CN112995415B - Intelligent customer service system and method based on big data analysis - Google Patents
Intelligent customer service system and method based on big data analysis Download PDFInfo
- Publication number
- CN112995415B CN112995415B CN202110403539.1A CN202110403539A CN112995415B CN 112995415 B CN112995415 B CN 112995415B CN 202110403539 A CN202110403539 A CN 202110403539A CN 112995415 B CN112995415 B CN 112995415B
- Authority
- CN
- China
- Prior art keywords
- user
- customer service
- processed
- text
- module
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/42382—Text-based messaging services in telephone networks such as PSTN/ISDN, e.g. User-to-User Signalling or Short Message Service for fixed networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/2218—Call detail recording
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5141—Details of processing calls and other types of contacts in an unified manner
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/523—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing with call distribution or queueing
- H04M3/5238—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing with call distribution or queueing with waiting time or load prediction arrangements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/527—Centralised call answering arrangements not requiring operator intervention
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an intelligent customer service system and a method based on big data analysis, wherein the intelligent customer service system comprises an information text receiving module, a user classification module, an identification type obtaining and identifying module, an electronic customer service access module, an artificial customer service access module and a text comparison module, the information text receiving module is used for receiving an information text sent by a user, the user classification module is used for obtaining the time interval between the sending time of the information text and the sending time of the information text sent by the previous user, when the time interval is greater than an interval time threshold value, the user is marked as a user to be processed, when the time interval is less than or equal to the interval time threshold value, the user is marked as a processed user, and the identification type obtaining and identifying module is used for obtaining the user identification type of the user to be processed.
Description
Technical Field
The invention relates to the technical field of big data, in particular to an intelligent customer service system and method based on big data analysis.
Background
The online customer service is used for providing timely service for the customers in various applications, and comprises an artificial customer service and an electronic customer service, wherein the electronic customer service is used for responding questions asked by the customers through a machine, and the artificial customer service is used for responding the questions asked by the customers through a real person. In the prior art, the problem is directly transferred to the manual customer service, namely the problem is transferred to the electronic customer service, and the manual customer service is accessed when the electronic customer service cannot be solved, but the working efficiency of the two modes is lower.
Disclosure of Invention
The invention aims to provide an intelligent customer service system and method based on big data analysis, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: an intelligent customer service system based on big data analysis comprises an information text receiving module, a user classification module, an identification type obtaining and identifying module, an electronic customer service access module, an artificial customer service access module and a text comparison module, wherein the information text receiving module is used for receiving an information text sent by a user, the user classification module is used for obtaining the time interval between the sending time of the information text and the sending time of the information text sent by the last user, when the time interval is greater than an interval time threshold value, the user is marked as a user to be processed, when the time interval is less than or equal to the interval time threshold value, the user is marked as a processed user, the identification type obtaining and identifying module is used for obtaining the user identification type of the user to be processed, and the user identification type comprises a first identification, a second identification and a third identification, when the user identification of the user to be processed is a first identification, the electronic customer service access module is enabled to work, when the user identification of the user to be processed is a third identification, the manual customer service access module is enabled to work, when the user identification of the user to be processed is a second identification, the text comparison module is enabled to work, the electronic customer service access module is used for transferring an information text sent by the user to be processed into the electronic customer service, the manual customer service access module distributes manual customer service to the user to be processed, the information text sent by the user to be processed is transferred into the distributed manual customer service, and the text comparison module judges whether the information text sent by the user is transferred into the electronic customer service or the manual customer service is distributed to the user to be processed according to the information sent by the user to be processed.
Further, the intelligent customer service system also comprises an identification type dividing module, wherein the identification type dividing module comprises a communication frequency obtaining and comparing module, a first identification adding module, a first text dividing module, a first proportion calculating module, a first proportion comparing module, a second identification adding module and a third identification adding module, the communication frequency obtaining and comparing module is used for obtaining the frequency of initiating communication with the customer service by a user in a latest preset time period, when the frequency of initiating communication with the customer service is smaller than a first frequency threshold value, the first identification adding module is used for adding a first identification to the user identification of the user, when the frequency of initiating communication with the customer service is larger than or equal to the first frequency threshold value, the first text dividing module is used for obtaining the number m of text contents recently communicated with the customer service by the user for a times, and each text content sent by the user is compared with a problem text in the knowledge base, when the similarity between a certain text content sent by a user and all question texts in a knowledge base is smaller than a first similarity threshold, dividing the text sent by the user into a first text, counting the number n of the text content communicated with customer service for the latest a times by a first proportion calculation module, calculating a first proportion P = n/m, comparing the first proportion with the first proportion threshold by the first proportion comparison module, adding a second identifier to the user identifier of the user by a second identifier adding module when the first proportion is smaller than the first proportion threshold, and adding a third identifier to the user identifier of the user by a third identifier adding module when the first proportion is larger than or equal to the first proportion threshold.
Further, the text comparison module comprises a text similarity acquisition module and a second similarity comparison module, the text similarity acquisition module is used for acquiring the information text sent by the user to be processed and comparing the similarity between the information text and all the question texts in the knowledge base, the second similarity comparison module is used for comparing the similarity acquired by the text similarity acquisition module with a second similarity threshold, when the acquired similarity is smaller than the second similarity threshold, the manual customer service access module is enabled to work, and when the similarity between the information text and all the question texts in the knowledge base is larger than or equal to the second similarity threshold, the electronic customer service access module is enabled to work.
Further, the artificial customer service access module comprises a first parameter acquisition module, a second parameter acquisition module, a third parameter acquisition module, a comprehensive parameter acquisition module and a sequencing distribution module, wherein the first parameter acquisition module is used for acquiring the number J of processed users for each artificial customer service, normalizing the number J of a certain artificial customer service to obtain a first parameter X of the artificial customer service, the second parameter acquisition module is used for acquiring the communication text content of each artificial customer service and the processed users, extracting the problem text sent to the artificial customer service by the processed users as the reference text of the artificial customer service, comparing the similarity between the information text sent by the users to be processed and each reference text of the artificial customer service, setting the similarity as the comparison similarity of the corresponding artificial customer service, and sequencing the comparison similarities from big to small, selecting the first comparison similarity as the reference similarity of the corresponding artificial customer service, normalizing the reference similarity K of a certain artificial customer service to obtain a second parameter of the artificial customer service, the third parameter acquisition module extracts the average reply time interval of the processed user for replying the corresponding artificial customer service from the communication text content of each artificial customer service and the processed user, the average reply time interval P of a certain artificial customer service is normalized to obtain a third parameter Z of the artificial customer service, the comprehensive parameter acquisition module calculates comprehensive parameters according to the first parameter, the second parameter and the third parameter, the sorting and distributing module sorts the comprehensive parameters in a descending order, distributes the first sorted manual customer service to the user to be processed, and transfers the information text sent by the user to be processed to the distributed manual customer service.
An intelligent customer service method based on big data analysis comprises the following steps:
when an information text sent by a certain user is received, acquiring the time interval between the sending time of the information text and the sending time of the information text sent by the previous user, if the time interval is greater than an interval time threshold, the user is a user to be processed, and if the time interval is less than or equal to the interval time threshold, the user is a processed user;
acquiring a user identification type of a user to be processed, wherein the user identification type comprises a first identification, a second identification and a third identification, and the user identification type is determined according to user history and customer service communication content;
if the user identification of the user to be processed is the first identification, transferring the information text sent by the user to be processed into the electronic customer service, wherein the electronic customer service replies the user according to the text content in a knowledge base, and the knowledge base is used for pre-storing the problem text and the corresponding reply text;
if the user identification of the user to be processed is the second identification, judging whether the information text sent by the user is transferred into the electronic customer service or distributing the manual customer service to the user to be processed according to the information sent by the user to be processed;
and if the user identification of the user to be processed is the third identification, distributing the manual customer service to the user to be processed, and transferring the information text sent by the user to be processed into the distributed manual customer service.
Further, the determining of the user identification type according to the user history and the customer service communication content comprises the following steps:
acquiring the times of initiating communication with customer service by a user in a latest preset time period, adding a user identifier of the user as a first identifier if the times of initiating communication with the customer service is less than a first time threshold,
if the number of times of initiating communication with the customer service is more than or equal to a first time threshold value, acquiring the number m of text contents communicated with the customer service for the latest a times of the user, comparing each text content sent by the user with the question texts in the knowledge base, if the similarity between a certain text content sent by the user and all the question texts in the knowledge base is less than the first similarity threshold value, the text sent by the user is a first text,
counting the number n of the text contents which are communicated with the customer service for the latest a times of the user as a first text, calculating a first proportion P = n/m,
if the first occupation ratio is larger than or equal to the first occupation ratio threshold value, adding the user identification of the user as a third identification,
and if the first occupation ratio is smaller than the first occupation ratio threshold, adding the user identification of the user as a second identification.
Further, the step of judging whether to transfer the information sent by the user to be processed to the electronic customer service or to allocate the manual customer service to the user to be processed includes the following steps:
acquiring an information text sent by the user to be processed, if the similarity between the information text and all question texts in a knowledge base is smaller than a second similarity threshold value, distributing artificial customer service to the user to be processed, and transferring the information text sent by the user to be processed into the distributed artificial customer service;
otherwise, the information sent by the user to be processed is transferred to the electronic customer service.
Further, the step of allocating manual customer service to the user to be processed includes the following steps:
acquiring the number J of processed users of each artificial customer service reception, and carrying out normalization processing on the number J of a certain artificial customer service to obtain a first parameter X = (J-Jmin)/(Jmax-Jmin) of the artificial customer service, wherein Jmax is the maximum value of the number of the processed users of each artificial customer service reception, and Jmin is the minimum value of the number of the processed users of each artificial customer service reception;
obtaining the communication text content of each artificial customer service and the processed user thereof at present, extracting the problem text sent to the artificial customer service by the processed user as the reference text of the artificial customer service, comparing the similarity between the information text sent by the user to be processed and each reference text of the artificial customer service, setting the similarity as the comparison similarity of the corresponding artificial customer service,
sorting the comparison similarities according to a descending order, selecting the first comparison similarity as the reference similarity of the corresponding artificial customer service, and carrying out normalization processing on the reference similarity K of a certain artificial customer service to obtain a second parameter Y = (K-Kmin)/(Kmax-Kmin) of the artificial customer service;
extracting the average reply time interval of the processed user for replying the corresponding artificial customer service from the communication text content of each artificial customer service and the processed user, and carrying out normalization processing on the average reply time interval P of a certain artificial customer service to obtain a third parameter Z = (P-Pmin)/(Pmax-Pmin) of the artificial customer service;
then the overall parameter W =0.52 (1-X) + 0.26Y + 0.22Z;
and sequencing the comprehensive parameters from large to small, distributing the first ordered manual customer service to the user to be processed, and transferring the information text sent by the user to be processed into the distributed manual customer service.
Further, the step of transferring the information sent by the user to be processed to the e-customer service further includes:
and acquiring the communication time length between the user and the electronic customer service, and if the communication time length is more than or equal to the threshold value of the communication time length, transferring the voice call of the user to the artificial customer service.
Compared with the prior art, the invention has the following beneficial effects: according to the invention, the user type identification is added to the user in advance through the communication history of the user and the customer service, whether the user is accessed to the artificial customer service or the electronic customer service is judged by identifying the user type identification, and whether the user is accessed to the artificial customer service is determined through the information text content sent by the user when the user type identification cannot be determined, so that the communication efficiency between the user and the customer service is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a block diagram of an intelligent customer service system based on big data analysis according to the present invention.
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 derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides a technical solution: an intelligent customer service system based on big data analysis comprises an information text receiving module, a user classification module, an identification type obtaining and identifying module, an electronic customer service access module, an artificial customer service access module and a text comparison module, wherein the information text receiving module is used for receiving an information text sent by a user, the user classification module is used for obtaining the time interval between the sending time of the information text and the sending time of the information text sent by the last user, when the time interval is greater than an interval time threshold value, the user is marked as a user to be processed, when the time interval is less than or equal to the interval time threshold value, the user is marked as a processed user, the identification type obtaining and identifying module is used for obtaining the user identification type of the user to be processed, and the user identification type comprises a first identification, a second identification and a third identification, when the user identification of the user to be processed is a first identification, the electronic customer service access module is enabled to work, when the user identification of the user to be processed is a third identification, the manual customer service access module is enabled to work, when the user identification of the user to be processed is a second identification, the text comparison module is enabled to work, the electronic customer service access module is used for transferring an information text sent by the user to be processed into the electronic customer service, the manual customer service access module distributes manual customer service to the user to be processed, the information text sent by the user to be processed is transferred into the distributed manual customer service, and the text comparison module judges whether the information text sent by the user is transferred into the electronic customer service or the manual customer service is distributed to the user to be processed according to the information sent by the user to be processed.
The intelligent customer service system also comprises an identification type dividing module, wherein the identification type dividing module comprises a communication frequency acquisition and comparison module, a first identification adding module, a first text dividing module, a first proportion calculation module, a first proportion comparison module, a second identification adding module and a third identification adding module, the communication frequency acquisition and comparison module is used for acquiring the frequency of initiating communication with customer service in a latest preset time period by a user, when the frequency of initiating communication with the customer service is less than a first frequency threshold value, the first identification adding module is used for adding a first identification to the user identification of the user, when the frequency of initiating communication with the customer service is more than or equal to the first frequency threshold value, the first text dividing module is used for acquiring the number m of text contents recently communicated with the customer service a times by the user, and each text content sent by the user is compared with a problem text in a knowledge base, when the similarity between a certain text content sent by a user and all question texts in a knowledge base is smaller than a first similarity threshold, dividing the text sent by the user into a first text, counting the number n of the text content communicated with customer service for the latest a times by a first proportion calculation module, calculating a first proportion P = n/m, comparing the first proportion with the first proportion threshold by the first proportion comparison module, adding a second identifier to the user identifier of the user by a second identifier adding module when the first proportion is smaller than the first proportion threshold, and adding a third identifier to the user identifier of the user by a third identifier adding module when the first proportion is larger than or equal to the first proportion threshold.
The text comparison module comprises a text similarity acquisition module and a second similarity comparison module, the text similarity acquisition module is used for acquiring the information text sent by the user to be processed and comparing the similarity between the information text and all the question texts in the knowledge base, the second similarity comparison module is used for comparing the similarity acquired by the text similarity acquisition module with a second similarity threshold, the manual customer service access module is enabled to work when the acquired similarities are smaller than the second similarity threshold, and the electronic customer service access module is enabled to work when the similarities between the information text and all the question texts in the knowledge base are larger than or equal to the second similarity threshold.
The artificial customer service access module comprises a first parameter acquisition module, a second parameter acquisition module, a third parameter acquisition module, a comprehensive parameter acquisition module and a sequencing distribution module, wherein the first parameter acquisition module is used for acquiring the number J of processed users for each artificial customer service, normalizing the number J of a certain artificial customer service to obtain a first parameter X of the artificial customer service, the second parameter acquisition module is used for acquiring the communication text content of each artificial customer service and the processed users thereof at present, extracting the problem text sent to the artificial customer service by the processed users from the communication text content as the reference text of the artificial customer service, comparing the similarity between the information text sent by the users to be processed and each reference text of the artificial customer service, setting the similarity as the comparison similarity of the corresponding artificial customer service, and sequencing the comparison similarities from large to small, selecting the first comparison similarity as the reference similarity of the corresponding artificial customer service, normalizing the reference similarity K of a certain artificial customer service to obtain a second parameter of the artificial customer service, the third parameter acquisition module extracts the average reply time interval of the processed user for replying the corresponding artificial customer service from the communication text content of each artificial customer service and the processed user, the average reply time interval P of a certain artificial customer service is normalized to obtain a third parameter Z of the artificial customer service, the comprehensive parameter acquisition module calculates comprehensive parameters according to the first parameter, the second parameter and the third parameter, the sorting and distributing module sorts the comprehensive parameters in a descending order, distributes the first sorted manual customer service to the user to be processed, and transfers the information text sent by the user to be processed to the distributed manual customer service.
An intelligent customer service method based on big data analysis comprises the following steps:
when an information text sent by a certain user is received, acquiring the time interval between the sending time of the information text and the sending time of the information text sent by the previous user, if the time interval is greater than an interval time threshold, the user is a user to be processed, and if the time interval is less than or equal to the interval time threshold, the user is a processed user and is used for judging whether the user is a user who has access to customer service or not; if a certain user has not sent the information text before, the user is a user to be processed;
acquiring a user identification type of a user to be processed, wherein the user identification type comprises a first identification, a second identification and a third identification, and the user identification type is determined according to user history and customer service communication content;
the user identification type is determined according to the user history and the customer service communication content, and the method comprises the following steps:
acquiring the number of times that a user initiates communication with customer service in a latest preset time period, and adding a first identifier to a user identifier of the user if the number of times of initiating communication with customer service is smaller than a first time threshold value;
if the number of times of initiating communication with the customer service is larger than or equal to a first time threshold value, acquiring the number m of text contents communicated with the customer service for the latest a times of the user, comparing each text content sent by the user with the problem texts in the knowledge base, and if the similarity between a certain text content sent by the user and all the problem texts in the knowledge base is smaller than the first similarity threshold value, determining the similarity between the text content sent by the user for the latest a times of the user and the problem texts in the knowledge base, wherein the similarity is used for determining whether most problems of the user can be solved by the electronic customer service;
counting the number n of the text contents which are communicated with the customer service for the latest a times of the user as a first text, calculating a first proportion P = n/m,
if the first occupation ratio is larger than or equal to the first occupation ratio threshold value, adding the user identification of the user as a third identification,
and if the first occupation ratio is smaller than the first occupation ratio threshold, adding the user identification of the user as a second identification.
If the user identification of the user to be processed is the first identification, transferring the information text sent by the user to be processed into the electronic customer service, wherein the electronic customer service replies the user according to the text content in a knowledge base, and the knowledge base is used for pre-storing the problem text and the corresponding reply text;
if the user identification of the user to be processed is a second identification, acquiring an information text sent by the user to be processed, if the similarity between the information text and all the problem texts in the knowledge base is smaller than a second similarity threshold value, distributing artificial customer service to the user to be processed, and transferring the information text sent by the user to be processed into the distributed artificial customer service;
otherwise, the information sent by the user to be processed is transferred to the electronic customer service.
And if the user identification of the user to be processed is the third identification, distributing the manual customer service to the user to be processed, and transferring the information text sent by the user to be processed into the distributed manual customer service.
The step of distributing the manual customer service to the user to be processed comprises the following steps:
acquiring the number J of processed users of each artificial customer service reception, and carrying out normalization processing on the number J of a certain artificial customer service to obtain a first parameter X = (J-Jmin)/(Jmax-Jmin) of the artificial customer service, wherein Jmax is the maximum value of the number of the processed users of each artificial customer service reception, and Jmin is the minimum value of the number of the processed users of each artificial customer service reception;
obtaining the communication text content of each artificial customer service and the processed user thereof at present, extracting the problem text sent to the artificial customer service by the processed user as the reference text of the artificial customer service, comparing the similarity between the information text sent by the user to be processed and each reference text of the artificial customer service, setting the similarity as the comparison similarity of the corresponding artificial customer service,
sorting the comparison similarities according to a descending order, selecting the first comparison similarity as the reference similarity of the corresponding artificial customer service, and carrying out normalization processing on the reference similarity K of a certain artificial customer service to obtain a second parameter Y = (K-Kmin)/(Kmax-Kmin) of the artificial customer service;
extracting the average reply time interval of the processed user for replying the corresponding artificial customer service from the communication text content of each artificial customer service and the processed user, and carrying out normalization processing on the average reply time interval P of a certain artificial customer service to obtain a third parameter Z = (P-Pmin)/(Pmax-Pmin) of the artificial customer service;
then the overall parameter W =0.52 (1-X) + 0.26Y + 0.22Z;
and sequencing the comprehensive parameters from large to small, distributing the first ordered manual customer service to the user to be processed, and transferring the information text sent by the user to be processed into the distributed manual customer service.
The step of transferring the information sent by the user to be processed to the electronic customer service further comprises the following steps:
and acquiring the communication time length between the user and the electronic customer service, and if the communication time length is more than or equal to the threshold value of the communication time length, transferring the voice call of the user to the artificial customer service.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. An intelligent customer service system based on big data analysis is characterized by comprising an information text receiving module, a user classification module, an identification type obtaining and identifying module, an electronic customer service access module, an artificial customer service access module and a text comparison module, wherein the information text receiving module is used for receiving an information text sent by a user, the user classification module is used for obtaining the time interval between the sending time of the information text and the sending time of the information text sent by the previous user, when the time interval is greater than an interval time threshold value, the user is marked as a user to be processed, when the time interval is less than or equal to the interval time threshold value, the user is marked as a processed user, the identification type obtaining and identifying module is used for obtaining the user identification type of the user to be processed, and the user identification type comprises a first identification, The system comprises a first identifier, a second identifier, a third identifier, an electronic customer service access module, an artificial customer service access module and a text comparison module, wherein the first identifier is used for identifying the user to be processed;
the intelligent customer service system also comprises an identification type dividing module, wherein the identification type dividing module comprises a communication frequency acquisition and comparison module, a first identification adding module, a first text dividing module, a first proportion calculation module, a first proportion comparison module, a second identification adding module and a third identification adding module, the communication frequency acquisition and comparison module is used for acquiring the frequency of initiating communication with customer service in a latest preset time period by a user, when the frequency of initiating communication with the customer service is less than a first frequency threshold value, the first identification adding module is used for adding a first identification to the user identification of the user, when the frequency of initiating communication with the customer service is more than or equal to the first frequency threshold value, the first text dividing module is used for acquiring the number m of text contents recently communicated with the customer service a times by the user, and each text content sent by the user is compared with a problem text in a knowledge base, when the similarity between a certain text content sent by a user and all question texts in a knowledge base is smaller than a first similarity threshold, dividing the text sent by the user into a first text, counting the number n of the text content communicated with customer service for the latest a times by a first proportion calculation module, calculating a first proportion P = n/m, comparing the first proportion with the first proportion threshold by the first proportion comparison module, adding a second identifier to the user identifier of the user by a second identifier adding module when the first proportion is smaller than the first proportion threshold, and adding a third identifier to the user identifier of the user by a third identifier adding module when the first proportion is larger than or equal to the first proportion threshold.
2. The intelligent customer service system based on big data analysis according to claim 1, wherein: the text comparison module comprises a text similarity acquisition module and a second similarity comparison module, the text similarity acquisition module is used for acquiring the information text sent by the user to be processed and comparing the similarity between the information text and all the question texts in the knowledge base, the second similarity comparison module is used for comparing the similarity acquired by the text similarity acquisition module with a second similarity threshold, the manual customer service access module is enabled to work when the acquired similarities are smaller than the second similarity threshold, and the electronic customer service access module is enabled to work when the similarities between the information text and all the question texts in the knowledge base are larger than or equal to the second similarity threshold.
3. The intelligent customer service system based on big data analysis according to claim 2, wherein: the artificial customer service access module comprises a first parameter acquisition module, a second parameter acquisition module, a third parameter acquisition module, a comprehensive parameter acquisition module and a sequencing distribution module, wherein the first parameter acquisition module is used for acquiring the number J of processed users for each artificial customer service, normalizing the number J of a certain artificial customer service to obtain a first parameter X of the artificial customer service, the second parameter acquisition module is used for acquiring the communication text content of each artificial customer service and the processed users thereof at present, extracting the problem text sent to the artificial customer service by the processed users from the communication text content as the reference text of the artificial customer service, comparing the similarity between the information text sent by the users to be processed and each reference text of the artificial customer service, setting the similarity as the comparison similarity of the corresponding artificial customer service, and sequencing the comparison similarities from large to small, selecting the first comparison similarity as the reference similarity of the corresponding artificial customer service, normalizing the reference similarity K of a certain artificial customer service to obtain a second parameter of the artificial customer service, the third parameter acquisition module extracts the average reply time interval of the processed user for replying the corresponding artificial customer service from the communication text content of each artificial customer service and the processed user, the average reply time interval P of a certain artificial customer service is normalized to obtain a third parameter Z of the artificial customer service, the comprehensive parameter acquisition module calculates comprehensive parameters according to the first parameter, the second parameter and the third parameter, the sorting and distributing module sorts the comprehensive parameters in a descending order, distributes the first sorted manual customer service to the user to be processed, and transfers the information text sent by the user to be processed to the distributed manual customer service.
4. An intelligent customer service method based on big data analysis is characterized in that: the intelligent customer service method comprises the following steps:
when an information text sent by a certain user is received, acquiring the time interval between the sending time of the information text and the sending time of the information text sent by the previous user, if the time interval is greater than an interval time threshold, the user is a user to be processed, and if the time interval is less than or equal to the interval time threshold, the user is a processed user;
acquiring a user identification type of a user to be processed, wherein the user identification type comprises a first identification, a second identification and a third identification, and the user identification type is determined according to user history and customer service communication content;
if the user identification of the user to be processed is the first identification, transferring the information text sent by the user to be processed into the electronic customer service, wherein the electronic customer service replies the user according to the text content in a knowledge base, and the knowledge base is used for pre-storing the problem text and the corresponding reply text;
if the user identification of the user to be processed is the second identification, judging whether the information text sent by the user is transferred into the electronic customer service or distributing the manual customer service to the user to be processed according to the information sent by the user to be processed;
if the user identification of the user to be processed is the third identification, distributing artificial customer service to the user to be processed, and transferring the information text sent by the user to be processed into the distributed artificial customer service;
the user identification type is determined according to the user history and the customer service communication content, and the method comprises the following steps:
acquiring the times of initiating communication with customer service by a user in a latest preset time period, adding a user identifier of the user as a first identifier if the times of initiating communication with the customer service is less than a first time threshold,
if the number of times of initiating communication with the customer service is more than or equal to a first time threshold value, acquiring the number m of text contents communicated with the customer service for the latest a times of the user, comparing each text content sent by the user with the question texts in the knowledge base, if the similarity between a certain text content sent by the user and all the question texts in the knowledge base is less than the first similarity threshold value, the text sent by the user is a first text,
counting the number n of the text contents which are communicated with the customer service for the latest a times of the user as a first text, calculating a first proportion P = n/m,
if the first occupation ratio is larger than or equal to the first occupation ratio threshold value, adding the user identification of the user as a third identification,
and if the first occupation ratio is smaller than the first occupation ratio threshold, adding the user identification of the user as a second identification.
5. The intelligent customer service method based on big data analysis according to claim 4, wherein: the step of judging whether the information sent by the user to be processed is transferred to the electronic customer service or the manual customer service is distributed to the user to be processed comprises the following steps:
acquiring an information text sent by the user to be processed, if the similarity between the information text and all question texts in a knowledge base is smaller than a second similarity threshold value, distributing artificial customer service to the user to be processed, and transferring the information text sent by the user to be processed into the distributed artificial customer service;
otherwise, the information sent by the user to be processed is transferred to the electronic customer service.
6. The intelligent customer service method based on big data analysis according to claim 5, wherein: the step of distributing the manual customer service to the user to be processed comprises the following steps:
acquiring the number J of processed users of each artificial customer service reception, and carrying out normalization processing on the number J of a certain artificial customer service to obtain a first parameter X = (J-Jmin)/(Jmax-Jmin) of the artificial customer service, wherein Jmax is the maximum value of the number of the processed users of each artificial customer service reception, and Jmin is the minimum value of the number of the processed users of each artificial customer service reception;
obtaining the communication text content of each artificial customer service and the processed user thereof at present, extracting the problem text sent to the artificial customer service by the processed user as the reference text of the artificial customer service, comparing the similarity between the information text sent by the user to be processed and each reference text of the artificial customer service, setting the similarity as the comparison similarity of the corresponding artificial customer service,
sorting the comparison similarities according to a descending order, selecting the first comparison similarity as the reference similarity of the corresponding artificial customer service, and carrying out normalization processing on the reference similarity K of a certain artificial customer service to obtain a second parameter Y = (K-Kmin)/(Kmax-Kmin) of the artificial customer service, wherein Kmax is the maximum value of the reference similarities of the artificial customer services, and Kmin is the minimum value of the reference similarities of the artificial customer services;
extracting an average reply time interval for the processed user to reply the corresponding artificial customer service from the communication text content of each artificial customer service and the processed user, and carrying out normalization processing on the average reply time interval P of a certain artificial customer service to obtain a third parameter Z = (P-Pmin)/(Pmax-Pmin) of the artificial customer service, wherein Pmax is the maximum value of the average reply time interval of each artificial customer service, and Pmin is the maximum value of the average reply time interval of each artificial customer service;
then the overall parameter W =0.52 (1-X) + 0.26Y + 0.22Z;
and sequencing the comprehensive parameters from large to small, distributing the first ordered manual customer service to the user to be processed, and transferring the information text sent by the user to be processed into the distributed manual customer service.
7. The intelligent customer service method based on big data analysis according to claim 6, wherein: the step of transferring the information sent by the user to be processed to the electronic customer service further comprises the following steps:
and acquiring the communication time length between the user and the electronic customer service, and if the communication time length is more than or equal to the threshold value of the communication time length, transferring the voice call of the user to the artificial customer service.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110403539.1A CN112995415B (en) | 2021-04-15 | 2021-04-15 | Intelligent customer service system and method based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110403539.1A CN112995415B (en) | 2021-04-15 | 2021-04-15 | Intelligent customer service system and method based on big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112995415A CN112995415A (en) | 2021-06-18 |
| CN112995415B true CN112995415B (en) | 2021-08-06 |
Family
ID=76339875
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110403539.1A Active CN112995415B (en) | 2021-04-15 | 2021-04-15 | Intelligent customer service system and method based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112995415B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105072173A (en) * | 2015-08-03 | 2015-11-18 | 谌志群 | Customer service method and system for automatically switching between automatic customer service and artificial customer service |
| CN107071193A (en) * | 2016-11-28 | 2017-08-18 | 阿里巴巴集团控股有限公司 | The method and apparatus of interactive answering system accessing user |
| CN109660680A (en) * | 2019-02-06 | 2019-04-19 | 刘兴丹 | A kind of method, apparatus of selectivity access voice communication |
| CN110472023A (en) * | 2019-07-10 | 2019-11-19 | 深圳追一科技有限公司 | Customer service switching method, device, computer equipment and storage medium |
| CN110570215A (en) * | 2019-09-06 | 2019-12-13 | 北京金融资产交易所有限公司 | Intelligent customer service system |
| CN110879837A (en) * | 2018-09-06 | 2020-03-13 | 华为技术有限公司 | Information processing method and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102348904B1 (en) * | 2017-07-25 | 2022-01-07 | 삼성에스디에스 주식회사 | Method for providing chatting service with chatbot assisted by human counselor |
| CN108764937A (en) * | 2018-05-02 | 2018-11-06 | 开源物联网（广州）有限公司 | It can iteration intelligent customer service system |
| CN112365894B (en) * | 2020-11-09 | 2024-05-17 | 青岛易蓓教育科技有限公司 | AI-based composite voice interaction method and device and computer equipment |
-
2021
- 2021-04-15 CN CN202110403539.1A patent/CN112995415B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105072173A (en) * | 2015-08-03 | 2015-11-18 | 谌志群 | Customer service method and system for automatically switching between automatic customer service and artificial customer service |
| CN107071193A (en) * | 2016-11-28 | 2017-08-18 | 阿里巴巴集团控股有限公司 | The method and apparatus of interactive answering system accessing user |
| CN110879837A (en) * | 2018-09-06 | 2020-03-13 | 华为技术有限公司 | Information processing method and device |
| CN109660680A (en) * | 2019-02-06 | 2019-04-19 | 刘兴丹 | A kind of method, apparatus of selectivity access voice communication |
| CN110472023A (en) * | 2019-07-10 | 2019-11-19 | 深圳追一科技有限公司 | Customer service switching method, device, computer equipment and storage medium |
| CN110570215A (en) * | 2019-09-06 | 2019-12-13 | 北京金融资产交易所有限公司 | Intelligent customer service system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112995415A (en) | 2021-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| MXPA03006586A (en) | System and method for composite customer segmentation. | |
| CN109978608A (en) | The marketing label analysis extracting method and system of target user's portrait | |
| CN111954173B (en) | Method, device, server and computer readable storage medium for sending short message | |
| US8139756B2 (en) | Method, apparatus, and computer product for computing skill value | |
| CN107230103A (en) | A kind of precision marketing system | |
| CN107231393B (en) | Session processing method and device | |
| CN106657007A (en) | Method for recognizing abnormal batch ticket booking behavior based on DBSCAN model | |
| CN113033909A (en) | Portable user analysis method, device, equipment and computer storage medium | |
| CN113205129B (en) | Cheating group identification method and device, electronic equipment and storage medium | |
| CN114936727A (en) | Work order distribution system, method and computer equipment | |
| CN107977855B (en) | Method and device for managing user information | |
| CN110365605B (en) | Message sending method, device, equipment and storage medium | |
| CN114265974A (en) | Client portrait label recommendation system and method | |
| CN112995415B (en) | Intelligent customer service system and method based on big data analysis | |
| CN111782735A (en) | Wool party flow identification method and device | |
| CN114649085A (en) | Emergency medical supplies management system based on big data | |
| CN117557214A (en) | Approval aging early warning method and device for approval process information and storage medium | |
| CN116167674A (en) | Logistics complaint list input method, device, equipment and storage medium | |
| CN106296284A (en) | A kind of method that block chain identifies favor information | |
| CN111478779A (en) | Method and device for determining unlimited set meal and computing equipment | |
| KR20050010099A (en) | Call recommender system for outbound call center | |
| CN108683551B (en) | Pipeline type flow control method and device | |
| CN114125046B (en) | Information touch system based on 5G | |
| CN114006945A (en) | Intelligent grouping distribution method of Internet of things data and Internet of things platform | |
| CN108564380B (en) | Telecommunication user classification method based on iterative decision tree |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220829 Address after: Room 108, Building 1, No. 11, Chang'an Road, Infant Industry Cultural and Creative Park, Jinjiang Economic Development Zone (Wuli Park), Quanzhou City, Fujian Province, 362000 Patentee after: Quanzhou Kejuhui Technology Co.,Ltd. Address before: 510330 Room 201, 8 Haicheng East Street, Xingang East Road, Haizhu District, Guangzhou City, Guangdong Province Patentee before: Guangzhou Gru Information Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220906 Address after: 362000 No. C103, building C, Chuangke street, Sanchuang garden, Luoshan street, Jinjiang City, Quanzhou City, Fujian Province Patentee after: Quanzhou Huiren Intelligent Technology Co.,Ltd. Address before: Room 108, Building 1, No. 11, Chang'an Road, Infant Industry Cultural and Creative Park, Jinjiang Economic Development Zone (Wuli Park), Quanzhou City, Fujian Province, 362000 Patentee before: Quanzhou Kejuhui Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |