machine response'.
Step S309: selecting an undetermined sub-interactive segment, determining whether the customer question of the sub-interactive segment is related to the service, if not, entering step S310, and if so, entering step S311.
Step S310: this sub-interaction segment is skipped, i.e. the sub-interaction segment is not analyzed anymore.
Step S311: and judging whether the machine response of the sub-interactive segment hits the answer, if so, entering the step S310, and if not, entering the step S312.
Step S312: and splicing the sub-interactive segments to the basic interactive segment.
Step S313: and judging whether all the sub-interactive segments are completely traversed, if so, entering the step S314, and otherwise, returning to the step S309.
Step S314: and transmitting the spliced data along with the channel.
Corresponding to the method embodiment, the present application further provides a data processing apparatus, and a schematic structural diagram of the data processing apparatus provided by the present application is shown in fig. 4, and may include:
a judging module 41 and a processing module 42; wherein,
the judging module 41 is configured to, in the process of interaction between the electronic customer service and the customer, judge whether the data volume of the historical interaction data of the electronic customer service and the customer exceeds a preset threshold value when acquiring an instruction for switching to the artificial customer service;
the processing module 42 is configured to transmit the historical interaction data to the human seat client along with the route if the determination result is negative; if the judgment result is yes, screening out data meeting the preset condition from the historical interactive data, and transmitting the screened data to the manual seat client along with the path, so that the manual seat can rapidly restore the scene.
In the application, if the data size of the historical interactive data of the electronic customer service and the customer is small, because no pressure exists in manual agent browsing, the historical interactive data is not screened and is directly transmitted along with the route, and the response time and the processing resources of the customer service system can be saved.
If the data volume of the historical interactive data of the electronic customer service and the customer is large, the data meeting the preset conditions are screened out to be transmitted along with the route, so that the manual agent can achieve information synchronization and scene quick restoration. The data meeting the preset conditions refers to historical interactive data which can help a human agent to quickly restore the scene.
And when the screened data is transmitted along with the path, the screened data is transmitted along with the path to the manual seat client according to the time sequence.
The application provides a data processing device, in the process that electronic customer service and customer interact, when the instruction of switching artifical customer service is obtained, instead of directly transmitting the historical interactive data of electronic customer service and customer to the artifical seat client along with the route, judge whether the data bulk of historical interactive data exceeds the preset threshold value first, determine the historical interactive data that need follow the route transmission according to the judged result, guarantee that the data bulk of follow the route transmission to the artifical seat is less, be convenient for the artifical seat to carry out scene restoration fast simultaneously.
In an alternative embodiment, the processing module 42 screens out data meeting the preset condition from the historical interaction data, which includes:
the processing module 42 determines a preset amount of data from the historical interaction data in a time-reversed order; screening target data from the data which exceed the preset number, wherein the target data are as follows: customer questions related to the business, and machine responses corresponding to the customer questions, wherein the machine responses do not hit the answers; the determined preset amount of data and the target data are the data meeting the preset condition.
In an optional embodiment, the data processing apparatus may further include:
the marking module is used for carrying out first marking on a customer question and carrying out second marking on a machine response corresponding to the customer question in the process of interaction between the electronic customer service and the customer; the first label is used for representing whether the customer question is relevant to the business or not, and the second label is used for representing whether the machine response hits the answer or not.
In an alternative embodiment, the tagging module first tags the customer's question, comprising: the marking module carries out word segmentation processing on the questions of the client to obtain a plurality of words; and judging whether at least one of the multiple participles exists in a preset service word bank, if so, marking the customer question as being related to the service, otherwise, marking the customer question as being unrelated to the service.
In an alternative embodiment, the tagging module second tags the machine response corresponding to the customer's question, comprising: if the machine response is not obtained from the preset knowledge base, the machine response is marked as a missed answer, otherwise, the machine response is marked as a hit answer.
In an alternative embodiment, the processing module 42 screens out the target data from the portion of the data exceeding the preset number, including: the processing module 42 screens out the target data from the data exceeding the preset number according to the corresponding mark of the data.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
It should be understood that the technical problems can be solved by combining and combining the features of the embodiments from the claims.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A data processing method, comprising:
in the process of interaction between the electronic customer service and a customer, when an instruction for switching to the manual customer service is obtained, judging whether the data volume of historical interaction data of the electronic customer service and the customer exceeds a preset threshold value or not;
if the judgment result is negative, transmitting the historical interactive data to a manual seat client along the path;
if the judgment result is yes, screening out data meeting preset conditions from the historical interactive data, and transmitting the screened data to the manual seat client along with the path, so that the manual seat can rapidly restore the scene.
2. The method of claim 1, wherein the step of screening out data meeting preset conditions from the historical interaction data comprises:
determining a preset amount of data from the historical interactive data according to the time reverse sequence;
screening target data from the data which exceed the preset number, wherein the target data are as follows: a customer question related to a service, a machine response corresponding to the customer question, the machine response missing an answer;
the preset amount of data and the target data are data meeting preset conditions.
3. The method of claim 2, further comprising:
in the process of interaction between the electronic customer service and a customer, carrying out first marking on a customer question and carrying out second marking on a machine response corresponding to the customer question;
the first label is used for representing whether the customer question is relevant to business or not, and the second label is used for representing whether the machine response hits an answer or not.
4. The method of claim 3, wherein said first marking of customer questions comprises:
performing word segmentation processing on the customer question to obtain a plurality of words;
and judging whether at least one of the multiple participles exists in a preset service word bank, if so, marking the customer question as being related to the service, otherwise, marking the customer question as being unrelated to the service.
5. The method of claim 3, wherein said second tagging the machine response corresponding to the customer question comprises:
if the machine response is not obtained from a preset knowledge base, marking the machine response as a missed answer, otherwise marking the machine response as a hit answer.
6. The method of claim 3, wherein said screening target data from the portion of data exceeding the preset amount comprises:
and screening out target data from the data exceeding the preset number according to the marks corresponding to the data.
7. A data processing apparatus, comprising:
the system comprises a judging module, a processing module and a processing module, wherein the judging module is used for judging whether the data volume of historical interaction data of an electronic customer service and a customer exceeds a preset threshold value when an instruction of switching to an artificial customer service is obtained in the process of interaction between the electronic customer service and the customer;
the processing module is used for transmitting the historical interaction data to a manual seat client along with the path if the judgment result is negative; if the judgment result is yes, screening out data meeting preset conditions from the historical interactive data, and transmitting the screened data to the manual seat client along with the path, so that the manual seat can rapidly restore the scene.
8. The apparatus of claim 7, wherein the processing module screens out data meeting a preset condition from the historical interaction data, and comprises:
the processing module determines a preset amount of data from the historical interactive data according to the time reverse sequence; screening target data from the data which exceed the preset number, wherein the target data are as follows: a customer question related to a service, a machine response corresponding to the customer question, the machine response missing an answer; the preset amount of data and the target data are data meeting preset conditions.
9. The apparatus of claim 8, further comprising:
the system comprises a marking module, a query module and a response module, wherein the marking module is used for carrying out first marking on a customer question and carrying out second marking on a machine response corresponding to the customer question in the process of interaction between an electronic customer service and the customer; the first label is used for representing whether the customer question is relevant to business or not, and the second label is used for representing whether the machine response hits an answer or not.
10. The apparatus of claim 9, wherein the processing module screens out target data from the portion of data that exceeds the preset amount, comprising:
and the processing module screens out target data from the data exceeding the preset number according to the marks corresponding to the 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 | 中国移动通信集团公司 | 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 | 中国移动通信集团公司 | 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 |
|---|---|---|
| CN109670837A (en) | Recognition methods, device, computer equipment and the storage medium of bond default risk | |
| CN109299399B (en) | Learning content recommendation method and terminal equipment | |
| CN107315841A (en) | A kind of information search method, apparatus and system | |
| CN103365904B (en) | A kind of advertising message searching method and system | |
| CN108536414A (en) | Method of speech processing, device and system, mobile terminal | |
| CN107465739B (en) | The method and device of entity channel user drainage | |
| CN105704000A (en) | Information prompting method, device and instant communication system | |
| CN101546334A (en) | Method, device and browsing system for prompting webpage information search result in browser | |
| TW200901021A (en) | System and method for customizing a user interface | |
| CN104834691A (en) | Voice robot | |
| CN107798102A (en) | A kind of page display method and device | |
| CN109513211A (en) | Processing method, device and the game resource display systems of fine arts resource file | |
| JP2018538599A (en) | Method and apparatus for grouping web page labels in a web browser | |
| CN106484738A (en) | A kind of page processing method and device | |
| CN107392614A (en) | The implementation method and device of off-line transaction | |
| CN105989114A (en) | Collection content recommendation method and terminal | |
| CN107256266A (en) | Query content display method and system | |
| CN106294601A (en) | Data processing method and device | |
| CN113450796B (en) | Voice report generation method, device, equipment and storage medium | |
| CN114969303A (en) | Questionnaire investigation method, device, equipment and storage medium | |
| CN107301581A (en) | A kind of merchandise news counseling services and marketing system | |
| CN109670031A (en) | Data processing method and device | |
| CN107943398A (en) | Information acquisition method and equipment | |
| CN104503893A (en) | Activity state information storage and analysis methods in android system, and electronic terminal | |
| CN103577276B (en) | The standby system and method for user's operation data |
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 |